No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Biomonitoring and precision health in deep space supported by artificial intelligence
Abstract
Human exploration of deep space will involve missions of substantial distance and duration. To effectively mitigate health hazards, paradigm shifts in astronaut health systems are necessary to enable Earth-independent healthcare, rather than Earth-reliant. Here we present a summary of decadal recommendations from a workshop organized by NASA on artificial intelligence, machine learning and modelling applications that offer key solutions toward these space health challenges. The workshop recommended various biomonitoring approaches, biomarker science, spacecraft/habitat hardware, intelligent software and streamlined data management tools in need of development and integration to enable humanity to thrive in deep space. Participants recommended that these components culminate in a maximally automated, autonomous and intelligent Precision Space Health system, to monitor, aggregate and assess biomedical statuses.
... By leveraging computational models trained on large-scale omics datasets, researchers can predict the toxicological properties of chemical compounds, prioritize compounds for further testing, and extrapolate toxicity data across chemical classes and species (Yang et al., 2018). Additionally, AI-driven approaches can facilitate the identification of novel biomarkers and molecular signatures of chemical exposure that may serve as early indicators of adverse health outcomes (Scott et al., 2023). ...
... mechanisms, and early detection of potential safety concerns, leading to informed decision-making and optimization of drug candidates (Beilmann et al., 2019). The environmental monitoring and biomonitoring programs utilize AI/ML algorithms and omics-based biomarkers to assess chemical exposures and environmental health risks (Scott et al., 2023). For instance, transcriptomics and proteomics profiling of aquatic organisms exposed to pollutants enable the identification of molecular biomarkers indicative of environmental stress and contaminant effects, informing regulatory decisions and ecosystem management strategies (Hampel et al., 2016). ...
Chemical risk assessment plays a pivotal role in safeguarding public health and environmental safety by evaluating the potential hazards and risks associated with chemical exposures. In recent years, the convergence of artificial intelligence (AI), machine learning (ML), and omics technologies has revolutionized the field of chemical risk assessment, offering new insights into toxicity mechanisms, predictive modeling, and risk management strategies. This perspective review explores the synergistic potential of AI/ML and omics in deciphering clastogen-induced genomic instability for carcinogenic risk prediction. We provide an overview of key findings, challenges, and opportunities in integrating AI/ML and omics technologies for chemical risk assessment, highlighting successful applications and case studies across diverse sectors. From predicting genotoxicity and mutagenicity to elucidating molecular pathways underlying carcinogenesis, integrative approaches offer a comprehensive framework for understanding chemical exposures and mitigating associated health risks. Future perspectives for advancing chemical risk assessment and cancer prevention through data integration, advanced machine learning techniques, translational research, and policy implementation are discussed. By implementing the predictive capabilities of AI/ML and omics technologies, researchers and policymakers can enhance public health protection, inform regulatory decisions, and promote sustainable development for a healthier future.
... On the basis of mathematical principles and computer science, AI and ML methodology trains algorithms to predict outcomes and probabilities of interest [9][10][11] . A parallel review article reviews the workshop participants' recommendations regarding the roles of AI and ML for astronaut, ecosystem and precision space health 12 . ...
... Due to limited bandwidth in space, our efforts should focus on developing multi-faceted solutions including pre-training lightweight models on larger Earth-bound datasets, federated training 166 , edge computing 167 and onboard processing. A more in-depth discussion of these solutions is in the accompanying workshop review article 12 . ...
Space biology research aims to understand fundamental spaceflight effects on organisms, develop foundational knowledge to support deep space exploration and, ultimately, bioengineer spacecraft and habitats to stabilize the ecosystem of plants, crops, microbes, animals and humans for sustained multi-planetary life. To advance these aims, the field leverages experiments, platforms, data and model organisms from both spaceborne and ground-analogue studies. As research is extended beyond low Earth orbit, experiments and platforms must be maximally automated, light, agile and intelligent to accelerate knowledge discovery. Here we present a summary of decadal recommendations from a workshop organized by the National Aeronautics and Space Administration on artificial intelligence, machine learning and modelling applications that offer solutions to these space biology challenges. The integration of artificial intelligence into the field of space biology will deepen the biological understanding of spaceflight effects, facilitate predictive modelling and analytics, support maximally automated and reproducible experiments, and efficiently manage spaceborne data and metadata, ultimately to enable life to thrive in deep space. © 2023, This is a U.S. Government work and not under copyright protection in the US; foreign
... As humanity ventures deeper into space, space omics will play an invaluable role in preserving crew health and performance. The integration of artificial intelligence-driven diagnostics, wearable biosensors and gene-based interventions could redefine how medical care is approached both in space and on Earth (Scott et al., 2023). Space omics will be essential for long-term space colonization efforts, ensuring that humans can thrive and not merely survive in extraterrestrial environments. ...
... Realtime and onboard processing of behavioral data can enable more advanced experimental paradigms and relieve the burden on crew time by reducing the need for manual animal welfare checks. Finally, the integration and automation of these technologies will be essential for developing "self-driving labs" and autonomous biomonitoring 124,125 . Summary and outlook Past and future use of animal models to understand adaptations to the space environment Animals have long been used in spaceflight exploration; while the initial focus was on whether humans could survive microgravity conditions, the shift has since moved to understanding how to remediate the damaging physiological impacts of being in the space environment for extended periods. ...
Animals have played a vital role in every stage of space exploration, from early sub-orbital flights to contemporary missions. New physiological and psychological challenges arise with plans to venture deeper into the solar system. Advances in chimeric and knockout animal models, along with genetic modification techniques have enhanced our ability to study the effects of microgravity in greater detail. However, increased investment in the purposeful design of habitats and payloads, as well as in AI-enhanced behavioral monitoring in orbit can better support the ethical and effective use of animals in deep space research.
... clinical, behavioral, environmental, physiological) from sensors and non-invasive wearables (e.g. biomarkers) will be integrated into learning systems to enhance predictive and clinical decision support [54]. In addition to astronaut support, AI will assist in automating and optimizing biological experiments in space via real-time in situ data processing and predictive modelling [55]. ...
... Scott et al. [43] published a review of a NASA workshop held in June 2021 regarding artificial intelligence and modeling for space biology, discussing the experience of biologists, clinicians, AI and machine learning experts, who wanted to articulate the requirements necessary to create an AI-driven, proactive precision space health (PSH) system. The design for the future of space health integrated four main factors-predictive, preventative, participatory, and personalized. ...
... The fields of space biology and space health are rapidly expanding and becoming more essential as humanity embarks on missions to the Moon, Mars, and other deep space missions beyond low Earth orbit. The heightened biomedical risks and new challenges associated with deep space missions ( 1 ) necessitate the discovery of new knowledge, the development of new health countermeasures and the creation of novel ecosystems ( 2 ,3 ), life support systems, crop production methods, in situ biomedical research and biomedical support capabilities ( 4 ). Supporting distant and long-duration missions is our new paradigm that requires biological and health-related data to be findable, accessible, interoperable and reusable (FAIR) ( 5 ,6 ). ...
Space biology and health data are critical for the success of deep space missions and sustainable human presence off-world. At the core of effectively managing biomedical risks is the commitment to open science principles, which ensure that data are findable, accessible, interoperable, reusable, reproducible and maximally open. The 2021 integration of the Ames Life Sciences Data Archive with GeneLab to establish the NASA Open Science Data Repository significantly enhanced access to a wide range of life sciences, biomedical-clinical and mission telemetry data alongside existing ‘omics data from GeneLab. This paper describes the new database, its architecture and new data streams supporting diverse data types and enhancing data submission, retrieval and analysis. Features include the biological data management environment for improved data submission, a new user interface, controlled data access, an enhanced API and comprehensive public visualization tools for environmental telemetry, radiation dosimetry data and ‘omics analyses. By fostering global collaboration through its analysis working groups and training programs, the open science data repository promotes widespread engagement in space biology, ensuring transparency and inclusivity in research. It supports the global scientific community in advancing our understanding of spaceflight's impact on biological systems, ensuring humans will thrive in future deep space missions.
... clinical, behavioral, environmental, physiological) from sensors and non-invasive wearables (e.g. biomarkers) will be integrated into learning systems to enhance predictive and clinical decision support [51]. In addition to astronaut support, AI will assist in automating and optimizing biological experiments in space via realtime in situ data processing and predictive modelling [52]. ...
We present the multi-mission MARTEMIS campaign, designed to affordably, comprehensively, and definitively retire risks of future Mars mission architectures and to deliver substantial science, inspiration, and national posture benefits to NASA and its international and commercial partners. The MARTEMIS concept won Best-in-Theme for the "Long-duration Mars Simulation on the Moon" category of the 2024 NASA Revolutionary AeroSpace Concepts Academic Linkage (RASC-AL) competition, and its primary innovation is the robust risk reduction afforded by thousands of crew-months on the Moon within a framework that also optimizes exploration time and the cost of the campaign. A trade study of 23 alternative campaign architectures, each with 1 to 17 missions of varying crew size, surface time, transit time, and margin parameters was conducted. The estimated lifecycle cost of each campaign architecture was traded off against novel benefit metrics aligned with NASA's Moon to Mars (M2M) Strategy and Objectives. These included metrics for the elimination of knowledge gaps, the degree of international participation, crew time available for science, as well as proxies for commercial alignment such as total investment in lunar infrastructure. The recommended MARTEMIS campaign of 13 missions was optimized using a Design of Experiments process and Standard Taguchi Orthogonal Arrays [1] for efficient knowledge acquisition. This report also includes comprehensive descriptions of the dual-habitat architecture; Concept of Operations (CONOPS); mission control operations under nominal, contingency, and emergency conditions; a full technology roadmap; and a risk burn-down plan. A total of 154 crew over 6 years representing 26 countries participate in MARTEMIS, resulting in a predicted 77% knowledge gap closure, 296 crew months of lunar science time, and the establishment of 56 habitable modules/rovers for a lifecycle cost of 1.6B per annum, and the remaining 112 crew representing all continents. Overall, MARTEMIS informs and accelerates the development of a safe and cost-effective lunar permanence campaign by NASA and its international and commercial partners. It promotes the required thematic objective of a safe and sustainable human presence on Mars, while also delivering immediate returns in terms of science, inspiration, national posture, and a robust foundation for a future lunar economy.
... Additionally, advancements in blockchain technology may provide new solutions for securing and verifying educational credentials and certifications. The synergy between these technologies and AI/cloud computing will likely drive innovation in teaching and learning, creating new opportunities for enhancing education [9]. ...
The integration of artificial intelligence (AI) and cloud computing is driving a revolution in educational technology (EdTech) by enhancing personalized learning experiences while ensuring robust data security. AI-powered learning platforms leverage sophisticated algorithms to adapt educational content and instructional methods to meet individual students' needs, preferences, and learning styles. This personalization promotes more effective and engaging learning experiences, addressing the diverse needs of students across various educational settings. Simultaneously, cloud computing provides the necessary infrastructure for scalable and flexible data management, enabling the storage and processing of vast amounts of educational data securely. Cloud-based solutions facilitate real-time access to learning resources, support collaborative learning environments, and ensure that sensitive student data is protected through advanced security measures. As educational institutions increasingly adopt these technologies, balancing the benefits of personalized learning with the imperative to safeguard data privacy and security becomes crucial. The future of AI-powered learning in the cloud promises further advancements in educational personalization and data protection, driving continued innovation in the EdTech sector and enhancing the overall learning experience.
... OSDR's dedication to comprehensive and unambiguous metadata, coupled with the utilization of the GLOpenAPI, underscores its readiness for analysis and artificial intelligence applications. The data query method illustrated here marks an initial step toward realizing the goal of Precision Space Health 10,11 . In cases where users seek to employ private medical datasets such as those collected on I4 for research purposes, an application process is in place that mandates approval from an institutional review board (IRB). ...
The increasing accessibility of commercial and private space travel necessitates a profound understanding of its impact on human health. The NASA Open Science Data Repository (OSDR) provides transparent and FAIR access to biological studies, notably the SpaceX Inspiration4 (I4) mission, which amassed extensive data from civilian astronauts. This dataset encompasses omics and clinical assays, facilitating comprehensive research on space-induced biological responses. These data allow for multi-modal, longitudinal assessments, bridging the gap between human and model organism studies. Crucially, community-driven data standards established by NASA’s OSDR Analysis Working Groups empower artificial intelligence and machine learning to glean invaluable insights, guiding future mission planning and health risk mitigation. This article presents a concise guide to access and analyze I4 data in OSDR, including programmatic access through GLOpenAPI. This pioneering effort establishes a precedent for post-mission health monitoring programs within space agencies, propelling research in the burgeoning field of commercial space travel’s impact on human physiology.
... Their proposal states that prepared, historical training data is used for model training and validation to construct the machine learning-based "Digital Twin Model." In research [15], scientists look into how to use machine learning and physics-based models to create a digital twin that can detect structural damage to wind turbines in real time. Performance of ML method in handling a substantial volume of IoT data can be leveraged by converting the physical models into one. ...
A new paradigm and technology at vanguard of Industry 4.0 revolution is digital twin (DT), which seeks to use virtual counterpart in real time to describe behaviours of physical things. Its expansion has been aided by application of DT in predictive maintenance. Healthcare system requires intelligent architecture with the use of cutting-edge technology. In terms of outcomes, speed, efficiency, new smart methods are contrasted with traditional healthcare method. The objective of this study is to present a unique approach for cyber twin recognition in augmented reality and virtual reality models for monitoring infants in intensive care units. The approach is based on a 6G healthcare network 4.0 and machine learning models. Here, a convolutional probabilistic multilayer perceptron neural network with 6G healthcare network 4.0 has been used to do machine learning for the ICU-based infant monitoring system. By examining breathing data and saturated blood oxygen level (SpO2), device will also be able to identify serious respiratory diseases. The cyber twin protection model, which is based on the cloud virtual software defined network model, improves network security. Throughput, latency, QoS, training accuracy, validation accuracy, network security, and network robustness are all considered in experimental analysis. Proposed technique attained throughput 91%, latency 81%, QoS 86%, training accuracy 89%, validation accuracy 95%, network security 88%, network robustness 82%.
... OSDR's dedication to comprehensive and unambiguous metadata, coupled with the utilization of the GLOpenAPI, underscores its readiness for analysis and artificial intelligence applications. The data query method illustrated here marks an initial step toward realizing the goal of Precision Space Health [9,10]. In cases where users seek to employ private medical datasets such as those collected on I4 for research purposes, an application process is in place that mandates approval from an institutional review board (IRB). ...
The increasing accessibility of commercial and private space travel necessitates a profound understanding of its impact on human health. The NASA Open Science Data Repository (OSDR) provides transparent and FAIR access to biological studies, notably the SpaceX Inspiration4 (I4) mission, which amassed extensive data from civilian astronauts. This dataset encompasses omics and clinical assays, facilitating comprehensive research on space-induced biological responses. These data allow for multi-modal, longitudinal assessments, bridging the gap between human and model organism studies.
Crucially, community-driven data standards established by NASA's OSDR Analysis Working Groups empower artificial intelligence and machine learning to glean invaluable insights, guiding future mission planning and health risk mitigation. This article presents a concise guide to access and analyze I4 data in OSDR, including programmatic access through GLOpenAPI. This pioneering effort establishes a precedent for post-mission health monitoring programs within space agencies, propelling research in the burgeoning field of commercial space travel's impact on human physiology.
... The systems will use on-board models capable of autonomously assessing, aggregating, and analysing multi-layered data to provide clinical decision support. Leveraging artificial intelligence and machine learning, these systems will rely on high-quality, analysis-ready data collected across three layers: habitat environment (physical, chemical, biological), non-invasive human data (cognitive tests, physiological measurements, questionnaires), and molecular/cellular biomarkers from swabs and blood samples [3,4,5]. Collaborating across multiple international and interdisciplinary institutions, this experiment serves as a pilot for future projects, evaluating data collection effectiveness and exploring integration into a unified system. ...
Exploration-and specifically human exploration-of the Moon and Mars has been of interest for the space community and general public for many years. However, these missions possess significant risks which might be mitigated through testing the technology in terrestrial, space analogous environments. ICEE.Space, a startup funded by the ESA BIC, Czech Republic, conducts such analogue missions focusing on subsurface locations in lava tubes. Two analogue missions were conducted by ICEE.Space in lava tubes in Iceland, namely CHILL ICE-1 in 2021 and CHILL ICE-2 in 2022, with several corresponding publications already online. Building on the legacy of these missions, ICEE Space collaborated with the Astroland Interplanetary Agency in Santander, Spain which owns a subsurface analog site in karst caves in Cantabria, Spain, for the APICES mission in August 2023. Astroland Interplanetary Agency is coordinated by European Moon and Mars and the mission station serves as a scientific lab, training facility, and analogue of Mars. The overarching objective of APICES was to assess and expand the in-house competencies of ICEE.Space, with the goal to create standard and adaptable missions at new sites with a range of diverse natural environments. The APICES mission had the advantage of an existing infrastructure, habitat, equipment, control centre, and the experience of already ongoing missions in the cave. A key difference to previous missions and campaigns hosted by ICEE.Space was the greatly reduced onsite Mission Control Centre (MCC) crew of 4, that was responsible for the execution of the tasks and accomplishing on-site mission objectives involving 6 Analogue Astronauts (AA)-versus a ratio of 25:3 (MCC:AA) for CHILL-ICE missions. Assessing and comparing the large and completely in-house CHILL-ICE missions with the reduced collaborated APICES mission, will give a good baseline for future optimization of processes, reusability, and scalability for ICEE.Space. The research objectives of APICES were multifold and the overview of the mission was presented at the IAC 2023. Facilitation of scientific research in multiple domains, especially high quality human and microbial research, conducting state of art research in life sciences and human factors, and bringing in technological and protocol inventions were the main pillars of the APICES mission. The conducted experiments have the long-term goal to be repeated in future ICEE.Space campaign locations and to help optimise the protocols that ICEE.Space plans to use for future research.
... The systems will use on-board models capable of autonomously assessing, aggregating, and analysing multi-layered data to provide clinical decision support. Leveraging artificial intelligence and machine learning, these systems will rely on high-quality, analysis-ready data collected across three layers: habitat environment (physical, chemical, biological), non-invasive human data (cognitive tests, physiological measurements, questionnaires), and molecular/cellular biomarkers from swabs and blood samples [3,4,5]. Collaborating across multiple international and interdisciplinary institutions, this experiment serves as a pilot for future projects, evaluating data collection effectiveness and exploring integration into a unified system. ...
Exploration-and specifically human exploration-of the Moon and Mars has been of interest for the space community and general public for many years. However, these missions possess significant risks which might be mitigated through testing the technology in terrestrial, space analogous environments. ICEE.Space, a startup funded by the ESA BIC, Czech Republic, conducts such analogue missions focusing on subsurface locations in lava tubes. Two analogue missions were conducted by ICEE.Space in lava tubes in Iceland, namely CHILL ICE-1 in 2021 and CHILL ICE-2 in 2022, with several corresponding publications already online. Building on the legacy of these missions, ICEE Space collaborated with the Astroland Interplanetary Agency in Santander, Spain which owns a subsurface analog site in karst caves in Cantabria, Spain, for the APICES mission in August 2023. Astroland Interplanetary Agency is coordinated by European Moon and Mars and the mission station serves as a scientific lab, training facility, and analogue of Mars. The overarching objective of APICES was to assess and expand the in-house competencies of ICEE.Space, with the goal to create standard and adaptable missions at new sites with a range of diverse natural environments. The APICES mission had the advantage of an existing infrastructure, habitat, equipment, control centre, and the experience of already ongoing missions in the cave. A key difference to previous missions and campaigns hosted by ICEE.Space was the greatly reduced onsite Mission Control Centre (MCC) crew of 4, that was responsible for the execution of the tasks and accomplishing on-site mission objectives involving 6 Analogue Astronauts (AA)-versus a ratio of 25:3 (MCC:AA) for CHILL-ICE missions. Assessing and comparing the large and completely in-house CHILL-ICE missions with the reduced collaborated APICES mission, will give a good baseline for future optimization of processes, reusability, and scalability for ICEE.Space. The research objectives of APICES were multifold and the overview of the mission was presented at the IAC 2023. Facilitation of scientific research in multiple domains, especially high quality human and microbial research, conducting state of art research in life sciences and human factors, and bringing in technological and protocol inventions were the main pillars of the APICES mission. The conducted experiments have the long-term goal to be repeated in future ICEE.Space campaign locations and to help optimise the protocols that ICEE.Space plans to use for future research.
Adaptable display with spatial imaging, fostering advancements in extended reality with unconventional form requirements, is indispensable in scientific research, telemedicine, rescue, and space exploration. The adjustable photon spin angular momentum derived from chiral optical materials offer applicative lights for binocular stereo imaging displays, thus allowing an unimaginable immersive experience while maintaining awareness of surroundings. However, current chiral illuminant struggles to obtain adequate electroluminescence asymmetry during power-on display. Here, we present a designed self-positioning strategy to build new flexible spatial displays, integrating numerous multilayered circularly polarized electroluminescent microdevices, for real-time depth information control on the screen. With the devices’ luminescence asymmetry value of up to 1.0 under electro-excitation, we visualize third-dimensional information using our chiral material-integrated tablet. Afterward, combined with a robot, we realize a series of remote human-machine interaction operations based on extended reality conditions. Our adaptable spatial display bridges the gap between virtuality and reality, making pioneering explorations in chiral luminous fields for extended reality and beyond.
Defecation, a fundamental physiological process, remains underexplored despite its importance in human health. To address this gap, a smart toilet system is developed that enables real‐time monitoring of defecation behaviors. Analyzing 45 defecation events from 11 participants, key defecation parameters are identified, including stool dropping duration, stool thickness, and eu‐tenesmus interval. Stool dropping duration follows a log‐normal distribution, with longer durations (>5 s) linked to lower Bristol Stool Form Scale (BSFS) scores, suggesting constipation (p = 0.008 for BSFS1/2/3 vs BSFS5/6/7). Stool thickness decreases with increasing BSFS scores (p = 5 × 10⁻⁶ for BSFS1/2/3 vs BSFS5/6/7), validating its role as an objective marker for bowel function. Eu‐tenesmus is introduced, defined as the interval between the last stool drop and cleansing, averaging 74.8 s. It shows significant gender differences (p = 0.014) but no correlation with stool consistency, suggesting its potential as an independent biomarker for gut health. Defecation behaviors between humans and animals is also compared in detail. Longitudinal monitoring demonstrates the potential for personalized health tracking and dietary recommendations. Furthermore, the feasibility of biometric identification is established using 11 defecation‐related parameters, including stool properties and cleansing behavior. These features enable high participant differentiation, supporting non‐invasive identity verification.
Good linearity and radiation resistance of conductance updates in memristive synapses are crucial for their use in neuromorphic computing chips in space. Here, the Au/Al:HfOx/TiOx/Ti memristive synapses with good linearity are prepared. The effects of irradiation on the memristive performances are studied through 60Co -ray irradiation experiments. The effect of irradiation on the image recognition accuracy of the neural network based on the memristive synapse crossbar array is predicted. The results show that the devices maintained good conductance update linearity under irradiation. When the 60Co -ray irradiation reaches 1 Mrad(Si), the nonlinearity (NL) of conductance update only increases from 0.096 to 0.163, and the image recognition accuracy of the memristor neural network decreases by about 2% (from 91% to 89%). The initial value of oxygen defect content in HfOx resistive materials after Al doping modification is relatively high (36%), which can explain why irradiation has little effect on conductance update linearity and recognition accuracy. These results suggest that the Au/Al:HfOx/TiOx/Ti memristors show good radiation resistance under 60Co -ray irradiation, which makes them promising candidates for artificial synapses in space applications.
NASA’s space life sciences research programs established a decades-long legacy of enhancing our ability to safely explore the cosmos. From Skylab and the Space Shuttle Program to the NASA Balloon Program and the International Space Station National Lab, these programs generated priceless data that continue to paint a vibrant picture of life in space. These data are available to the scientific community in various data repositories, including the NASA Ames Life Sciences Data Archive (ALSDA) and NASA GeneLab. Here we recognize the 30-year anniversary of data access through ALSDA and the 10-year anniversary of GeneLab.
Understanding the dynamic adaptive plasticity of microorganisms has been advanced by studying their responses to extreme environments. Spaceflight research platforms provide a unique opportunity to study microbial characteristics in new extreme adaptational modes, including sustained exposure to reduced forces of gravity and associated low fluid shear force conditions. Under these conditions, unexpected microbial responses occur, including alterations in virulence, antibiotic and stress resistance, biofilm formation, metabolism, motility, and gene expression, which are not observed using conventional experimental approaches. Here, we review biological and physical mechanisms that regulate microbial responses to spaceflight and spaceflight analog environments from both the microbe and host-microbe perspective that are relevant to human health and habitat sustainability. We highlight instrumentation and technology used in spaceflight microbiology experiments, their limitations, and advances necessary to enable next-generation research. As spaceflight experiments are relatively rare, we discuss ground-based analogs that mimic aspects of microbial responses to reduced gravity in spaceflight, including those that reduce mechanical forces of fluid flow over cell surfaces which also simulate conditions encountered by microorganisms during their terrestrial lifecycles. As spaceflight mission durations increase with traditional astronauts and commercial space programs send civilian crews with underlying health conditions, microorganisms will continue to play increasingly critical roles in health and habitat sustainability, thus defining a new dimension of occupational health. The ability of microorganisms to adapt, survive, and evolve in the spaceflight environment is important for future human space endeavors and provides opportunities for innovative biological and technological advances to benefit life on Earth.
Recent years have witnessed tremendous advances in machine learning techniques for wearable sensors and bioelectronics, which play an essential role in real-time sensing data analysis to provide clinical-grade information for personalized healthcare. To this end, supervised learning and unsupervised learning algorithms have emerged as powerful tools, allowing for the detection of complex patterns and relationships in large, high-dimensional data sets. In this Review, we aim to delineate the latest advancements in machine learning for wearable sensors, focusing on key developments in algorithmic techniques, applications, and the challenges intrinsic to this evolving landscape. Additionally, we highlight the potential of machine-learning approaches to enhance the accuracy, reliability, and interpretability of wearable sensor data and discuss the opportunities and limitations of this emerging field. Ultimately, our work aims to provide a roadmap for future research endeavors in this exciting and rapidly evolving area.
Spaceflight induces molecular, cellular and physiological shifts in astronauts and poses myriad biomedical challenges to the human body, which are becoming increasingly relevant as more humans venture into space1–6. Yet current frameworks for aerospace medicine are nascent and lag far behind advancements in precision medicine on Earth, underscoring the need for rapid development of space medicine databases, tools and protocols. Here we present the Space Omics and Medical Atlas (SOMA), an integrated data and sample repository for clinical, cellular and multi-omic research profiles from a diverse range of missions, including the NASA Twins Study⁷, JAXA CFE study8,9, SpaceX Inspiration4 crew10–12, Axiom and Polaris. The SOMA resource represents a more than tenfold increase in publicly available human space omics data, with matched samples available from the Cornell Aerospace Medicine Biobank. The Atlas includes extensive molecular and physiological profiles encompassing genomics, epigenomics, transcriptomics, proteomics, metabolomics and microbiome datasets, which reveal some consistent features across missions, including cytokine shifts, telomere elongation and gene expression changes, as well as mission-specific molecular responses and links to orthologous, tissue-specific mouse datasets. Leveraging the datasets, tools and resources in SOMA can help to accelerate precision aerospace medicine, bringing needed health monitoring, risk mitigation and countermeasure data for upcoming lunar, Mars and exploration-class missions.
The recent acceleration of commercial, private, and multi-national spaceflight has created an unprecedented level of activity in low Earth orbit (LEO), concomitant with the highest-ever number of crewed missions entering space and preparations for exploration-class (>1 year) missions. Such rapid advancement into space from many new companies, countries, and space-related entities has enabled a“Second Space Age.” This new era is also poised to leverage, for the first time, modern tools and methods of molecular biology and precision medicine, thus enabling precision aerospace medicine for the crews. The applications of these biomedical technologies and algorithms are diverse, encompassing multi-omic, single-cell, and spatial biology tools to investigate human and microbial responses to spaceflight. Additionally, they extend to the development of new imaging techniques, real-time cognitive assessments, physiological monitoring, and personalized risk profiles tailored for astronauts. Furthermore, these technologies enable advancements in pharmacogenomics (PGx), as well as the identification of novel spaceflight biomarkers and the development of corresponding countermeasures. In this review, we highlight some of the recent biomedical research from the National Aeronautics and Space Administration (NASA), Japan Aerospace Exploration Agency (JAXA), European Space Agency (ESA), and other space agencies, and also detail the commercial spaceflight sector’s (e.g. SpaceX, Blue Origin, Axiom, Sierra Space) entrance into aerospace medicine and space biology, the first aerospace medicine biobank, and the myriad upcoming missions that will utilize these tools to ensure a permanent human presence beyond LEO, venturing out to other planets and moons.
The present status of artificial intelligence (AI) and the Internet of Things (IoT) research is primarily concerned with the ways in which these technologies may contribute to sustainable development and the common good. The accomplishment of significant environmental sustainability using AI has now attracted researchers to cope with current environmental challenges related to biomonitoring and control of pollution, preventing the endangered species, conquering climate change, integrated waste management, and so forth. Biomonitoring deals with the measurement of the level of pollutants in an organism that is responsible for physiochemical, molecular, and genetic alteration in cells, tissues, and organs. Biomonitoring can maintain the quality of the environment. Although the IoT and AI have tremendous benefits, e.g., automation, time saving, unbiasedness, auto calibration, the ability to do tasks in harsh environmental conditions, fast and accurate forecasting, and alike. But, on the other hand, it could lead to high energy consumption, generating lots of toxic e-waste, higher costs, unemployment, emotionlessness, a lower rate of creativity, etc. Hence, the presentation and the right blend of AI, IoT, and humans for a sustainable and eco-friendly environment need to be established. Moreover, the prime concern is the management of complex data security and consistent and strong internet connectivity throughout the cities and villages.
Antarctica provides a unique environment for studying human adaptability, characterized by controlled conditions, limited sensory stimulation, and significant challenges in logistics and communication. This longitudinal study investigates the relationship between stress indicators, with a specific focus on mean sleep heart rate, during a COVID-19 quarantine and subsequent 83 days long summer Antarctic expedition at the J. G. Mendel Czech Antarctic Station. Our novel approach includes daily recordings of sleep heart rate and weekly assessments of emotions, stress, and sleep quality. Associations between variables were analyzed using the generalized least squares method, providing unique insights into nuances of adaptation. The results support previous findings by providing empirical evidence on the stress reducing effect of Antarctic summer expedition and highlight the importance of previous experience and positive emotions, with the novel contribution of utilizing physiological data in addition to psychological measures. High-frequency sampling and combination of psychological and physiological data addresses a crucial gap in the research of stress. This study contributes valuable knowledge to the field of psychophysiology and has implications for expedition planners, research organizations, teams in action settings, pandemic prevention protocols, global crises, and long-duration spaceflight missions. Comprehensive insights promote the well-being and success of individuals in extreme conditions.
Background: Understanding and countering the well-established negative health consequences of spaceflight remains a primary challenge preventing safe deep space exploration. Targeted/personalized therapeutics are at the forefront of space medicine strategies, and cross-species molecular signatures now define the ‘typical’ spaceflight response. However, a lack of direct genotype–phenotype associations currently limits the robustness and, therefore, the therapeutic utility of putative mechanisms underpinning pathological changes in flight. Methods: We employed the worm Caenorhabditis elegans as a validated model of space biology, combined with ‘NemaFlex-S’ microfluidic devices for assessing animal strength production as one of the most reproducible physiological responses to spaceflight. Wild-type and dys-1 (BZ33) strains (a Duchenne muscular dystrophy (DMD) model for comparing predisposed muscle weak animals) were cultured on the International Space Station in chemically defined media before loading second-generation gravid adults into NemaFlex-S devices to assess individual animal strength. These same cultures were then frozen on orbit before returning to Earth for next-generation sequencing transcriptomic analysis. Results: Neuromuscular strength was lower in flight versus ground controls (16.6% decline, p < 0.05), with dys-1 significantly more (23% less strength, p < 0.01) affected than wild types. The transcriptional gene ontology signatures characterizing both strains of weaker animals in flight strongly corroborate previous results across species, enriched for upregulated stress response pathways and downregulated mitochondrial and cytoskeletal processes. Functional gene cluster analysis extended this to implicate decreased neuronal function, including abnormal calcium handling and acetylcholine signaling, in space-induced strength declines under the predicted control of UNC-89 and DAF-19 transcription factors. Finally, gene modules specifically altered in dys-1 animals in flight again cluster to neuronal/neuromuscular pathways, suggesting strength loss in DMD comprises a strong neuronal component that predisposes these animals to exacerbated strength loss in space. Conclusions: Highly reproducible gene signatures are strongly associated with space-induced neuromuscular strength loss across species and neuronal changes in calcium/acetylcholine signaling require further study. These results promote targeted medical efforts towards and provide an in vivo model for safely sending animals and people into deep space in the near future.
Rules are needed for human research in commercial spaceflight
Space biology research aims to understand fundamental spaceflight effects on organisms, develop foundational knowledge to support deep space exploration and, ultimately, bioengineer spacecraft and habitats to stabilize the ecosystem of plants, crops, microbes, animals and humans for sustained multi-planetary life. To advance these aims, the field leverages experiments, platforms, data and model organisms from both spaceborne and ground-analogue studies. As research is extended beyond low Earth orbit, experiments and platforms must be maximally automated, light, agile and intelligent to accelerate knowledge discovery. Here we present a summary of decadal recommendations from a workshop organized by the National Aeronautics and Space Administration on artificial intelligence, machine learning and modelling applications that offer solutions to these space biology challenges. The integration of artificial intelligence into the field of space biology will deepen the biological understanding of spaceflight effects, facilitate predictive modelling and analytics, support maximally automated and reproducible experiments, and efficiently manage spaceborne data and metadata, ultimately to enable life to thrive in deep space. © 2023, This is a U.S. Government work and not under copyright protection in the US; foreign
Lunar dust (LD), the component of lunar regolith with particle sizes less than 20 μm, covers the surface of the Moon. Due to its fineness, jagged edges, and electrostatic charge, LD adheres to and coats almost any surface it contacts. As a result, LD poses known risks to the proper functioning of electronic and mechanical equipment on the lunar surface. However, its mechanical irritancy and chemical reactivity may also pose serious health risks to humans by a number of mechanisms. While Apollo astronauts reported mild short-lived respiratory symptoms, the spectrum of health effects associated with high-dose acute exposure or chronic low-dose exposure are not yet well-understood. This paper explores known and potential human risks of exposure to LD which are thought to be important in planning upcoming lunar missions and planetary surface work.
The development and deployment of machine learning systems can be executed easily with modern tools, but the process is typically rushed and means-to-an-end. Lack of diligence can lead to technical debt, scope creep and misaligned objectives, model misuse and failures, and expensive consequences. Engineering systems, on the other hand, follow well-defined processes and testing standards to streamline development for high-quality, reliable results. The extreme is spacecraft systems, with mission critical measures and robustness throughout the process. Drawing on experience in both spacecraft engineering and machine learning (research through product across domain areas), we’ve developed a proven systems engineering approach for machine learning and artificial intelligence: the Machine Learning Technology Readiness Levels framework defines a principled process to ensure robust, reliable, and responsible systems while being streamlined for machine learning workflows, including key distinctions from traditional software engineering, and a lingua franca for people across teams and organizations to work collaboratively on machine learning and artificial intelligence technologies. Here we describe the framework and elucidate with use-cases from physics research to computer vision apps to medical diagnostics. The development of machine learning systems has to ensure their robustness and reliability. The authors introduce a framework that defines a principled process of machine learning system formation, from research to production, for various domains and data scenarios.
NASA and commercial spaceflight companies will soon be retuning humans to the Moon and then eventually sending them on to Mars. These distant planetary destinations will pose new risks—in particular for the health of the astronaut crews. The bulk of the evidence characterizing human health and performance in spaceflight has come from missions in Low Earth Orbit. As missions last longer and travel farther from Earth, medical risk is expected to contribute an increasing proportion of total mission risk. To date, there have been no reliable estimates of how much. The Integrated Medical Model (IMM) is a Probabilistic Risk Assessment (PRA) Monte-Carlo simulation tool developed by NASA for medical risk assessment. This paper uses the IMM to provide an evidence-based, quantified medical risk estimate comparison across different spaceflight mission durations. We discuss model limitations and unimplemented capabilities providing insight into the complexity of medical risk estimation for human spaceflight. The results enable prioritization of medical needs in the context of other mission risks. These findings provide a reasonable bounding estimate for medical risk in missions to the Moon and Mars and hold value for risk managers and mission planners in performing cost-benefit trades for mission capability and research investments.
Continued COVID-19 surges have highlighted the need for widespread testing in addition to vaccination for disease containment. SARS-COV-2 RNA can be found in faecal matter, making human stool another potential source for COVID-19 diagnostics. In this commentary, we highlight potential strategies to use a smart toilet platform to passively monitor COVID-19 surges, enabling earlier detection of infected individuals and promoting public health.
During space missions, astronauts are faced with a variety of challenges that are unique to spaceflight and that have been known to cause physiological changes in humans over a period of time. Several of these changes occur at the microbiome level, a complex ensemble of microbial communities residing in various anatomic sites of the human body, with a pivotal role in regulating the health and behavior of the host. The microbiome is essential for day-to-day physiological activities, and alterations in microbiome composition and function have been linked to various human diseases. For these reasons, understanding the impact of spaceflight and space conditions on the microbiome of astronauts is important to assess significant health risks that can emerge during long-term missions and to develop countermeasures. Here, we review various conditions that are caused by long-term space exploration and discuss the role of the microbiome in promoting or ameliorating these conditions, as well as space-related factors that impact microbiome composition. The topics explored pertain to microgravity, radiation, immunity, bone health, cognitive function, gender differences and pharmacomicrobiomics. Connections are made between the trifecta of spaceflight, the host and the microbiome, and the significance of these interactions for successful long-term space missions.
Objective
Early identification of chronic diseases is a pillar of precision medicine as it can lead to improved outcomes, reduction of disease burden, and lower healthcare costs. Predictions of a patient’s health trajectory have been improved through the application of machine learning approaches to electronic health records (EHRs). However, these methods have traditionally relied on “black box” algorithms that can process large amounts of data but are unable to incorporate domain knowledge, thus limiting their predictive and explanatory power. Here, we present a method for incorporating domain knowledge into clinical classifications by embedding individual patient data into a biomedical knowledge graph.
Materials and Methods
A modified version of the Page rank algorithm was implemented to embed millions of deidentified EHRs into a biomedical knowledge graph (SPOKE). This resulted in high-dimensional, knowledge-guided patient health signatures (ie, SPOKEsigs) that were subsequently used as features in a random forest environment to classify patients at risk of developing a chronic disease.
Results
Our model predicted disease status of 5752 subjects 3 years before being diagnosed with multiple sclerosis (MS) (AUC = 0.83). SPOKEsigs outperformed predictions using EHRs alone, and the biological drivers of the classifiers provided insight into the underpinnings of prodromal MS.
Conclusion
Using data from EHR as input, SPOKEsigs describe patients at both the clinical and biological levels. We provide a clinical use case for detecting MS up to 5 years prior to their documented diagnosis in the clinic and illustrate the biological features that distinguish the prodromal MS state.
The Spaceflight Associated Neuro-ocular Syndrome (SANS), associated with the headward fluid shifts incurred in microgravity during long-duration missions, remains a high-priority health and performance risk for human space exploration. To help characterize the pathophysiology of SANS, NASA’s VESsel GENeration Analysis (VESGEN) software was used to map and quantify vascular adaptations in the retina before and after 70 days of bed rest at 6-degree Head-Down Tilt (HDT), a well-studied microgravity analog. Results were compared to the retinal vascular response of astronauts following 6-month missions to the International Space Station (ISS). By mixed effects modeling, the trends of vascular response were opposite. Vascular density decreased significantly in the 16 retinas of eight astronauts and in contrast, increased slightly in the ten retinas of five subjects after HDT (although with limited significance). The one astronaut retina diagnosed with SANS displayed the greatest vascular loss. Results suggest that microgravity is a major variable in the retinal mediation of fluid shifts that is not reproduced in this HDT bed rest model.
There are medical treatment vulnerabilities in longer-duration space missions present in the current International Space Station crew health care system with risks, arising from spaceflight-accelerated pharmaceutical degradation and resupply lag times. Bioregenerative life support systems may be a way to close this risk gap by leveraging in situ resource utilization (ISRU) to perform pharmaceutical synthesis and purification. Recent literature has begun to consider biological ISRU using microbes and plants as the basis for pharmaceutical life support technologies. However, there has not yet been a rigorous analysis of the processing and quality systems required to implement biologically produced pharmaceuticals for human medical treatment. In this work, we use the equivalent system mass (ESM) metric to evaluate pharmaceutical purification processing strategies for longer-duration space exploration missions. Monoclonal antibodies, representing a diverse therapeutic platform capable of treating multiple space-relevant disease states, were selected as the target products for this analysis. We investigate the ESM resource costs (mass, volume, power, cooling, and crew time) of an affinity-based capture step for monoclonal antibody purification as a test case within a manned Mars mission architecture. We compare six technologies (three biotic capture methods and three abiotic capture methods), optimize scheduling to minimize ESM for each technology, and perform scenario analysis to consider a range of input stream compositions and pharmaceutical demand. We also compare the base case ESM to scenarios of alternative mission configuration, equipment models, and technology reusability. Throughout the analyses, we identify key areas for development of pharmaceutical life support technology and improvement of the ESM framework for assessment of bioregenerative life support technologies.
Clinical workflows in oncology depend on predictive and prognostic biomarkers. However, the growing number of complex biomarkers contributes to costly and delayed decision-making in routine oncology care and treatment. As cancer is expected to rank as the leading cause of death and the single most important barrier to increasing life expectancy in the 21st century, there is a major emphasis on precision medicine, particularly individualisation of treatment through better prediction of patient outcome. Over the past few years, both surgical and pathology specialties have suffered cutbacks and a low uptake of pathology specialists means a solution is required to enable high-throughput screening and personalised treatment in this area to alleviate bottlenecks. Digital imaging in pathology has undergone an exponential period of growth. Deep-learning (DL) platforms for hematoxylin and eosin (H&E) image analysis, with preliminary artificial intelligence (AI)-based grading capabilities of specimens, can evaluate image characteristics which may not be visually apparent to a pathologist and offer new possibilities for better modelling of disease appearance and possibly improve the prediction of disease stage and patient outcome. Although digital pathology and AI are still emerging areas, they are the critical components for advancing personalised medicine. Integration of transcriptomic analysis, clinical information and AI-based image analysis is yet an uncultivated field by which healthcare professionals can make improved treatment decisions in cancer. This short review describes the potential application of integrative AI in offering better detection, quantification, classification, prognosis and prediction of breast and prostate cancer and also highlights the utilisation of machine learning systems in biomarker evaluation.
Significance
The digital twin paradigm holds great promise for medicine, even though many technical and scientific challenges remain to be overcome, most importantly the efficient integration of many heterogeneous component models. This is an unsolved problem even in industry. It has long been understood that such models need to be built in a modular fashion, connecting together component models of individual biological processes. In conventional implementations, however, the dependency structure of the modules reflects the dependencies among these processes, making it all but impossible to modify or expand the digital twin without breaking it. This paper presents a fundamental reorganization of the internal digital twin architecture into a hub-and-spokes design that completely circumvents this dependency problem.
Traditionally underutilized human excreta have emerged as a rich source of digital biomarkers for disease prevention and early detection. In this Comment, we highlight the breadth of digital biomarkers that can be extracted from human excreta and their potential uses in the context of ‘precision health’.
Ultrasound‐guided regional anesthesia involves visualizing sono‐anatomy to guide needle insertion and the perineural injection of local anesthetic. Anatomical knowledge and recognition of anatomical structures on ultrasound are known to be imperfect amongst anesthesiologists. This investigation evaluates the performance of an assistive artificial intelligence (AI) system in aiding the identification of anatomical structures on ultrasound. Three independent experts in regional anesthesia reviewed 40 ultrasound scans of seven body regions. Unmodified ultrasound videos were presented side‐by‐side with AI‐highlighted ultrasound videos. Experts rated the overall system performance, ascertained whether highlighting helped identify specific anatomical structures, and provided opinion on whether it would help confirm the correct ultrasound view to a less experienced practitioner. Two hundred and seventy‐five assessments were performed (five videos contained inadequate views); mean highlighting scores ranged from 7.87 to 8.69 (out of 10). The Kruskal–Wallis H‐test showed a statistically significant difference in the overall performance rating (χ²[6] = 36.719, asymptotic p < 0.001); regions containing a prominent vascular landmark ranked most highly. AI‐highlighting was helpful in identifying specific anatomical structures in 1330/1334 cases (99.7%) and for confirming the correct ultrasound view in 273/275 scans (99.3%). These data demonstrate the clinical utility of an assistive AI system in aiding the identification of anatomical structures on ultrasound during ultrasound‐guided regional anesthesia. Whilst further evaluation must follow, such technology may present an opportunity to enhance clinical practice and energize the important field of clinical anatomy amongst clinicians.
The molecular signaling cascades that regulate angiogenesis and microvascular remodeling are fundamental to normal development, healthy physiology, and pathologies such as inflammation and cancer. Yet quantifying such complex, fractally branching vascular patterns remains difficult. We review application of NASA’s globally available, freely downloadable VESsel GENeration (VESGEN) Analysis software to numerous examples of 2D vascular trees, networks, and tree-network composites. Upon input of a binary vascular image, automated output includes informative vascular maps and quantification of parameters such as tortuosity, fractal dimension, vessel diameter, area, length, number, and branch point. Previous research has demonstrated that cytokines and therapeutics such as vascular endothelial growth factor, basic fibroblast growth factor (fibroblast growth factor-2), transforming growth factor-beta-1, and steroid triamcinolone acetonide specify unique “fingerprint” or “biomarker” vascular patterns that integrate dominant signaling with physiological response. In vivo experimental examples described here include vascular response to keratinocyte growth factor, a novel vessel tortuosity factor; angiogenic inhibition in humanized tumor xenografts by the anti-angiogenesis drug leronlimab; intestinal vascular inflammation with probiotic protection by Saccharomyces boulardii , and a workflow programming of vascular architecture for 3D bioprinting of regenerative tissues from 2D images. Microvascular remodeling in the human retina is described for astronaut risks in microgravity, vessel tortuosity in diabetic retinopathy, and venous occlusive disease.
Heart rhythm assessment is indispensable in diagnosis and management of many cardiac conditions and to study heart rate variability in healthy individuals. We present a proof-of-concept system for acquiring individual heart beats using smart speakers in a fully contact-free manner. Our algorithms transform the smart speaker into a short-range active sonar system and measure heart rate and inter-beat intervals (R-R intervals) for both regular and irregular rhythms. The smart speaker emits inaudible 18–22 kHz sound and receives echoes reflected from the human body that encode sub-mm displacements due to heart beats. We conducted a clinical study with both healthy participants and hospitalized cardiac patients with diverse structural and arrhythmic cardiac abnormalities including atrial fibrillation, flutter and congestive heart failure. Compared to electrocardiogram (ECG) data, our system computed R-R intervals for healthy participants with a median error of 28 ms over 12,280 heart beats and a correlation coefficient of 0.929. For hospitalized cardiac patients, the median error was 30 ms over 5639 heart beats with a correlation coefficient of 0.901. The increasing adoption of smart speakers in hospitals and homes may provide a means to realize the potential of our non-contact cardiac rhythm monitoring system for monitoring of contagious or quarantined patients, skin sensitive patients and in telemedicine settings. Anran Wang et al. present a contact-free method of monitoring individual heart beats by converting smart-speakers into active sonar systems. Their approach is capable of measuring heart rhythms with high accuracy in both healthy participants and hospitalized patients, and may be a useful healthcare tool for remote diagnosis or patient monitoring.
There has long been an interest in understanding how the hazards from spaceflight may trigger or exacerbate human diseases. With the goal of advancing our knowledge on physiological changes during space travel, NASA GeneLab provides an open-source repository of multi-omics data from real and simulated spaceflight studies. Alone, this data enables identification of biological changes during spaceflight, but cannot infer how that may impact an astronaut at the phenotypic level. To bridge this gap, Scalable Precision Medicine Oriented Knowledge Engine (SPOKE), a heterogeneous knowledge graph connecting biological and clinical data from over 30 databases, was used in combination with GeneLab transcriptomic data from six studies. This integration identified critical symptoms and physiological changes incurred during spaceflight.
Saliva omics has immense potential for non-invasive diagnostics, including monitoring very young or elderly populations, or individuals in remote locations. In this study, multiple saliva omics from an individual were monitored over three periods (100 timepoints) involving: (1) hourly sampling over 24 h without intervention, (2) hourly sampling over 24 h including immune system activation using the standard 23-valent pneumococcal polysaccharide vaccine, (3) daily sampling for 33 days profiling the post-vaccination response. At each timepoint total saliva transcriptome and proteome, and small RNA from salivary extracellular vesicles were profiled, including mRNA, miRNA, piRNA and bacterial RNA. The two 24-h periods were used in a paired analysis to remove daily variation and reveal vaccination responses. Over 18,000 omics longitudinal series had statistically significant temporal trends compared to a healthy baseline. Various immune response and regulation pathways were activated following vaccination, including interferon and cytokine signaling, and MHC antigen presentation. Immune response timeframes were concordant with innate and adaptive immunity development, and coincided with vaccination and reported fever. Overall, mRNA results appeared more specific and sensitive (timewise) to vaccination compared to other omics. The results suggest saliva omics can be consistently assessed for non-invasive personalized monitoring and immune response diagnostics.
Purpose:
Ocular structural and functional changes, collectively termed spaceflight-associated neuro-ocular syndrome (SANS), have been described in astronauts undergoing long-duration missions in the microgravity environment of the International Space Station. We tested the hypothesis that retinal vascular remodeling, particularly by smaller vessels, mediates the chronic headward fluid shifts associated with SANS.
Methods:
As a retrospective study, arterial and venous patterns extracted from 30° infrared Heidelberg Spectralis retinal images of eight crew members acquired before and after six-month missions were analyzed with NASA's recently released VESsel GENeration Analysis (VESGEN) software. Output parameters included the fractal dimension and overall vessel length density that was further classified into large and small vascular branching generations. Vascular results were compared with SANS-associated clinical ocular measures.
Results:
Significant postflight decreases in Df, Lv, and in smaller but not larger vessels were quantified in 11 of 16 retinas for arteries and veins (P value for Df, Lv, and smaller vessels in all 16 retinas were ≤0.033). The greatest vascular decreases occurred in the only retina displaying clinical evidence of SANS by choroidal folds and optic disc edema. In the remaining 15 retinas, decreases in vascular density from Df and Lv ranged from minimal to high by a custom Subclinical Vascular Pathology Index.
Conclusions:
Together with VESGEN, the Subclinical Vascular Pathology Index may represent a new, useful SANS biomarker for advancing the understanding of SANS etiology and developing successful countermeasures for long duration space exploration in microgravity, although further research is required to better characterize retinal microvascular adaptations.
Liquid biopsies based on cell-free DNA (cfDNA) or exosomes provide a noninvasive approach to monitor human health and disease but have not been utilized for astronauts. Here, we profile cfDNA characteristics, including fragment size, cellular deconvolution, and nucleosome positioning, in an astronaut during a year-long mission on the International Space Station, compared to his identical twin on Earth and healthy donors. We observed a significant increase in the proportion of cell-free mitochondrial DNA (cf-mtDNA) inflight, and analysis of post-flight exosomes in plasma revealed a 30-fold increase in circulating exosomes and patient-specific protein cargo (including brain-derived peptides) after the year-long mission. This longitudinal analysis of astronaut cfDNA during spaceflight and the exosome profiles highlights their utility for astronaut health monitoring, as well as cf-mtDNA levels as a potential biomarker for physiological stress or immune system responses related to microgravity, radiation exposure, and the other unique environmental conditions of spaceflight.
The increasing power consumption in the existing computation architecture presents grand challenges for the performance and reliability of very‐large‐scale integrated circuits. Inspired by the characteristics of the human brain for processing complicated tasks with low power, neuromorphic computing is intensively investigated for decreasing power consumption and enriching computation functions. Hardware implementation of neuromorphic computing with emerging devices substantially reduces power consumption down to a few mW cm⁻², compared with the central processing unit based on conventional Si complementary metal–oxide semiconductor (CMOS) technologies (50–100 W cm⁻²). Herein, a brief introduction on the characteristics of neuromorphic computing is provided. Then, emerging devices for low‐power neuromorphic computing are overviewed, e.g., resistive random access memory with low power consumption (< pJ) per synaptic event. A few computation models for artificial neural networks (NNs), including spiking neural network (SNN) and deep neural network (DNN), which boost power efficiency by simplifying the computing procedure and minimizing memory access are discussed. A few examples for system‐level demonstration are described, such as mixed synchronous–asynchronous and reconfigurable convolution neuron network (CNN)–recurrent NN (RNN) for low‐power computing.
Understanding the impact of space exploration remains biologically elusive. Cell Press is dedicating this month to spaceflight (Afshinnekoo et al., 2020), with the open science NASA GeneLab database enabling the study revealing mitochondria as a key biological feature from spaceflight (da Silveira et al., 2020).
Clonal hematopoiesis (CH) occurs when blood cells harboring an advantageous mutation propagate faster than others. These mutations confer a risk for hematological cancers and cardiovascular disease. Here, we analyze CH in blood samples from a pair of twin astronauts over 4 years in bulk and fractionated cell populations using a targeted CH panel, linked-read whole-genome sequencing, and deep RNA sequencing. We show CH with distinct mutational profiles and increasing allelic fraction that includes a high-risk, TET2 clone in one subject and two DNMT3A mutations on distinct alleles in the other twin. These astronauts exhibit CH almost two decades prior to the mean age at which it is typically detected and show larger shifts in clone size than age-matched controls or radiotherapy patients, based on a longitudinal cohort of 157 cancer patients. As such, longitudinal monitoring of CH may serve as an important metric for overall cancer and cardiovascular risk in astronauts.
Deep space exploration will require real-time, minimally invasive monitoring of astronaut health to mitigate the potential health impairments caused by space radiation and microgravity. Genotoxic stress in humans can be monitored by quantifying the amount of DNA double-strand breaks (DSBs) in immune cells from a simple finger prick. In a cohort of 674 healthy donors, we show that the endogenous level of DSBs increases with age and with latent cytomegalovirus infection. To map the range of human responses to space radiation, we then study DSB induction and repair in immune cells from 319 healthy donors after the cells are exposed to galactic cosmic ray components and lymphocytes from 30 cancer patients after radiotherapy. Individuals with low baseline DSB have fewer clinical complications, enhanced DNA damage repair responses, and a functional dose-dependent cytokine response in healthy donor cells. This supports the use of DSB monitoring for health resilience in space.
The National Aeronautics and Space Administration (NASA) Twins Study created an integrative molecular profile of an astronaut during NASA’s first 1-year mission on the International Space Station (ISS) and included comparisons to an identical Earth-bound twin. The unique biochemical profiles observed when landing on Earth after such a long mission (e.g., spikes in interleukin-1 [IL-1]/6/10, c-reactive protein [CRP], C-C motif chemokine ligand 2 [CCL2], IL-1 receptor antagonist [IL-1ra], and tumor necrosis factor alpha [TNF-α]) opened new questions about the human body’s response to gravity and how to plan for future astronauts, particularly around initiation or resolution of inflammation. Here, single-cell, multi-omic (100-plex epitope profile and gene expression) profiling of peripheral blood mononuclear cells (PBMCs) showed changes to blood cell composition and gene expression post-flight, specifically for monocytes and dendritic cell precursors. These were consistent with flight-induced cytokine and immune system stress, followed by skeletal muscle regeneration in response to gravity. Finally, we examined these profiles relative to 6-month missions in 28 other astronauts and detail potential pharmacological interventions for returning to gravity in future missions.
NASA’s plans for space exploration include a return to the Moon to stay—boots back on the lunar surface with an orbital outpost. This station will be a launch point for voyages to destinations further away in our solar system, including journeys to the red planet Mars. To ensure success of these missions, health and performance risks associated with the unique hazards of spaceflight must be adequately controlled. These hazards—space radiation, altered gravity fields, isolation and confinement, closed environments, and distance from Earth—are linked with over 30 human health risks as documented by NASA’s Human Research Program. The programmatic goal is to develop the tools and technologies to adequately mitigate, control, or accept these risks. The risks ranked as “red” have the highest priority based on both the likelihood of occurrence and the severity of their impact on human health, performance in mission, and long-term quality of life. These include: (1) space radiation health effects of cancer, cardiovascular disease, and cognitive decrements (2) Spaceflight-Associated Neuro-ocular Syndrome (3) behavioral health and performance decrements, and (4) inadequate food and nutrition. Evaluation of the hazards and risks in terms of the space exposome—the total sum of spaceflight and lifetime exposures and how they relate to genetics and determine the whole-body outcome—will provide a comprehensive picture of risk profiles for individual astronauts. In this review, we provide a primer on these “red” risks for the research community. The aim is to inform the development of studies and projects with high potential for generating both new knowledge and technologies to assist with mitigating multisystem risks to crew health during exploratory missions.
Graphical Abstract Highlights d Spaceflight miRNA signature validated in multiple organism models d Components of miRNA signature related to space radiation and microgravity d Downstream targets and circulating dependence of miRNAs in NASA Twins Study d Inhibition of key microvasculature miRNAs mitigates space radiation impact (C.E.M.), afshin.beheshti@nasa.gov (A.B.) In Brief Malkani et al. uncover the role of circulating microRNAs as both a potential biomarker for health risks associated with spaceflight and a countermeasure to mitigate the damage caused to the body by the space environment. SUMMARY We have identified and validated a spaceflight-associated microRNA (miRNA) signature that is shared by rodents and humans in response to simulated, short-duration and long-duration spaceflight. Previous studies have identified miRNAs that regulate rodent responses to spaceflight in low-Earth orbit, and we have confirmed the expression of these proposed spaceflight-associated miRNAs in rodents reacting to simulated spaceflight conditions. Moreover, astronaut samples from the NASA Twins Study confirmed these expression signatures in miRNA sequencing, single-cell RNA sequencing (scRNA-seq), and single-cell assay for transposase accessible chromatin (scATAC-seq) data. Additionally, a subset of these miRNAs (miR-125, miR-16, and let-7a) was found to regulate vascular damage caused by simulated deep space radiation. To demonstrate the physiological relevance of key spaceflight-associated miRNAs, we utilized antagomirs to inhibit their expression and successfully rescue simulated deep-space-radiation-mediated damage in human 3D vascular constructs.
The mission of NASA’s GeneLab database (https://genelab.nasa.gov/) is to collect, curate, and provide access to the genomic, transcriptomic, proteomic and metabolomic (so-called ‘omics’) data from biospecimens flown in space or exposed to simulated space stressors, maximizing their utilization. This large collection of data enables the exploration of molecular network responses to space environments using a systems biology approach. We review here the various components of the GeneLab platform, including the new data repository web interface, and the GeneLab Online Data Entry (GEODE) web portal, which will support the expansion of the database in the future to include companion non-omics assay data. We discuss our design for GEODE, particularly how it promotes investigators providing more accurate metadata, reducing the curation effort required of GeneLab staff. We also introduce here a new GeneLab Application Programming Interface (API) specifically designed to support tools for the visualization of processed omics data. We review the outreach efforts by GeneLab to utilize the spaceflight data in the repository to generate novel discoveries and develop new hypotheses, including spearheading data analysis working groups, and a high school student training program. All these efforts are aimed ultimately at supporting precision risk management for human space exploration.
Image semantic segmentation is one of the key problems in computer vision. Despite the enormous advances in applications, almost all the image semantic segmentation algorithms fail to achieve satisfactory segmentation results due to lack of sensitivity to details, or difficulty in evaluating the global similarity of pixels, or both. Posting-processing enhancement methods, as the outstandingly crucial means to ameliorate the above-mentioned inherent flaws of algorithms, are almost based on conditional random fields (CRFs). Inspired by CRFs, this paper proposes a novel post-processing enhancement framework with theoretical simplicity from the perspective of filtering, and a new weighted composite filter (WCF) is designed to enhance the segmentation masks in a unified framework. First, by adjusting the weight ratio, the WCF is decomposed into a local part and a global part. Secondly, a guided image filter is designed as the local filter, which can restore boundary information to present necessary details. Moreover, a minimum spanning tree (MST)-based filter is designed as the global filter to provide a natural measure of global pixel similarity for image matching. Thirdly, a unified post-processing enhancement framework, including selection and normalization, WCF and argmax, is designed. Finally, the effectiveness and superiority of the proposed method for enhancement, as well as its range of applications, are verified through experiments.
The complexities of modern biomedicine are rapidly increasing. Thus, modeling and simulation have become increasingly important as a strategy to understand and predict the trajectory of pathophysiology, disease genesis, and disease spread in support of clinical and policy decisions. In such cases, inappropriate or ill-placed trust in the model and simulation outcomes may result in negative outcomes, and hence illustrate the need to formalize the execution and communication of modeling and simulation practices. Although verification and validation have been generally accepted as significant components of a model’s credibility, they cannot be assumed to equate to a holistic credible practice, which includes activities that can impact comprehension and in-depth examination inherent in the development and reuse of the models. For the past several years, the Committee on Credible Practice of Modeling and Simulation in Healthcare, an interdisciplinary group seeded from a U.S. interagency initiative, has worked to codify best practices. Here, we provide Ten Rules for credible practice of modeling and simulation in healthcare developed from a comparative analysis by the Committee’s multidisciplinary membership, followed by a large stakeholder community survey. These rules establish a unified conceptual framework for modeling and simulation design, implementation, evaluation, dissemination and usage across the modeling and simulation life-cycle. While biomedical science and clinical care domains have somewhat different requirements and expectations for credible practice, our study converged on rules that would be useful across a broad swath of model types. In brief, the rules are: (1) Define context clearly. (2) Use contextually appropriate data. (3) Evaluate within context. (4) List limitations explicitly. (5) Use version control. (6) Document appropriately. (7) Disseminate broadly. (8) Get independent reviews. (9) Test competing implementations. (10) Conform to standards. Although some of these are common sense guidelines, we have found that many are often missed or misconstrued, even by seasoned practitioners. Computational models are already widely used in basic science to generate new biomedical knowledge. As they penetrate clinical care and healthcare policy, contributing to personalized and precision medicine, clinical safety will require established guidelines for the credible practice of modeling and simulation in healthcare.
Variation in the human gut microbiome can reflect host lifestyle and behaviors and influence disease biomarker levels in the blood. Understanding the relationships between gut microbes and host phenotypes are critical for understanding wellness and disease. Here, we examine associations between the gut microbiota and~150 host phenotypic features across~3,400 individuals. We identify major axes of taxonomic variance in the gut and a putative diversity maximum along the Firmicutes-to-Bacteroidetes axis. Our analyses reveal both known and unknown associations between microbiome composition and host clinical markers and lifestyle factors, including host-microbe associations that are composition-specific. These results suggest potential opportunities for targeted interventions that alter the composition of the microbiome to improve host health. By uncovering the interrelationships between host diet and lifestyle factors, clinical blood markers, and the human gut microbiome at the population-scale, our results serve as a roadmap for future studies on host-microbe interactions and interventions.
We present a novel mathematical formalism to predict the kinetics of DNA damage repair after exposure to both low- and high-LET radiation (X rays; 350 MeV/n 40Ar; 600 MeV/n 56Fe). Our method is based on monitoring DNA damage repair protein 53BP1 that forms radiation-induced foci (RIF) at locations of DNA double-strand breaks (DSB) in the nucleus and comparing its expression in primary skin fibroblasts isolated from 15 mice strains. We previously reported strong evidence for clustering of nearby DSB into single repair units as opposed to the classic "contact-first" model where DSB are considered immobile. Here we apply this clustering model to evaluate the number of remaining RIF over time. We also show that the newly introduced kinetic metrics can be used as surrogate biomarkers for in vivo radiation toxicity, with potential applications in radiotherapy and human space exploration. In particular, we observed an association between the characteristic time constant of RIF repair measured in vitro and survival levels of immune cells collected from irradiated mice. Moreover, the speed of DNA damage repair correlated not only with radiation-induced cellular survival in vivo, but also with spontaneous cancer incidence data collected from the Mouse Tumor Biology database, suggesting a relationship between the efficiency of DSB repair after irradiation and cancer risk.
The human immune system varies extensively between individuals, but variation within individuals over time has not been well characterized. Systems-level analyses allow for simultaneous quantification of many interacting immune system components and the inference of global regulatory principles. Here, we present a longitudinal, systems-level analysis in 99 healthy adults 50 to 65 years of age and sampled every third month for 1 year. We describe the structure of interindividual variation and characterize extreme phenotypes along a principal curve. From coordinated measurement fluctuations, we infer relationships between 115 immune cell populations and 750 plasma proteins constituting the blood immune system. While most individuals have stable immune systems, the degree of longitudinal variability is an individual feature. The most variable individuals, in the absence of overt infections, exhibited differences in markers of metabolic health suggestive of a possible link between metabolic and immunologic homeostatic regulation.
The Project Baseline Health Study (PBHS) was launched to map human health through a comprehensive understanding of both the health of an individual and how it relates to the broader population. The study will contribute to the creation of a biomedical information system that accounts for the highly complex interplay of biological, behavioral, environmental, and social systems. The PBHS is a prospective, multicenter, longitudinal cohort study that aims to enroll thousands of participants with diverse backgrounds who are representative of the entire health spectrum. Enrolled participants will be evaluated serially using clinical, molecular, imaging, sensor, self-reported, behavioral, psychological, environmental, and other health-related measurements. An initial deeply phenotyped cohort will inform the development of a large, expanded virtual cohort. The PBHS will contribute to precision health and medicine by integrating state of the art testing, longitudinal monitoring and participant engagement, and by contributing to the development of an improved platform for data sharing and analysis.
During 2019 and 2020, NASA's Environmental Control and Life Support (ECLS) technology development projects have taken vital steps toward establishing readiness for the next generation of human space exploration missions. Technology demonstration systems from last year have been operated on the International Space Station (ISS) and others have been launched. Progress has been made toward future technology demonstrations. Facility and hardware development have been initiated for ground testing that strategically complements technology demonstration aboard the International Space Station (ISS) and some ground testing has been initiated. Reliability studies are being conducted to define requirements for flight demonstration and ground testing as well as inform other investments to support exploration missions. These efforts support NASA-led missions beyond LEO which include Gateway, lunar surface, Mars transportation, and Mars surface mission architectures. This paper provides an overview of the current ECLS strategic planning and roadmap as well as a synopsis of key technology and maturation project tasks that occurred in 2019 and early 2020 to support the strategic needs. Plans for the remainder of 2020 and subsequent years are also described.
Continuous health monitoring and integrated diagnostic devices, worn on the body and used in the home, will help to identify and prevent early manifestations of disease. However, challenges lie ahead in validating new health monitoring technologies and in optimizing data analytics to extract actionable conclusions from continuously obtained health data.
Research on astronaut health and model organisms have revealed six features of spaceflight biology that guide our current understanding of fundamental molecular changes that occur during space travel. The features include oxidative stress, DNA damage, mitochondrial dysregulation, epigenetic changes (including gene regulation), telomere length alterations, and microbiome shifts. Here we review the known hazards of human spaceflight, how spaceflight affects living systems through these six fundamental features, and the associated health risks of space exploration. We also discuss the essential issues related to the health and safety of astronauts involved in future missions, especially planned long-duration and Martian missions.
Organs-on-chips (OoCs), also known as microphysiological systems or 'tissue chips' (the terms are synonymous), have attracted substantial interest in recent years owing to their potential to be informative at multiple stages of the drug discovery and development process. These innovative devices could provide insights into normal human organ function and disease pathophysiology, as well as more accurately predict the safety and efficacy of investigational drugs in humans. Therefore, they are likely to become useful additions to traditional preclinical cell culture methods and in vivo animal studies in the near term, and in some cases replacements for them in the longer term. In the past decade, the OoC field has seen dramatic advances in the sophistication of biology and engineering, in the demonstration of physiological relevance and in the range of applications. These advances have also revealed new challenges and opportunities, and expertise from multiple biomedical and engineering fields will be needed to fully realize the promise of OoCs for fundamental and translational applications. This Review provides a snapshot of this fast-evolving technology, discusses current applications and caveats for their implementation, and offers suggestions for directions in the next decade.
In this paper, we describe an ongoing multi-institution study in using emplaced computational resources such as high-volume storage and fast processing to enable instruments to gather and store much more data than would normally be possible, even if it cannot be downlinked to Earth in any reasonable time. The primary focus of the study is designing science pipelines for on-site summarization, archival for future downlink, and multisensor fusion. A secondary focus is on providing support for increasingly autonomous systems, including mapping, planning, and multi-platform collaboration. Key to both of these concepts is treating the spacecraft not as an autonomous agent but as an interactive batch processor, which allows us to avoid “quantum leaps” in machine intelligence required to realize the concepts. Our goal is to discuss preliminary results and technical directions for the community, and identify promising new opportunities for multi-sensor fusion with the help of planetary researchers.
Neuromorphic computing takes inspiration from the brain to create energy-efficient hardware for information processing, capable of highly sophisticated tasks. Systems built with standard electronics achieve gains in speed and energy by mimicking the distributed topology of the brain. Scaling-up such systems and improving their energy usage, speed and performance by several orders of magnitude requires a revolution in hardware. We discuss how including more physics in the algorithms and nanoscale materials used for data processing could have a major impact in the field of neuromorphic computing. We review striking results that leverage physics to enhance the computing capabilities of artificial neural networks, using resistive switching materials, photonics, spintronics and other technologies. We discuss the paths that could lead these approaches to maturity, towards low-power, miniaturized chips that could infer and learn in real time. Neuromorphic computing takes inspiration from the brain to create energy-efficient hardware for information processing, capable of highly sophisticated tasks. Including more physics in the algorithms and nanoscale materials used for computing could have a major impact in this field.
Recent advances in ultrasound technology have made ultrasound equipment more versatile, portable and accessible than ever. Modern hand-held, ultra-portable ultrasound devices have been developed by multiple companies and are contributing to make bedside ultrasound evaluation a practice available to all physicians. The significance of making point-of-care ultrasound a common practice that all physicians can eventually use in the evaluation of their patients is changing the way medicine is practiced, allowing physicians to quickly obtain valuable information to complement the traditional physical exam. Despite the proven benefits of using bedside ultrasound imaging as a part of the patient evaluation and for procedure guidance, adoption of this technology is still not widespread among anesthesiology clinicians, nor is there uniform teaching of ultrasound skills to anesthesia residents and faculty. Among obstacles that have been identified as precluding achievement of the goal of widespread utilization of POCUS among anesthesia professionals and trainees is the availability of equipment for all physicians when it is needed and lack of instructor supervision for trainees who desire to use ultrasound but do not always have an instructor knowledgeable in POCUS with them when an US exam is warranted. We analyze the characteristics, advantages and limitations of available ultra-portable, hand-held ultrasound devices, with a focus on the Butterfly IQ pocket-probe, which is available at our institution, and how some of its features, like the capacity to emulate multiple transducers and its cloud-sharing and teleguidance technology, may contribute to increase the availability and utilization of POCUS by anesthesia clinicians.
Machine learning has been highly successful in data-intensive applications but is often hampered when the data set is small. Recently, Few-shot Learning (FSL) is proposed to tackle this problem. Using prior knowledge, FSL can rapidly generalize to new tasks containing only a few samples with supervised information. In this article, we conduct a thorough survey to fully understand FSL. Starting from a formal definition of FSL, we distinguish FSL from several relevant machine learning problems. We then point out that the core issue in FSL is that the empirical risk minimizer is unreliable. Based on how prior knowledge can be used to handle this core issue, we categorize FSL methods from three perspectives: (i) data, which uses prior knowledge to augment the supervised experience; (ii) model, which uses prior knowledge to reduce the size of the hypothesis space; and (iii) algorithm, which uses prior knowledge to alter the search for the best hypothesis in the given hypothesis space. With this taxonomy, we review and discuss the pros and cons of each category. Promising directions, in the aspects of the FSL problem setups, techniques, applications, and theories, are also proposed to provide insights for future research.
INTRODUCTION: The Integrated Medical Model (IMM) is a quantified, evidence-based decision support tool developed by National Aeronautics and Space Administration (NASA) to assist in the assessment of the medical risk of human spaceflight missions. The IMM utilizes a probabilistic risk assessment (PRA) approach to simulate potential in-flight medical events and resultant health and mission outcomes. METHODS: The IMM has been utilized to estimate the medical risk associated with International Space Station (ISS) missions. The IMM outputs that have been most informative to the ISS program are the probabilities of evacuation (pEVAC) and loss of crew life (pLOCL). These outputs are incorporated into a continuously maintained ISS PRA model so that its quantification of total ISS mission risk includes the medical risk. RESULTS: Results of this analysis revealed that the forecasted risk values of pEVAC and pLOCL due to medical events were improved by using the IMM with the ISS PRA model instead of using data from prior sources in which these values were underestimated. DISCUSSION: The IMM provides an evidence-based PRA approach to directly communicate and integrate medical risk with other ISS risks. A comparison of IMM outputs of pEVAC and pLOCL to empirical spaceflight data and analog population data revealed that IMM outputs were comparable with actual experience. With appropriate outcome context, these findings increase subject matter expert confidence in the accuracy of IMM risk estimates. IMM outputs provide quantifiable objective estimates of medical risk that can be used to inform mission risk assessments and to optimize crew health. Walton ME, Kerstman EL. Quantification of medical risk on the International Space Station using the Integrated Medical Model . Aerosp Med Hum Perform. 2020; 91(4):332–342.
Federated learning involves training statistical models over remote devices or siloed data centers, such as mobile phones or hospitals, while keeping data localized. Training in heterogeneous and potentially massive networks introduces novel challenges that require a fundamental departure from standard approaches for large-scale machine learning, distributed optimization, and privacy-preserving data analysis. In this article, we discuss the unique characteristics and challenges of federated learning, provide a broad overview of current approaches, and outline several directions of future work that are relevant to a wide range of research communities.
To date, more than 565 professional astronauts have flown in space, of whom only 11% have been women. Of these, ∼565 have been NASA astronauts, of whom 86% have been men and 14% have been women. This cohort of professional astronauts has been uniquely fit and exceptionally well trained. The advent of commercial spaceflight will see a wider range of individuals enter space, who lie on a variegated continuum of physical fitness, metabolic fitness, disease complexity, drug therapeutics, and genetics. Yet, there are currently little data on individuals of lesser fitness entering space. In addition, the initial planetary missions to Mars will embark without any data associated with such a mission (e.g., 3 years). Even as we begin to gather such data from the initial Mars missions, the cohorts will be small with uncertain generalizability. While spaceflight medicine has grown in sophistication, we are still faced with clear knowledge gaps. This occurs just as the community of space travelers is about to expand and the complexity of planetary missions is at its most ambitious. Fortunately, the advent of comprehensive molecular profiling, including some in mission, allows us to address some of these unknowns by applying complex molecular analytics to individuals and developing personalized countermeasures derived from those analytics.