Matthieu Komorowski

• MRes, MD
• PhD Student at Imperial College London

In this chapter, the reader will learn about the most common tools available for exploring a dataset, which is essential in order to gain a good understanding of the features and potential issues of a dataset, as well as helping in hypothesis generation.

Komorowski M, Watkins SD, Lebuffe G, Clark JB. Potential anesthesia protocols for space exploration missions. Aviat Space Environ Med 2013; 84:226–33. In spaceflight beyond low Earth’s orbit, medical conditions requiring surgery are of a high level of concern because of their potential impact on crew health and mission success. Whereas surgical tec...

During future space exploration missions, the risk of medical events requiring surgery is significant, and will likely rely on anesthetic techniques. Available options during spaceflight include local, regional (nerve block) and general anesthesia. No actual invasive anesthesia was ever performed on humans in space or immediately after landing, and...

Background: The question of the safety of anaesthetic procedures performed by non anaesthetists or even by non physicians has long been debated. We explore here this question in the hypothetical context of an exploration mission to Mars. During future interplanetary space missions, the risk of medical conditions requiring surgery and anaesthetic t...

Purpose of review: Missions to the Moon or more distant planets are planned in the next future, and will push back the limits of our experience in providing medical support in remote environments. Medical preparedness is ongoing, and involves planning for emergency surgical interventions and anaesthetic procedures. This review will summarise what p...

Chest X-ray radiographs (CXRs) play a pivotal role in diagnosing and monitoring cardiopulmonary diseases. However, lung opac- ities in CXRs frequently obscure anatomical structures, impeding clear identification of lung borders and complicating the localization of pathology. This challenge significantly hampers segmentation accuracy and precise les...

The safety of Artificial Intelligence (AI) systems is as much one of human decision-making as a technological question. In AI-driven decision support systems, particularly in high-stakes settings such as healthcare, ensuring the safety of human-AI interactions is paramount, given the potential risks of following erroneous AI recommendations. To exp...

Pivotal moments in sepsis care occur in the emergency department (ED), however, and it is unclear whether ED data is adequate to inform reinforcement learning (RL) models. We evaluated the early opportunity for the AI Clinician, a validated ICU-based RL-model, as a use case. Amongst emergency sepsis patients, model parameters were often missing and...

Radiology reporting generative AI holds significant potential to alleviate clinical workloads and streamline medical care. However, achieving high clinical accuracy is challenging, as radiological images often feature subtle lesions and intricate structures. Existing systems often fall short, largely due to their reliance on fixed size, patch-level...

Objectives Understanding the burden of disease of sepsis is essential for monitoring the effectiveness of international strategies to improve sepsis care. Our objective was to describe the multinational trend of sepsis-related mortality for the period 1985–2019 from the WHO Mortality Database. Design Retrospective analysis of the WHO Mortality Dat...

Machine learning (ML) tools for acute respiratory distress syndrome (ARDS) detection and prediction are increasingly used. Therefore, understanding risks and benefits of such algorithms is relevant at the bedside. ARDS is a complex and severe lung condition that can be challenging to define precisely due to its multifactorial nature. It often arise...

We studied clinical AI-supported decision-making as an example of a high-stakes setting in which explainable AI (XAI) has been proposed as useful (by theoretically providing physicians with context for the AI suggestion and thereby helping them to reject unsafe AI recommendations). Here, we used objective neurobehavioural measures (eye-tracking) to...

Background: Sepsis, an acute and potentially fatal systemic response to infection, significantly impacts global health by affecting millions annually. Prompt identification of sepsis is vital, as treatment delays lead to increased fatalities through progressive organ dysfunction. While recent studies have delved into leveraging Machine Learning (M...

Large randomized trials in sepsis have generally failed to find effective novel treatments. This is increasingly attributed to patient heterogeneity, including heterogeneous cardiovascular changes in septic shock. We discuss the potential for machine learning systems to personalize cardiovascular resuscitation in sepsis. While the literature is rep...

Background Out-of-hospital cardiac arrest (OHCA) represents a major burden for society and health care, with an average incidence in adults of 67 to 170 cases per 100,000 person-years in Europe and in-hospital survival rates of less than 10%. Patients and practitioners would benefit from a prognostication tool for long-term good neurological outcom...

This paper presents a human factors qualitative study on an AI application for managing sepsis in Intensive Care Units (ICUs). The study involved semi-structured interviews with nine ICU clinicians and nurses across three London hospitals. It consisted of two parts: the first applied methods to understand sepsis resuscitation processes and establis...

This scoping review focuses on the essential role of models for causal inference in shaping actionable artificial intelligence (AI) designed to aid clinicians in decision-making. The objective was to identify and evaluate the reporting quality of studies introducing models for causal inference in intensive care units (ICUs), and to provide recommen...

The influence of AI recommendations on physician behaviour remains poorly characterised. We assess how clinicians’ decisions may be influenced by additional information more broadly, and how this influence can be modified by either the source of the information (human peers or AI) and the presence or absence of an AI explanation (XAI, here using si...

How do artificial neural networks and other forms of artificial intelligence interfere with methods and practices in the sciences? Which interdisciplinary epistemological challenges arise when we think about the use of AI beyond its dependency on big data? Not only the natural sciences, but also the social sciences and the humanities seem to be inc...

In the context of Artificial Intelligence (AI)-driven decision support systems for high-stakes environments, particularly in healthcare, ensuring the safety of human-AI interactions is paramount, given the potential risks associated with erroneous AI outputs. To address this, we conducted a prospective observational study involving 38 intensivists...

Long duration spaceflights to the Moon or Mars are at risk for emergency medical events. Managing a hypoxemic distress and performing an advanced airway procedure such as oro-tracheal intubation may be complicated under weightlessness due to ergonomic constraints. An emergency free-floating intubation would be dangerous because of high failure rate...

Background: We conducted a scoping review of machine learning systems that inform individualised cardiovascular resuscitation of adults in hospital with sepsis. Our study reviews the resuscitation tasks that the systems aim to assist with, system robustness and potential to improve patient care, and progress towards deployment in clinical practice....

INTRODUCTION: During future interplanetary space missions, a number of health conditions may arise, owing to the hostile environment of space and the myriad of stressors experienced by the crew. When managing these conditions, crews will be required to make accurate, timely clinical decisions at a high level of autonomy, as telecommunication delays...

Background: The challenge of responsibly guiding clinicians to incorporate AI recommendations and explanations into their day-to-day practice has thus far neglected the realm of decisions outside of diagnosis (where there is no gold standard to compare against). We assess how clinicians' decisions may be influenced by additional information more br...

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 l...

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 art...

Open international challenges are becoming the de facto standard for assessing computer vision and image analysis algorithms. In recent years, new methods have extended the reach of pulmonary airway segmentation that is closer to the limit of image resolution. Since EXACT'09 pulmonary airway segmentation, limited effort has been directed to quantit...

Over the last years, there have been advances in the use of data-driven techniques to improve the definition, early recognition, subtypes characterisation, prognostication and treatment personalisation of sepsis. Some of those involve the discovery or evaluation of biomarkers or digital signatures of sepsis or sepsis sub-phenotypes. It is hoped tha...

Introduction: Since Gagarin became the first human to travel into space and complete one orbit around the Earth, on 12 April 1961, the number of manned spaceflights has increased significantly. Spaceflight is still complex and has potential risk for incidents and accidents. The aim of this study was to analyze how safe it is for humans to travel in...

Aim To review and appraise the quality of studies that present models for causal inference of time-varying treatment effects in the adult intensive care unit (ICU) and give recommendations to improve future research practice. Methods We searched Embase, MEDLINE ALL, Web of Science Core Collection, Google Scholar, medRxiv, and bioRxiv up to March 2...

Objectives Establishing confidence in the safety of Artificial Intelligence (AI)-based clinical decision support systems is important prior to clinical deployment and regulatory approval for systems with increasing autonomy. Here, we undertook safety assurance of the AI Clinician, a previously published reinforcement learning-based treatment recomm...

(1) Background: Intensive care unit (ICU) survivors from severe COVID-19 acute respiratory distress syndrome (CARDS) with chronic critical illness (CCI) may be considered vast resource consumers with a poor prognosis. We hypothesized that a holistic approach combining an early intensive rehabilitation with a protocol of difficult weaning would impr...

Abstract: Background: Although there have been no reported cardiac arrests in space to date, the risk of severe medical events occurring during long-duration spaceflights is a major concern. These critical events can endanger both the crew as well as the mission and include cardiac arrest, which would require cardiopulmonary resuscitation (CPR). Th...

Human space exploration beyond low Earth orbit will involve missions of significant distance and duration. To effectively mitigate myriad space health hazards, paradigm shifts in data and space health systems are necessary to enable Earth-independence, rather than Earth-reliance. Promising developments in the fields of artificial intelligence and m...

Space biology research aims to understand fundamental effects of spaceflight 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 fiel...

Artificial intelligence (AI) has the potential to identify treatable phenotypes, optimise ventilation strategies, and provide clinical decision support for patients who require mechanical ventilation. Gallifant and colleagues performed a systematic review to identify studies using AI to solve a diverse range of clinical problems in the ventilated p...

Reinforcement Learning (RL) is emerging as tool for tackling complex control and decision-making problems. However, in high-risk environments such as healthcare, manufacturing, automotive or aerospace, it is often challenging to bridge the gap between an apparently optimal policy learnt by an agent and its real-world deployment, due to the uncertai...

Levels of Autonomy are an important guide to structure our thinking of capability, expectation and safety in autonomous systems. Here we focus on autonomy in the context of digital healthcare, where autonomy maps out differently to e.g. self-driving cars. Specifically we focus here on mapping levels of autonomy to clinical decision support systems...

PurposeThe trajectory of mechanically ventilated patients with coronavirus disease 2019 (COVID-19) is essential for clinical decisions, yet the focus so far has been on admission characteristics without consideration of the dynamic course of the disease in the context of applied therapeutic interventions.Methods We included adult patients undergoin...

This focused review summarizes the medical, logistical and environmental challenges that would be associated with dealing with a traumatic surgical case during an interplanetary space mission in the near future.

Background To date the description of mechanically ventilated patients with Coronavirus Disease 2019 (COVID-19) has focussed on admission characteristics with no consideration of the dynamic course of the disease. Here, we present a data-driven analysis of granular, daily data from a representative proportion of patients undergoing invasive mechani...

Background: With the "Artemis"-mission mankind will return to the Moon by 2024. Prolonged periods in space will not only present physical and psychological challenges to the astronauts, but also pose risks concerning the medical treatment capabilities of the crew. So far, no guideline exists for the treatment of severe medical emergencies in microg...

Objectives: To investigate patients' characteristics, management, and outcomes in the critically ill population admitted to the ICU for severe acute respiratory syndrome coronavirus disease 2019 pneumonia causing an acute respiratory distress syndrome. Design: Retrospective case-control study. Setting: A 34-bed ICU of a tertiary hospital. Pat...

Objective To systematically examine the design, reporting standards, risk of bias, and claims of studies comparing the performance of diagnostic deep learning algorithms for medical imaging with that of expert clinicians. Design Systematic review. Data sources Medline, Embase, Cochrane Central Register of Controlled Trials, and the World Health O...

Context: Whether critical care improvements over the last ten years extend to all hospitals has not been described. Objective: To examine the temporal trends of critical care outcomes in minority and non-minority serving hospitals. Design: Inception cohort of critically ill patients. Measurements: Using the Philips Health Care electronic Int...

Zusammenfassung Das Ziel der vorliegenden Arbeit ist es, einen Überblick über den aktuellen Stand der Forschung zum Atemwegsmanagement in Schwerelosigkeit zu geben. Dafür wurde ein narratives Review von bisher publizierter Literatur über Atemwegsmanagement in (simulierter) Schwerelosigkeit erstellt. Mittels einer Suche in PubMed wurden 3 Originalar...

Health-related data is noisy and stochastic in implying the true physiological states of patients, limiting information contained in single-moment observations for sequential clinical decision making. We model patient-clinician interactions as partially observable Markov decision processes (POMDPs) and optimize sequential treatment based on belief...

In this document, we explore in more detail our published work (Komorowski, Celi, Badawi, Gordon, & Faisal, 2018) for the benefit of the AI in Healthcare research community. In the above paper, we developed the AI Clinician system, which demonstrated how reinforcement learning could be used to make useful recommendations towards optimal treatment d...

Sepsis is the leading cause of mortality in the ICU. It is challenging to manage because individual patients respond differently to treatment. Thus, tailoring treatment to the individual patient is essential for the best outcomes. In this paper, we take steps toward this goal by applying a mixture-of-experts framework to personalize sepsis treatmen...

In this Comment, we provide guidelines for reinforcement learning for decisions about patient treatment that we hope will accelerate the rate at which observational cohorts can inform healthcare practice in a safe, risk-conscious manner.

Sepsis is the leading cause of mortality in the ICU. It is challenging to manage because individual patients respond differently to treatment. Thus, tailoring treatment to the individual patient is essential for the best outcomes. In this paper, we take steps toward this goal by applying a mixture-of-experts framework to personalize sepsis treatmen...

Future space exploration missions will take humans far beyond low Earth orbit and require complete crew autonomy. The ability to provide anaesthesia will be important given the expected risk of severe medical events requiring surgery. Knowledge and experience of such procedures during space missions is currently extremely limited. Austere and isola...

Sepsis is a dangerous condition that is a leading cause of patient mortality. Treating sepsis is highly challenging, because individual patients respond very differently to medical interventions and there is no universally agreed-upon treatment for sepsis. In this work, we explore the use of continuous state-space model-based reinforcement learning...

Simulation-based approaches to disease progression allow us to make counterfactual predictions about the effects of an untried series of treatment choices. However, building accurate simulators of disease progression is challenging, limiting the utility of these approaches for real world treatment planning. In this work, we present a novel simulati...

Sensitivity to choice of reward functions for HIV therapy selection. Illustration of KDM’s performance relative to varying choices of reward function for the HIV therapy selection task. We tested three alternative formulations of reward functions. Overall, KDM’s performance is relatively robust against the choice of reward function. (PDF)

Zusammenfassung Hintergrund Im Jahr 2017 wurden weltweit etwa 4 Milliarden Menschen mit einem Flugzeug transportiert. Die International Air Transport Association (IATA) prognostiziert für Europa bis zum Jahr 2034 eine durchschnittliche jährliche Steigerung der Passagierzahlen von 2,7%. In der zivilen Luftfahrt treten Notfälle an Bord (sogenannte In...

Sepsis is the third leading cause of death worldwide and the main cause of mortality in hospitals1–3, but the best treatment strategy remains uncertain. In particular, evidence suggests that current practices in the administration of intravenous fluids and vasopressors are suboptimal and likely induce harm in a proportion of patients1,4–6. To tackl...

Objectives: Although one third or more of critically ill patients in the United States are obese, obesity is not incorporated as a contributing factor in any of the commonly used severity of illness scores. We hypothesize that selected severity of illness scores would perform differently if body mass index categorization was incorporated and that...

As mankind strives to explore space beyond the moon by planning space exploration missions to Mars and as space tourism becomes closer to operational viability, medical planning for those missions must consider the possibility of life threatening medical emergencies. For Earth, well-established and proven guidelines concerning cardiopulmonary resus...

Zusammenfassung Im Lichte zukünftiger Langzeitraumfahrtmissionen fernab der Erdumlaufbahn besitzt die Fähigkeit der Crew zur autonomen, medizinischen Versorgung einen besonderen Stellenwert. Hier ist insbesondere die Durchführung einer Anästhesie bei einer dringend notwendigen Operation von entscheidender Bedeutung, um unter Umständen die Mission w...

In this work, we consider the problem of estimating a behaviour policy for use in Off-Policy Policy Evaluation (OPE) when the true behaviour policy is unknown. Via a series of empirical studies, we demonstrate how accurate OPE is strongly dependent on the calibration of estimated behaviour policy models: how precisely the behaviour policy is estima...

Hospital intensive care units (ICUs) care for severely ill patients, many of whom require some form of organ support. Clinicians in ICUs are often challenged with integrating large volumes of continuously recorded physiological and clinical data in order to diagnose and treat patients. In this work, we focus on developing interpretable models for p...

Much attention has been devoted recently to the development of machine learning algorithms with the goal of improving treatment policies in healthcare. Reinforcement learning (RL) is a sub-field within machine learning that is concerned with learning how to make sequences of decisions so as to optimize long-term effects. Already, RL algorithms have...

Off-policy reinforcement learning enables near-optimal policy from suboptimal experience, thereby provisions opportunity for artificial intelligence applications in healthcare. Previous works have mainly framed patient-clinician interactions as Markov decision processes, while true physiological states are not necessarily fully observable from clin...

We study the problem of off-policy policy evaluation (OPPE) in RL. In contrast to prior work, we consider how to estimate both the individual policy value and average policy value accurately. We draw inspiration from recent work in causal reasoning, and propose a new finite sample generalization error bound for value estimates from MDP models. Usin...

By the end of the year 2016, approximately 3 billion people worldwide travelled by commercial air transport. Between 1 out of 14,000 and 1 out of 50,000 passengers will experience acute medical problems/emergencies during a flight (i.e., in-flight medical emergency). Cardiac arrest accounts for 0.3% of all in-flight medical emergencies. So far, no...

Background: Pneumonia is responsible for approximately 230,000 deaths in Europe, annually. Comprehensive and comparable reports on pneumonia mortality trends across the European Union (EU) are lacking. Methods: A temporal analysis of national mortality statistics to compare trends in pneumonia age-standardised death rates (ASDR) of EU countries...

Travelling to the stars is a dream nearly as old as mankind itself. Nowadays, spaceflight is in many ways common business, becoming even accessible to space tourists. However, many problems remain to be solved before humanity can venture into deep space with an acceptable level of risk, and medical preparedness is one of them. The management of any...

Sepsis is a leading cause of mortality in intensive care units and costs hospitals billions annually. Treating a septic patient is highly challenging, because individual patients respond very differently to medical interventions and there is no universally agreed-upon treatment for sepsis. In this work, we propose an approach to deduce treatment po...

Objective: Severity of illness scores rest on the assumption that patients have normal physiologic values at baseline and that patients with similar severity of illness scores have the same degree of deviation from their usual state. Prior studies have reported differences in baseline physiology, including laboratory markers, between obese and nor...

Sepsis is a leading cause of mortality in intensive care units (ICUs) and costs hospitals billions annually. Treating a septic patient is highly challenging, because individual patients respond very differently to medical interventions and there is no universally agreed-upon treatment for sepsis. Understanding more about a patient's physiological s...