ArticlePublisher preview available
To read the full-text of this research, you can request a copy directly from the authors.

Abstract and Figures

This work describes a novel end-to-end data ingestion and runtime processing pipeline, which is a core part of a technical solution aiming to monitor frailty indices of patients during and after treatment and improve their quality of life. The focus of this work is on the technical architectural details and the functionalities provided, which have been developed in a manner that are extensible, scalable and fault-tolerant by design. Extensibility refers to both data sources and the exact specification of analysis techniques. Our platform can combine data not only from multiple sensor types but also from electronic health records. Also, the analysis component can process the patient data both individually and in combination with other patients, while exploiting both cloud and edge resources. We have shown concrete examples of advanced analytics and evaluated the scalability of the system, which has been fully prototyped.
This content is subject to copyright. Terms and conditions apply.
Vol.:(0123456789)
1 3
Social Network Analysis and Mining (2022) 12:63
https://doi.org/10.1007/s13278-022-00891-y
ORIGINAL ARTICLE
Scalable real‑time health data sensing andanalysis enabling
collaborative care delivery
IliasDimitriadis1 · IoannisMavroudopoulos1· StylianiKyrama1· TheodorosToliopoulos1· AnastasiosGounaris1·
AthenaVakali1· AntonisBillis2· PanagiotisBamidis2
Received: 31 December 2021 / Revised: 30 March 2022 / Accepted: 3 May 2022
© The Author(s), under exclusive licence to Springer-Verlag GmbH Austria, part of Springer Nature 2022
Abstract
This work describes a novel end-to-end data ingestion and runtime processing pipeline, which is a core part of a technical
solution aiming to monitor frailty indices of patients during and after treatment and improve their quality of life. The focus
of this work is on the technical architectural details and the functionalities provided, which have been developed in a manner
that are extensible, scalable and fault-tolerant by design. Extensibility refers to both data sources and the exact specification
of analysis techniques. Our platform can combine data not only from multiple sensor types but also from electronic health
records. Also, the analysis component can process the patient data both individually and in combination with other patients,
while exploiting both cloud and edge resources. We have shown concrete examples of advanced analytics and evaluated the
scalability of the system, which has been fully prototyped.
Keywords Data ingestion· Streaming analytics· Frailty monitoring· Cloud processing· Edge processing
1 Introduction
Nowadays, there is an increasing need for runtime moni-
toring and analysis of patient behaviour especially after
serious treatments. For example, cancer refers to a group
of diseases, where abnormal cells divide without control
causing multiple health problems by invading nearby tis-
sues. According to Eurostat, cancer is responsible for more
than one quarter (25.8%) of the total number of deaths in
the European Union.1 Due to such seriousness of this dis-
ease group, vast research efforts have been undertaken to
develop effective and efficient treatment for cancer patients.
However, these treatments usually come with a cost in terms
of side effects lasting well beyond the end of the treatment.
Multiple researchers have identified various late effects
of cancer treatment (Ganz 2001; Agrawal 2014; Schover
etal. 2014; Stein etal. 2008; Lenihan and Cardinale 2012;
Balducci 2007). Among the extended list of late effects of
cancer treatment for adult populations, frailty is one of the
most important ones (Ommundsen etal. 2014; Bennett etal.
2013; Ness and Wogksch 2020; Ethun etal. 2017). This, in
turn, calls for development of methodologies and platforms
for the monitoring of frailty indices of patients during and
after their treatment process in order to identify the reasons,
Ilias Dimitriadis, Ioannis Mavroudopoulos and Styliani Kyrama are
contributed equally to this work.
* Ilias Dimitriadis
idimitriad@csd.auth.gr
Ioannis Mavroudopoulos
mavroudo@csd.auth.gr
Styliani Kyrama
kyrastyl@csd.auth.gr
Theodoros Toliopoulos
tatoliop@csd.auth.gr
Anastasios Gounaris
gounaria@csd.auth.gr
Athena Vakali
avakali@csd.auth.gr
Antonis Billis
ampillis@med.auth.gr
Panagiotis Bamidis
bamidis@med.auth.gr
1 Department ofInformatics, Aristotle University
ofThessaloniki, Thessaloníki, Greece
2 School ofMedicine, Aristotle University ofThessaloniki,
Thessaloníki, Greece 1 https:// ec. europa. eu/ euros tat/.
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
ResearchGate has not been able to resolve any citations for this publication.
Article
Full-text available
Managing multi-tenant edge devices with heterogeneous capabilities scattered across an urban area requires significant communication and computing power, which is challenging when devices are also resource-constrained. These devices play a crucial role in smart city monitoring systems by notifying various municipal organizations about a wide range of ongoing complex events. Some recent approaches in complex event processing use a publish-subscribe architectural pattern to decouple simple event producers from complex event consumers. However, they did not fully address communication efficiency or diverse quality of service (QoS) requirements in aggregating events. This paper proposes a new architecture that integrates the publish-subscribe architectural pattern with software-defined network technology for urban monitoring applications. The architecture enhances monitoring applications with capabilities of distributed processing and detection of complex events. It also enables application developers to define QoS requirements and supports the TESLA complex event specification language. The main focus of our work is on energy and network efficiency. The simulation results demonstrate significant improvements in energy consumption and data packet traffic compared to three close baselines.
Article
Full-text available
The active field of research is to achieve fast answers with minimal energy usage in mobile edge computing. The latest development of mobile edge computing (MEC) is a new model for allowing access to advanced computing resources at the edge of the network, near-end devices, enabling an abundance of latency-sensitive services needed for Internet of Things (IoT) devices. IoT devices associatedwith the Internet has enlarged intense and the data created by these devices. This would need offloading IoT tasks to dischargehigh computation and storage to resource-rich nodeslikeCloud Computing and Mobile Edge Computing. One of the considerations of cloud-based IoT environments is resource management, which generally revolves around workload balance, resource allocation, resource provisioning, task scheduling, and quality of service to attain performance enhancements. Effective resource management is a challenging problem in mobile edge computing and can deliver high-quality services to mobile devices. When a user demands (tasks) run on a local mobile device, energy consumption rises instead of in the cloud. In the server environment, latency becomes a problem where the task is done rather than on the handheld device. Hence in this paper, the mobile Edge computing-based resource management and task scheduling (MEC-RMTS) framework has been proposed for efficient task-offloading strategies, low latency, and scalable IoT network computing for smartphone devices. Thus, the suggestedmethodhelps the resource manager in the mobile edge computing system concerning scheduling the offloading tasks to reduce the total service time and enhance the effectiveness of mobile edge computing resources. First, the proposed system uses Power Usage (PU) to decrease energy consumption, a Transmission problem for smartphone phones. Using the almost convex technique, designers answer PU and present a gradient-dependent Game Model (GM). Then, as a mixed-intelligent, non-linear program model, the issue of Common Needs and Resource Utilization (CNRU) is used to minimize request delays. The simulation results show that MEC-RMTSF is implemented to save energy usage to 7.1% and has a delayed 0.95sfor allocating resourcesand scheduling management.
Article
Full-text available
Remote monitoring of physical frailty is important to personalize care for slowing down the frailty process and/or for the healthy recovery of older adults following acute or chronic stressors. Taking the Fried frailty criteria as a reference to determine physical frailty and frailty phenotypes (slowness, weakness, exhaustion, inactivity), this study aimed to explore the benefit of machine learning to determine the least number of digital biomarkers of physical frailty measurable from a pendant sensor during activities of daily living. Two hundred and fifty-nine older adults were classified into robust or pre-frail/frail groups based on the physical frailty assessments by the Fried frailty criteria. All participants wore a pendant sensor at the sternum level for 48 h. Of seventeen sensor-derived features extracted from a pendant sensor, fourteen significant features were used for machine learning based on logistic regression modeling and a recursive feature elimination technique incorporating bootstrapping. The combination of percentage time standing, percentage time walking, walking cadence, and longest walking bout were identified as optimal digital biomarkers of physical frailty and frailty phenotypes. These findings suggest that a combination of sensor-measured exhaustion, inactivity, and speed have potential to screen and monitor people for physical frailty and frailty phenotypes.
Article
Full-text available
Diseases can affect organs such as the heart, lungs, brain, muscles, or vocal folds, which can then alter an individual’s voice. Therefore, voice analysis using artificial intelligence opens new opportunities for healthcare. From using vocal biomarkers for diagnosis, risk prediction, and remote monitoring of various clinical outcomes and symptoms, we offer in this review an overview of the various applications of voice for health-related purposes. We discuss the potential of this rapidly evolving environment from a research, patient, and clinical perspective. We also discuss the key challenges to overcome in the near future for a substantial and efficient use of voice in healthcare.
Article
Internet of Things (IoT) is an ever-expanding ecosystem that integrates software, hardware, physical objects, and computing devices to communicate, collect, and exchange data. The IoT provides a seamless platform to facilitate interactions between humans and a variety of physical and virtual things, including personalized healthcare domains. Lack of access to medical resources, growth of the elderly population with chronic diseases and their needs for remote monitoring, an increase in medical costs, and the desire for telemedicine in developing countries, make the IoT an interesting subject in healthcare systems. The IoT has a potential to decrease the strain on sanitary systems besides providing tailored health services to improve the quality of life. Therefore, this paper aims to identify, compare systematically, and classify existing investigations taxonomically in the Healthcare IoT (HIoT) systems by reviewing 146 articles between 2015 and 2020. Additionally, we present a comprehensive taxonomy in the HIoT, analyze the articles technically, and classify them into five categories, including sensor-based, resource-based, communication-based, application-based, and security-based approaches. Furthermore, the benefits and limitations of the selected methods, with a comprehensive comparison in terms of evaluation techniques, evaluation tools, and evaluation metrics, are included. Finally, based on the reviewed studies, power management, trust and privacy, fog computing, and resource management as leading open issues; tactile Internet, social networks, big data analytics, SDN/NFV, Internet of nano things, and blockchain as important future trends; and interoperability, real-testbed implementation, scalability, and mobility as challenges are worth more studying and researching in HIoT systems.
Article
Background: Cognitive frailty (CF), defined as the simultaneous presence of cognitive impairment and physical frailty, is a clinical symptom in early-stage dementia with promise in assessing the risk of dementia. The purpose of this study was to use wearables to determine the most sensitive digital gait biomarkers to identify CF. Methods: Of 121 older adults (age = 78.9 ± 8.2 years, body mass index = 26.6 ± 5.5 kg/m2) who were evaluated with a comprehensive neurological exam and the Fried frailty criteria, 41 participants (34%) were identified with CF and 80 participants (66%) were identified without CF. Gait performance of participants was assessed under single task (walking without cognitive distraction) and dual task (walking while counting backward from a random number) using a validated wearable platform. Participants walked at habitual speed over a distance of 10 m. A validated algorithm was used to determine steady-state walking. Gait parameters of interest include steady-state gait speed, stride length, gait cycle time, double support, and gait unsteadiness. In addition, speed and stride length were normalized by height. Results: Our results suggest that compared to the group without CF, the CF group had deteriorated gait performances in both single-task and dual-task walking (Cohen's effect size d = 0.42-0.97, p < 0.050). The largest effect size was observed in normalized dual-task gait speed (d = 0.97, p < 0.001). The use of dual-task gait speed improved the area under the curve (AUC) to distinguish CF cases to 0.76 from 0.73 observed for the single-task gait speed. Adding both single-task and dual-task gait speeds did not noticeably change AUC. However, when additional gait parameters such as gait unsteadiness, stride length, and double support were included in the model, AUC was improved to 0.87. Conclusions: This study suggests that gait performances measured by wearable sensors are potential digital biomarkers of CF among older adults. Dual-task gait and other detailed gait metrics provide value for identifying CF above gait speed alone. Future studies need to examine the potential benefits of gait performances for early diagnosis of CF and/or tracking its severity over time.
Article
Recent advances in networking and mobile technologies such as 5G, long-term evolution (LTE), LiFi, wireless broadband (WiBro), WiFi-Direct, Bluetooth Low Energy (BLE) have paved the way for intelligent and smart services. With an average of more than 6.5 devices per person, a plethora of applications are being developed especially related to healthcare. Although, current edge devices such as smartphone and smartwatch are becoming increasingly more powerful and more affordable, there are certain tasks such as those involving machine learning that require higher computational resources, thereby resulting in higher energy consumption in the case of edge devices. Offloading tasks to co-located edge nodes such as fog (a cloud-like localized, smaller resource pool), or a femto-cloud (integration of multiple edge nodes) is one viable solution to address the issues such as performing compute-intensive tasks, and managing energy consumption. The outbreak of coronavirus disease 2019 (COVID-19) and becoming a pandemic has also made a case for edge computing (involving smartphone, wearables, health sensors) for the detection of symptoms to quarantine potential carriers of the virus. We focus on how various forms of smart and opportunistic healthcare (oHealth) can be provided by leveraging edge computing that makes use of a machine learning-based approach. We apply k-nearest neighbors (kNN), naive Bayes (NB), and support vector classification (SVC) algorithms on real data trace for the healthcare and safety-related scenarios we considered. The empirical results obtained provide useful insights into machine learning-based task offloading in edge computing.
Article
Introduction: Concern about falling is a prevalent worry among community-dwelling older adults and may contribute to a decline in physical and mental health. This study aimed to examine the association between mobility performance and concern about falling. Methods: Older adults aged 65 years and older, with Mini-Mental State Examination score ≥24, and ambulatory (with or without the assistive device) were included. Concern about falling was evaluated with Falls Efficacy Scale-International (FES-I) scores. Participants with high concern about falling were identified using the cutoff of FES-I ≥23. Participants' motor capacity was assessed in standardized walking tests under single- and dual-task conditions. Participants' mobility performance was measured based on a 48-h trunk accelerometry signal from a wearable pendant sensor. Results: No significant differences were observed at participant characteristics across groups with different levels of concern about falling (low: N = 64, age = 76.3 ± 7.2 years, female = 46%; high: N = 59, age = 79.3 ± 9.1 years, female = 47%), after propensity matching with BMI, age, depression, and cognition. With adjustment of motor capacity (stride velocity and stride length under single- and dual-task walking conditions), participants with high concern about falling had significantly poorer mobility performance than those with low concern about falling, including lower walking quantity (walking bouts, steps and time per day, and walking bout average, walking bout variability, and longest walking bout, p ≤ 0.013), and poorer daily-life gait (stride velocity and gait variability, p ≤ 0.023), and poorer walking quality (frontal gait symmetry, and trunk acceleration and velocity intensity, p ≤ 0.041). The selected mobility performance metrics (daily steps and frontal gait symmetry) could significantly contribute to identifying older adults with high concern about falling (p ≤ 0.042), having better model performance (p = 0.036) than only walking quantity (daily steps) with adjustment of confounding effects from the motor capacity (stride length under dual-task walking condition). Conclusion: There is an association between mobility performance and concern about falling in older adults. Mobility performance metrics can serve as predictors to identify older adults with high concern about falling, potentially providing digital biomarkers for clinicians to remotely track older adults' change of concern about falling via applications of remote patient monitoring.