Applications of Machine Learning in Real-Life Digital Health Interventions: Review of the Literature.

BACKGROUND: Machine learning has attracted considerable research interest toward developing smart digital health interventions. These interventions have the potential to revolutionize health care and lead to substantial outcomes for patients and medical professionals. OBJECTIVE: Our objective was to review the literature on applications of machine learning in real-life digital health interventions, aiming to improve the understanding of researchers, clinicians, engineers, and policy makers in developing robust and impactful data-driven interventions in the health care domain. METHODS: We searched the PubMed and Scopus bibliographic databases with terms related to machine learning, to identify real-life studies of digital health interventions incorporating machine learning algorithms. We grouped those interventions according to their target (ie, target condition), study design, number of enrolled participants, follow-up duration, primary outcome and whether this had been statistically significant, machine learning algorithms used in the intervention, and outcome of the algorithms (eg, prediction). RESULTS: Our literature search identified 8 interventions incorporating machine learning in a real-life research setting, of which 3 (37%) were evaluated in a randomized controlled trial and 5 (63%) in a pilot or experimental single-group study. The interventions targeted depression prediction and management, speech recognition for people with speech disabilities, self-efficacy for weight loss, detection of changes in biopsychosocial condition of patients with multiple morbidity, stress management, treatment of phantom limb pain, smoking cessation, and personalized nutrition based on glycemic response. The average number of enrolled participants in the studies was 71 (range 8-214), and the average follow-up study duration was 69 days (range 3-180). Of the 8 interventions, 6 (75%) showed statistical significance (at the P=.05 level) in health outcomes. CONCLUSIONS: This review found that digital health interventions incorporating machine learning algorithms in real-life studies can be useful and effective. Given the low number of studies identified in this review and that they did not follow a rigorous machine learning evaluation methodology, we urge the research community to conduct further studies in intervention settings following evaluation principles and demonstrating the potential of machine learning in clinical practice.

A Survey of Mobile Phone Sensing, Self-Reporting, and Social Sharing for Pervasive Healthcare.

The current institution-based model for healthcare service delivery faces enormous challenges posed by an aging population and the prevalence of chronic diseases. For this reason, pervasive healthcare, i.e., the provision of healthcare services to individuals anytime anywhere, has become a major focus for the research community. In this paper, we map out the current state of pervasive healthcare research by presenting an overview of three emerging areas in personalized health monitoring, namely: 1) mobile phone sensing via in-built or external sensors, 2) self-reporting for manually captured health information, such as symptoms and behaviors, and 3) social sharing of health information within the individual's community. Systems deployed in a real-life setting as well as proofs-of-concept for achieving pervasive health are presented, in order to identify shortcomings and increase our understanding of the requirements for the next generation of pervasive healthcare systems addressing these three areas.

Framework of sensor-based monitoring for pervasive patient care.

Sensor-based health systems can often become difficult to use, extend and sustain. The authors propose a framework for designing sensor-based health monitoring systems aiming to provide extensible and usable monitoring services in the scope of pervasive patient care. The authors' approach relies on a distributed system for monitoring the patient health status anytime-anywhere and detecting potential health complications, for which healthcare professionals and patients are notified accordingly. Portable or wearable sensing devices measure the patient's physiological parameters, a smart mobile device collects and analyses the sensor data, a Medical Center system receives notifications on the detected health condition, and a Health Professional Platform is used by formal caregivers in order to review the patient condition and configure monitoring schemas. A Service-oriented architecture is utilised to provide extensible functional components and interoperable interactions among the diversified system components. The framework was applied within the REMOTE ambient-assisted living project in which a prototype system was developed, utilising Bluetooth to communicate with the sensors and Web services for data exchange. A scenario of using the REMOTE system and preliminary usability results show the applicability, usefulness and virtue of our approach.

Development and usability of a personalized sensor-based system for pervasive healthcare.

Although a plethora of remote health monitoring systems have been proposed for chronic conditions, the challenge posed by the changing patient needs and the requirement for personalization in health monitoring to move beyond proprietary, difficult to extend, and unsustainable solutions still pertains. In this direction, we describe a mobile health system based on a smartphone, portable/wearable sensors for measuring the patient's physiological parameters, and back-end platforms for the health professionals to monitor the patient condition and configure monitoring plans in an individualized manner. A prototype system was developed based on a Service-oriented Architecture and integrating commercially available sensing devices. An experimental study has been conducted with 53 patients in order to investigate the usability of the proposed system. The patients were able to perform the majority of the target tasks successfully (Success Rate = 77%), while the perceived usability using the System Usability Scale (SUS) was found to be above average (SUS score = 73%), indicating that the patients overall perceived the system as both easy to use and useful.