Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Sep 21, 2018
Date Accepted: Jan 26, 2019
Applications of Machine Learning in Real-life Digital Health Interventions: A Review of the Literature
ABSTRACT
Background:
Machine learning has attracted considerable research interest towards developing smart digital interventions. These interventions can revolutionize healthcare and may lead to substantial outcomes for patients and medical professionals.
Objective:
Provide a literature review of 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 healthcare domain.
Methods:
The bibliographic databases of PubMed and Scopus were searched 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 type (e.g., target condition), the study design, the number of enrolled participants, the follow-up duration, the primary outcome and whether this had been statistically significant, the machine learning algorithms used in the intervention, as well as the outcome of the algorithms (e.g., 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 at 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. Significantly positive outcomes were reported in 6 interventions (75%).
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 do 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 medical care. Clinical Trial: Not applicable
Citation
