Applications of Machine Learning in Real-Life Digital Health Interventions: Review of the Literature
Open accessThe DOI matches its Crossref record; 48 of the 48 references it cites were found in a registry or an index.
Abstract
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Preferred Reporting Items for Systematic Reviews and Meta-Analyses: the PRISMA statement
Moher, D., Liberati, A., Tetzlaff, J., Altman, D. G., & for the PRISMA Group (2009) · BMJ · doi:10.1136/bmj.b2535 · Cited by 83,823
Preferred Reporting Items for Systematic Reviews and Meta-Analyses: The PRISMA Statement
Moher, D., Liberati, A., Tetzlaff, J., Altman, D. G., & The PRISMA Group (2009) · PLoS Medicine · doi:10.1371/journal.pmed.1000097 · Cited by 64,042 · cited 1×
“The systematic review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines [19].”
Wang, G., Ma, R., Qiao, G., Wada, K., Aizawa, Y., & Satoh, T. (2015) · Integrative Medicine International · doi:10.1159/000368408 · Cited by 18,657
Comparison of PubMed, Scopus, Web of Science, and Google Scholar: strengths and weaknesses
Falagas, M. E., Pitsouni, E. I., Malietzis, G. A., & Pappas, G. (2008) · The FASEB Journal · doi:10.1096/fj.07-9492lsf · Cited by 5,039
Self-management education: History, definition, outcomes, and mechanisms
Lorig, K. R., & Holman, H. R. (2003) · Annals of Behavioral Medicine · doi:10.1207/s15324796abm2601_01 · Cited by 4,094 · cited 1×
“These studies also demonstrated the latest efforts to promote individuals’ personalized self-management and to put them at the center of health care [38].”
BackgroundPredicting the future - big data, machine learning, and clinical medicine
Obermeyer, Z., & Emanuel, E. J. (2016) · New England Journal of Medicine · doi:10.1056/nejmp1606181 · Cited by 3,652 · cited 1×
“With the advent of new tools and algorithms for machine learning, a new class of smart digital health interventions can be developed, which could revolutionize effective health care delivery [5].”
BackgroundPersonalized nutrition by prediction of glycemic responses
Zeevi, D., Korem, T., Zmora, N., Israeli, D., Rothschild, D., Weinberger, A., Ben-Yacov, O., Lador, D., Avnit-Sagi, T., Lotan-Pompan, M., et al. (2015) · Cell · doi:10.1016/j.cell.2015.11.001 · Cited by 2,929 · cited 8×
“In this context, the retrospective validation of algorithms and models, given the availability of one or more datasets, constitutes only the first step in the evaluation process [28].”
InfluentialDoes tailoring matter? Meta-analytic review of tailored print health behavior change interventions
Noar, S. M., Benac, C. N., & Harris, M. S. (2007) · Psychological Bulletin · doi:10.1037/0033-2909.133.4.673 · Cited by 2,136 · cited 1×
“Considering the effectiveness of tailored messaging in influencing health behavior change [39], further research in this area is warranted.”
Blundell, J. E., Baker, J. L., Boyland, E., Blaak, E., Charzewska, J., de Henauw, S., Frühbeck, G., Gonzalez-Gross, M., Hebebrand, J., Holm, L., et al. (2017) · Obesity Facts · doi:10.1159/000455952 · Cited by 1,945
Miotto, R., Li, L., Kidd, B. A., & Dudley, J. T. (2016) · Scientific Reports · doi:10.1038/srep26094 · Cited by 1,710
Research works printed but not linked: 2
- Cruz, JA, 2007, Cancer Inform, 2, 59
- 2016, Monitoring and Evaluating Digital Health Interventions: A Practical Guide to Conducting Research and Assessment
Cited by
Items 201–245 of 245
Machine Learning-Based MRI LAVA Dynamic Enhanced Scanning for the Diagnosis of Hilar Lesions
Wang, H., Wang, S., & Zhou, L. (2022) · Computational and Mathematical Methods in Medicine · doi:10.1155/2022/9592970 · Cited by 1
“Machine learning needs to extract feature parameters from images during classification and recognition and then carry out targeted analysis, which may miss some critical information and reduce the model’s accuracy [25, 26].”
BackgroundReal - Time AI and Machine Learning Applications in Healthcare Management
Poornima, D., Premalatha, J. S., Abirami, G., Triveni, K., & Bobby, M. P. (2023) · International Conference on Emerging Research in Computational Science (ICERCS) · doi:10.1109/icercs57948.2023.10434180 · Cited by 1
“In order to offer actual-time statistics analysis and insights, IoT-ADNN ought to coordinate well with a wide sort of medical gadgets and software systems [3].”
BackgroundDeep Learning–Based Surrounding Descriptor for the Visually Challenged
Vamsi, T. M. N., Shankar, K., Karthik, G., Puruvi, M., & Chanti, B. (2024) · Springer proceedings in mathematics & statistics · doi:10.1007/978-3-031-51167-7_15 · Cited by 1
Wahyudi, I., & Sulaiman, L. (2024) · THRIVE Health Science Journal · doi:10.56566/thrive.v1i2.240 · Cited by 2
“It is crucial for schools to address these challenges and ensure that all students have access to the necessary resources and support to feel included and supported (Ekeland et al., 2010; Triantafyllidis & Tsanas, 2019).”
BackgroundThe Growing Application Potential of Machine Learning in Healthcare Systems of Modernity
França, R. P., Bonacin, R., & Monteiro, A. C. B. (2024) · Springer eBooks · doi:10.1007/978-3-031-72676-7_1 · Cited by 1
Visual Understanding and Navigation for the Visually Impaired Using Image Captioning
Uikey, J., Undre, I., Vasani, U., Shaikh, A., Mirajkar, R., & Bagade, J. V. (2025) · International Conference on Cognitive Computing in Engineering, Communications, Sciences and Biomedical Health Informatics (IC3ECSBHI) · doi:10.1109/ic3ecsbhi63591.2025.10991312 · Cited by 1
“However, most of these studies have shortcomings since they have not tested the machine learning methodologies in adequate levels; therefore, rigorous study should be performed to establish clinical potential in healthcare [8].”
Tsanas, A., & Arora, S. (2019) · IEEE International Conference on Bioinformatics and Bioengineering (BIBE) · doi:10.1109/bibe.2019.00178 · Cited by 2
“We envisage this work being a step towards the direction of developing practical tools which may assist real-life health interventions, moving beyond standard research studies which are rarely translated into clinical practice [24].”
BackgroundSelf-citationLuo, G., Stone, B. L., Sheng, X., He, S., Koebnick, C., & Nkoy, F. L. (2021) · JMIR Research Protocols · doi:10.2196/27065 · Cited by 3
“In fact, the black-box issue has been a major reason for the slow adoption of machine learning in clinical practice, despite machine learning often producing the highest prediction accuracy among all predictive modeling methods [33,123-127].”
BackgroundDhaliwal, B., Neil‐Sztramko, S., Boston-Fisher, N., Buckeridge, D. L., & Dobbins, M. (2021) · JMIR Public Health and Surveillance · doi:10.2196/26503 · Cited by 3
“It holds promise as a methodological toolbox for supporting public health decision-making and improving population health outcomes, although the evidence is based on a small number of preliminary studies [27,28].”
BackgroundScheplitz, T., Burwitz, M., & Weimann, T. G. (2022) · Hawaii International Conference on System Sciences (HICSS) · doi:10.24251/hicss.2022.502 · Cited by 1
Digital technologies for bowel management: A scoping review
Iyawa, G. E., Henton, S., Maltinsky, W., Casson, A. J., Taylor, A., Lake, D., Medina-Lombardero, S., Saleh, M., & Crichton, M. L. (2024) · Procedia Computer Science · doi:10.1016/j.procs.2024.06.353 · Cited by 3
“This is similar to other studies reviewing the application of digital technologies such as AI and machine learning in predicting, detecting and managing diseases 31 .”
ResultTowards Machine Learning approach for Digital-Health intervention program.
Santhanagopalan, M., Chetty, M., Foale, C., & Klein, B. (2019) · FedUni ResearchOnline (Federation University Australia)
Diabetes Disease through Machine Learning: A comparative study
Marques, G., Pires, I. M., & García, N. M. (2020) · doi:10.1145/3445815.3445828
Discovering Healthcare Data Patterns by Artificial Intelligence Methods
Krikščiūnienė, D., Sakalauskas, V., Ognjanović, I., & Šendelj, R. (2022) · Intelligent systems reference library · doi:10.1007/978-3-030-79353-1_10
“This research topic is very popular and attract attention of many researchers [1–7].”
BackgroundTran, Q., Chin, Y.-P., Nguyen, P., Lee, M., Yang, H., Huang, C., Le, N. Q. K., Hsu, M., Li, Y., & Su, S. (2020) · doi:10.2196/preprints.17888
Tsanas, A. (2022) · International Conference on Telecommunications and Signal Processing (TSP) · doi:10.1109/tsp55681.2022.9851271
“We envisage these considerations may be useful if the field is to move beyond standard highly controlled research studies which are rarely translated into clinical practice [28], and therefore researchers should explore innovative solutions, which come with new challenges, to facilitate uptake and generalize findings…”
BackgroundSelf-citationMaalouf, M., Bader, M., & Jelinek, H. F. (2022) · doi:10.2196/preprints.43927
REWEIGHTED COMPONENTS IN DIET QUALITY SCORES AND MORTALITY RISK ASSOCIATIONS
Parker, H. (2022) · Digital Commons - URI (University of Rhode Island) · doi:10.23860/diss-parker-haley-2022
Poonam, & Batra, N. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-28183-9_29
Stress Prevention Measures in the Workplace
Erskine, J., & Fauquet-Alekhine, P. (2023) · Springer eBooks · doi:10.1007/978-3-031-27349-0_20
Overmars, L. M. (2024) · Utrecht University Repository (Utrecht University) · doi:10.33540/1263 · Cited by 1
Transformation in Healthcare Industry to Boost Patient Engagement using AI
Gandhi, P. (2024) · Journal of Informatics Education and Research · doi:10.52783/jier.v4i2.1003
Model for Predicting the Effect of Sibutramine Therapy in Obesity
Danilov, S. D., Matveev, G. A., Babenko, A. Y., & Shlyakhto, E. V. (2024) · Journal of Personalized Medicine · doi:10.3390/jpm14080811 · Cited by 2
“There is evidence showing the effectiveness of using artificial intelligence in decision support for various dietary interventions in obesity management [13–16].”
BackgroundCosta, J. P., Godoy, W. F., Biagi, L., & Bertachi, A. H. (2023) · Anais do ... Simpósio Brasileiro de Sistemas Elétricos · doi:10.20906/sbai-sbse-2023/3924
Nuerlan, M. (2025) · Highlights in Science Engineering and Technology · doi:10.54097/fvsc1952
Machine Learning in Health: A Systematic Review
Padovam, A. R. C., Pereira, D. R., & Attux, R. (2025) · doi:10.5753/sbcas_estendido.2025.6992
Quality of Life, Risk Behavior, and Digital Engagement
Berceanu, D. C.-A., Pânişoară, G., Popovici, A.-F., & Malureanu, A. (2025) · Studia Universitatis Babeș-Bolyai Psychologia-Paedagogia · doi:10.24193/subbpsyped.2025.1.07
Transforming healthcare through IoT: A survey of challenges and solutions
Mehak, Shrivastava, P., Channi, H. K., & Kaur, J. (2025) · AIP conference proceedings · doi:10.1063/5.0271022
Kirkwood, J. R., Galloway, N., Lindsay, R. S., Manataki, A., Wake, D. J., & Reynolds, R. M. (2025) · Diabetic Medicine · doi:10.1111/dme.70171 · Cited by 1
“40 In a review by Sahota et al. 41 of 36 randomised control trials of clinical decision support systems, 63% (22/35) of the studies showed an improvement in care; they found, however, that the improvements were in processes of care rather than patient outcomes.”
Choi, S.-G., Lee, E.-Y., Lee, O.-J., Kim, S., Kang, J.-Y., & Lim, J. S. (2022) · Figshare · doi:10.6084/m9.figshare.19727499
Online Transdiagnostic Self-Help Interventions
Klimczak, K. S., Donahue, M. L., & Bowers, E. M. (2026) · Springer eBooks · doi:10.1007/978-3-032-08980-9_12 · Cited by 2
Sintura, Y. C. M., & Ortíz, W. A. A. (2026) · Scientific Reports · doi:10.1038/s41598-026-39453-z
Sparrock, L. S., Vidrine, J. I., Vinci, C., Naqa, I. M. E., Sutton, S. K., Salloum, R. G., Dallery, J., Crane, T. E., Penedo, F. J., Brockway, S. J., et al. (2026) · JMIR Research Protocols · doi:10.2196/92288
“Despite this potential, machine and deep learning remain underutilized in mHealth interventions [62].”
Kundu, A., Selby, P. L., Felsky, D., Moraes, T. J., Planinac, L. C., & Chaiton, M. (2026) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph23040527
“Several ML-based real-life digital health interventions have demonstrated effectiveness in predicting and managing depression, psychological conditions, lifestyle change, and smoking cessation [10].”
Fukuda, Y., & Fukuda, K. (2026) · Digital Health · doi:10.1177/20552076261444907
“4,7,19,30,32,33”
Dharmaratnakar, A., Ranganathan, S., Sinha, A., & Das, D. (2026) · IEEE International Conference on Digital Health (ICDH) · doi:10.1109/icdh72779.2026.00059
“However, self-directed at-home physiotherapy is plagued by chronically low compliance rates and high instances of incorrect exercise execution [1].”
P, M. J. A., Madhesh Kumar, M., Vayshak, K., V, & Surendhar, A. (2026) · INDIAN JOURNAL OF ALLIED HEALTH SCIENCE · doi:10.66159/ijahs.2026.2106
Sun, Y., & Wu, L.-Y. (2026) · Frontiers in Public Health · doi:10.3389/fpubh.2026.1841351 · Cited by 3
“Such platforms can tailor content to individual learners’ needs, track progress, and provide timely interventions, thereby enhancing engagement and learning outcomes (67, 68).”
Federated learning for speech and text based depression detection
Gaikwad, P. P., & Venkatesan, M. (2026) · AIP conference proceedings · doi:10.1063/5.0344267
Luo, Y., Liu, T., & Chen, Y. (2026) · Hereditas · doi:10.1186/s41065-026-00698-3
“Machine learning is a new type of algorithm and statistical model that has been applied by an increasing number of researchers to screen and identify disease biomarkers [14, 15].”
Medical AI across Data Regimes to Promote Proactive Health
Li, P., Wu, J., Zuo, Q., Zhang, L., & Zhan, Q. (2026) · Health Data Science · doi:10.34133/hds.0495
“Many of these ML models retain a degree of interpretability through feature importance analyses or decision-tree structures to enable transparent clinical decision support [ 2 , 21 , 22 ].”
Leveraging machine learning for symptom-based malaria diagnosis: a predictive model approach
Ruban, S., Varenya, V., Shanthini, H., Rai, S., & Subramani, S. (2026) · Neural Computing and Applications · doi:10.1007/s00521-026-12305-7 · Cited by 1
Eder, P. A., Moser, O., Rashid, A., Schlemm, E., Hessler, J., von Jouanne-Diedrich, H. K., Ziegler, V., & Soda, H. (2026) · Research Square · doi:10.21203/rs.3.rs-10095424/v1
Mental health monitoring in the workplace using artificial intelligence: A scoping review
Lodewyk, K., Tian, J., Kurkova, V., Modanloo, S., Dennett, L., Noble, J., Greenshaw, A., & Hayward, J. (2026) · PLOS Digital Health · doi:10.1371/journal.pdig.0001743
“Combing sensor data with AI techniques has shown promise in remote monitoring of diabetes, hypertension, atrial fibrillation, depression, anxiety, psychosis, stress and more [24].”
Metadata
- Authors
- Triantafyllidis, A. K., & Tsanas, A.
- Affiliations
- Aristotle University of Thessaloniki (GR)
- University of Oxford (GB)
- Corresponding author
- Triantafyllidis, Andreas K
- Venue
- Journal of Medical Internet Research
- Publisher
- JMIR Publications Inc.
- Published
- 2019-04-05
- Volume
- 21
- Issue
- 4
- Pages
- e12286
- ISSN
- 1438-8871 (ISSN-L)
- PMC
- PMC6473205
- OpenAlex
- W2926287779
- Cited by
- 243
- References
- 48
- Citations by year
- 2026: 17 · 2025: 29 · 2024: 36 · 2023: 44 · 2022: 40 · 2021: 40 · 2020: 29 · 2019: 8
- FWCI
- 1.40
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- Locations
- Journal of Medical Internet Research (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Edinburgh Research Explorer (University of Edinburgh) (submittedVersion, cc-by)
- Funders
- Wellcome Trust (098461/Z/12/Z)
- Scottish Government
- British Heart Foundation
- Department of Health and Social Care
- University of Oxford
- Public Health Agency
- Chief Scientist Office, Scottish Government Health and Social Care Directorate
- Medical Research Council (098461/Z/12/Z)
- Engineering and Physical Sciences Research Council
- Economic and Social Research Council
- Health and Social Care Research and Development Division
- Health Data Research UK
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Health Professions › General Health Professions › Mobile Health and mHealth Applications
- Social Sciences › Psychology › Applied Psychology › Digital Mental Health Interventions
- Keywords
- machine learning, digital health interventions, real-world applications, depression prediction, speech recognition, stress management, phantom limb pain, smoking cessation, personalized nutrition, glycemic response, speech disorders
- MeSH terms
- Machine Learning, Humans, Quality of Health Care, Telemedicine, Data Mining
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.
