Advertisement

A Scoping Review of the Use of Machine Learning in Health Economics and Outcomes Research: Part 1—Data From Wearable Devices

Published:September 15, 2022DOI:https://doi.org/10.1016/j.jval.2022.08.005

      Highlights

      • The widespread use of wearable devices resulted in a constant flow of individual data related to one’s daily activities and certain biometrics. Machine learning (ML) has gained increasing attention in managing large amounts of complex wearable data. Health data collected from wearable devices, benefited by the advanced analyzing technologies such as ML, will likely generate meaningful knowledge in health economics and outcomes research (HEOR).
      • Our study describes how ML has been applied to data collected from wearable devices in HEOR, which has not been studied yet. ML has not only been applied to monitor general health status but also to monitor or forecast outcomes specific to certain types of disease or treatment. Most studies using devices that were not necessarily designed for medical purposes (eg, smartwatches) have started to be published in relatively recent years.
      • Our findings suggest a potential for the application of wearable data, coupled with ML techniques, to be expanded to disease- or treatment-specific research in HEOR. The detailed description of the emerging patterns of ML applications with wearable data can address uncertainties in how and when to use ML with wearable data among HEOR researchers, potentially generating additional real-world evidence that can inform treatment and reimbursement decisions.

      Abstract

      Objectives

      With the emerging use of machine learning (ML) techniques, there has been particular interest in using wearable data for health economics and outcomes research (HEOR). We aimed to understand the emerging patterns of how ML has been applied to wearable data in HEOR.

      Methods

      We identified studies published in PubMed between January 2016 and March 2021. Studies that included at least 1 HEOR-related Medical Subject Headings term, applied an ML, and used wearable data were eligible for inclusion. Two reviewers abstracted information including ML application types and data on which ML was applied and analyzed them using descriptive analyses.

      Results

      A total of 148 studies were identified from PubMed, among which 32 studies met the inclusion criteria. There has been an increase over time in the number of ML studies using wearable data. ML has been more frequently used for monitoring events in real time (78%) than to predict future events (22%). There has been a wide range of outcomes examined, ranging from general physical or mental health (24%) to more disease-specific outcomes (eg, disease incidence [19%] and progression [13%]) and treatment-related outcomes (eg, treatment adherence [9%] and outcomes [9%]). Data for ML models were more often derived from wearable devices with specific medical purposes (60%) than those without (40%).

      Conclusion

      There has been a wide range of applications of ML to wearable data. Both medical and nonmedical wearable devices have been used as a data source, showing the potential for providing rich data for ML studies in HEOR.

      Keywords

      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Value in Health
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

      1. Wearable technology market - growth, trends, COVID-19 impact, and forecasts (2022-2027). Mordor Intelligence.
      2. Wearable medical devices market size, share & COVID-19 impact analysis, by product (diagnostic & patient monitoring wearable medical devices, and therapeutic wearable medical devices); by application (remote patient monitoring & home healthcare, and sports and fitness); by distribution channel (retail pharmacies, online pharmacies, and hypermarkets & others), and regional forecast 2020-2027. Fortune Business Insights.
        • Chandrasekaran R.
        • Katthula V.
        • Moustakas E.
        Patterns of use and key predictors for the use of wearable health care devices by US adults: insights from a national survey.
        J Med Internet Res. 2020; 22e22443
        • McCarthy J.
        One in five U.S. adults use health apps, wearable trackers. GALLUP.
        • Guk K.
        • Han G.
        • Lim J.
        • et al.
        Evolution of wearable devices with real-time disease monitoring for personalized healthcare.
        Nanomaterials (Basel). 2019; 9: 813
        • Iqbal S.M.
        • Mahgoub I.
        • Du E.
        • et al.
        Advances in healthcare wearable devices.
        npj Flex Electron. 2021; 5: 1-14
        • Hicks J.L.
        • Althoff T.
        • Sosic R.
        • et al.
        Best practices for analyzing large-scale health data from wearables and smartphone apps.
        NPJ Digit Med. 2019; 2: 45
        • Peek N.
        • Holmes J.H.
        • Sun J.
        Technical challenges for big data in biomedicine and health: data sources, infrastructure, and analytics.
        Yearb Med Inform. 2014; 23: 42-47
        • Kruse C.S.
        • Goswamy R.
        • Raval Y.J.
        • Marawi S.
        Challenges and opportunities of big data in health care: a systematic review.
        JMIR Med Inform. 2016; 4: e5359
        • Catalyst N.
        Healthcare big data and the promise of value-based care.
        NEJM Catal. 2018; 4
        • Beam A.L.
        • Kohane I.S.
        Big data and machine learning in health care.
        JAMA. 2018; 319: 1317-1318
        • Charara S.
        How machine learning will take wearable data to the next level. WAREABLE.
        • Azodo I.
        • Williams R.
        • Sheikh A.
        • Cresswell K.
        Opportunities and challenges surrounding the use of data from wearable sensor devices in health care: qualitative interview study.
        J Med Internet Res. 2020; 22e19542
        • Cho S.
        • Ensari I.
        • Weng C.
        • Kahn M.G.
        • Natarajan K.
        Factors affecting the quality of person-generated wearable device data and associated challenges: rapid systematic review.
        JMIR Mhealth Uhealth. 2021; 9e20738
      3. About HEOR. The Professional Society for Health Economics and Outcomes Research.
      4. MeSH - machine learning. National Library of Medicine, National Center for Biotechnology Information.
        https://www.ncbi.nlm.nih.gov/mesh/2010029
        Date accessed: June 15, 2022
        • Doupe P.
        • Faghmous J.
        • Basu S.
        Machine learning for health services researchers.
        Value Health. 2019; 22: 808-815
        • Sigcha L.
        • Pavón I.
        • Costa N.
        • et al.
        Automatic resting tremor assessment in Parkinson’s disease using smartwatches and multitask convolutional neural networks.
        Sensors. 2021; 21: 291
        • Meng Y.
        • Speier W.
        • Shufelt C.
        • et al.
        A machine learning approach to classifying self-reported health status in a cohort of patients with heart disease using activity tracker data.
        IEEE J Biomed Health Inform. 2019; 24: 878-884
        • Fozoonmayeh D.
        • Le H.V.
        • Wittfoth E.
        • et al.
        A scalable smartwatch-based medication intake detection system using distributed machine learning.
        J Med Syst. 2020; 44: 1-14
        • Nguyen V.
        • Kunz H.
        • Taylor P.
        • et al.
        Insights into pharmacotherapy management for Parkinson’s disease patients using wearables activity data.
        Stud Health Technol Inform. 2018; 247: 156-160
      5. Cheon A, Jung SY, Prather C, et al. A machine learning approach to detecting low medication state with wearable technologies. In 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC); Montreal, QC; July 20-24, 2020. 4252-4255.

        • Rossi L.A.
        • Melstrom L.G.
        • Fong Y.
        • Sun V.
        Predicting post-discharge cancer surgery complications via telemonitoring of patient-reported outcomes and patient-generated health data.
        J Surg Oncol. 2021; 123: 1345-1352
        • Kamdar M.R.
        • Wu M.J.
        PRISM: a data-driven platform for monitoring mental health.
        Pac Symp Biocomput. 2016; 21: 333-344
        • Kim H.
        • Lee S.
        • Lee S.
        • Hong S.
        • Kang H.
        • Kim N.
        Depression prediction by using ecological momentary assessment, actiwatch data, and machine learning: observational study on older adults living alone.
        JMIR Mhealth Uhealth. 2019; 7e14149
        • Chae S.H.
        • Kim Y.
        • Lee K.-S.
        • Park H.S.
        Development and clinical evaluation of a web-based upper limb home rehabilitation system using a smartwatch and machine learning model for chronic stroke survivors: prospective comparative study.
        JMIR Mhealth Uhealth. 2020; 8e17216
        • Bini S.A.
        • Shah R.F.
        • Bendich I.
        • Patterson J.T.
        • Hwang K.M.
        • Zaid M.B.
        Machine learning algorithms can use wearable sensor data to accurately predict six-week patient-reported outcome scores following joint replacement in a prospective trial.
        J Arthroplasty. 2019; 34: 2242-2247
        • Park S.
        • Lee S.W.
        • Han S.
        • Cha M.
        Clustering insomnia patterns by data from wearable devices: algorithm development and validation study.
        JMIR Mhealth Uhealth. 2019; 7e14473
        • Cos H.
        • Li D.
        • Williams G.
        • et al.
        Predicting outcomes in patients undergoing pancreatectomy using wearable technology and machine learning: prospective cohort study.
        J Med Internet Res. 2021; 23e23595
        • Procter D.S.
        • Page A.S.
        • Cooper A.R.
        • et al.
        An open-source tool to identify active travel from hip-worn accelerometer, GPS and GIS data.
        Int J Behav Nutr Phys Act. 2018; 15: 91
        • Stehlik J.
        • Schmalfuss C.
        • Bozkurt B.
        • et al.
        Continuous wearable monitoring analytics predict heart failure hospitalization: the LINK-HF multicenter study.
        Circ Heart Fail. 2020; 13e006513
        • Thralls K.J.
        • Godbole S.
        • Manini T.M.
        • Johnson E.
        • Natarajan L.
        • Kerr J.
        A comparison of accelerometry analysis methods for physical activity in older adult women and associations with health outcomes over time.
        J Sports Sci. 2019; 37: 2309-2317
      6. Umematsu T, Sano A, Picard RW. Daytime data and LSTM can forecast tomorrow’s stress, health, and happiness. In 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC); Berlin, Germany; July 23-27, 2019. 2186-2190.

        • Awais M.
        • Chiari L.
        • Ihlen E.A.F.
        • Helbostad J.L.
        • Palmerini L.
        Physical activity classification for elderly people in free-living conditions.
        IEEE J Biomed Health Inform. 2018; 23: 197-207
        • Kerr J.
        • Patterson R.E.
        • Ellis K.
        • et al.
        Objective assessment of physical activity: classifiers for public health.
        Med Sci Sports Exerc. 2016; 48: 951
        • Faedda G.L.
        • Ohashi K.
        • Hernandez M.
        • et al.
        Actigraph measures discriminate pediatric bipolar disorder from attention-deficit/hyperactivity disorder and typically developing controls.
        J Child Psychol Psychiatry. 2016; 57: 706-716
        • Cheffena M.
        Fall detection using smartphone audio features.
        IEEE J Biomed Health Inform. 2015; 20: 1073-1080
        • Rahman S.A.
        • Adjeroh D.A.
        Deep learning using convolutional LSTM estimates biological age from physical activity.
        Sci Rep. 2019; 911425
      7. Hu Y, Bishnoi A, Kaur R, et al. Exploration of machine learning to identify community dwelling older adults with balance dysfunction using short duration accelerometer data. In 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC); Montreal, QC; July 20-24, 2020. 812-815.

        • Rahman S.
        • Irfan M.
        • Raza M.
        • Moyeezullah Ghori K.
        • Yaqoob S.
        • Awais M.
        Performance analysis of boosting classifiers in recognizing activities of daily living.
        Int J Environ Res Public Health. 2020; 17: 1082
        • Liu K.C.
        • Chan C.T.
        Significant change spotting for periodic human motion segmentation of cleaning tasks using wearable sensors.
        Sensors. 2017; 17: 187
        • Yamakawa T.
        • Miyajima M.
        • Fujiwara K.
        • et al.
        Wearable epileptic seizure prediction system with machine-learning-based anomaly detection of heart rate variability.
        Sensors. 2020; 20: 3987
      8. Pluntke U, Gerke S, Sridhar A, et al. Evaluation and classification of physical and psychological stress in firefighters using heart rate variability. In 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC); Berlin, Germany; July 23-27, 2019. 2207-2212.

      9. Kong Y, Posada-Quintero HF, Chon KH. Pain detection using a smartphone in real time. In 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC); Montreal, QC; July 20-24, 2020. 4526-4529.

        • Pardoel S.
        • Shalin G.
        • Nantel J.
        • Lemaire E.D.
        • Kofman J.
        Early detection of freezing of gait during walking using inertial measurement unit and plantar pressure distribution data.
        Sensors. 2021; 21: 2246
        • Hu B.
        • Dixon P.
        • Jacobs J.
        • Dennerlein J.T.
        • Schiffman J.M.
        Machine learning algorithms based on signals from a single wearable inertial sensor can detect surface- and age-related differences in walking.
        J Biomech. 2018; 71: 37-42
        • Huang S.
        • Li J.
        • Zhang P.
        • Zhang W.
        Detection of mental fatigue state with wearable ECG devices.
        Int J Med Inform. 2018; 119: 39-46
      10. Rahman MJ, Nemati E, Rahman M, et al. Toward early severity assessment of obstructive lung disease using multi-modal wearable sensor data fusion during walking. In 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC); Montreal, QC; July 20-24, 2020. 5935-5938.

        • Cai W.Y.
        • Guo J.H.
        • Zhang M.Y.
        • Ruan Z.X.
        • Zheng X.C.
        • Lv S.S.
        GBDT-based fall detection with comprehensive data from posture sensor and human skeleton extraction.
        J Healthc Eng. 2020; 20208887340
        • Cheng S.T.
        • Chow P.K.
        • Song Y.Q.
        • et al.
        Mental and physical activities delay cognitive decline in older persons with dementia.
        Am J Geriatr Psychiatry. 2014; 22: 63-74
        • Ravaglia G.
        • Forti P.
        • Lucicesare A.
        • et al.
        Physical activity and dementia risk in the elderly: findings from a prospective Italian study.
        Neurology. 2008; 70: 1786-1794
        • El-Saifi N.
        • Moyle W.
        • Jones C.
        • Tuffaha H.
        Medication adherence in older patients with dementia: a systematic literature review.
        J Pharm Pract. 2018; 31: 322-334
        • Shi L.
        • Chen S.-J.
        • Ma M.-Y.
        • et al.
        Sleep disturbances increase the risk of dementia: a systematic review and meta-analysis.
        Sleep Med Rev. 2018; 40: 4-16
        • Eckerling A.
        • Ricon-Becker I.
        • Sorski L.
        • Sandbank E.
        • Ben-Eliyahu S.
        Stress and cancer: mechanisms, significance and future directions.
        Nat Rev Cancer. 2021; 21: 767-785
        • Dai S.
        • Mo Y.
        • Wang Y.
        • et al.
        Chronic stress promotes cancer development.
        Front Oncol. 2020; 10: 1492
        • McLachlan K.J.
        • Gale C.R.
        The effects of psychological distress and its interaction with socioeconomic position on risk of developing four chronic diseases.
        J Psychosom Res. 2018; 109: 79-85
        • Wu R.
        • Liaqat D.
        • de Lara E.
        • et al.
        Feasibility of using a smartwatch to intensively monitor patients with chronic obstructive pulmonary disease: prospective cohort study.
        JMIR Mhealth Uhealth. 2018; 6e10046
        • Viswanathan V.
        Current and future perspective in the management of diabetes.
        J Indian Med Assoc. 2002; 100: 181-183
        • Rand L.
        • Dunn M.
        • Slade I.
        • Upadhyaya S.
        • Sheehan M.
        Understanding and using patient experiences as evidence in healthcare priority setting.
        Cost Eff Resour Alloc. 2019; 17: 20
        • O’Hare A.M.
        • Rodriguez R.A.
        • Bowling C.B.
        Caring for patients with kidney disease: shifting the paradigm from evidence-based medicine to patient-centered care.
        Nephrol Dial Transplant. 2016; 31: 368-375
        • Sedrak M.S.
        • Freedman R.A.
        • Cohen H.J.
        • et al.
        Older adult participation in cancer clinical trials: a systematic review of barriers and interventions.
        CA Cancer J Clin. 2021; 71: 78-92
        • Suykens J.A.
        • Vandewalle J.
        Least squares support vector machine classifiers.
        Neural Process Lett. 1999; 9: 293-300
        • Breiman L.
        Random forests.
        Mach Learn. 2001; 45: 5-32
      11. Chen T, Guestrin C. Xgboost: a scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; San Francisco, CA; August 13-17, 2016. 785-794.

        • Lin C.-F.
        • Wang S.-D.
        Fuzzy support vector machines.
        IEEE Trans Neural Netw. 2002; 13: 464-471
        • Dallora A.L.
        • Eivazzadeh S.
        • Mendes E.
        • Berglund J.
        • Anderberg P.
        Machine learning and microsimulation techniques on the prognosis of dementia: a systematic literature review.
        PLoS One. 2017; 12e0179804
        • Shen L.
        • Chen H.
        • Yu Z.
        • et al.
        Evolving support vector machines using fruit fly optimization for medical data classification.
        Knowl Based Syst. 2016; 96: 61-75
        • Garg A.
        • Mago V.
        Role of machine learning in medical research: a survey.
        Comput Sci. 2021; 40100370
        • Kakarmath S.
        • Esteva A.
        • Arnaout R.
        • et al.
        Best practices for authors of healthcare-related artificial intelligence manuscripts.
        NPJ Digit Med. 2020; 3: 134
        • Mateen B.A.
        • Liley J.
        • Denniston A.K.
        • et al.
        Improving the quality of machine learning in health applications and clinical research.
        Nat Mach Intell. 2020; 2: 554-556
        • Ngiam K.Y.
        • Khor W.
        Big data and machine learning algorithms for health-care delivery.
        Lancet Oncol. 2019; 20: e262-e273
        • Fuller D.
        • Colwell E.
        • Low J.
        • et al.
        Reliability and validity of commercially available wearable devices for measuring steps, energy expenditure, and heart rate: systematic review.
        JMIR Mhealth Uhealth. 2020; 8e18694
        • Mahloko L.
        • Adebesin F.
        A systematic literature review of the factors that influence the accuracy of consumer wearable health device data.
        in: Responsible Design, Implementation and Use of Information and Communication Technology. Vol 12067. 2020: 96-107
        • Cilliers L.
        Wearable devices in healthcare: privacy and information security issues.
        Health Inf Manag J. 2020; 49: 150-156
      12. de Oliveira BGRB. Preferred reporting items for systematic reviews and meta-analyses extension for scoping reviews (PRISMA-ScR) checklist. PRISMA.