Applying machine learning to predict future adherence to physical activity programs
Open accessAbstract
BACKGROUND: Identifying individuals who are unlikely to adhere to a physical exercise regime has potential to improve physical activity interventions. The aim of this paper is to develop and test adherence prediction models using objectively measured physical activity data in the Mobile Phone-Based Physical Activity Education program (mPED) trial. To the best of our knowledge, this is the first to apply Machine Learning methods to predict exercise relapse using accelerometer-recorded physical activity data. METHODS: We use logistic regression and support vector machine methods to design two versions of a Discontinuation Prediction Score (DiPS), which uses objectively measured past data (e.g., steps and goal achievement) to provide a numerical quantity indicating the likelihood of exercise relapse in the upcoming week. The respective prediction accuracy of these two versions of DiPS are compared, and then numerical simulation is performed to explore the potential of using DiPS to selectively allocate financial incentives to participants to encourage them to increase physical activity. RESULTS: we had access to a physical activity trial data that were continuously collected every 60 sec every day for 9 months in 210 participants. By using the first 15 weeks of data as training and test on weeks 16-30, we show that both versions of DiPS have a test AUC of 0.9 with high sensitivity and specificity in predicting the probability of exercise adherence. Simulation results assuming different intervention regimes suggest the potential benefit of using DiPS as a score to allocate resources in physical activity intervention programs in reducing costs over other allocation schemes. CONCLUSIONS: DiPS is capable of making accurate and robust predictions for future weeks. The most predictive features are steps and physical activity intensity. Furthermore, the use of DiPS scores can be a promising approach to determine when or if to provide just-in-time messages and step goal adjustments to improve compliance. Further studies on the use of DiPS in the design of physical activity promotion programs are warranted. TRIAL REGISTRATION: ClinicalTrials.gov NCT01280812 Registered on January 21, 2011.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Our work has shown that by using steps and physical activity intensity records, models can predict an individual's probability of disengagement from the intervention.
“Our work has shown that by using steps and physical activity intensity records, models can predict an individual’s probability of disengagement from the intervention [88].”
The Discontinuation Prediction Score had an AUC of 0.9 with high accuracy (>80%) and specificity (>80%).
“The score had an AUC of 0.9 with high accuracy (>80%) and specificity (>80%).”
From Smart wearable devices in cardiovascular care: Where we are and how to move forward (2021) · cites this paper as [105]
A simulation allocating financial incentives based on predicted exercise adherence resulted in theoretically greater adherence compared with random incentivization.
“A simulation was then performed in which financial incentives were allocated based on an individual’s predicted exercise adherence, resulting in a theoretically greater adherence compared with a random incentivization scheme.”
From Smart wearable devices in cardiovascular care: Where we are and how to move forward (2021) · cites this paper as [105]
Zhou et al. produced a tool to pre-empt non-adherence using a Discontinuation Prediction Score.
“Zhou et al. produced a tool to pre-empt the problem of non-adherence with use of a Discontinuation Prediction Score105.”
From Smart wearable devices in cardiovascular care: Where we are and how to move forward (2021) · cites this paper as [105]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Cortes, C., & Vapnik, V. N. (1995) · Machine Learning · doi:10.1023/a:1022627411411 · Cited by 34,565 · see citing works
Large-scale physical activity data reveal worldwide activity inequality
Althoff, T., Sosič, R., Hicks, J. L., King, A. C., Delp, S. L., & Leskovec, J. (2017) · Nature · doi:10.1038/nature23018 · Cited by 1,000 · see citing works
Health behavior models in the age of mobile interventions: are our theories up to the task?
Riley, W. T., Rivera, D. E., Atienza, A. A., Nilsen, W., Allison, S. M., & Mermelstein, R. (2011) · Translational Behavioral Medicine · doi:10.1007/s13142-011-0021-7 · Cited by 978 · see citing works
Booth, M. L., Owen, N., Bauman, A., Clavisi, O., & Leslie, E. (2000) · Preventive Medicine · doi:10.1006/pmed.2000.0661 · Cited by 774 · see citing works
Accuracy of Smartphone Applications and Wearable Devices for Tracking Physical Activity Data
Case, M. A., Burwick, H. A., Volpp, K. G., & Patel, M. S. (2015) · JAMA · doi:10.1001/jama.2014.17841 · Cited by 694 · see citing works
A Text Message–Based Intervention for Weight Loss: Randomized Controlled Trial
Patrick, K., Raab, F., Adams, M. A., Dillon, L., Zabinski, M., Rock, C. L., Griswold, W. G., & Norman, G. J. (2009) · Journal of Medical Internet Research · doi:10.2196/jmir.1100 · Cited by 671 · see citing works
Physical activity behavior change: Issues in adoption and maintenance.
Marcus, B. H., Forsyth, L. H., Stone, E. J., Dubbert, P. M., McKenzie, T. L., Dunn, A. L., & Blair, S. N. (2000) · Health Psychology · doi:10.1037/0278-6133.19.suppl1.32 · Cited by 570 · see citing works
Goodpaster, B. H., DeLany, J. P., Otto, A. D., Kuller, L., Vockley, J., South-Paul, J. E., Thomas, S. B., Brown, J., McTigue, K., Hames, K. C., et al. (2010) · JAMA · doi:10.1001/jama.2010.1505 · Cited by 558 · see citing works
Hurling, R., Catt, M., De Boni, M., Fairley, B. W., Hurst, T., Murray, P., Richardson, A., & Sodhi, J. S. (2007) · Journal of Medical Internet Research · doi:10.2196/jmir.9.2.e7 · Cited by 536 · see citing works
Ohkawara, K., Oshima, Y., Hikihara, Y., Ishikawa‐Takata, K., Tabata, I., & Tanaka, S. (2011) · British Journal Of Nutrition · doi:10.1017/s0007114510005441 · Cited by 463 · see citing works
Classifying household and locomotive activities using a triaxial accelerometer
Oshima, Y., Kawaguchi, K., Tanaka, S., Ohkawara, K., Hikihara, Y., Ishikawa‐Takata, K., & Tabata, I. (2010) · Gait & Posture · doi:10.1016/j.gaitpost.2010.01.005 · Cited by 372 · see citing works
Exploring Goal-setting, Rewards, Self-monitoring, and Sharing to Motivate Physical Activity
Munson, S. A., & Consolvo, S. (2012) · International Conference on Pervasive Computing Technologies for Healthcare · doi:10.4108/icst.pervasivehealth.2012.248691 · Cited by 360 · see citing works
Burke, L. E., Conroy, M. B., Sereika, S. M., Elci, O. U., Styn, M. A., Acharya, S. D., Sevick, M. A., Ewing, L. J., & Glanz, K. (2011) · Obesity · doi:10.1038/oby.2010.208 · Cited by 329 · see citing works
Jefferis, B. J. M. H., Sartini, C., Lee, I.-M. M., Choi, M., Amuzu, A., Gutierrez, C., Casas, J. P., Ash, S., LENNON, L. T., Wannamethee, S. G., et al. (2014) · BMC Public Health · doi:10.1186/1471-2458-14-382 · Cited by 271 · see citing works
MobileMums: A Randomized Controlled Trial of an SMS-Based Physical Activity Intervention
Fjeldsoe, B. S., Miller, Y. D., & Marshall, A. L. (2010) · Annals of Behavioral Medicine · doi:10.1007/s12160-010-9170-z · Cited by 244 · see citing works
Harris, T. J., Owen, C. G., Victor, C. R., Adams, R., & Cook, D. G. (2008) · British Journal of Sports Medicine · doi:10.1136/bjsm.2008.048033 · Cited by 236 · see citing works
Paterson, R., MacLeod, D., Thetford, D., Beattie, A., Graham, C. A., Lam, S., & Bell, D. (2006) · Clinical Medicine · doi:10.7861/clinmedicine.6-3-281 · Cited by 212 · see citing works
Cadmus‐Bertram, L., Marcus, B. H., Patterson, R. E., Parker, B. A., & Morey, B. L. (2015) · JMIR mhealth and uhealth · doi:10.2196/mhealth.4229 · Cited by 207 · see citing works
A Novel Diabetes Prevention Intervention Using a Mobile App
Fukuoka, Y., Gay, C. L., Joiner, K. L., & Vittinghoff, E. (2015) · American Journal of Preventive Medicine · doi:10.1016/j.amepre.2015.01.003 · Cited by 204 · see citing works
Self-citationSchuna, J. M., Johnson, W. D., & Tudor-Locke, C. E. (2013) · International Journal of Behavioral Nutrition and Physical Activity · doi:10.1186/1479-5868-10-126 · Cited by 181 · see citing works
Monitoring vital signs using early warning scoring systems: a review of the literature
Kyriacos, U., Jelsma, J. M., & Jordan, S. E. (2011) · Journal of Nursing Management · doi:10.1111/j.1365-2834.2011.01246.x · Cited by 177 · see citing works
Diabetes regimen behaviors. Predicting adherence.
McCaul, K. D., Glasgow, R. E., & Schafer, L. C. (1987) · PubMed · Cited by 176 · see citing works
An Adaptive Physical Activity Intervention for Overweight Adults: A Randomized Controlled Trial
Adams, M. A., Sallis, J. F., Norman, G. J., Hovell, M. F., Hekler, E. B., & Perata, E. (2013) · PLoS ONE · doi:10.1371/journal.pone.0082901 · Cited by 167 · see citing works
Perspectives on Adherence and Simplicity for HIV-Infected Patients on Antiretroviral Therapy
Stone, V. E., Jordan, J. C., Tolson, J. M., et al. (2004) · JAIDS Journal of Acquired Immune Deficiency Syndromes · doi:10.1097/00126334-200407010-00007 · Cited by 164 · see citing works
Joo, N.-S., & Kim, B.-T. (2007) · Journal of Telemedicine and Telecare · doi:10.1258/135763307783064331 · Cited by 161 · see citing works
Promoting physical activity through hand-held computer technology
King, A. C., Ahn, D. K., Oliveira, B. M., Atienza, A. A., Castro, C. M., & Gardner, C. D. (2008) · American Journal of Preventive Medicine · doi:10.1016/j.amepre.2007.09.025 · Cited by 160 · see citing works
A national early warning score for acutely ill patients
McGinley, A., & Pearse, R. M. (2012) · BMJ · doi:10.1136/bmj.e5310 · Cited by 154 · see citing works
Hekler, E. B., Buman, M. P., Grieco, L., Rosenberger, M., Winter, S. J., Haskell, W., & King, A. C. (2015) · JMIR mhealth and uhealth · doi:10.2196/mhealth.3505 · Cited by 137 · see citing works
Prospective evaluation of the effects of stress on exercise adherence in community-residing women.
Stetson, B. A., Rahn, J. M., Dubbert, P. M., Wilner, B. I., & Mercury, M. G. (1997) · Health Psychology · doi:10.1037//0278-6133.16.6.515 · Cited by 127 · see citing works
Bauer, S., de Niet, J. E., Timman, R., & Kordy, H. (2010) · Patient Education and Counseling · doi:10.1016/j.pec.2010.03.014 · Cited by 122 · see citing works
Zhou, M., Fukuoka, Y., Mintz, Y., Goldberg, K., Kaminsky, P., Flowers, E., & Aswani, A. (2018) · JMIR mHealth and uHealth · doi:10.2196/mhealth.9117 · Cited by 111 · see citing works
Self-citationAdams, M. A., Hurley, J. C., Todd, M., Bhuiyan, N., Jarrett, C. L., Tucker, W. J., Hollingshead, K. E., & Angadi, S. S. (2017) · BMC Public Health · doi:10.1186/s12889-017-4197-8 · Cited by 110 · see citing works
Prospective evaluation of the effects of stress on exercise adherence in community-residing women.
Stetson, B. A., Rahn, J. M., Dubbert, P. M., et al. (1997) · Health Psychology · doi:10.1037/0278-6133.16.6.515 · Cited by 102 · see citing works
Evaluation of a PDA-based dietary assessment and intervention program: a randomized controlled trial
Beasley, J. M., Riley, W. T., Davis, A., & Singh, J. (2008) · Journal of the American College of Nutrition · doi:10.1080/07315724.2008.10719701 · Cited by 99 · see citing works
Fukuoka, Y., Vittinghoff, E., Jong, S., & Haskell, W. L. (2010) · Preventive Medicine · doi:10.1016/j.ypmed.2010.06.006 · Cited by 89 · see citing works
Self-citationPredicting Adherence to Tamoxifen for Breast Cancer Adjuvant Therapy and Prevention
Lin, J., Zhang, S. M., & Manson, J. E. (2011) · Cancer Prevention Research · doi:10.1158/1940-6207.capr-11-0380 · Cited by 84 · see citing works
Assessment of coping with high-risk situations for exercise relapse among healthy women.
Simkin, L. R., & Gross, A. M. (1994) · Health Psychology · doi:10.1037/0278-6133.13.3.274 · Cited by 71 · see citing works
Rejeski, W. J., Axtell, R. S., Fielding, Katula, J. A., King, A. C., Manini, T. M., Marsh, A. P., Pahor, M., Rego, A., Tudor-Locke, C. E., et al. (2013) · Clinical Interventions in Aging · doi:10.2147/cia.s49737 · Cited by 71 · see citing works
Finding the Adaptive Sweet Spot
Konrad, A., Bellotti, V. M. E., Crenshaw, N. K., Tucker, S., Nelson, L., Du, H., Pirolli, P. L. T., & Whittaker, S. (2015) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/2702123.2702512 · Cited by 69 · see citing works
Fukuoka, Y., Haskell, W. L., Lin, F., & Vittinghoff, E. (2019) · JAMA Network Open · doi:10.1001/jamanetworkopen.2019.4281 · Cited by 68 · see citing works
Self-citationPersonalizing Mobile Fitness Apps using Reinforcement Learning.
Zhou, M., Mintz, Y. D., Fukuoka, Y., Goldberg, K. Y., Flowers, E., Kaminsky, P., Castillejo, A., & Aswani, A. J. (2018) · PubMed · Cited by 52 · see citing works
Self-citationMason, J. E., England, D., Denton, B. T., Smith, S. A., Kurt, M., & Shah, N. D. (2011) · Medical Decision Making · doi:10.1177/0272989x11404076 · Cited by 42 · see citing works
Behavioral Modeling in Weight Loss Interventions
Aswani, A. J., Kaminsky, P., Mintz, Y. D., Flowers, E., & Fukuoka, Y. (2016) · European Journal of Operational Research · doi:10.1016/j.ejor.2018.07.011 · Cited by 37 · see citing works
Self-citationFukuoka, Y., Zhou, M., Vittinghoff, E., et al. (2018) · JMIR Public Health and Surveillance · doi:10.2196/publichealth.9138 · Cited by 35 · see citing works
Self-citationiPhone as a physical activity measurement platform
Fujiki, Y. (2010) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/1753846.1754146 · Cited by 34 · see citing works
McCaul, K. D., Glasgow, R. E., & Schafer, L. C. (1987) · Medical Care · doi:10.1097/00005650-198709001-00005 · Cited by 34 · see citing works
A weight loss intervention using a commercial mobile application in Latino Americans—Adelgaza Trial
Fukuoka, Y., Vittinghoff, E., & Hooper, J. (2018) · Translational Behavioral Medicine · doi:10.1093/tbm/ibx039 · Cited by 29 · see citing works
Self-citationRole of Brain Structure in Predicting Adherence to a Physical Activity Regimen
Gujral, S., McAuley, E., Oberlin, L. E., Kramer, A. F., & Erickson, K. I. (2017) · Psychosomatic Medicine · doi:10.1097/psy.0000000000000526 · Cited by 25 · see citing works
MEWS: predicts hospital admission and mortality in emergency department patients
Vorwerk, C. (2009) · Emergency Medicine Journal · doi:10.1136/emj.2008.069062 · Cited by 4 · see citing works
Flagged first, then by citations
Research works printed but not linked: 1
- [9]Marlatt GA Gordon JR Relapse prevention: maintenance strategies in addictive behavior change 1985 New York Guilford Press
Cited by
Sorted by citations
Smart wearable devices in cardiovascular care: Where we are and how to move forward
Bayoumy, K., Gaber, M., Elshafeey, A., Mhaimeed, O., Dineen, E. H., Marvel, F. A., Martin, S. S., Muse, E. D., Turakhia, M. P., Tarakji, K. G., et al. (2021) · Nature Reviews Cardiology · doi:10.1038/s41569-021-00522-7 · Cited by 829 · see citing works
Zhang, J., Oh, Y. J., Lange, P., Yu, Z., & Fukuoka, Y. (2020) · Journal of Medical Internet Research · doi:10.2196/22845 · Cited by 363 · see citing works
Self-citationMuse, E. D., & Topol, E. J. (2024) · Cell Metabolism · doi:10.1016/j.cmet.2024.02.002 · Cited by 50 · see citing works
- Authors
- Zhou, M., Fukuoka, Y., Goldberg, K., Vittinghoff, E., & Aswani, A.
- Affiliations
- University of California, Berkeley (US)
- University of California, San Francisco (US)
- Corresponding author
- Zhou, Mo
- Venue
- BMC Medical Informatics and Decision Making
- Published
- 2019-08-22
- Volume
- 19
- Issue
- 1
- Pages
- 169-169
- ISSN
- 1472-6947 (ISSN-L)
- PMC
- PMC6704548
- OpenAlex
- W2969286020
- Cited by
- 45
- References
- 49
- Citations by year
- 2026: 4 · 2025: 5 · 2024: 8 · 2023: 7 · 2022: 6 · 2021: 12 · 2020: 3
- FWCI
- 3.59
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- BMC Medical Informatics and Decision Making (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- eScholarship (California Digital Library) (submittedVersion)
- eScholarship (California Digital Library) (submittedVersion, cc-by)
- Funders
- UC Center for Information Technology Research in the Interest of Society
- Philippine - California Advanced Research Institutes (IIID-2015-07)
- National Heart, Lung, and Blood Institute (R01HL104147)
- National Institute of Nursing Research (K24NR015812)
- Topics
- Health Sciences › Medicine › Physiology › Physical Activity and Health
- Health Sciences › Health Professions › General Health Professions › Mobile Health and mHealth Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Keywords
- physical activity adherence, accelerometer-measured activity, financial incentives, step count, physical activity intensity, support vector machine, logistic regression
- MeSH terms
- Machine Learning, Adult, Exercise Therapy, Female, Humans, Male, Middle Aged, Motivation, Patient Compliance, Exercise, Cell Phone
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
