Digital Phenotyping of Physical Activity and Mortality in Cancer Survivors

Abstract

Physical activity is central to cancer survivorship care, yet the prognostic value of its multiple dimensions remains poorly characterized. We aimed to define multidimensional, wearable-derived digital phenotypes of physical activity; determine their independent associations with all-cause mortality; identify dose–response thresholds for survival benefit; and evaluate their utility in machine learning mortality prediction among cancer survivors. This observational cohort study analyzed 9379 National Health and Nutrition Examination Survey (2011–2014) participants with wrist accelerometry and mortality follow-up, including 864 cancer survivors. Three Monitor-Independent Movement Summary (MIMS) phenotypes were derived: Volume, Intensity, and Variability. In fully adjusted Cox models, vigorous versus light patterns were associated with lower mortality (hazard ratios 0.33, 0.22, and 0.29 for Volume, Intensity, and Variability, respectively). Dose–response thresholds for survival benefit were identified (Intensity > 24, Volume > 4945, and Variability > 2.4). Protective associations were stronger in survivors with low functional limitation. Machine learning models discriminated well (Random Survival Forest AUC = 0.799), with external validation confirming generalizability (AUC = 0.773). Multidimensional digital phenotypes, particularly for peak intensity and variability, are independent mortality predictors, supporting their integration into precision cancer survivorship care. Interpretation is limited by the absence of cancer staging and treatment data.

Keywords

accelerometry / cancer survivors / digital phenotyping / mortality prediction / physical activity / wearable sensors

References

[1] C. L. Rock, C. A. Thomson, K. R. Sullivan, et al., “American Cancer Society Nutrition and Physical Activity Guideline for Cancer Survivors,” CA: A Cancer Journal for Clinicians 72, no. 3 (2022): 230–262.

[2] C. Sun, K. Li, H. Xu, et al., “Association of Healthy Lifestyle Score With All-Cause Mortality and Life Expectancy: A City-Wide Prospective Cohort Study of Cancer Survivors,” BMC Medicine 19 (2021): 158.

[3] J. Emery, P. Butow, J. Lai-Kwon, L. Nekhlyudov, M. Rynderman, and M. Jefford, “Management of Common Clinical Problems Experienced by Survivors of Cancer,” Lancet 399, no. 10334 (2022): 1537–1550.

[4] M. B. Lustberg, N. M. Kuderer, A. Desai, C. Bergerot, and G. H. Lyman, “Mitigating Long-Term and Delayed Adverse Events Associated With Cancer Treatment: Implications for Survivorship,” Nature Reviews Clinical Oncology 20, no. 8 (2023): 527–542.

[5] X. Wei, Y. Min, Z. Xiang, Y. Zeng, J. Wang, and L. Liu, “Joint Association of Physical Activity and Dietary Quality With Survival Among US Cancer Survivors: A Population-Based Cohort Study,” International Journal of Surgery 110, no. 9 (2024): 5585–5594.

[6] L. Fan, J. Zhang, F. Wang, S. Liu, and T. Lin, “Exploring Outdoor Activity Limitation (OAL) Factors Among Older Adults Using Interpretable Machine Learning,” Aging Clinical and Experimental Research 35, no. 9 (2023): 1955–1966.

[7] E. A. Salerno, P. F. Saint-Maurice, F. Wan, et al., “Prospective Associations Between Accelerometry-Derived Physical Activity and Sedentary Behaviors and Mortality Among Cancer Survivors,” JNCI Cancer Spectrum 7, no. 2 (2023): pkad007.

[8] C. Cao, C. M. Friedenreich, and L. Yang, “Association of Daily Sitting Time and Leisure-Time Physical Activity With Survival Among US Cancer Survivors,” JAMA Oncology 8, no. 3 (2022): 395–403.

[9] L. Fan, J. Zhao, J. Wang, et al., “Accelerometer-Measured Multidimensional Physical Activity Patterns and Physical Functional Decline: A Prospective National Cohort Study of Aging,” Journals of Gerontology, Series A: Biological Sciences and Medical Sciences 80, no. 8 (2025): glaf158.

[10] L. Fan, S. Liu, J. Zhao, et al., “Physical Activity Levels May Impact on the Risk of Premature Mortality in People With Epilepsy,” Nature Communications 16, no. 1 (November 2025): 9837.

[11] K. K. P. Gabriel, J. R. Morrow, and A. L. T. Woolsey, “Framework for Physical Activity as a Complex and Multidimensional Behavior,” supplement, Journal of Physical Activity and Health 9, no. s1 (January 2012): S11–S18.

[12] B. A. Franklin, T. M. Eijsvogels, A. Pandey, et al., “Physical Activity, Cardiorespiratory Fitness, and Cardiovascular Health: A Clinical Practice Statement of the ASPC Part I,” American Journal of Preventive Cardiology 13, no. 12 (2022): 100424.

[13] P. Zheng, J. D. Pleuss, D. S. Turner, S. W. Ducharme, and E. J. Aguiar, “Dose–Response Association Between Physical Activity (Daily Mims, Peak 30-Minute MIMS) and Cognitive Function Among Older Adults: NHANES 2011–2014,” Journals of Gerontology: Series A: Biological Sciences and Medical Sciences 78, no. 2 (2023): 286–291.

[14] G. M. Harari and S. D. Gosling, “Understanding Behaviours in Context Using Mobile Sensing,” Nature Reviews Psychology 2, no. 12 (2023): 767–779.

[15] H. Xiao, G. Ghazinour, A. Tabaczynski, et al., “Identifying Latent Profiles of Quality of Life and Lifestyle Behaviors in Cancer Survivors,” Journal of Cancer Survivorship 21 (2025): 1–2.

[16] S. L. Bachman, E. Gomes, S. Aryal, et al., “Do Measures of Real-World Physical Behavior Provide Insights Into the Well-Being and Physical Function of Cancer Survivors? Cross-Sectional Analysis,” JMIR Cancer 10 (July 2024): e53180.

[17] X. Hou, S. Lian, W. Liu, M. Li, and Y. Ling, “The Association Between Physical Activity Levels and Quality of Life in Elderly Lung Cancer Patients Undergoing Chemotherapy in China: A Cross-Sectional Study,” Supportive Care in Cancer 32, no. 12 (2024): 845.

[18] S. Magno, M. M. Rossi, A. Filippone, et al., “Screening for Physical Activity Levels in Non-Metastatic Breast Cancer Patients Undergoing Surgery: An Observational Study,” Integrative Cancer Therapies 21 (2022): 15347354221140327.

[19] J. Noone, J. M. Mucinski, J. P. DeLany, L. M. Sparks, and B. H. Goodpaster, “Understanding the Variation in Exercise Responses to Guide Personalized Physical Activity Prescriptions,” Cell Metabolism 36, no. 4 (April 2024): 702–724.

[20] S. Khurshid, M. A. Al-Alusi, T. W. Churchill, J. S. Guseh, and P. T. Ellinor, “Accelerometer-Derived ‘Weekend Warrior’ Physical Activity and Incident Cardiovascular Disease,” Journal of the American Medical Association 330, no. 3 (July 2023): 247–252.

[21] T. Ferguson, T. Olds, R. Curtis, et al., “Effectiveness of Wearable Activity Trackers to Increase Physical Activity and Improve Health: A Systematic Review of Systematic Reviews and Meta-Analyses,” Lancet Digital Health 4, no. 8 (August 2022): e615–e626.

[22] G. J. Williams, A. Al-Baraikan, F. E. Rademakers, et al., “Wearable Technology and the Cardiovascular System: The Future of Patient Assessment,” Lancet Digital Health 5, no. 7 (July, 2023): e467–e476.

[23] W. Zhou, Y. E. Chan, C. S. Foo, et al., “High-Resolution Digital Phenotypes From Consumer Wearables and Their Applications in Machine Learning of Cardiometabolic Risk Markers: Cohort Study,” Journal of Medical Internet Research 24, no. 7 (2022): e34669.

[24] D. Q. Liao, H. M. Li, H. J. Chen, et al., “Association of Accelerometer-Derived Physical Activity Pattern With the Risks of All-Cause, Cardiovascular Disease, and Cancer Death,” Journal of the American Heart Association 14, no. 8 (2025): e039225.

[25] S. W. S. MacDonald, L. Nyberg, and L. Bäckman, “Intra-Individual Variability in Behavior: Links to Brain Structure, Neurotransmission and Neuronal Activity,” Trends in Neurosciences 29, no. 8 (2006): 474–480.

[26] I. Mlakar, S. Lin, I. Aleksandraviča, et al., “Patients-Centered Survivorship Care Plan After Cancer Treatments Based on Big Data and Artificial Intelligence Technologies (PERSIST): A Multicenter Study Protocol to Evaluate Efficacy of Digital Tools Supporting Cancer Survivors,” BMC Medical Informatics and Decision Making 21 (2021): 243.

[27] Y. Nohara, K. Matsumoto, H. Soejima, and N. Nakashima, “Explanation of Machine Learning Models Using Shapley Additive Explanation and Application for Real Data in Hospital,” Computer Methods and Programs in Biomedicine 214 (2022): 106584.

[28] B. M. Bell, R. Alam, N. Alshurafa, et al., “Automatic, Wearable-Based, In-Field Eating Detection Approaches for Public Health Research: A Scoping Review,” NPJ Digital Medicine 3, no. 1 (2020): 38.

[29] G. A. Moseley, L. M. Ross, K. A. Collins-Bennett, R. North, J. L. Johnson, and W. E. Kraus, “Cumulative Effects of Training at Different Weekly Energy Expenditures on Cardiorespiratory Fitness and Markers of Metabolic Syndrome in STRRIDE-Extension,” Journal of Applied Physiology 138 (2025): 1532–1542.

[30] R. S. Metcalfe, J. A. Babraj, S. G. Fawkner, and N. B. J. Vollaard, “Towards the Minimal Amount of Exercise for Improving Metabolic Health: Beneficial Effects of Reduced-Exertion High-Intensity Interval Training,” European Journal of Applied Physiology 112, no. 7 (2012): 2767–2775.

[31] J. Li, Y. Li, M. M. Atakan, et al., “The Molecular Adaptive Responses of Skeletal Muscle to High-Intensity Exercise/Training and Hypoxia,” Antioxidants 9, no. 8 (2020): 656.

[32] J. C. Jarvis, “The Relationship Between Activity Pattern and Muscle Adaptation in Skeletal Muscle,” Artificial Organs 39, no. 10 (2015): 863–867.

[33] K. Blond, C. F. Brinkløv, M. Ried-Larsen, A. Crippa, and A. Grøntved, “Association of High Amounts of Physical Activity With Mortality Risk: A Systematic Review and Meta-Analysis,” British Journal of Sports Medicine 54, no. 20 (2020): 1195–1201.

[34] C. Andrade, “Physical Exercise and Health, 2: Benefits Associated With Different Levels and Patterns of Activity,” Journal of Clinical Psychiatry 84, no. 5 (2023): 49358.

[35] J. Burtscher, M. Kopp, J. Klimont, et al., “Age- and Sex-Dependent Associations Between Self-Reported Physical Activity Levels and Self-Reported Cardiovascular Risk Factors,” BMC Public Health 24, no. 1 (2024): 2843.

[36] R. W. Motl, W. Zhu, Y. Park, E. McAuley, J. A. Scott, and E. M. Snook, “Reliability of Scores From Physical Activity Monitors in Adults With Multiple Sclerosis,” Adapted Physical Activity Quarterly 24, no. 3 (2007): 245–253.

[37] R. E. Klaren, E. A. Hubbard, W. Zhu, and R. W. Motl, “Reliability of Accelerometer Scores for Measuring Sedentary and Physical Activity Behaviors in Persons With Multiple Sclerosis,” Adapted Physical Activity Quarterly 33, no. 2 (2016): 195–204.

[38] C. L. Johnson, S. M. Dohrmann, V. L. Burt, et al., National Health and Nutrition Examination Survey. US Department of Health and Human Services (CDC, 2014). Sample Design, 2011, 2014.

[39] L. McRoy, J. Epané, Z. Ramamonjiarivelo, et al., “Examining the Relationship Between Self-Reported Lifetime Cancer Diagnosis and Nativity: Findings From NHANES 2011–2018,” Cancer Causes & Control 33 (2022): 321–329.

[40] X. Li, Y. Zhang, Y. He, et al., “J-Shaped Association Between Serum Albumin Levels and Long-Term Mortality of Cardiovascular Disease: Experience in NHANES (2011–2014),” Frontiers in Cardiovascular Medicine 9 (2022): 1073120.

[41] B. R. Belcher, D. L. Wolff-Hughes, E. E. Dooley, et al., “US Population-Referenced Percentiles for Wrist-Worn Accelerometer-Derived Activity,” Medicine & Science in Sports & Exercise 53, no. 11 (2021): 2455–2464.

[42] L. Fan, J. Zhao, Y. Hu, et al., “Predicting Physical Functioning Status in Older Adults: Insights From Wrist Accelerometer Sensors and Derived Digital Biomarkers of Physical Activity,” Journal of the American Medical Informatics Association 31, no. 11 (2024): 2571–2582.

[43] L. J. Fan, F. Y. Wang, J. H. Zhao, et al., “From Physical Activity Patterns to Cognitive Status: Development and Validation of Novel Digital Biomarkers for Cognitive Assessment in Older Adults,” International Journal of Behavioral Nutrition and Physical Activity 22, no. 1 (2025): 11.

[44] Y. Jia, J. Ca, F. Yang, X. Dong, L. Zhou, and H. Long, “Association Between Family Income to Poverty Ratio and Nocturia in Adults Aged 20 Years and Older: A Study From NHANES 2005–2010,” PLoS One 19, no. 5 (2024): e0303927.

[45] L. Fan, J. Zhang, J. Zhao, F. Wang, T. Luo, and T. Lin, “PFIMPA: A Multimodal Approach to Predict Physical Function Impairment in Older Adults Using Physical Activity From Wrist-Worn Accelerometer,” IEEE Transactions on Instrumentation and Measurement 73 (2024): 1–13.

[46] L. Fan, J. Zhao, X. Wang, et al., “Site-Specific Pain Dynamics: Associations Between Accelerometer-Measured Physical Activity Patterns and Pain in Older Adults,” Journal of Headache and Pain 26, no. 1 (2025): 287.

Rights & permissions

2026 The Author(s). MedComm – Future Medicine published by John Wiley & Sons Australia, Ltd on behalf of Sichuan International Medical Exchange & Promotion Association (SCIMEA).