Using Machine Learning to Derive Just-In-Time and Personalized Predictors of Stress: Observational Study Bridging the Gap Between Nomothetic and Ideographic Approaches.
Open accessPublished version of a preprint
Abstract
BACKGROUND: Investigations into person-specific predictors of stress have typically taken either a population-level nomothetic approach or an individualized ideographic approach. Nomothetic approaches can quickly identify predictors but can be hindered by the heterogeneity of these predictors across individuals and time. Ideographic approaches may result in more predictive models at the individual level but require a longer period of data collection to identify robust predictors. OBJECTIVE: Our objectives were to compare predictors of stress identified through nomothetic and ideographic models and to assess whether sequentially combining nomothetic and ideographic models could yield more accurate and actionable predictions of stress than relying on either model. At the same time, we sought to maintain the interpretability necessary to retrieve individual predictors of stress despite using nomothetic models. METHODS: Data collected in a 1-year observational study of 79 participants performing low levels of exercise were used. Physical activity was continuously and objectively monitored by actigraphy. Perceived stress was recorded by participants via daily ecological momentary assessments on a mobile app. Environmental variables including daylight time, temperature, and precipitation were retrieved from the public archives. Using these environmental, actigraphy, and mobile assessment data, we built machine learning models to predict individual stress ratings using linear, decision tree, and neural network techniques employing nomothetic and ideographic approaches. The accuracy of the approaches for predicting individual stress ratings was compared based on classification errors. RESULTS: Across the group of patients, an individual's recent history of stress ratings was most heavily weighted in predicting a future stress rating in the nomothetic recurrent neural network model, whereas environmental factors such as temperature and daylight, as well as duration and frequency of bouts of exercise, were more heavily weighted in the ideographic models. The nomothetic recurrent neural network model was the highest performing nomothetic model and yielded 72% accuracy for an 80%/20% train/test split. Using the same 80/20 split, the ideographic models yielded 75% accuracy. However, restricting ideographic models to participants with more than 50 valid days in the training set, with the same 80/20 split, yielded 85% accuracy. CONCLUSIONS: We conclude that for some applications, nomothetic models may be useful for yielding higher initial performance while still surfacing personalized predictors of stress, before switching to ideographic models upon sufficient data collection.
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?
The most common use of artificial intelligence in the mental health apps was prediction (of mood, stress, and risk) (8/17 studies).
“The most common uses of artificial intelligence in the mental health apps were prediction (of mood, stress, and risk) (8/17 studies) [31–37,41]”
From Artificial intelligence and machine learning in mobile apps for mental health: A scoping review (2022) · cites this paper as [33]
There were a large variety of study types among the 17 studies, including pilot randomised controlled trials, observational studies, model evaluations, and a qualitative study.
“There were a large variety of study types among the 17 studies, including pilot randomised controlled trials (RCTs) [28–30], observational studies [31–35], model evaluations [36,37], and a qualitative study [38].”
From Artificial intelligence and machine learning in mobile apps for mental health: A scoping review (2022) · cites this paper as [33]
12 of the 17 included studies had sample sizes smaller than 100.
“12 of the 17 included studies had sample sizes smaller than 100 [28–31,33–35,37–39,41,42].”
From Artificial intelligence and machine learning in mobile apps for mental health: A scoping review (2022) · cites this paper as [33]
3 of the 17 studies focused on predicting or helping manage stress.
“predicting or helping manage stress [28,32,33]”
From Artificial intelligence and machine learning in mobile apps for mental health: A scoping review (2022) · cites this paper as [33]
Many of the studies successfully modelled data collected by the app or associated inputs to identify behaviours or responses associated with mental health conditions, provide natural language support, develop risk profiles, and deploy context-sensitive notifications or interventions.
“Many of the studies successfully modelled data collected by the app or associated inputs to identify behaviours or responses associated with mental health conditions [44], provide natural language support [29,30,38,40,42,43], develop risk profiles [31–37,41], and deploy context-sensitive notifications [28] or interventions [44].”
From Artificial intelligence and machine learning in mobile apps for mental health: A scoping review (2022) · cites this paper as [33]
Of the 12 studies that included an intervention period, only 3 (25%) had intervention periods longer than 1 year.
“of the 12 studies that included an intervention period, only 3 (25%) had intervention periods longer than 1 year [33–35].”
From Artificial intelligence and machine learning in mobile apps for mental health: A scoping review (2022) · cites this paper as [33]
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
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016 · see citing works
An introduction to ROC analysis
Fawcett, T. (2006) · Pattern Recognition Letters · doi:10.1016/j.patrec.2005.10.010 · Cited by 21,879 · see citing works
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555 · see citing works
On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.-R., & Samek, W. (2015) · PLOS ONE · doi:10.1371/journal.pone.0130140 · Cited by 4,524 · see citing works
Steyerberg, E. W. (2009) · Statistics for Biology and Health · doi:10.1007/978-0-387-77244-8 · Cited by 1,491 · see citing works
Wang, R., Chen, F., Chen, Z., Li, T., Harari, G., Tignor, S., Zhou, X., Ben-Zeev, D., & Campbell, A. T. (2014) · Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing · doi:10.1145/2632048.2632054 · Cited by 1,116 · see citing works
Accelerometer Use in Physical Activity: Best Practices and Research Recommendations
WARD, D. S., EVENSON, K. R., VAUGHN, A., RODGERS, A. B., & TROIANO, R. P. (2005) · Medicine & Science in Sports & Exercise · doi:10.1249/01.mss.0000185292.71933.91 · Cited by 779 · see citing works
Burg, M. M., Schwartz, J. E., Kronish, I. M., Diaz, K. M., Alcántara, C., Duer-Hefele, J., & Davidson, K. W. (2017) · Annals of Behavioral Medicine · doi:10.1007/s12160-017-9902-4 · Cited by 91 · see citing works
Self-citationSharmin, M., Raij, A. B., Epstien, D., Nahum-Shani, I. B., Beck, J. G., Vhaduri, S., Preston, K. L., & Kumar, S. (2015) · ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) · doi:10.1145/2750858.2807537 · Cited by 78 · see citing works
Using Behavioral Analytics to Increase Exercise: A Randomized N-of-1 Study
Yoon, S., Schwartz, J. E., Burg, M. M., Kronish, I. M., Alcántara, C., Julian, J., Parsons, F., Davidson, K. W., & Diaz, K. M. (2018) · American Journal of Preventive Medicine · doi:10.1016/j.amepre.2017.12.011 · Cited by 67 · see citing works
Self-citationSunshine on my shoulders: Weather, pollution, and emotional distress
Beecher, M. E., Eggett, D. L., Erekson, D. M., Rees, L. B., Bingham, J. L., Klundt, J. S., Bailey, R. J., Ripplinger, C., Kirchhoefer, J., Gibson, R., et al. (2016) · Journal of Affective Disorders · doi:10.1016/j.jad.2016.07.021 · Cited by 53 · see citing works
Tuarob, S., Tucker, C. S., Kumara, S. R. T., Giles, C. L., Pincus, A. L., Conroy, D. E., & Ram, N. (2017) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2017.02.010 · Cited by 42 · see citing works
Are Nomothetic or Ideographic Approaches Superior in Predicting Daily Exercise Behaviors?
Cheung, Y. K., Hsueh, P.-Y. S., Qian, M., Yoon, S., Meli, L., Diaz, K. M., Schwartz, J. E., Kronish, I. M., & Davidson, K. W. (2017) · Methods of Information in Medicine · doi:10.3414/me16-02-0051 · Cited by 34 · see citing works
Self-citationFrom Markers to Interventions: The Case of Just-in-Time Stress Intervention
Sarker, H., Hovsepian, K., Chatterjee, S., Nahum-Shani, I. B., Murphy, S. A., Spring, B. J., Ertin, E., Al’Absi, M., Nakajima, M., & Kumar, S. (2017) · Springer eBooks · doi:10.1007/978-3-319-51394-2_21 · Cited by 26 · see citing works
Flagged first, then by citations
Research works printed but not linked: 4
- [5]Plarre K Raij A Hossain S Ali A Nakajima M Al-absi M Ertin E Kamarck T Kumar S Scott M Siewiorek D Smailagic A Wittmers L Continuous inference of psychological stress from sensory measurements collected in the natural environment 2011 Proceedings of the 10th ACM/IEEE International Conference on Information Processing in Sensor Networks April 12-14, 2011 Chicago, IL
- [12]Shrikumar A Greenside P Kundaje A Learning Important Features Through Propagating Activation Differences 2017 Proceedings of the 34th International Conference on Machine Learning August 6-11, 2017 Sydney, Australia 3145 3153
- [13]Lundberg S Lee S A unified approach to interpreting model predictions 2017 Neural Information Processing Systems Dec 4-9, 2017 Long Beach, CA
- [18]Sundararajan M Taly A Yan Q Axiomatic Attribution for Deep Networks ICML 2017 ICML June 10-15, 2017 Long Beach, CA
Cited by
Sorted by citations
Why we need a small data paradigm
Hekler, E. B., Klasnja, P., Chevance, G., Golaszewski, N. M., Lewis, D. M., & Sim, I. (2019) · BMC Medicine · doi:10.1186/s12916-019-1366-x · Cited by 290 · see citing works
Innovative methods for observing and changing complex health behaviors: four propositions
Chevance, G., Perski, O., & Hekler, E. B. (2020) · Translational Behavioral Medicine · doi:10.1093/tbm/ibaa026 · Cited by 95 · see citing works
Efficacy of a Smartphone App Intervention for Reducing Caregiver Stress: Randomized Controlled Trial
Fuller‐Tyszkiewicz, M., Richardson, B., Little, K., Teague, S. J., Hartley-Clark, L., Capic, T., Khor, S., Cummins, R. A., Olsson, C. A., & Hutchinson, D. M. (2020) · JMIR Mental Health · doi:10.2196/17541 · Cited by 85 · see citing works
Naegelin, M., Weibel, R. P., Kerr, J. I., Schinazi, V. R., Marca, R. L., von Wangenheim, F., Hölscher, C., & Ferrario, A. (2023) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2023.104299 · Cited by 83 · see citing works
Artificial intelligence and machine learning in mobile apps for mental health: A scoping review
Milne-Ives, M., Selby, E., Inkster, B., Lam, C., & Meinert, E. (2022) · PLOS Digital Health · doi:10.1371/journal.pdig.0000079 · Cited by 68 · see citing works
Prediction of stress and drug craving ninety minutes in the future with passively collected GPS data
Epstein, D., Tyburski, M., Kowalczyk, W., Burgess-Hull, A., Phillips, K. A., Curtis, B. L., & Preston, K. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-0234-6 · Cited by 54 · see citing works
Single-subject research in psychiatry: facts and fictions
Zuidersma, M., Riese, H., Snippe, E., Booij, S. H., Wichers, M., & Bos, E. H. (2020) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2020.539777 · Cited by 54 · see citing works
Incorporating spatial autocorrelation into house sale price prediction using random forest model
Hu, L., Chun, Y., & Griffith, D. A. (2022) · Transactions in GIS · doi:10.1111/tgis.12931 · Cited by 34 · see citing works
Lamichhane, B., Zhou, J., & Sano, A. (2023) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2023.3265684 · Cited by 32 · see citing works
Ng, A., Wei, B., Jain, J., Ward, E. A., Tandon, S. D., Moskowitz, J. T., Krogh‐Jespersen, S., Wakschlag, L. S., & Alshurafa, N. I. (2022) · JMIR mhealth and uhealth · doi:10.2196/33850 · Cited by 27 · see citing works
Wu, T. E., Sherman, G. T., Giorgi, S., Thanneeru, P., Ungar, L., Kamath, P. S., Simonetto, D. A., Curtis, B. L., & Shah, V. H. (2023) · Hepatology Communications · doi:10.1097/hc9.0000000000000329 · Cited by 16 · see citing works
Woll, S., Birkenmaier, D., Biri, G. I., Nissen, R., Lutz, L., Schroth, M., Ebner‐Priemer, U., & Giurgiu, M. (2025) · JMIR mhealth and uhealth · doi:10.2196/59660 · Cited by 19 · see citing works
Affect Estimation with Wearable Sensors
Yan, S., Hosseinmardi, H., Kao, H.-T., Narayanan, S. S., Lerman, K., & Ferrara, E. (2020) · Journal of Healthcare Informatics Research · doi:10.1007/s41666-019-00066-z · Cited by 13 · see citing works
Schmitter‐Edgecombe, M., Luna, C. M., Dai, S., & Cook, D. J. (2024) · The Clinical Neuropsychologist · doi:10.1080/13854046.2024.2330143 · Cited by 12 · see citing works
Leenaerts, N., Soyster, P. D., Ceccarini, J., Sunaert, S. G., Fisher, A. J., & Vrieze, E. (2024) · Psychological Medicine · doi:10.1017/s0033291724000862 · Cited by 11 · see citing works
Choo, T.-H. J., Wall, M. M., Brodsky, B. S., Herzog, S., Mann, J. J., Stanley, B., & Galfalvy, H. (2024) · Journal of Affective Disorders · doi:10.1016/j.jad.2024.05.093 · Cited by 10 · see citing works
Yuan, S., Liu, Q., Huang, X., Tan, S., Bai, Z., Yu, J., Lei, F., Le, H., Ye, Q., Peng, X., et al. (2024) · Alzheimer s Research & Therapy · doi:10.1186/s13195-024-01663-w · Cited by 7 · see citing works
Using natural language processing to track negative emotions in the daily lives of adolescents.
Fisher, H., Jaffe, N., Pidvirny, K., Tierney, A. O., Pizzagalli, D. A., & Webb, C. A. (2026) · Journal of Psychopathology and Clinical Science · doi:10.1037/abn0001150 · Cited by 6 · see citing works
Interpretation of Artificial Intelligence Algorithms in the Prediction of Sepsis
Murugesan, I., Murugesan, K., Balasubramanian, L., & Arumugam, M. (2019) · Computing in cardiology · doi:10.22489/cinc.2019.332 · Cited by 6 · see citing works
Interpretation of Artificial Intelligence Algorithms in the Prediction of Sepsis
Murugesan, I., Murugesan, K., Balasubramanian, L., & Arumugam, M. (2019) · doi:10.23919/cinc49843.2019.9005667 · Cited by 2 · see citing works
Leenaerts, N., Soyster, P. D., Ceccarini, J., Sunaert, S. G., Fisher, A. J., & Vrieze, E. (2023) · doi:10.31234/osf.io/9utrv · Cited by 1 · see citing works
Ng, A., Wei, B., Jain, J., Ward, E. A., Tandon, S. D., Moskowitz, J. T., Krogh‐Jespersen, S., Wakschlag, L. S., & Alshurafa, N. I. (2021) · doi:10.2196/preprints.33850
Casini, E., Pierro, R. D., Preti, E., Madeddu, F., & Calati, R. (2023) · Minerva Psychiatry · doi:10.23736/s2724-6612.22.02406-x
Fletcher, R., Zeng, K., Yang, M. Y., Pietrzak, A., & Eddie, D. (2025) · Applied Psychophysiology and Biofeedback · doi:10.1007/s10484-025-09714-0
Naegelin, M., Weibel, R. P., Kerr, J. I., von Wangenheim, F., Schinazi, V. R., Marca, R. L., Hölscher, C., Nater, U. M., & Ferrario, A. (2025) · medRxiv · doi:10.1101/2025.08.02.25332538
Exploratory Digital Tools for Measuring Cognitive Health
Singh, D. S., & Weisenbach, D. S. L. (2025) · doi:10.1002/9781394295432.ch05
Wang, Z., Daniel, K. E., Barnes, L. E., & Chow, P. I. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791352
King, G. A., Vize, C. E., Beltz, A. M., & Wright, A. G. C. (2026) · Behavior Therapy · doi:10.1016/j.beth.2026.10.004
- Authors
- Rozet, A., Kronish, I. M., Schwartz, J. E., & Davidson, K. W.
- Affiliations
- Columbia University Irving Medical Center (US)
- Northwell Health (US)
- Corresponding author
- Rozet, Alan
- Venue
- Journal of Medical Internet Research
- Publisher
- JMIR Publications Inc.
- Published
- 2019-04-26
- Volume
- 21
- Issue
- 4
- Pages
- e12910
- ISSN
- 1438-8871 (ISSN-L)
- PMC
- PMC6658264
- OpenAlex
- W2919207316
- Cited by
- 28
- References
- 14
- Citations by year
- 2026: 3 · 2025: 4 · 2024: 4 · 2023: 5 · 2022: 3 · 2021: 1 · 2020: 5 · 2019: 3
- FWCI
- 3.52
- 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)
- Funders
- National Institutes of Health (5r01hl115941-03, UL1TR001873)
- National Heart, Lung, and Blood Institute (R01-HL115941)
- National Center for Advancing Translational Sciences
- Topics
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Mental Health Research Topics
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Emotion and Mood Recognition
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- perceived stress, actigraphy, physical activity, environmental factors, temperature, daylight, recurrent neural networks, decision tree, ecological momentary assessment, model interpretability
- MeSH terms
- Machine Learning, Adult, Data Collection, Female, Humans, Male, Middle Aged, Stress, Psychological, Young Adult
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
