Prediction of stress and drug craving ninety minutes in the future with passively collected GPS data
Open accessThe DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index.
Abstract
Just-in-time adaptive interventions (JITAIs), typically smartphone apps, learn to deliver therapeutic content when users need it. The challenge is to “push” content at algorithmically chosen moments without making users trigger it with effortful input. We trained a randomForest algorithm to predict heroin craving, cocaine craving, or stress (reported via smartphone app 3x/day) 90 min into the future, using 16 weeks of field data from 189 outpatients being treated for opioid-use disorder. We used only one form of continuous input (along with person-level demographic data), collected passively: an indicator of environmental exposures along the past 5 h of movement, as assessed by GPS. Our models achieved excellent overall accuracy—as high as 0.93 by the end of 16 weeks of tailoring—but this was driven mostly by correct predictions of absence. For predictions of presence, “believability” (positive predictive value, PPV) usually peaked in the high 0.70s toward the end of the 16 weeks. When the prediction target was more rare, PPV was lower. Our findings complement those of other investigators who use machine learning with more broadly based “digital phenotyping” inputs to predict or detect mental and behavioral events. When target events are comparatively subtle, like stress or drug craving, accurate detection or prediction probably needs effortful input from users, not passive monitoring alone. We discuss ways in which accuracy is difficult to achieve or even assess, and warn that high overall accuracy (including high specificity) can mask the abundance of false alarms that low PPV reveals.
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
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
Kuhn, M., & Johnson, K. (2013) · doi:10.1007/978-1-4614-6849-3 · Cited by 6,788
Analyzing developmental trajectories: A semiparametric, group-based approach.
Nagin, D. S. (1999) · Psychological Methods · doi:10.1037/1082-989x.4.2.139 · Cited by 2,346
Nahum-Shani, I., Smith, S. N., Spring, B. J., Collins, L. M., Witkiewitz, K., Tewari, A., & Murphy, S. A. (2018) · Annals of Behavioral Medicine · doi:10.1007/s12160-016-9830-8 · Cited by 2,171 · cited 1×
““Digital medicine” has many meanings, but one of the most exciting is the prospect of treating chronic disorders with just-intime adaptive interventions (JITAIs).(1,2) JITAIs, which currently exist in various stages of development and validation, are mobile treatments that learn to deliver therapeutic content exactly…”
BackgroundCity living and urban upbringing affect neural social stress processing in humans
Lederbogen, F., Kirsch, P., Haddad, L., Streit, F., Tost, H., Schuch, P., Wüst, S., Pruessner, J. C., Rietschel, M., Deuschle, M., et al. (2011) · Nature · doi:10.1038/nature10190 · Cited by 1,584 · cited 1×
“…results from our pilot study, 5 mental events with detectable physiological concomitants and important health consequences may occur without subjective awareness; 58,59 thus, while self-report is an important check on detection accuracy, a user “ denial ” might not always indicate a false alarm.”
BackgroundNew Data from the Addiction Severity Index Reliability and Validity in Three Centers
McLELLAN, A. T., LUBORSKY, L., CACCIOLA, J., GRIFFITH, J., EVANS, F., BARR, H. L., & OʼBRIEN, C. P. (1985) · The Journal of Nervous and Mental Disease · doi:10.1097/00005053-198507000-00005 · Cited by 1,503
Digital Phenotyping: Technology for a New Science of Behavior
Insel, T. R. (2017) · JAMA · doi:10.1001/jama.2017.11295 · Cited by 833 · cited 1×
“Recent approaches to this problem have used digital phenotyping, a set of strategies that encompasses logging almost everything that can be sensed by a smartphone’s operating system.(4) (We list many published examples in the “Discussion” section).”
BackgroundMicrorandomized trials: An experimental design for developing just-in-time adaptive interventions.
Klasnja, P., Hekler, E. B., Shiffman, S., Boruvka, A., Almirall, D., Tewari, A., & Murphy, S. A. (2015) · Health Psychology · doi:10.1037/hea0000305 · Cited by 671 · cited 1×
“The matching of interventional content to momentary situations is an active area of theory development and requires specialized study designs.(65) Our research group is pursuing these two aims—prediction accuracy and content development—on parallel tracks until we are confident that we can combine them.”
BackgroundHarnessing context sensing to develop a mobile intervention for depression
Burns, M. N., Begale, M., Duffecy, J., Gergle, D., Karr, C. J., Giangrande, E., & Mohr, D. C. (2011) · Journal of Medical Internet Research · doi:10.2196/jmir.1838 · Cited by 646
Contrasts and Correlations in Effect-Size Estimation
Rosnow, R. L., Rosenthal, R., & Rubin, D. B. (2000) · Psychological Science · doi:10.1111/1467-9280.00287 · Cited by 513
Canzian, L., & Musolesi, M. (2015) · Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing · doi:10.1145/2750858.2805845 · Cited by 477 · cited 1×
“80s.(23,25,27,30,35,40) These are mostly averages across all participants in a given study; many of the published reports do not provide information on how accuracy varied across people or time.”
Result
Cited by
Ecological momentary interventions for mental health: A scoping review
Balaskas, A., Schueller, S. M., Cox, A. L., & Doherty, G. (2021) · PLOS ONE · doi:10.1371/journal.pone.0248152 · Cited by 235
Passive Health Monitoring Using Large Scale Mobility Data
Zhang, Y., Xu, F., Li, T., Kostakos, V., Hui, P., & Li, Y. (2021) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3448078 · Cited by 10
“Health-related apps can utilize the data to accurately predict the likelihood of users requiring hospital treatment, then raise timely warnings to the user.”
BackgroundInfluentialAltweck, L., Schmidt, S., & Tomczyk, S. (2024) · JMIR Research Protocols · doi:10.2196/54728 · Cited by 4
Altweck, L., Schmidt, S., & Tomczyk, S. (2023) · doi:10.2196/preprints.54728 · Cited by 4
Metadata
- Authors
- Epstein, D. H., Tyburski, M., Kowalczyk, W. J., Burgess-Hull, A. J., Phillips, K. A., Curtis, B. L., & Preston, K. L.
- Venue
- npj Digital Medicine
- Published
- 2020-03-04
- Volume
- 3
- Issue
- 1
- Pages
- 26-26
- ISSN
- 2398-6352 (ISSN-L)
- OpenAlex
- W3009908488
- Cited by
- 61
- References
- 28
- FWCI
- 7.56
- Type
- journal article
- Language
- en
- Open access
- gold
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Prediction of stress and drug craving ninety minutes in the future with passively collected GPS data. https://app.cochat.ai/papers/10.1038/s41746-020-0234-6
- The paper
- Epstein, D. H., Tyburski, M., Kowalczyk, W. J., Burgess-Hull, A. J., Phillips, K. A., Curtis, B. L., & Preston, K. L. (2020). Prediction of stress and drug craving ninety minutes in the future with passively collected GPS data. npj Digital Medicine. https://doi.org/10.1038/s41746-020-0234-6
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.