EUVIMEDEUVIMED entdecken
ValidierungsstudieOpen Access · CC BY 4.0

Passive data do not improve prediction or detection of alcohol consumption beyond temporal patterns in major depression: A 90-day cross-validated study

Anna M Langener, Dawson Haddox, Daniel M Mackin, George D Price, Damien Lekkas, Amanda C Collins, Tess Z Griffin, Michael V Heinz, Matthew D Nemesure, Subigya Nepal, Arvind Pillai, Andrew T Campbell und 1 weitere

Addictive Behaviors · 2026

DOI: 10.1016/j.addbeh.2026.108624 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift Addictive Behaviors, 2026. Verfasst von Anna M Langener und 12 weiteren Autor:innen. Beteiligte Einrichtung: Center for Technology and Behavioral Health, Geisel School of Medicine, Dartmouth College, Lebanon, NH, United States. Electronic address: anna.m.lan…. Hauptthemen laut MEDLINE: Major Depressive Disorder, Alcohol Drinking, Deep Learning. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIDA NIH HHS, NIMH NIH HHS, National Institute of Mental Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Major Depressive Disorder (MDD) is one of the most prevalent psychological disorders and frequently co-occurs with alcohol use disorders, increasing the risk of functional impairment. Monitoring alcohol use during depression treatment is therefore critical for early intervention. Passively collected data via devices like smartphones and smartwatches, offers a low-burden method for monitoring behavior in real time. This study investigated whether deep learning models trained on passively collected data (i.e., accelerometer, heart rate, respiratory rate, screen usage, and GPS data) could detect and predict alcohol use in individuals with MDD. Data were collected from 300 clinically depressed individuals who were enrolled in the Tracking Depression Study, a 90-day longitudinal study. Participants self-reported their alcohol use every week by completing the Timeline FollowBack. We trained models to predict same-day and next-day alcohol use. To validate these models, we split the data by participant, so that predictions were made on individuals who were not included in the training set. The models achieved moderate performance (mean AUC = 0.67 for both prediction tasks) when capturing both interindividual (between-person) and intraindividual (within-person) variability. Similar performances were observed when evaluating the model exclusively on predicting intraindividual variability (AUCs = 0.69 same-day, 0.68 next-day). However, model performance remained comparable to a baseline using only the day of week as predictor. These findings suggest that much of the predictive signal derives from temporal patterns. This indicates that interventions aligned with such temporal cues may already be effective, and that the added value of our model appears limited.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Major Depressive DisorderAlcohol DrinkingDeep LearningHumansFemaleMaleAdultLongitudinal StudiesPredictive Learning ModelsMiddle AgedPrediction AlgorithmsSmartphoneHeart Rate

Stichwörter der Autor:innen

Alcohol useDeep learningJITAIJust-in-time adaptive interventionsMajor depressive disorderMeta learnerPassive sensing

Autor:innen und Institutionen

  • Center for Technology and Behavioral Health, Geisel School of Medicine, Dartmouth College, Lebanon, NH, United States. Electronic address: anna.m.langener@dartmouth.edu.
  • Department of Psychology, University of Arizona, Tucson, AZ, United States.
  • Department of Psychiatry, Geisel School of Medicine, Dartmouth College, Lebanon, NH, United States.
  • Center for Technology and Behavioral Health, Geisel School of Medicine, Dartmouth College, Lebanon, NH, United States; Quantitative Biomedical Sciences Program, Dartmouth College, Lebanon, NH, United States.
  • Department of Medical Social Sciences, Feinberg School of Medicine, Northwestern University, Chicago, IL, United States.
  • Deparment of Psychiatry, Massachusetts General Hospital, Boston, MA, United States; Department of Psychiatry, Harvard Medical School, Boston, MA, United States.

Förderung

  • NIDA NIH HHS
  • NIMH NIH HHS
  • National Institute of Mental Health
  • National Institute of General Medical Sciences

Zitieren

APA

Langener, A. M., Haddox, D., Mackin, D. M., Price, G. D., Lekkas, D., Collins, A. C., Griffin, T. Z., Heinz, M. V., Nemesure, M. D., Nepal, S., Pillai, A., Campbell, A. T., & Jacobson, N. C. (2026). Passive data do not improve prediction or detection of alcohol consumption beyond temporal patterns in major depression: A 90-day cross-validated study. Addictive Behaviors. https://doi.org/10.1016/j.addbeh.2026.108624

Vancouver

Langener AM, Haddox D, Mackin DM, Price GD, Lekkas D, Collins AC, et al. Passive data do not improve prediction or detection of alcohol consumption beyond temporal patterns in major depression: A 90-day cross-validated study. Addictive Behaviors. 2026. doi:10.1016/j.addbeh.2026.108624

BibTeX
@article{Langener2026,
  author = {Langener, Anna M and Haddox, Dawson and Mackin, Daniel M and Price, George D and Lekkas, Damien and Collins, Amanda C and Griffin, Tess Z and Heinz, Michael V and Nemesure, Matthew D and Nepal, Subigya and Pillai, Arvind and Campbell, Andrew T and Jacobson, Nicholas C},
  title = {Passive data do not improve prediction or detection of alcohol consumption beyond temporal patterns in major depression: A 90-day cross-validated study},
  journal = {Addictive Behaviors},
  year = {2026},
  doi = {10.1016/j.addbeh.2026.108624}
}
Kostenlos starten →