{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T00:51:42Z","timestamp":1784854302859,"version":"3.55.0"},"reference-count":42,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Science Foundation (NSF)","award":["2406251"],"award-info":[{"award-number":["2406251"]}]},{"name":"National Science Foundation (NSF)","award":["U54GM138062"],"award-info":[{"award-number":["U54GM138062"]}]},{"name":"National Institute of General Medical Sciences (NIGMS)","award":["2406251"],"award-info":[{"award-number":["2406251"]}]},{"name":"National Institute of General Medical Sciences (NIGMS)","award":["U54GM138062"],"award-info":[{"award-number":["U54GM138062"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AI"],"abstract":"<jats:p>Substance use disorders affect 17.3% of Americans. Digital health solutions that use machine learning to detect substance use from wearable biosignal data can eventually pave the way for real-time digital interventions. However, difficulties in addressing severe between-subject data heterogeneity have hampered the adaptation of machine learning approaches for substance use detection, necessitating more robust technological solutions. We tested the utility of personalized machine learning using participant-specific convolutional neural networks (CNNs) enhanced with self-supervised learning (SSL) to detect drug use. In a pilot feasibility study, we collected data from 9 participants using Fitbit Charge 5 devices, supplemented by ecological momentary assessments to collect real-time labels of substance use. We implemented a baseline 1D-CNN model with traditional supervised learning and an experimental SSL-enhanced model to improve individualized feature extraction under limited label conditions. Results: Among the 9 participants, we achieved an average area under the receiver operating characteristic curve score across participants of 0.695 for the supervised CNNs and 0.729 for the SSL models. Strategic selection of an optimal threshold enabled us to optimize either sensitivity or specificity while maintaining reasonable performance for the other metric. Conclusion: These findings suggest that Fitbit data have the potential to enhance substance use monitoring systems. However, the small sample size in this study limits its generalizability to diverse populations, so we call for future research that explores SSL-powered personalization at a larger scale.<\/jats:p>","DOI":"10.3390\/ai5040131","type":"journal-article","created":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T09:30:18Z","timestamp":1733391018000},"page":"2725-2738","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Monitoring Substance Use with Fitbit Biosignals: A Case Study on Training Deep Learning Models Using Ecological Momentary Assessments and Passive Sensing"],"prefix":"10.3390","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1726-8871","authenticated-orcid":false,"given":"Shizhe","family":"Li","sequence":"first","affiliation":[{"name":"Department of Statistics, Stanford University, Stanford, CA 94305, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8880-6219","authenticated-orcid":false,"given":"Chunzhi","family":"Fan","sequence":"additional","affiliation":[{"name":"Institute for Computational and Mathematical Engineering, Stanford University, Stanford, CA 94305, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2714-9476","authenticated-orcid":false,"given":"Ali","family":"Kargarandehkordi","sequence":"additional","affiliation":[{"name":"Department of Information and Computer Sciences, University of Hawaii at Manoa, Honolulu, HI 96822, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9474-1069","authenticated-orcid":false,"given":"Yinan","family":"Sun","sequence":"additional","affiliation":[{"name":"Communication & Information Sciences, University of Hawaii at Manoa, Honolulu, HI 96822, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5162-668X","authenticated-orcid":false,"given":"Christopher","family":"Slade","sequence":"additional","affiliation":[{"name":"Department of Information and Computer Sciences, University of Hawaii at Manoa, Honolulu, HI 96822, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1367-818X","authenticated-orcid":false,"given":"Aditi","family":"Jaiswal","sequence":"additional","affiliation":[{"name":"Department of Information and Computer Sciences, University of Hawaii at Manoa, Honolulu, HI 96822, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8634-6472","authenticated-orcid":false,"given":"Roberto M.","family":"Benzo","sequence":"additional","affiliation":[{"name":"Division of Cancer Prevention and Control, The Ohio State University College of Medicine, Columbus, OH 43210, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7693-8845","authenticated-orcid":false,"given":"Kristina T.","family":"Phillips","sequence":"additional","affiliation":[{"name":"Center for Integrated Health Care Research, Kaiser Permanente Hawaii, Honolulu, HI 96817, USA"},{"name":"Department of Health Systems Science, Kaiser Permanente Bernard J. Tyson School of Medicine, Pasadena, CA 91101, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3276-4411","authenticated-orcid":false,"given":"Peter","family":"Washington","sequence":"additional","affiliation":[{"name":"Department of Information and Computer Sciences, University of Hawaii at Manoa, Honolulu, HI 96822, USA"},{"name":"Division of Clinical Informatics and Digital Transformation, Department of Medicine, University of California, San Francisco, CA 94143, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"key":"ref_1","unstructured":"Substance Abuse and Mental Health Services Administration (2023). Key Substance Use and Mental Health Indicators in the United States: Results from the 2022 National Survey on Drug Use and Health."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"e22443","DOI":"10.2196\/22443","article-title":"Patterns of Use and Key Predictors for the Use of Wearable Health Care Devices by US Adults: Insights from a National Survey","volume":"22","author":"Chandrasekaran","year":"2020","journal-title":"J. Med. Internet Res."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1007\/s40429-020-00318-8","article-title":"Wearable and wireless mHealth technologies for substance use disorder","volume":"7","author":"Goldfine","year":"2020","journal-title":"Curr. Addict. Rep."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"23405","DOI":"10.1109\/JIOT.2022.3207090","article-title":"An overview of wearable biosensor systems for real-time substance use detection","volume":"9","author":"Rumbut","year":"2022","journal-title":"IEEE Internet Things J."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Islam, T., and Washington, P. (2024). Non-Invasive Biosensing for Healthcare Using Artificial Intelligence: A Semi-Systematic Review. Biosensors, 14.","DOI":"10.3390\/bios14040183"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Ferreri, F., Bourla, A., Mouchabac, S., and Karila, L. (2018). e-Addictology: An overview of new technologies for assessing and intervening in addictive behaviors. Front. Psychiatry, 9.","DOI":"10.3389\/fpsyt.2018.00051"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"104013","DOI":"10.1016\/j.brat.2021.104013","article-title":"Digital biomarkers of anxiety disorder symptom changes: Personalized deep learning models using smartphone sensors accurately predict anxiety symptoms from ecological momentary assessments","volume":"149","author":"Jacobson","year":"2022","journal-title":"Behav. Res. Ther."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"e39995","DOI":"10.2196\/39995","article-title":"Detecting Prolonged Stress in Real Life Using Wearable Biosensors and Ecological Momentary Assessments: Naturalistic Experimental Study","volume":"25","author":"Tutunji","year":"2023","journal-title":"J. Med. Internet Res."},{"key":"ref_9","first-page":"530","article-title":"Momentary Craving, Craving Variability, and Cannabis Use: Associations With THC Concentrates and Sex","volume":"84","author":"Phillips","year":"2023","journal-title":"J. Stud. Alcohol Drugs"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1016\/j.addbeh.2018.01.004","article-title":"Does social context matter? An ecological momentary assessment study of marijuana use among college students","volume":"83","author":"Phillips","year":"2018","journal-title":"Addict. Behav."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"42","DOI":"10.26828\/cannabis\/2022.01.005","article-title":"Momentary patterns of alcohol and cannabis co-use in college students: Assessing the temporal association with anxiety","volume":"5","author":"Phillips","year":"2022","journal-title":"Cannabis"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"486","DOI":"10.1037\/a0017074","article-title":"Ecological momentary assessment (EMA) in studies of substance use","volume":"21","author":"Shiffman","year":"2009","journal-title":"Psychol. Assess."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10916-015-0337-9","article-title":"iMStrong: Deployment of a biosensor system to detect cocaine use","volume":"39","author":"Carreiro","year":"2015","journal-title":"J. Med. Syst."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1007\/s13181-014-0439-7","article-title":"Real-time mobile detection of drug use with wearable biosensors: A pilot study","volume":"11","author":"Carreiro","year":"2015","journal-title":"J. Med. Toxicol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"107929","DOI":"10.1016\/j.drugalcdep.2020.107929","article-title":"Wearable sensor-based detection of stress and craving in patients during treatment for substance use disorder: A mixed methods pilot study","volume":"209","author":"Carreiro","year":"2020","journal-title":"Drug Alcohol Depend."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Sundaravadivel, P., Fitzgerald, A., and Indic, P. (2019, January 16\u201318). i-SAD: An Edge-Intelligent IoT-Based Wearable for Substance Abuse Detection. Proceedings of the 2019 IEEE International Symposium on Smart Electronic Systems (iSES) (Formerly iNiS), Rourkela, India.","DOI":"10.1109\/iSES47678.2019.00035"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1016\/j.gaitpost.2017.11.019","article-title":"Using phone sensors and an artificial neural network to detect gait changes during drinking episodes in the natural environment","volume":"60","author":"Suffoletto","year":"2018","journal-title":"Gait Posture"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Natarajan, A., Parate, A., Gaiser, E., Angarita, G., Malison, R., Marlin, B., and Ganesan, D. (2013, January 8\u201312). Detecting cocaine use with wearable electrocardiogram sensors. Proceedings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing, Zurich, Switzerland.","DOI":"10.1145\/2493432.2493496"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Mahmud, M., Fang, H., Wang, H., Carreiro, S., and Boyer, E. (2018, January 5\u20138). Automatic detection of opioid intake using wearable biosensor. Proceedings of the International Conference on Computing, Networking and Communications (ICNC), Maui, HI, USA.","DOI":"10.1109\/ICCNC.2018.8390334"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3478107","article-title":"OpiTrack: A Wearable-Based Clinical Opioid Use Tracker with Temporal Convolutional Attention Networks","volume":"5","author":"Gullapalli","year":"2021","journal-title":"Proc. ACM Interact. Mob. Wearable Ubiquitous Technol."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Rumbut, J., Singh, D., Fang, H., Wang, H., Carreiro, S., and Boyer, E. (2019, January 25\u201327). Poster abstract: Detecting kratom intoxication in wearable biosensor data. Proceedings of the IEEE\/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE), Arlington, VA, USA.","DOI":"10.1109\/CHASE48038.2019.00028"},{"key":"ref_22","first-page":"310","article-title":"A Machine Learning-based Approach for Collaborative Non-Adherence Detection during Opioid Abuse Surveillance using a Wearable Biosensor","volume":"5","author":"Singh","year":"2019","journal-title":"Biomed. Eng. Syst. Technol. Int. Jt. Conf. BIOSTEC Revis. Sel. Pap."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Wang, J., Fang, H., Carreiro, S., Wang, H., and Boyer, E. (2017, January 26\u201329). A New Mining Method to Detect Real Time Substance Use Events from Wearable Biosensor Data Stream. Proceedings of the International Conference on Computing, Networking, and Communications, Valley, CA, USA.","DOI":"10.1109\/ICCNC.2017.7876173"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"e52171","DOI":"10.2196\/52171","article-title":"A comparison of personalized and generalized approaches to emotion recognition using consumer wearable devices: Machine learning study","volume":"3","author":"Li","year":"2024","journal-title":"JMIR AI"},{"key":"ref_25","unstructured":"Islam, T., and Washington, P. (2023, January 23\u201329). Personalized Prediction of Recurrent Stress Events Using Self-Supervised Learning on Multimodal Time-Series Data. Proceedings of the International Conference on Machine Learning (ICML) 2023 Workshop on Artificial Intelligence & Human Computer Interaction, Honolulu, HI, USA."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"e55615","DOI":"10.2196\/55615","article-title":"Personalized AI-Driven Real-Time Models to Predict Stress-Induced Blood Pressure Spikes Using Wearable Devices: Proposal for a Prospective Cohort Study","volume":"13","author":"Kargarandehkordi","year":"2024","journal-title":"JMIR Res. Protoc."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"e46493","DOI":"10.2196\/46493","article-title":"Personalized Deep Learning for Substance Use in Hawaii: Protocol for a Passive Sensing and Ecological Momentary Assessment Study","volume":"13","author":"Sun","year":"2024","journal-title":"JMIR Res. Protoc."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Shi, R., Chen, Z., Wang, H., Sun, P., Trull, T., and Shang, Y. (2015, January 1\u20135). mAAS\u2014A mobile ambulatory assessment system for alcohol craving studies. Proceedings of the IEEE 39th Annual Computer Software and Applications Conference, Taichung, Taiwan.","DOI":"10.1109\/COMPSAC.2015.242"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/j.drugalcdep.2015.03.024","article-title":"Continuous in-the-field measurement of heart rate: Correlates of drug use, craving, stress, and mood in polydrug users","volume":"151","author":"Kennedy","year":"2015","journal-title":"Drug Alcohol Depend."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Wang, K., Luo, J., Zhang, T., Ouyang, Y., Zhou, C., and Lu, Y. (2019). Effect of physical activity on drug craving of women with substance use disorder in compulsory isolation: Mediating effect of internal inhibition. Front. Psychol., 10.","DOI":"10.3389\/fpsyg.2019.01928"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Zhang, T., Wang, K., Li, N., Hurr, C., and Luo, J. (2021). The relationship between different amounts of physical exercise, internal inhibition, and drug craving in individuals with substance-use disorders. Int. J. Environ. Res. Public Health, 18.","DOI":"10.3390\/ijerph182312436"},{"key":"ref_32","unstructured":"Bhutta, B.S., Alghoula, F., and Berim, I. (2024, October 25). Hypoxia. StatPearls [Internet], Available online: https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK482316\/."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Berro, L.F., Espa\u00f1a, R.A., Mong, J.A., and Gould, R.W. (2023). Editorial: Sleep and circadian rhythm disruptions associated with substance use disorders. Front. Neurosci., 17.","DOI":"10.3389\/fnins.2023.1165084"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"4777","DOI":"10.1038\/s41380-023-02241-6","article-title":"Circadian rhythm disruptions associated with opioid use disorder in synaptic proteomes of human dorsolateral prefrontal cortex and nucleus accumbens","volume":"28","author":"Puig","year":"2023","journal-title":"Mol. Psychiatry"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1186\/s13722-016-0056-7","article-title":"Sleep abnormalities associated with alcohol, cannabis, cocaine, and opiate use: A comprehensive review","volume":"11","author":"Angarita","year":"2016","journal-title":"Addict. Sci. Clin. Pract."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Guo, Q., Wang, J., Liu, H., Wu, D., and Liao, S. (2022). Nicotine Ingestion Reduces Heart Rate Variability in Young Healthy Adults. BioMed Res. Int., 2022.","DOI":"10.1155\/2022\/4286621"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1093\/ntr\/ntr004","article-title":"A single 4 mg dose of nicotine decreases heart rate variability in healthy nonsmokers: Implications for smoking cessation programs","volume":"13","author":"Sjoberg","year":"2011","journal-title":"Nicotine Tob. Res."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1080\/15504263.2018.1526431","article-title":"Resting Heart Rate Variability: Exploring Associations With Symptom Severity in Adults With Substance Use Disorders and Posttraumatic Stress","volume":"15","author":"Wardle","year":"2019","journal-title":"J. Dual Diagn."},{"key":"ref_39","unstructured":"Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., and Isard, M. (2016, January 2\u20134). TensorFlow: A system for large-scale machine learning. Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16), Savannah, Georgia."},{"key":"ref_40","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_41","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Eom, S., Eom, S., and Washington, P. (2023, January 29). SIM-CNN: Self-supervised individualized multimodal learning for stress prediction on nurses using biosignals. Proceedings of the Workshop on Machine Learning for Multimodal Healthcare Data, Honolulu, HI, USA.","DOI":"10.1101\/2023.08.25.23294640"}],"container-title":["AI"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2673-2688\/5\/4\/131\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T16:45:35Z","timestamp":1760114735000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2673-2688\/5\/4\/131"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":42,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["ai5040131"],"URL":"https:\/\/doi.org\/10.3390\/ai5040131","relation":{},"ISSN":["2673-2688"],"issn-type":[{"value":"2673-2688","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,3]]}}}