{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:31:02Z","timestamp":1785544262629,"version":"3.56.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,4,20]],"date-time":"2021-04-20T00:00:00Z","timestamp":1618876800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,4,20]],"date-time":"2021-04-20T00:00:00Z","timestamp":1618876800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Excess alcohol use is an important determinant of death and disability. Machine learning (ML)-driven interventions leveraging smart-breathalyzer data may help reduce these harms. We developed a digital phenotype of long-term smart-breathalyzer behavior to predict individuals\u2019 breath alcohol concentration (BrAC) levels trained on data from a smart breathalyzer. We analyzed roughly one million datapoints from 33,452 users of a commercial smart-breathalyzer device, collected between 2013 and 2017. For validation, we analyzed the associations between state-level observed smart-breathalyzer BrAC levels and impaired-driving motor vehicle death rates. Behavioral, geolocation-based, and time-series-derived features were fed to an ML algorithm using training (70% of the cohort), development (10% of the cohort), and test (20% of the cohort) sets to predict the likelihood of a BrAC exceeding the legal driving limit (0.08\u2009g\/dL). States with higher average BrAC levels had significantly higher alcohol-related driving death rates, adjusted for the number of users per state <jats:italic>B<\/jats:italic> (SE)\u2009=\u200991.38 (15.16), <jats:italic>p<\/jats:italic>\u2009&lt;\u20090.01. In the independent test set, the ML algorithm predicted the likelihood of a given user-initiated BrAC sample exceeding BrAC\u2009\u2265\u20090.08\u2009g\/dL, with an area under the curve (AUC) of 85%. Highly predictive features included users\u2019 prior BrAC trends, subjective estimation of their BrAC (or AUC\u2009=\u200982% without the self-estimate), engagement and self-monitoring, time since the last measure, and hour of the day. In conclusion, an ML algorithm successfully quantified a digital phenotype of behavior, predicting naturalistic BrAC levels exceeding 0.08\u2009g\/dL (a threshold associated with alcohol-related harm) with good discrimination capability. This result establishes a foundation for future research on precision behavioral medicine digital health interventions using smart breathalyzers and passive monitoring approaches.<\/jats:p>","DOI":"10.1038\/s41746-021-00441-4","type":"journal-article","created":{"date-parts":[[2021,4,20]],"date-time":"2021-04-20T10:56:45Z","timestamp":1618916205000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["Machine learning prediction of blood alcohol concentration: a digital signature of smart-breathalyzer behavior"],"prefix":"10.1038","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6191-6432","authenticated-orcid":false,"given":"Kirstin","family":"Aschbacher","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian S.","family":"Hendershot","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0310-3326","authenticated-orcid":false,"given":"Geoffrey","family":"Tison","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Judith A.","family":"Hahn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8490-0270","authenticated-orcid":false,"given":"Robert","family":"Avram","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeffrey E.","family":"Olgin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5197-7696","authenticated-orcid":false,"given":"Gregory M.","family":"Marcus","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,4,20]]},"reference":[{"key":"441_CR1","unstructured":"World Health Organization. Global Status Report on Alcohol and Health (World Health Organization, 2018)."},{"key":"441_CR2","doi-asserted-by":"publisher","first-page":"2383","DOI":"10.1016\/S0140-6736(16)00648-6","volume":"387","author":"AH Mokdad","year":"2016","unstructured":"Mokdad, A. H. et al. Global burden of diseases, injuries, and risk factors for young people\u2019s health during 1990\u20132013: a systematic analysis for the Global Burden of Disease Study 2013. Lancet 387, 2383\u20132401 (2016).","journal-title":"Lancet"},{"key":"441_CR3","doi-asserted-by":"publisher","first-page":"1015","DOI":"10.1016\/S0140-6736(18)31310-2","volume":"392","author":"MG Griswold","year":"2018","unstructured":"Griswold, M. G. et al. Alcohol use and burden for 195 countries and territories, 1990\u20132016: a systematic analysis for the Global Burden of Disease Study 2016. Lancet 392, 1015\u20131035 (2018).","journal-title":"Lancet"},{"key":"441_CR4","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.addbeh.2017.11.039","volume":"83","author":"S Bae","year":"2018","unstructured":"Bae, S., Chung, T., Ferreira, D., Dey, A. K. & Suffoletto, B. Mobile phone sensors and supervised machine learning to identify alcohol use events in young adults: Implications for just-in-time adaptive interventions. Addict. Behav. 83, 42\u201347 (2018).","journal-title":"Addict. Behav."},{"key":"441_CR5","unstructured":"Governors Highway Safety Association. Alcohol impaired driving. http:\/\/www.ghsa.org\/state-laws\/issues\/Alcohol-Impaired-Driving (2019)."},{"key":"441_CR6","doi-asserted-by":"publisher","first-page":"205520761774675","DOI":"10.1177\/2055207617746752","volume":"3","author":"BC Riordan","year":"2017","unstructured":"Riordan, B. C. et al. The accuracy and promise of personal breathalysers for research: Steps toward a cost-effective reliable measure of alcohol intoxication? Digit. Health 3, 205520761774675 (2017).","journal-title":"Digit. Health"},{"key":"441_CR7","doi-asserted-by":"crossref","unstructured":"Delgado, M. K. et al. Test accuracy of smartphone-paired breathalysers: a validation study. In Oral Presentations, Vol. 23, A15.1-A15 (BMJ Publishing Group Ltd, 2017).","DOI":"10.1136\/injuryprev-2017-042560.39"},{"key":"441_CR8","doi-asserted-by":"publisher","first-page":"1944","DOI":"10.1016\/j.addbeh.2012.12.017","volume":"38","author":"ER Aston","year":"2013","unstructured":"Aston, E. R. & Liguori, A. Self-estimation of blood alcohol concentration: a review. Addict. Behav. 38, 1944\u20131951 (2013).","journal-title":"Addict. Behav."},{"key":"441_CR9","doi-asserted-by":"crossref","unstructured":"David, C. N. On the prospects for a (deep) learning health care system. JAMA 320, 1099\u20131100 (2018).","DOI":"10.1001\/jama.2018.11103"},{"key":"441_CR10","doi-asserted-by":"crossref","unstructured":"Dietterich, T. G. Ensemble methods in machine learning. In Multiple Classifier Systems. MCS 2000. Lecture Notes in Computer Science (eds Kittler, J. & Roli, F.), Vol. 1857, 1\u201315 (Springer, 2000).","DOI":"10.1007\/3-540-45014-9_1"},{"key":"441_CR11","doi-asserted-by":"crossref","unstructured":"Chen, T. & Guestrin, C. XGBoost: a scalable tree boosting system. In Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD \u201916 785\u2013794 (ACM Press, 2016).","DOI":"10.1145\/2939672.2939785"},{"key":"441_CR12","doi-asserted-by":"publisher","first-page":"1215","DOI":"10.1001\/jama.2017.11295","volume":"318","author":"TR Insel","year":"2017","unstructured":"Insel, T. R. Digital phenotyping. JAMA 318, 1215 (2017).","journal-title":"JAMA"},{"key":"441_CR13","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1177\/1535370217750088","volume":"243","author":"RM Califf","year":"2018","unstructured":"Califf, R. M. Biomarker definitions and their applications. Exp. Biol. Med. 243, 213\u2013221 (2018).","journal-title":"Exp. Biol. Med."},{"key":"441_CR14","doi-asserted-by":"publisher","DOI":"10.2196\/mhealth.3895","volume":"3","author":"C Garnett","year":"2015","unstructured":"Garnett, C., Crane, D., West, R., Brown, J. & Michie, S. Identification of behavior change techniques and engagement strategies to design a smartphone app to reduce alcohol consumption using a formal consensus method. JMIR mHealth uHealth 3, e73 (2015).","journal-title":"JMIR mHealth uHealth"},{"key":"441_CR15","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1037\/a0024275","volume":"26","author":"PD Quinn","year":"2012","unstructured":"Quinn, P. D. & Fromme, K. Event-level associations between objective and subjective alcohol intoxication and driving after drinking across the college years. Psychol. Addict. Behav. 26, 384\u2013392 (2012).","journal-title":"Psychol. Addict. Behav."},{"key":"441_CR16","first-page":"4766","volume":"12","author":"SM Lundberg","year":"2017","unstructured":"Lundberg, S. M., Allen, P. G. & Lee, S.-I. A unified approach to interpreting model predictions. Adv. Neural Inf. Process Syst. 12, 4766\u20134775 (2017).","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"441_CR17","doi-asserted-by":"publisher","first-page":"1761","DOI":"10.2105\/AJPH.2016.303321","volume":"106","author":"ME Rossheim","year":"2016","unstructured":"Rossheim, M. E. et al. Feeling no buzz or a slight buzz is common when legally drunk. Am. J. Public Health 106, 1761\u20131762 (2016).","journal-title":"Am. J. Public Health"},{"key":"441_CR18","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1111\/acer.14239","volume":"44","author":"AM White","year":"2020","unstructured":"White, A. M., Castle, I. J. P., Hingson, R. W. & Powell, P. A. Using death certificates to explore changes in alcohol-related mortality in the United States, 1999 to 2017. Alcohol. Clin. Exp. Res. 44, 178\u2013187 (2020).","journal-title":"Alcohol. Clin. Exp. Res."},{"key":"441_CR19","doi-asserted-by":"publisher","first-page":"1381","DOI":"10.1111\/j.1360-0443.2010.02975.x","volume":"105","author":"S Rooke","year":"2010","unstructured":"Rooke, S., Thorsteinsson, E., Karpin, A., Copeland, J. & Allsop, D. Computer-delivered interventions for alcohol and tobacco use: a meta-analysis. Addiction 105, 1381\u20131390 (2010).","journal-title":"Addiction"},{"key":"441_CR20","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1136\/eb-2018-102891","volume":"21","author":"J Torous","year":"2018","unstructured":"Torous, J., Nicholas, J., Larsen, M. E., Firth, J. & Christensen, H. Clinical review of user engagement with mental health smartphone apps: evidence, theory and improvements. Evid. Based Ment. Health 21, 116\u2013119 (2018).","journal-title":"Evid. Based Ment. Health"},{"key":"441_CR21","doi-asserted-by":"publisher","first-page":"205520761559533","DOI":"10.1177\/2055207615595335","volume":"1","author":"LG Morrison","year":"2015","unstructured":"Morrison, L. G. Theory-based strategies for enhancing the impact and usage of digital health behaviour change interventions: a review. Digit. Health 1, 205520761559533 (2015).","journal-title":"Digit. Health"},{"key":"441_CR22","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.jada.2010.10.008","volume":"111","author":"LE Burke","year":"2011","unstructured":"Burke, L. E., Wang, J. & Sevick, M. A. Self-monitoring in weight loss: a systematic review of the literature. J. Am. Diet. Assoc. 111, 92\u2013102 (2011).","journal-title":"J. Am. Diet. Assoc."},{"key":"441_CR23","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.jsat.2017.09.013","volume":"83","author":"E Aharonovich","year":"2017","unstructured":"Aharonovich, E., Stohl, M., Cannizzaro, D. & Hasin, D. HealthCall delivered via smartphone to reduce co-occurring drug and alcohol use in HIV-infected adults: a randomized pilot trial. J. Subst. Abuse Treat. 83, 15\u201326 (2017).","journal-title":"J. Subst. Abuse Treat."},{"key":"441_CR24","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1056\/NEJMra1511480","volume":"374","author":"ND Volkow","year":"2016","unstructured":"Volkow, N. D., Koob, G. F. & McLellan, A. T. Neurobiologic advances from the brain disease model of addiction. N. Engl. J. Med. 374, 363\u2013371 (2016).","journal-title":"N. Engl. J. Med."},{"key":"441_CR25","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1016\/j.tips.2013.01.004","volume":"34","author":"JP Huston","year":"2013","unstructured":"Huston, J. P., Silva, M. A. D. S., Topic, B. & M\u00fcller, C. P. What\u2019s conditioned in conditioned place preference? Trends Pharmacol. Sci. 34, 162\u2013166 (2013).","journal-title":"Trends Pharmacol. Sci."},{"key":"441_CR26","doi-asserted-by":"publisher","first-page":"pyv102","DOI":"10.1093\/ijnp\/pyv102","volume":"19","author":"S Schade","year":"2016","unstructured":"Schade, S. & Paulus, W. D-cycloserine in neuropsychiatric diseases: a systematic review. Int. J. Neuropsychopharmacol. 19, pyv102 (2016).","journal-title":"Int. J. Neuropsychopharmacol."},{"key":"441_CR27","doi-asserted-by":"publisher","first-page":"1274","DOI":"10.1111\/add.12557","volume":"109","author":"JC Garbutt","year":"2014","unstructured":"Garbutt, J. C. et al. Clinical and biological moderators of response to naltrexone in alcohol dependence: a systematic review of the evidence. Addiction 109, 1274\u20131284 (2014).","journal-title":"Addiction"},{"key":"441_CR28","doi-asserted-by":"publisher","first-page":"2053","DOI":"10.1080\/10826084.2019.1618328","volume":"54","author":"SP Byrne","year":"2019","unstructured":"Byrne, S. P., Haber, P., Baillie, A., Giannopolous, V. & Morley, K. Cue exposure therapy for alcohol use disorders: what can be learned from exposure therapy for anxiety disorders? Subst. Use Misuse 54, 2053\u20132063 (2019).","journal-title":"Subst. Use Misuse"},{"key":"441_CR29","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/j.drugalcdep.2010.03.017","volume":"111","author":"CA Conklin","year":"2010","unstructured":"Conklin, C. A., Perkins, K. A., Robin, N., McClernon, F. J. & Salkeld, R. P. Bringing the real world into the laboratory: personal smoking and nonsmoking environments. Drug Alcohol Depend. 111, 58\u201363 (2010).","journal-title":"Drug Alcohol Depend."},{"key":"441_CR30","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1001\/jamapsychiatry.2013.4642","volume":"71","author":"DH Gustafson","year":"2014","unstructured":"Gustafson, D. H. et al. A smartphone application to support recovery from alcoholism a randomized clinical trial. JAMA Psychiatry 71, 566\u2013572 (2014).","journal-title":"JAMA Psychiatry"},{"key":"441_CR31","unstructured":"Colorado Department of Transportation. CDOT and BACtrack Announce Partnership to Reduce Impaired Driving (Colorado Department of Transportation, Accessed 9 Aug 2019); https:\/\/www.codot.gov\/news\/2017-news\/august\/cdot-and-bactrack-announce-partnership-to-reduce-impaired-driving."},{"key":"441_CR32","doi-asserted-by":"publisher","first-page":"2453","DOI":"10.1111\/acer.13897","volume":"42","author":"K Witkiewitz","year":"2018","unstructured":"Witkiewitz, K. et al. Drinking risk level reductions associated with improvements in physical health and quality of life among individuals with alcohol use disorder. Alcohol. Clin. Exp. Res. 42, 2453\u20132465 (2018).","journal-title":"Alcohol. Clin. Exp. Res."},{"key":"441_CR33","unstructured":"Centers for Disease Control and Prevention. Impaired Driving: Get the Facts|Motor Vehicle Safety|CDC Injury Center (Centers for Disease Control and Prevention, Accessed 9 Oct 2017); https:\/\/www.cdc.gov\/motorvehiclesafety\/impaired_driving\/impaired-drv_factsheet.html."},{"key":"441_CR34","unstructured":"United States Census Bureau. Metropolitan and Micropolitan Statistical Areas Totals: 2010-2018 (United States Census Bureau, Accessed 9 Oct 2017); https:\/\/www.census.gov\/data\/tables\/time-series\/demo\/popest\/2010s-total-metro-and-micro-statistical-areas.html."},{"key":"441_CR35","unstructured":"United States Census Bureau. Geography Program. Explanation of the 2010 Urban Area to ZIP Code Tabulation Area Relationship File (United States Census Bureau, Accessed 9 Oct 2017); https:\/\/www.census.gov\/programs-surveys\/geography.html."},{"key":"441_CR36","unstructured":"United States Census Bureau. 2010 Urban Area FAQs: Urban-Rural Classification Program (United States Census Bureau, Accessed 9 Oct 2017); https:\/\/www.census.gov\/programs-surveys\/geography\/about\/faq\/2010-urban-area-faq.html."},{"key":"441_CR37","doi-asserted-by":"publisher","first-page":"2270","DOI":"10.2105\/AJPH.2009.186007","volume":"100","author":"AC Wagenaar","year":"2010","unstructured":"Wagenaar, A. C., Tobler, A. L. & Komro, K. A. Effects of alcohol tax and price policies on morbidity and mortality: a systematic review. Am. J. Public Health 100, 2270\u20132278 (2010).","journal-title":"Am. J. Public Health"},{"key":"441_CR38","unstructured":"Tax Foundation. State Sales, Gasoline, Cigarette, and Alcohol Tax Rates by State, 2000\u20132014 (Tax Foundation, Accessed 31 July 2019); https:\/\/taxfoundation.org\/state-sales-gasoline-cigarette-and-alcohol-tax-rates\/."},{"key":"441_CR39","doi-asserted-by":"publisher","first-page":"S195","DOI":"10.1016\/j.amepre.2007.04.003","volume":"32","author":"S Galea","year":"2007","unstructured":"Galea, S., Ahern, J., Tracy, M. & Vlahov, D. Neighborhood income and income distribution and the use of cigarettes, alcohol, and marijuana. Am. J. Prev. Med. 32, S195\u2013S202 (2007).","journal-title":"Am. J. Prev. Med."},{"key":"441_CR40","unstructured":"US Census Bureau. Income and Poverty in the United States: 2017 (US Census Bureau, Accessed 17 Sep 2018); https:\/\/www.census.gov\/library\/publications\/2018\/demo\/p60-263.html."},{"key":"441_CR41","unstructured":"Centers for Disease Control and Prevention. U.S. Chronic Disease Indicators (CDI). Data.gov (Centers for Disease Control and Prevention, Accessed 17 Sep 2018); https:\/\/catalog.data.gov\/dataset\/u-s-chronic-disease-indicators-cdi."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00441-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00441-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00441-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,3]],"date-time":"2022-12-03T18:49:46Z","timestamp":1670093386000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00441-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,20]]},"references-count":41,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["441"],"URL":"https:\/\/doi.org\/10.1038\/s41746-021-00441-4","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,20]]},"assertion":[{"value":"28 May 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 April 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests. Apart from providing a dataset as described, the company BACtrack had no role in the study.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"74"}}