Machine learning prediction of blood alcohol concentration: a digital signature of smart-breathalyzer behavior

Abstract 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’ breath alcohol...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Kirstin Aschbacher, Christian S. Hendershot, Geoffrey Tison, Judith A. Hahn, Robert Avram, Jeffrey E. Olgin, Gregory M. Marcus
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Computer applications to medicine. Medical informatics R858-859.7
Acceso en línea:	https://doaj.org/article/68cb6f10c04a437287ff26a0b88550f1
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:68cb6f10c04a437287ff26a0b88550f1
record_format	dspace
spelling	oai:doaj.org-article:68cb6f10c04a437287ff26a0b88550f12021-12-02T18:27:51ZMachine learning prediction of blood alcohol concentration: a digital signature of smart-breathalyzer behavior10.1038/s41746-021-00441-42398-6352https://doaj.org/article/68cb6f10c04a437287ff26a0b88550f12021-04-01T00:00:00Zhttps://doi.org/10.1038/s41746-021-00441-4https://doaj.org/toc/2398-6352Abstract 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’ 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 g/dL). States with higher average BrAC levels had significantly higher alcohol-related driving death rates, adjusted for the number of users per state B (SE) = 91.38 (15.16), p < 0.01. In the independent test set, the ML algorithm predicted the likelihood of a given user-initiated BrAC sample exceeding BrAC ≥ 0.08 g/dL, with an area under the curve (AUC) of 85%. Highly predictive features included users’ prior BrAC trends, subjective estimation of their BrAC (or AUC = 82% 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 g/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.Kirstin AschbacherChristian S. HendershotGeoffrey TisonJudith A. HahnRobert AvramJeffrey E. OlginGregory M. MarcusNature PortfolioarticleComputer applications to medicine. Medical informaticsR858-859.7ENnpj Digital Medicine, Vol 4, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Computer applications to medicine. Medical informatics R858-859.7
spellingShingle	Computer applications to medicine. Medical informatics R858-859.7 Kirstin Aschbacher Christian S. Hendershot Geoffrey Tison Judith A. Hahn Robert Avram Jeffrey E. Olgin Gregory M. Marcus Machine learning prediction of blood alcohol concentration: a digital signature of smart-breathalyzer behavior
description	Abstract 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’ 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 g/dL). States with higher average BrAC levels had significantly higher alcohol-related driving death rates, adjusted for the number of users per state B (SE) = 91.38 (15.16), p < 0.01. In the independent test set, the ML algorithm predicted the likelihood of a given user-initiated BrAC sample exceeding BrAC ≥ 0.08 g/dL, with an area under the curve (AUC) of 85%. Highly predictive features included users’ prior BrAC trends, subjective estimation of their BrAC (or AUC = 82% 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 g/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.
format	article
author	Kirstin Aschbacher Christian S. Hendershot Geoffrey Tison Judith A. Hahn Robert Avram Jeffrey E. Olgin Gregory M. Marcus
author_facet	Kirstin Aschbacher Christian S. Hendershot Geoffrey Tison Judith A. Hahn Robert Avram Jeffrey E. Olgin Gregory M. Marcus
author_sort	Kirstin Aschbacher
title	Machine learning prediction of blood alcohol concentration: a digital signature of smart-breathalyzer behavior
title_short	Machine learning prediction of blood alcohol concentration: a digital signature of smart-breathalyzer behavior
title_full	Machine learning prediction of blood alcohol concentration: a digital signature of smart-breathalyzer behavior
title_fullStr	Machine learning prediction of blood alcohol concentration: a digital signature of smart-breathalyzer behavior
title_full_unstemmed	Machine learning prediction of blood alcohol concentration: a digital signature of smart-breathalyzer behavior
title_sort	machine learning prediction of blood alcohol concentration: a digital signature of smart-breathalyzer behavior
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/68cb6f10c04a437287ff26a0b88550f1
work_keys_str_mv	AT kirstinaschbacher machinelearningpredictionofbloodalcoholconcentrationadigitalsignatureofsmartbreathalyzerbehavior AT christianshendershot machinelearningpredictionofbloodalcoholconcentrationadigitalsignatureofsmartbreathalyzerbehavior AT geoffreytison machinelearningpredictionofbloodalcoholconcentrationadigitalsignatureofsmartbreathalyzerbehavior AT judithahahn machinelearningpredictionofbloodalcoholconcentrationadigitalsignatureofsmartbreathalyzerbehavior AT robertavram machinelearningpredictionofbloodalcoholconcentrationadigitalsignatureofsmartbreathalyzerbehavior AT jeffreyeolgin machinelearningpredictionofbloodalcoholconcentrationadigitalsignatureofsmartbreathalyzerbehavior AT gregorymmarcus machinelearningpredictionofbloodalcoholconcentrationadigitalsignatureofsmartbreathalyzerbehavior
_version_	1718377982035230720

Machine learning prediction of blood alcohol concentration: a digital signature of smart-breathalyzer behavior

Ejemplares similares