Predictive modeling of addiction lapses in a mobile health application

Ming Yuan Chih; Timothy Patton; Fiona M. McTavish; Andrew J. Isham; Chris L. Judkins-Fisher; Amy K. Atwood; David H. Gustafson

doi:10.1016/j.jsat.2013.08.004

Predictive modeling of addiction lapses in a mobile health application

Ming Yuan Chih, Timothy Patton, Fiona M. McTavish, Andrew J. Isham, Chris L. Judkins-Fisher, Amy K. Atwood, David H. Gustafson

Health and Clinical Sciences

Research output: Contribution to journal › Article › peer-review

67 Scopus citations

Abstract

The chronically relapsing nature of alcoholism leads to substantial personal, family, and societal costs. Addiction-comprehensive health enhancement support system (A-CHESS) is a smartphone application that aims to reduce relapse. To offer targeted support to patients who are at risk of lapses within the coming week, a Bayesian network model to predict such events was constructed using responses on 2,934 weekly surveys (called the Weekly Check-in) from 152 alcohol-dependent individuals who recently completed residential treatment. The Weekly Check-in is a self-monitoring service, provided in A-CHESS, to track patients' recovery progress. The model showed good predictability, with the area under receiver operating characteristic curve of 0.829 in the 10-fold cross-validation and 0.912 in the external validation. The sensitivity/specificity table assists the tradeoff decisions necessary to apply the model in practice. This study moves us closer to the goal of providing lapse prediction so that patients might receive more targeted and timely support.

Original language	English
Pages (from-to)	29-35
Number of pages	7
Journal	Journal of Substance Abuse Treatment
Volume	46
Issue number	1
DOIs	https://doi.org/10.1016/j.jsat.2013.08.004
State	Published - Jan 2014

Bibliographical note

Funding Information:
This study was funded by the U.S. National Institute on Alcohol Abuse and Alcoholism (NIAAA) grant R01 AA017192. The sponsors had no further role in the study design; in the collection, analysis, and/or interpretation of the data; in the writing of the report; or in the decision to submit the paper for publication. The content is solely the responsibility of the authors and does not necessarily represent the official views of the NIAAA or the National Institutes of Health. Preliminary results of this study have been presented as a poster in the 2011 Annual Symposium of American Medical Informatics Association.

Keywords

Alcoholism
Lapse prediction
MHealth
Machine learning
Relapse

ASJC Scopus subject areas

Psychiatric Mental Health
Medicine (miscellaneous)
Clinical Psychology
Psychiatry and Mental health

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/j.jsat.2013.08.004

Cite this

@article{5250f82eb8d1460f9b36bdd4a56c54dc,

title = "Predictive modeling of addiction lapses in a mobile health application",

abstract = "The chronically relapsing nature of alcoholism leads to substantial personal, family, and societal costs. Addiction-comprehensive health enhancement support system (A-CHESS) is a smartphone application that aims to reduce relapse. To offer targeted support to patients who are at risk of lapses within the coming week, a Bayesian network model to predict such events was constructed using responses on 2,934 weekly surveys (called the Weekly Check-in) from 152 alcohol-dependent individuals who recently completed residential treatment. The Weekly Check-in is a self-monitoring service, provided in A-CHESS, to track patients' recovery progress. The model showed good predictability, with the area under receiver operating characteristic curve of 0.829 in the 10-fold cross-validation and 0.912 in the external validation. The sensitivity/specificity table assists the tradeoff decisions necessary to apply the model in practice. This study moves us closer to the goal of providing lapse prediction so that patients might receive more targeted and timely support.",

keywords = "Alcoholism, Lapse prediction, MHealth, Machine learning, Relapse",

author = "Chih, {Ming Yuan} and Timothy Patton and McTavish, {Fiona M.} and Isham, {Andrew J.} and Judkins-Fisher, {Chris L.} and Atwood, {Amy K.} and Gustafson, {David H.}",

note = "Funding Information: This study was funded by the U.S. National Institute on Alcohol Abuse and Alcoholism (NIAAA) grant R01 AA017192. The sponsors had no further role in the study design; in the collection, analysis, and/or interpretation of the data; in the writing of the report; or in the decision to submit the paper for publication. The content is solely the responsibility of the authors and does not necessarily represent the official views of the NIAAA or the National Institutes of Health. Preliminary results of this study have been presented as a poster in the 2011 Annual Symposium of American Medical Informatics Association. ",

year = "2014",

month = jan,

doi = "10.1016/j.jsat.2013.08.004",

language = "English",

volume = "46",

pages = "29--35",

number = "1",

}

TY - JOUR

T1 - Predictive modeling of addiction lapses in a mobile health application

AU - Chih, Ming Yuan

AU - Patton, Timothy

AU - McTavish, Fiona M.

AU - Isham, Andrew J.

AU - Judkins-Fisher, Chris L.

AU - Atwood, Amy K.

AU - Gustafson, David H.

N1 - Funding Information: This study was funded by the U.S. National Institute on Alcohol Abuse and Alcoholism (NIAAA) grant R01 AA017192. The sponsors had no further role in the study design; in the collection, analysis, and/or interpretation of the data; in the writing of the report; or in the decision to submit the paper for publication. The content is solely the responsibility of the authors and does not necessarily represent the official views of the NIAAA or the National Institutes of Health. Preliminary results of this study have been presented as a poster in the 2011 Annual Symposium of American Medical Informatics Association.

PY - 2014/1

Y1 - 2014/1

N2 - The chronically relapsing nature of alcoholism leads to substantial personal, family, and societal costs. Addiction-comprehensive health enhancement support system (A-CHESS) is a smartphone application that aims to reduce relapse. To offer targeted support to patients who are at risk of lapses within the coming week, a Bayesian network model to predict such events was constructed using responses on 2,934 weekly surveys (called the Weekly Check-in) from 152 alcohol-dependent individuals who recently completed residential treatment. The Weekly Check-in is a self-monitoring service, provided in A-CHESS, to track patients' recovery progress. The model showed good predictability, with the area under receiver operating characteristic curve of 0.829 in the 10-fold cross-validation and 0.912 in the external validation. The sensitivity/specificity table assists the tradeoff decisions necessary to apply the model in practice. This study moves us closer to the goal of providing lapse prediction so that patients might receive more targeted and timely support.

AB - The chronically relapsing nature of alcoholism leads to substantial personal, family, and societal costs. Addiction-comprehensive health enhancement support system (A-CHESS) is a smartphone application that aims to reduce relapse. To offer targeted support to patients who are at risk of lapses within the coming week, a Bayesian network model to predict such events was constructed using responses on 2,934 weekly surveys (called the Weekly Check-in) from 152 alcohol-dependent individuals who recently completed residential treatment. The Weekly Check-in is a self-monitoring service, provided in A-CHESS, to track patients' recovery progress. The model showed good predictability, with the area under receiver operating characteristic curve of 0.829 in the 10-fold cross-validation and 0.912 in the external validation. The sensitivity/specificity table assists the tradeoff decisions necessary to apply the model in practice. This study moves us closer to the goal of providing lapse prediction so that patients might receive more targeted and timely support.

KW - Alcoholism

KW - Lapse prediction

KW - MHealth

KW - Machine learning

KW - Relapse

UR - http://www.scopus.com/inward/record.url?scp=84886775560&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84886775560&partnerID=8YFLogxK

U2 - 10.1016/j.jsat.2013.08.004

DO - 10.1016/j.jsat.2013.08.004

M3 - Article

C2 - 24035143

AN - SCOPUS:84886775560

SN - 0740-5472

VL - 46

SP - 29

EP - 35

JO - Journal of Substance Abuse Treatment

JF - Journal of Substance Abuse Treatment

IS - 1

ER -

Predictive modeling of addiction lapses in a mobile health application

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this