Predicting the first smoking lapse during a quit attempt: A machine learning approach.
Just-in-time adaptive intervention
Machine learning
Smartphones
Smoking cessation
mHealth
Journal
Drug and alcohol dependence
ISSN: 1879-0046
Titre abrégé: Drug Alcohol Depend
Pays: Ireland
ID NLM: 7513587
Informations de publication
Date de publication:
01 01 2021
01 01 2021
Historique:
received:
28
03
2020
revised:
11
09
2020
accepted:
26
09
2020
pubmed:
24
10
2020
medline:
29
5
2021
entrez:
23
10
2020
Statut:
ppublish
Résumé
Just-in-time adaptive interventions (JITAI) aim to prevent smoking lapse using tailored support delivered via mobile technology in the moments when it is most needed. Effective smoking cessation JITAI rely on the development of accurate decision rules that determine when someone is most likely to lapse. The primary goal of the present study was to identify the strongest predictors of first lapse among smokers undergoing a quit attempt. Smokers attending a clinic-based smoking cessation program (n = 74) were asked to complete ecological momentary assessments five times daily on study-provided smartphones for 4 weeks post-quit. A three-stage modeling process utilized Cox proportional hazards regression to examine time to lapse a function of 31 predictors. First, univariate models evaluated the relationship between each predictor and time to lapse. Second, the elastic net machine learning algorithm was used to select the best predictors. Third, backwards elimination further reduced the set of predictors to optimize parsimony. Univariate models identified seven predictors significantly related to time to lapse. The elastic net algorithm retained five: perceived odds of smoking today, confidence in ability to avoid smoking, motivation to avoid smoking, urge to smoke, and cigarette availability. The reduced model demonstrated inadequate approximation to the non-penalized baseline model. Accurate estimation of moments of high risk for smoking lapse remains an important goal in the development of JITAI. These results demonstrate the utility of exploratory data-driven approaches to variable selection. The results of this study can inform future JITAI by highlighting targets for intervention.
Sections du résumé
BACKGROUND
Just-in-time adaptive interventions (JITAI) aim to prevent smoking lapse using tailored support delivered via mobile technology in the moments when it is most needed. Effective smoking cessation JITAI rely on the development of accurate decision rules that determine when someone is most likely to lapse. The primary goal of the present study was to identify the strongest predictors of first lapse among smokers undergoing a quit attempt.
METHODS
Smokers attending a clinic-based smoking cessation program (n = 74) were asked to complete ecological momentary assessments five times daily on study-provided smartphones for 4 weeks post-quit. A three-stage modeling process utilized Cox proportional hazards regression to examine time to lapse a function of 31 predictors. First, univariate models evaluated the relationship between each predictor and time to lapse. Second, the elastic net machine learning algorithm was used to select the best predictors. Third, backwards elimination further reduced the set of predictors to optimize parsimony.
RESULTS
Univariate models identified seven predictors significantly related to time to lapse. The elastic net algorithm retained five: perceived odds of smoking today, confidence in ability to avoid smoking, motivation to avoid smoking, urge to smoke, and cigarette availability. The reduced model demonstrated inadequate approximation to the non-penalized baseline model.
CONCLUSIONS
Accurate estimation of moments of high risk for smoking lapse remains an important goal in the development of JITAI. These results demonstrate the utility of exploratory data-driven approaches to variable selection. The results of this study can inform future JITAI by highlighting targets for intervention.
Identifiants
pubmed: 33092911
pii: S0376-8716(20)30505-6
doi: 10.1016/j.drugalcdep.2020.108340
pmc: PMC8496911
mid: NIHMS1639273
pii:
doi:
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
108340Subventions
Organisme : NCI NIH HHS
ID : P30 CA225520
Pays : United States
Organisme : NIDA NIH HHS
ID : R00 DA046564
Pays : United States
Informations de copyright
Copyright © 2020 Elsevier B.V. All rights reserved.
Références
Nicotine Tob Res. 2013 Oct;15(10):1651-4
pubmed: 23703731
J Med Internet Res. 2020 Mar 9;22(3):e16907
pubmed: 32149716
Addict Behav. 1990;15(2):105-14
pubmed: 2343783
Tob Prev Cessat. 2017 Apr 12;3:12
pubmed: 32432186
J Subst Abuse Treat. 2009 Apr;36(3):235-43
pubmed: 18715743
Front Behav Neurosci. 2018 May 07;12:89
pubmed: 29867390
MMWR Morb Mortal Wkly Rep. 2017 Jan 06;65(52):1457-1464
pubmed: 28056007
MMWR Recomm Rep. 1998 Oct 9;47(RR-18):v-xv, 1-16
pubmed: 9784089
Addiction. 1996 Dec;91(12):1797-802
pubmed: 8997761
Psychol Addict Behav. 2002 Dec;16(4):342-5
pubmed: 12503908
J Med Internet Res. 2016 Oct 17;18(10):e275
pubmed: 27751985
MMWR Morb Mortal Wkly Rep. 2005 Jul 1;54(25):625-8
pubmed: 15988406
J Affect Disord. 2018 Jul;234:276-281
pubmed: 29554616
Drug Alcohol Depend. 2007 Dec 1;91(2-3):159-68
pubmed: 17628353
Am J Public Health. 2004 Feb;94(2):269-78
pubmed: 14759942
BMC Public Health. 2010 Apr 27;10:211
pubmed: 20420707
Psychol Assess. 2009 Dec;21(4):486-97
pubmed: 19947783
J Abnorm Psychol. 2002 Nov;111(4):531-45
pubmed: 12428767
Nicotine Tob Res. 2016 May 28;19(3):379-383
pubmed: 27235703
J Consult Clin Psychol. 1996 Apr;64(2):366-79
pubmed: 8871421
Ann Behav Med. 2018 May 18;52(6):446-462
pubmed: 27663578
J Med Internet Res. 2016 Dec 12;18(12):e321
pubmed: 27956375
Nicotine Tob Res. 2014 Oct;16(10):1371-8
pubmed: 24893602
Am J Public Health. 1992 Jun;82(6):816-20
pubmed: 1585961
Stat Med. 2002 Dec 30;21(24):3803-22
pubmed: 12483768
Nicotine Tob Res. 2019 Jan 4;21(2):173-179
pubmed: 29059349
MMWR Morb Mortal Wkly Rep. 2018 Dec 07;67(48):1342-1346
pubmed: 30521502
Nicotine Tob Res. 2013 Nov;15(11):1883-91
pubmed: 23780705
MMWR Morb Mortal Wkly Rep. 2018 Nov 09;67(44):1225-1232
pubmed: 30408019
Public Health. 2003 Nov;117(6):383-8
pubmed: 14522152
Annu Rev Clin Psychol. 2008;4:1-32
pubmed: 18509902
Milbank Q. 2008 Dec;86(4):601-27
pubmed: 19120982