Literature DB >> 28110725

Classifying smoking urges via machine learning.

Antoine Dumortier1, Ellen Beckjord2, Saul Shiffman3, Ervin Sejdić4.   

Abstract

BACKGROUND AND
OBJECTIVE: Smoking is the largest preventable cause of death and diseases in the developed world, and advances in modern electronics and machine learning can help us deliver real-time intervention to smokers in novel ways. In this paper, we examine different machine learning approaches to use situational features associated with having or not having urges to smoke during a quit attempt in order to accurately classify high-urge states.
METHODS: To test our machine learning approaches, specifically, Bayes, discriminant analysis and decision tree learning methods, we used a dataset collected from over 300 participants who had initiated a quit attempt. The three classification approaches are evaluated observing sensitivity, specificity, accuracy and precision.
RESULTS: The outcome of the analysis showed that algorithms based on feature selection make it possible to obtain high classification rates with only a few features selected from the entire dataset. The classification tree method outperformed the naive Bayes and discriminant analysis methods, with an accuracy of the classifications up to 86%. These numbers suggest that machine learning may be a suitable approach to deal with smoking cessation matters, and to predict smoking urges, outlining a potential use for mobile health applications.
CONCLUSIONS: In conclusion, machine learning classifiers can help identify smoking situations, and the search for the best features and classifier parameters significantly improves the algorithms' performance. In addition, this study also supports the usefulness of new technologies in improving the effect of smoking cessation interventions, the management of time and patients by therapists, and thus the optimization of available health care resources. Future studies should focus on providing more adaptive and personalized support to people who really need it, in a minimum amount of time by developing novel expert systems capable of delivering real-time interventions.
Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Entities:  

Keywords:  Feature selection; Machine learning; Smoking cessation; Smoking urges; Supervised learning

Mesh:

Year:  2016        PMID: 28110725      PMCID: PMC5289882          DOI: 10.1016/j.cmpb.2016.09.016

Source DB:  PubMed          Journal:  Comput Methods Programs Biomed        ISSN: 0169-2607            Impact factor:   5.428


  14 in total

1.  Quitting smoking among adults--United States, 2001-2010.

Authors: 
Journal:  MMWR Morb Mortal Wkly Rep       Date:  2011-11-11       Impact factor: 17.586

Review 2.  Ecological momentary assessment.

Authors:  Saul Shiffman; Arthur A Stone; Michael R Hufford
Journal:  Annu Rev Clin Psychol       Date:  2008       Impact factor: 18.561

3.  Do smokers crave cigarettes in some smoking situations more than others? Situational correlates of craving when smoking.

Authors:  Michael S Dunbar; Deborah Scharf; Thomas Kirchner; Saul Shiffman
Journal:  Nicotine Tob Res       Date:  2010-02-04       Impact factor: 4.244

4.  A day at a time: predicting smoking lapse from daily urge.

Authors:  S Shiffman; J B Engberg; J A Paty; W G Perz; M Gnys; J D Kassel; M Hickcox
Journal:  J Abnorm Psychol       Date:  1997-02

5.  Point process analyses of variations in smoking rate by setting, mood, gender, and dependence.

Authors:  Saul Shiffman; Stephen L Rathbun
Journal:  Psychol Addict Behav       Date:  2011-09

6.  Relapse following smoking cessation: a situational analysis.

Authors:  S Shiffman
Journal:  J Consult Clin Psychol       Date:  1982-02

Review 7.  Smoking cessation intervention: an evidence-based approach.

Authors:  Rafael Laniado-Laborín
Journal:  Postgrad Med       Date:  2010-03       Impact factor: 3.840

Review 8.  Ecological momentary assessment (EMA) in studies of substance use.

Authors:  Saul Shiffman
Journal:  Psychol Assess       Date:  2009-12

9.  Understanding and using sensitivity, specificity and predictive values.

Authors:  Rajul Parikh; Annie Mathai; Shefali Parikh; G Chandra Sekhar; Ravi Thomas
Journal:  Indian J Ophthalmol       Date:  2008 Jan-Feb       Impact factor: 1.848

10.  Current cigarette smoking among adults - United States, 2005-2012.

Authors:  Israel T Agaku; Brian A King; Shanta R Dube
Journal:  MMWR Morb Mortal Wkly Rep       Date:  2014-01-17       Impact factor: 17.586

View more
  6 in total

1.  Using Elastic Net Penalized Cox Proportional Hazards Regression to Identify Predictors of Imminent Smoking Lapse.

Authors:  Robert Suchting; Emily T Hébert; Ping Ma; Darla E Kendzor; Michael S Businelle
Journal:  Nicotine Tob Res       Date:  2019-01-04       Impact factor: 4.244

2.  Towards a Smart Smoking Cessation App: A 1D-CNN Model Predicting Smoking Events.

Authors:  Maryam Abo-Tabik; Nicholas Costen; John Darby; Yael Benn
Journal:  Sensors (Basel)       Date:  2020-02-17       Impact factor: 3.576

3.  Predictors of perceived success in quitting smoking by vaping: A machine learning approach.

Authors:  Rui Fu; Robert Schwartz; Nicholas Mitsakakis; Lori M Diemert; Shawn O'Connor; Joanna E Cohen
Journal:  PLoS One       Date:  2022-01-14       Impact factor: 3.240

4.  Covariate adjustment of spirometric and smoking phenotypes: The potential of neural network models.

Authors:  Kirsten Voorhies; Ruofan Bie; John E Hokanson; Scott T Weiss; Ann Chen Wu; Julian Hecker; Georg Hahn; Dawn L Demeo; Edwin Silverman; Michael H Cho; Christoph Lange; Sharon M Lutz
Journal:  PLoS One       Date:  2022-05-11       Impact factor: 3.752

5.  Are Machine Learning Methods the Future for Smoking Cessation Apps?

Authors:  Maryam Abo-Tabik; Yael Benn; Nicholas Costen
Journal:  Sensors (Basel)       Date:  2021-06-22       Impact factor: 3.576

6.  Prediction of stress and drug craving ninety minutes in the future with passively collected GPS data.

Authors:  David H Epstein; Matthew Tyburski; William J Kowalczyk; Albert J Burgess-Hull; Karran A Phillips; Brenda L Curtis; Kenzie L Preston
Journal:  NPJ Digit Med       Date:  2020-03-04
  6 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.