Data-Driven Approaches to Smoking Cessation Unraveling Predictors of Quitting through Machine Learning

Abstract

In order to define the usefulness of machine learning in this domain and to pinpoint the machine learning techniques that have been used, a comprehensive review of the literature has been conducted. Multiple searches in MEDLINE, Science Citation Index, Social Science Citation Index, EMBASE, CINAHL Plus, APA PsycINFO, PubMed, Cochrane Central Register of Controlled Trials, and IEEE Xplore were conducted for the current study through December 9, 2022. Studies reporting cigarette smoking cessation results (smoking status and cigarette consumption) as well as a variety of experimental designs (such as cross-sectional and longitudinal) were considered as inclusion criteria. The effectiveness of behavioral markers, biomarkers, and other predictors was evaluated as a predictor of smoking cessation outcomes. Twelve papers were found in our systematic review that met our inclusion criteria. This review includes.