Development of Machine Learning Models for Prediction of Smoking Cessation Outcome

Cheng-Chien Lai,Betty Chia-Chen Chang,Wei-Hsin Huang,Lee-Ching Hwang

doi:10.3390/ijerph18052584

Abstract

Predictors for success in smoking cessation have been studied, but a prediction model capable of providing a success rate for each patient attempting to quit smoking is still lacking. The aim of this study is to develop prediction models using machine learning algorithms to predict the outcome of smoking cessation. Data was acquired from patients underwent smoking cessation program at one medical center in Northern Taiwan. A total of 4875 enrollments fulfilled our inclusion criteria. Models with artificial neural network (ANN), support vector machine (SVM), random forest (RF), logistic regression (LoR), k-nearest neighbor (KNN), classification and regression tree (CART), and naïve Bayes (NB) were trained to predict the final smoking status of the patients in a six-month period. Sensitivity, specificity, accuracy, and area under receiver operating characteristic (ROC) curve (AUC or ROC value) were used to determine the performance of the models. We adopted the ANN model which reached a slightly better performance, with a sensitivity of 0.704, a specificity of 0.567, an accuracy of 0.640, and an ROC value of 0.660 (95% confidence interval (CI): 0.617–0.702) for prediction in smoking cessation outcome. A predictive model for smoking cessation was constructed. The model could aid in providing the predicted success rate for all smokers. It also had the potential to achieve personalized and precision medicine for treatment of smoking cessation.

Highlights

Cigarette smoking is an important global health issue [1] and is a well-known modifiable risk factor for many diseases including cancer, cardiovascular diseases, respiratory diseases, malfunction of the reproductive system, and many other organ systems [2]
Hyperparameters of the models were adjusted aggressively with experiments to achieve the best performance for the validation dataset
We constructed predictive models using seven different machine learning methods predict success rate of smoking cessation for seven currentdifferent smokers machine with datalearnIn our to study, wethe constructed predictive models using available at the first visit

Summary

Introduction

Cigarette smoking is an important global health issue [1] and is a well-known modifiable risk factor for many diseases including cancer, cardiovascular diseases, respiratory diseases, malfunction of the reproductive system, and many other organ systems [2]. It is estimated that smoking and exposure to secondhand smoke reduced life expectancy by 15 years [3]. Smoking cessation has been proven to be beneficial in many aspects of human health, including decreasing the risk of lung cancers, other cancers, heart attack, stroke, and chronic lung disease [4]. Within the first five years of smoking cessation [5]. More than one quarter of adult smokers are making attempts to quit smoking [6]. Assisting patients in quitting smoking is an important task for healthcare providers

Objectives

Methods

Results

Conclusion