Machine Learning Models for Predicting Smoking-Related Health Decline and Disease Risk

2025-11-18

AI Summary

Delayed diagnosis of smoking-related health conditions remains a critical clinical challenge due to insufficient early warning systems. Method: Leveraging a large-scale cross-sectional dataset of 55,691 routine health examinations, we developed an interpretable machine learning framework focused on key biomarkers—including blood pressure, triglycerides, hepatic enzymes, and serum creatinine—to identify high-risk individuals. We integrated SHAP (Shapley Additive Explanations) for model interpretability to support clinical decision-making and systematically benchmarked Random Forest, XGBoost, and LightGBM. Results: Random Forest achieved the highest performance (AUC = 0.926). The framework enables non-invasive, low-cost detection of subclinical health deterioration attributable to smoking during standard physical examinations, offering a deployable AI tool for public health screening and timely preventive interventions.

Technology Category

• Machine Learning: Transparent, Interpretable, Explainable ML
• Humans and AI: Explainable AI (XAI) for Human Understanding
• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Smoking continues to be a major preventable cause of death worldwide, affecting millions through damage to the heart, metabolism, liver, and kidneys. However, current medical screening methods often miss the early warning signs of smoking-related health problems, leading to late-stage diagnoses when treatment options become limited. This study presents a systematic comparative evaluation of machine learning approaches for smoking-related health risk assessment, emphasizing clinical interpretability and practical deployment over algorithmic innovation. We analyzed health screening data from 55,691 individuals, examining various health indicators, including body measurements, blood tests, and demographic information. We tested three advanced prediction algorithms - Random Forest, XGBoost, and LightGBM - to determine which could most accurately identify people at high risk. This study employed a cross-sectional design to classify current smoking status based on health screening biomarkers, not to predict future disease development. Our Random Forest model performed best, achieving an Area Under the Curve (AUC) of 0.926, meaning it could reliably distinguish between high-risk and lower-risk individuals. Using SHAP (SHapley Additive exPlanations) analysis to understand what the model was detecting, we found that key health markers played crucial roles in prediction: blood pressure levels, triglyceride concentrations, liver enzyme readings, and kidney function indicators (serum creatinine) were the strongest signals of declining health in smokers.

Problem

• Machine learning models predict smoking-related health decline using biomarkers
• Early detection of smoking risks missed by current screening methods
• Identifying key health indicators for smoking-related disease risk assessment

Innovation

• Random Forest model achieved 0.926 AUC for risk classification
• SHAP analysis identified key biomarkers for clinical interpretability
• Compared three ML algorithms using health screening data