Impact of Tobacco Smoking on Health Care Utilization and Medical Costs in Chronic Obstructive Pulmonary Disease, Coronary Heart Disease and Diabetes

Economic burden of chronic obstructive pulmonary disease in Morocco: a cost of illness study

Chronic obstructive pulmonary disease (COPD) carries an important economic burden worldwide. However, the cost of this disease in Morocco is not well explored. This study aimed to estimate the economic cost associated with COPD in Morocco and identify its determinants. A cost-of-illness, prevalence-based study using a bottom-up approach method, including COPD patients, was carried out in 2021-2022. The cost was estimated from a societal perspective, and the time horizon was 1 year. Data collection was performed using a questionnaire including socio-demographic, clinical data, and utilization of health care resources in 2019: hospitalization, medical tests, medications, and medical visits. Direct health cost (DHC) was estimated by multiplying the use of health services by the official prices (unit costs) published by the National Agency for Health Insurance. The indirect cost (IC) represented by labor productivity losses was calculated using the human capital method. Costs were compared according to different sociodemographic and clinical factors. We included 159 patients; 82.4% were men, 80.4% were current or former smokers, and 78.7% were categorized as "high-risk" groups (grades C-D). The DHC was estimated at $1816.6 per patient per year. Pharmaceutical and hospitalization costs represented the highest part of the total DHC (42.5% and 22.1%, respectively). The IC was estimated at $709.5±1081.3 per patient per year. DHC increased with increasing disease severity and with the number of severe exacerbations (p<0.001). Current and former smokers were more costly to the healthcare system than nonsmokers (p=0.029). IC also increased with the number of severe exacerbations (p=0.003). In this study, we showed that COPD in Morocco generates important costs for the health system, mainly related to smoking and the severity of the disease. It is therefore important to strengthen tobacco control measures in our country.

Predicting total healthcare demand using machine learning: separate and combined analysis of predisposing, enabling, and need factors

OBJECTIVE

Predicting healthcare demand is essential for effective resource allocation and planning. This study applies Andersen's Behavioral Model of Health Services Use, focusing on predisposing, enabling, and need factors, using data from the 2022 Turkey Health Survey by TUIK. Machine learning methods provide a powerful approach to analyze these factors and their combined impact on healthcare utilization, offering valuable insights for health policy.

METHODS

Seven different machine learning models-Decision Tree, Random Forest, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Logistic Regression, XGBoost, and Gradient Boosting-were utilized. Feature selection was conducted to identify the most significant factors influencing healthcare demand. The models were evaluated for accuracy and generalization ability using performance metrics such as recall, precision, F1 score, and ROC AUC.

RESULTS

The study identified key features affecting healthcare demand. For predisposing factors, gender, educational level, and age group were significant. Enabling factors included treatment costs, community interest, and payment difficulties. Need factors were influenced by smoking status, chronic diseases, and overall health status. The models demonstrated high recall (approximately 0.90) and strong F1 scores (ranging from 0.87 to 0.88), indicating a balanced performance between precision and recall. Among the models, Gradient Boosting, XGBoost, and Logistic Regression consistently outperformed others, achieving the highest predictive accuracy. Random Forest and SVM also performed well, showing robust classification capability.

CONCLUSIONS

The findings highlight the effectiveness of machine learning methods in predicting healthcare demand, providing valuable insights for health policy and resource allocation. Gradient Boosting, XGBoost, and Logistic Regression emerged as the most reliable models, demonstrating superior generalization and classification performance. Understanding the separate and combined effects of predisposing, enabling, and need factors on healthcare demand can contribute to more efficient and data-driven healthcare planning, facilitating strategic decision-making in resource allocation and service delivery.

The association between cigarette smoking and health care service utilization among middle-aged and elderly adults in China

Objective

To assess the associations between tobacco use and health care service utilization in Chinese individuals aged more or equal to 40 years old.

Method

This research was a cross-sectional study using data from eight provinces in China, and the final sample consisted of 4,733 observations (4,749 participants) aged more or equal to 40 years old. The dependent variable was health care utilization measured by outpatient and inpatient service utilization. Descriptive statistics were used to summarize the socio-demographic characteristics of the sample according to smoking status. The association between tobacco use and health care service utilization was examined by an instrumental variable (IV) probit model.

Results

Of the respondents interviewed in 2020, 3,116 (65.84%) were never smokers, 654 (13.82%) were smokers with the smoking index (SI) <400, and 963(20.34%) were smokers with SI≥400. Smokers with SI <400 reported a 6.80% higher probability of using outpatient services. Smokers with SI <400 and SI≥400 reported a 3.10 and 4.20% higher average probability of using ≥3 outpatient visits than never smokers, respectively. Additionally, smokers with SI <400 and SI≥400 reported a 6.30 and 6.20% higher average probability of using inpatient services than those who had not smoked. Moreover, smokers with SI≥400 were more likely to have had ≥2 hospital visits than nonsmokers.

Conclusions

Smokers make greater use of health care services. Control of smoking may ease the burden of related health care utilization.