Optimizing cardiovascular disease mortality prediction: a super learner approach in the tehran lipid and glucose study.

BACKGROUND & AIM: Cardiovascular disease (CVD) is the most important cause of death in the world and has a potential impact on health care costs, this study aimed to evaluate the performance of machine learning survival models and determine the optimum model for predicting CVD-related mortality. METHOD: In this study, the research population was all participants in Tehran Lipid and Glucose Study (TLGS) aged over 30 years. We used the Gradient Boosting model (GBM), Support Vector Machine (SVM), Super Learner (SL), and Cox proportional hazard (Cox-PH) models to predict the CVD-related mortality using 26 features. The dataset was randomly divided into training (80%) and testing (20%). To evaluate the performance of the methods, we used the Brier Score (BS), Prediction Error (PE), Concordance Index (C-index), and time-dependent Area Under the Curve (TD-AUC) criteria. Four different clinical models were also performed to improve the performance of the methods. RESULTS: Out of 9258 participants with a mean age of (SD; range) 43.74 (15.51; 20-91), 56.60% were female. The CVD death proportion was 2.5% (228 participants). The death proportion was significantly higher in men (67.98% M, 32.02% F). Based on predefined selection criteria, the SL method has the best performance in predicting CVD-related mortality (TD-AUC > 93.50%). Among the machine learning (ML) methods, The SVM has the worst performance (TD-AUC = 90.13%). According to the relative effect, age, fasting blood sugar, systolic blood pressure, smoking, taking aspirin, diastolic blood pressure, Type 2 diabetes mellitus, hip circumference, body mss index (BMI), and triglyceride were identified as the most influential variables in predicting CVD-related mortality. CONCLUSION: According to the results of our study, compared to the Cox-PH model, Machine Learning models showed promising and sometimes better performance in predicting CVD-related mortality. This finding is based on the analysis of a large and diverse urban population from Tehran, Iran.

Water pipe smoking and stroke: A systematic review and meta-analysis.

OBJECTIVE: Despite the damaging effects of water pipe on physical health, there is little information about the potential harmful effects of this tobacco on stroke. This study aims to investigate the relationship between water pipe smoking and stroke. METHOD: A systematic review was conducted including Ovid SP, Embase, Pubmed, Web of Science, Scopus, and Google Scholar databases with focus on cohort, case-control, and cross-sectional studies. We reviewed all studies reporting on water pipe smoking and stroke. The funnel plot and the Egger regression test were used to assess publication bias. RESULTS: In the four eligible studies, there were a total of 2759 participants that 555 patients had at least once experienced stroke. Meta-analysis revealed positive association between water pipe smoking and stroke with pooled adjusted OR 2.79 (95% CI: 1.74-3.84; I 2 = 0 , p = . 741 ${I^2}\; = \;\;0,{\mathrm{\;}}p\;\; = {\mathrm{\;\;}}.741$ ) and the funnel plot shows asymmetry publication bias. CONCLUSIONS: We found a higher effect of water pipe smoking on stroke compared to cigarette smoking and concluded that water pipe increases the risk of stroke by 2.79. Hence, because most of the water pipe consumer society is young, especially women, policies and decisions need to be taken to control the supply of this tobacco to the market and more provide education on the health problem of water pipe smoking. IMPLICATIONS: This study provides a higher effect of water pipe smoking on stroke. Physicians and researchers who intend to study in the field of stroke should better examine the effects of water pipe (including time of use, dose-response, long-term effects, and risk factors) on stroke.

Zero-Inflated Count Regression Models in Solving Challenges Posed by Outlier-Prone Data; an Application to Length of Hospital Stay.

Introduction: Ignoring outliers in data may lead to misleading results. Length of stay (LOS) is often considered a count variable with a high frequency of outliers. This study exemplifies the potential of robust methodologies in enhancing the accuracy and reliability of analyses conducted on skewed and outlier-prone count data of LOS. Methods: The application of Zero-Inflated Poisson (ZIP) and robust Zero-Inflated Poisson (RZIP) models in solving challenges posed by outlier LOS data were evaluated. The ZIP model incorporates two components, tackling excess zeros with a zero-inflation component and modeling positive counts with a Poisson component. The RZIP model introduces the Robust Expectation-Solution (RES) algorithm to enhance parameter estimation and address the impact of outliers on the model's performance. Results: Data from 254 intensive care unit patients were analyzed (62.2% male). Patients aged 65 or older accounted for 58.3% of the sample. Notably, 38.6% of patients exhibited zero LOS. The overall mean LOS was 5.89 (± 9.81) days, and 9.45% of cases displayed outliers. Our analysis using the RZIP model revealed significant predictors of LOS, including age, underlying comorbidities (p<0.001), and insurance status (p=0.013). Model comparison demonstrated the RZIP model's superiority over ZIP, as evidenced by lower Akaike information criteria (AIC) and Bayesians information criteria (BIC) values. Conclusions: The application of the RZIP model allowed us to uncover meaningful insights into the factors influencing LOS, paving the way for more informed decision-making in hospital management.

Application of Mixture Cure with the Doubly Censoring Model in Estimation of Initiation Age and Prevalence of Water-Pipe Smoking in Iran: a New Approach in Population-Based Studies.

BACKGROUND: The initiation age and prevalence of smoking water-pipe are two important parameters for establishing preventive policies. Thus, the present study was conducted to introduce a new approach for estimating and evaluating the effect of demographic variables on the initiation age and prevalence of smoking water-pipe. MATERIALS AND METHODS: The STEPwise approach for non-communicable disease risk factors surveillance (STEPS) 2011 data were used and daily smokers and non-smokers with the age range of 16 to 70 years were included in the study. A survival mixture cure rate model with doubly censoring was used. RESULTS: Totally, 9764 individuals were enrolled in the study. No significant association was observed between the initiation age and gender (HR=1.07, 95% CI: 0.76, 1.58), whereas there was a significant difference between initiation age and area of residence (HR=0.62, 95% CI: 0.44, 0.88). The mean age of starting smoking was 25.82 years (95% CI: 24.13, 27.63). The odds of smoking in men were higher than in women (OR=2.34, 95% CI: 1.79, 3.7). The prevalence of smoking had a significant association with socioeconomic status (OR=0.84, 95% CI: 0.72, 0.97), but no association with the level of education (OR=1.06, 95% CI: 0.97, 1.15) and place of residence (OR=1.2, 95% CI: 0.93, 1.57) was found. The estimated prevalence of smoking water-pipe in total, men, and women was 4.8% (95% CI: 4.19%, 5.51%), 7.77% (95% CI: 6.76%, 8.86%), and 3.47% (95% CI: 2.8%, 4.25%). CONCLUSION: A new statistical methodology was applied to estimate and evaluate the effect of demographic variables on the initiation age and prevalence of water-pipe smoking.