Predictive Analysis for Cardiovascular Outcomes Using Ai

Background Cardiovascular diseases (CVD) continue to be one of the leading causes of deaths globally meaning that risk evaluation and predictive efforts need to start early to ensure proper management is done. The goal of this study is to conduct quantitative predictive analysis to find key predictive risk factors with the aid of machine learning models in hopes of improving cardiovascular outcomes. Methods A cross-sectional survey design was employed by reaching out to 273 respondents through a standardized questionnaire. Together with demographic factors, lifestyle, and medical history information about the respondents that is relevant to the risk of CVD was collected as well. Other tests that were performed include normality tests (Shapiro-Wilk), reliability tests (Cronbach’s Alpha), and correlational tests. The data was predictively modeled using Logistic Regression, Random Forest, and Decision Tree classifier models evaluated based on accuracy, precision, recall, and F1 score. Results The normality test proved that the continuous variables of height, weight, and BMI do indeed support and conform to a normal distribution. The test also suggests there is a low internal consistency which is led by the low Cronbach’s alpha value of 0.037 meaning that cardiovascular risk assessment is multidimensional. The results of predictive modeling were overall relatively low and failed to be predicted reliably but random forest achieved the highest performance as expected (accuracy: 16.36%) though was still much too low. Class imbalance and lack of predictive features are likely causes of model performance. Conclusion The results underscore the difficulties associated with estimating cardiovascular outcomes with the traditional machine learning models. The study points out that incorporating advanced feature selection, bigger datasets, and more sophisticated AI tools like deep learning and real-time information from wearables is essential. Although these models are imperfect, AI-based predictive analytics provide a chance for integrating early cardiovascular disease risk stratification and tailored interventions in medicine. More work needs to be done in preprocessing the data, class imbalance, and ensemble techniques to improve the accuracy of predictions and effectiveness in clinical medicine