پیوندهای مفید
آمار
| تعداد نشریات | 20 |
| تعداد شمارهها | 1,247 |
| تعداد مقالات | 11,352 |
| تعداد مشاهده مقاله | 81,441,227 |
| تعداد دریافت فایل اصل مقاله | 116,906,836 |
Enhancing Clinical Reliability in Coronary Artery Disease (CAD) Diagnosis: A Hybrid Machine Learning Approach Utilizing Genetic Algorithm-Optimized AdaBoost Decision Trees | ||
| Health Management & Information Science | ||
| مقالات آماده انتشار، پذیرفته شده، انتشار آنلاین از تاریخ 14 دی 1404 | ||
| نوع مقاله: Original Article | ||
| شناسه دیجیتال (DOI): 10.30476/jhmi.2026.109799.1341 | ||
| نویسندگان | ||
| Parisa Eslami* 1؛ Narges Mahmoudi2 | ||
| 1Clinical Education Research Center, Health Human Resources Research Center, School of Health Management and Information Sciences, Shiraz University of Medical Sciences, Shiraz, Iran | ||
| 2School of Health Management and Information Sciences, Isfahan University of Medical Sciences, Isfahan, Iran | ||
| چکیده | ||
| Abstract Background: Accurate and reliable diagnosis of coronary artery disease (CAD) is critical, requiring predictive models that minimize classification errors, particularly False Positives (FPs), due to high clinical costs. This study aimed to identify an optimized classifier with maximal predictive reliability using the Z-Alizadeh Sani dataset. Method: The methodology employed a dual-stage feature selection process comparing the Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). The Synthetic Minority Over-Sampling Technique (SMOTE) was subsequently applied to mitigate class imbalance. Models were evaluated using a strict performance criterion that considered a comprehensive set of metrics—including Sensitivity, Accuracy, and the Area Under the Receiver Operating Characteristic curve (AUC). Results: The proposed hybrid model, GA + AdaBoost Decision Tree, demonstrated the highest overall predictive reliability. It achieved an accuracy of 95.88% and an exceptionally high Specificity of 98.08%, significantly surpassing comparable high-accuracy models in the literature. Furthermore, the model achieved a robust AUC of 0.972. Conclusion: The model offers a clinically superior diagnostic tool, with a low false-positive rate, ensuring highly reliable patient screening. This work successfully establishes a new benchmark for reliable CAD diagnosis by prioritizing clinical safety through optimized specificity. | ||
| کلیدواژهها | ||
| Cardiovascular disease؛ Coronary artery disease؛ Machine learning؛ Genetic algorithm؛ Decision Trees | ||
|
آمار تعداد مشاهده مقاله: 5 |
||