Cardiovascular disease continues to be a significant worldwide health issue, where early detection is essential due to the frequently asymptomatic beginning of heart attacks. This research presents a model for predicting the risk of heart disease utilizing the Random Forest (RF) algorithm, trained on clinical data obtained from Zheen Hospital in Erbil, Iran. The data can be found online through the Mendeley Data website. The Synthetic Minority Oversampling Technique (SMOTE) was used to fix the problem of uneven class sizes, and Shapley Additive Explanations (SHAP) were used to explain how the model made its predictions. The RF model, improved with the best settings and evaluated with the F1-score, achieved impressive results, which are more than 99% for training, validation, and testing data. These results underscore its capacity to discover minority class patterns, crucial for recognizing rare yet significant occurrences. SHAP analysis identified troponin, creatine kinase-MB, and age as the primary predictors. The new idea is not just about individual methods but how they work together for predicting cardiovascular disease, especially by making AI easier to understand and dealing with uneven data using real clinical information. The subsequent study will aim to enhance robustness and generalizability across diverse patient populations.
Jaringan kolaborasi para penulis
8 penulis ·
10 tautan kepenulisan bersama
Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.
Islamic University of Indonesia
Organisasi berbeda
Organisasi sama
Afiliasi tidak diketahui
Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.