| Autor: |
Vishali, P., Chandrasekaran, S., Viswanathan, K. K., Makhmudov, J. |
| Předmět: |
|
| Zdroj: |
AIP Conference Proceedings; 2024, Vol. 3244 Issue 1, p1-10, 10p |
| Abstrakt: |
Polycystic Ovary Syndrome (PCOS) stands as a significant health concern affecting women globally, characterized by hormonal imbalances and reproductive irregularities. Predicting the syndrome before it develops to critical stage, can reduce further health conditions. The important aspect of our research is to predict the syndrome using machine learning methods. We compared the accuracy of three Machine Learning methods namely Naive Bayes, Logistic Regression and Random Forest in predicting PCOS. Also, we evaluated measures like recall, precision, F1 score, specificity and ROC to validate the models' performance. We found Random Forest model as the most trustable method and dominated other two models in all aspects, demonstrating its capability in prediction of PCOS at earlier levels. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
