Gynecological disease prediction by machine learning

The rapid change in climate affects the ecosystem of animal life worldwide. The consumption of processed foods and excess pesticides on crops create different difficulties for the human body. Nowadays especially girls are suffering from various kinds of gynecological diseases. Miscarriage and Anemia are very common among them. Machine learning algorithms are well-liked and widely used for disease forecasting. The detailed information we obtained from the survey established the data set. To predict gynecological diseases, we utilized 5 machine learning algorithms. Three of them are statistical based like Decision Tree, K- Nearest Neighbor (KNN), and Naive Bayes classifier and 2 are hybrid modeling like Decision tree and SVM(DT&SVM), Random Forest, and Naïve Bayes (RF&NB). We took into account the top algorithm for gynecological illness prediction, according to the correct interpretation. The best results were obtained by the Decision Tree ensemble and Naïve Bayes out of all the algorithms, with an accuracy of 86.30% and a Recall score of 87.15%.  Thanks to the top completion method, our model has excellent gynecological illness prediction capabilities.