Gynecological disease prediction by machine learning
Department of CSE, Daffodil International University, Dhaka, Dhaka, Bangladesh.
Research Article
World Journal of Advanced Research and Reviews, 2024, 23(03), 2107–2112
Publication history:
Received on 08 August 2024; revised on 17 September 2024; accepted on 19 September 2024
Abstract:
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.
Keywords:
Gynecological disease; Machine learning; Data Analysis; Statistical Analysis
Full text article in PDF:
Copyright information:
Copyright © 2024 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0