Hybrid Machine Learning Model for Early Discovery and Prediction of Polycystic Ovary Syndrome

Female fertility is impaired by the medical disorder known as polycystic ovary syndrome (PCOS), which affects those who are of childbearing age or gradually past it. This medical condition raises the possibility of intricate long-term problems. Boosting and bagging algorithms provide exceptional rec...

Full description

Saved in:
Bibliographic Details
Published in2022 Second International Conference on Advanced Technologies in Intelligent Control, Environment, Computing & Communication Engineering (ICATIECE) pp. 1 - 8
Main Authors Swamy, Samatha R, K S, Nandini Prasad
Format Conference Proceeding
LanguageEnglish
Published IEEE 16.12.2022
Subjects
Bagging
Boosting
Feature selection
Machine Learning
Machine learning algorithms
Medical conditions
Medical domain
PCOS
Pediatrics
Predictive models
Psychology
Support vector machine classification
Tuning
Online AccessGet full text

Cover

More Information
Summary:Female fertility is impaired by the medical disorder known as polycystic ovary syndrome (PCOS), which affects those who are of childbearing age or gradually past it. This medical condition raises the possibility of intricate long-term problems. Boosting and bagging algorithms provide exceptional recognition capabilities, particularly in the medical field. Here, presenting the hybrid machine learning model, i.e. Hybrid classifier is developed by combining the Support Vector Machine, Random Forest, and XGboosting algorithms. In order to evaluate the best machine learning technique, the hybrid model is tested using a PCOS dataset that was obtained from the repository. Basic approaches for comparing the findings of various classifiers considered including Gradient Boosting, Random Forest, Logistic Regression, AdaBoosting, SVM, Decision Tree, and MLP were taken into consideration. The hybrid model is giving 93.8% of accuracy in discovering the PCOS at early stages.
DOI:10.1109/ICATIECE56365.2022.10047488