Related Experiment Video
Updated: Jul 3, 2025
07:15
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
6.8K
Screening ovarian cancer by using risk factors: machine learning assists
1Department of Health Information Management, Student Research Committee, School of Health Management and Information Sciences Branch, Iran University of Medical Sciences, Tehran, Iran. raoof.n1370@gmail.com.
Biomedical Engineering Online
|February 12, 2024
Summary
Machine learning models can effectively screen high-risk ovarian cancer (OC) groups. The XG-Boost algorithm demonstrated the highest predictive accuracy, offering a promising tool for early detection and prevention strategies.
Area of Science:
- Oncology
- Medical Informatics
- Data Science
Background:
- Ovarian cancer (OC) is a significant public health concern due to its prevalence and aggressive nature.
- Lack of effective preventive strategies contributes to high morbidity and mortality rates.
- Risk prediction through screening offers a potential avenue for OC prevention.
Purpose of the Study:
- To leverage machine learning (ML) for developing predictive models to identify high-risk groups for ovarian cancer.
- To provide practical screening solutions for ovarian cancer prevention.
Main Methods:
- Retrospective analysis of 1516 suspicious ovarian cancer cases from six clinical settings (2015-2019).
- Development and comparison of six ML algorithms: XG-Boost, Random Forest, J-48, SVM, KNN, and ANN.
- Evaluation of model performance using the Area Under the Receiver Operating Characteristic Curve (AU-ROC).
Main Results:
- The XG-Boost model achieved the highest predictive performance for ovarian cancer.
- XG-Boost demonstrated an AU-ROC of 0.93 (95% CI [0.91-0.95]).
Conclusions:
- Machine learning approaches show significant predictive power and interoperability for ovarian cancer screening.
- ML-driven risk stratification can facilitate targeted preventive strategies for high-risk individuals.
