A Hybrid Algorithm of ML and XAI to Prevent Breast Cancer: A Strategy to Support Decision Making
Open Access
Abstract
Worldwide, the coronavirus has intensified the management problems of health services, significantly harming patients. Some of the most affected processes have been cancer patients’ prevention, diagnosis, and treatment. Breast cancer is the most affected, with more than 20 million cases and at least 10 million deaths by 2020. Various studies have been carried out to support the management of this disease globally. This paper presents a decision support strategy for health teams based on machine learning (ML) tools and explainability algorithms (XAI). The main methodological contributions are: first, the evaluation of different ML algorithms that allow classifying patients with and without cancer from the available dataset; and second, an ML methodology mixed with an XAI algorithm, which makes it possible to predict the disease and interpret the variables and how they affect the health of patients. The results show that first, the XGBoost Algorithm has a better predictive capacity, with an accuracy of 0.813 for the train data and 0.81 for the test data; and second, with the SHAP algorithm, it is possible to know the relevant variables and their level of significance in the prediction, and to quantify the impact on the clinical condition of the patients, which will allow health teams to offer early and personalized alerts for each patient.Keywords
Funding Information
- Chilean National Agency of Research and Development (2021-21211244, 2018-21182013)
- PFCHA/Doctorado Becas Chile (2021-21211244, 2018-21182013)
This publication has 99 references indexed in Scilit:
- A support vector machine-based ensemble algorithm for breast cancer diagnosisEuropean Journal of Operational Research, 2018
- Machine Learning with Applications in Breast Cancer Diagnosis and PrognosisDesigns, 2018
- Research on Logistic Regression Algorithm of Breast Cancer Diagnose Data by Machine Learning2018
- Risk Factors of Breast Cancer in Women: A New Evidence from Surakarta, Central Java, Indonesia2018
- Use of FDG-PET or PET/CT to detect recurrent colorectal cancer in patients with elevated CEA: a systematic review and meta-analysisInternational Journal of Colorectal Disease, 2013
- Use of Data Mining Techniques to Determine and Predict Length of Stay of Cardiac PatientsHealthcare Informatics Research, 2013
- Multiparametric Magnetic Resonance Imaging and Ultrasound Fusion Biopsy Detect Prostate Cancer in Patients with Prior Negative Transrectal Ultrasound BiopsiesJournal of Urology, 2012
- Development of Novel Breast Cancer Recurrence Prediction Model Using Support Vector MachineJournal of Breast Cancer, 2012
- Triple negative breast cancer cell lines: One tool in the search for better treatment of triple negative breast cancerBreast Disease, 2011
- Machine learning techniques to diagnose breast cancer2010