Explainable Artificial Intelligence Models for Breast Cancer Prediction Using Shap and Boosting Algorithms

View at publisher Summarise with VIRAT
Authors: T.Chitra Devi, P. Sathish Kumar, K.K.Arun Prasad, R. Sahana
Cited by: 0
References: 19

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Despite Several Decades Of Research On Breast Cancer, It Has Remained One Of The Most Lethal Types Of Cancer Among Women Over The Years And Highlights The Importance Of Achieving High-Accuracy And Explainable Results In Machine Learning Models. This Research Presents A Meticulous Yet Explainable Machine Learning Model That Predicts Breast Cancer Based On The Wisconsin Breast Cancer Dataset (WBCD), Which Not Only Demonstrates High Accuracy In Breast Cancer Predictions But Also Identifies Topological Features In Breast Cancer Predictions With Significant Model-Prediction Accuracy. Pearson's Correlation Heat Maps Confirmed That Morphological Features Of Significance Related To Tumour Size And Boundaries Are Significantly Correlated With Each Other. Based On Benign And Malignant Correlation Graphs Of Patients, The Developed Model Was Capable Of Identifying Topological Features Related To Prime Factors Determining Model-Prediction Accuracy In Breast Cancer That Vary In Cohorts. Model Explanations Of High-Prediction Accuracy In Breast Cancer Predictions Based On The LIME Model Provided Key Factors That Significantly Influence Malignant Models Of Breast Cancer Predictions Related To Area, Perimeter, Radius, And Concavity. This Was Shown To Have The Same Predictive Accuracy As The Best State-Of-The-Art Explainable AI Models Between The Years Of 2020 And 2025 While Remaining Explainable. In Sum, The Efficiency Of The Methodologies Of Statistical Approaches, Network Analysis, And Explainable AI To Make An Accurate Classification Of Breast Cancer Is Emphasised, And It Provides A Good Foundation For Possible Extensions In The Future.

Fields of Study & Subjects

Artificial Intelligence in Healthcare AI in cancer detection Explainable Artificial Intelligence (XAI)

Publication details

Journal / source
International Conference on Communication, Computing and Electronics Systems (ICCCES)
Pages
1–9
Publication date
21 January 2026
Language
EN