Integrating Genetic AI and Deep Learning for Breast Cancer Risk Prediction: A Multi-Model Approach

DOI

10.2991/978-94-6463-704-5_16How to use a DOI?

Keywords

Genetic AI (GAI); Deep Learning (DL); Genetic-Enhanced Deep Breast Cancer Risk Network (G-DBCRN); Convolutional Neural Networks (CNNs)

Abstract

Breast cancer is one of the most common causes of cancer death, and precise early risk evaluation is the key to improving patient prognosis. Here, we present a new genetic automated intelligence with deep learning (GAID) model integrating data from common female BRCA variants and iPROM measures, as well as high-resolution breast imaging to improve breast carcinoma risk prediction. The G-DBCRN, our model genetic-enhanced deep breast cancer risk network achieved overall of 92% accuracy, AUC of 0.94 as well as sensitivity and specificity at 89% and 90%, respectively.) The model performed robustly (mean AUC: 0.91) in populations with underrepresentation when evaluated across several demographic groups. Finally, interpretation analysis with SHAP values revealed important genetic markers and imaging features consistent with established clinical risk factors, indicating that the model can capture biologically meaningful information.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Kranti K. Dewangan
AU  - Satya Prakash Sahu
AU  - Rekh Ram Janghel
PY  - 2025
DA  - 2025/04/30
TI  - Integrating Genetic AI and Deep Learning for Breast Cancer Risk Prediction: A Multi-Model Approach
BT  - Proceedings of the International Conference on Smart Health and Intelligent Technologies (ICSHit-2024)
PB  - Atlantis Press
SP  - 211
EP  - 222
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-704-5_16
DO  - 10.2991/978-94-6463-704-5_16
ID  - Dewangan2025
ER  -