Published December 13, 2025 | Version v1

HYBRID AI MODEL INTEGRATING GENETIC, IMAGING, AND CLINICAL DATA FOR EARLY BREAST CANCER DETECTION

Description

We present a hybrid artificial intelligence (AI) approach for early breast cancer detection that jointly leverages genetic, imaging, and clinical data. The model comprises three modality-specific encoders (genetic, mammography/MRI/ultrasound, and structured clinical variables) whose embeddings are fused at the feature level and fed to a unified classifier. In a proof-of-concept evaluation on a multi-modal cohort, the hybrid model achieved ~0.93 ROC-AUC with ~94% sensitivity and ~88% specificity, outperforming single-modality baselines. We discuss design choices (fusion strategy, robustness to missing modalities), limitations (data availability, explainability), and directions for clinical integration.

Files

1 (10).pdf

Files (377.3 kB)

Name Size
md5:9029b3c4c03666c39615c179374516d6
377.3 kB Preview Download