Details of Research Outputs

Background: The pr ognosis of br east cancer is often unfav ora b le, emphasizing the need for early metastasis risk detection and accu- rate tr eatment pr edictions. This study aimed to dev elop a nov el m ulti-modal dee p learning model using pr eoperati v e data to pr edict disease-fr ee survi v al ( DFS ) . Methods: We r etr ospecti v el y collected pathology imaging, molecular and clinical data from The Cancer Genome Atlas and one independent institution in China. We developed a novel Deep Learning Clinical Medicine Based Pathological Gene Multi-modal ( Dee pClinMed-PGM ) model for DFS pr ediction, inte gr ating clinicopathological data with molecular insights. The patients included the training cohort ( n = 741 ) , internal validation cohort ( n = 184 ) , and external testing cohort ( n = 95 ) . Result: Inte gr ating multi-modal data into the DeepClinMed-PGM model significantly improved area under the receiver operating c har acteristic curve ( AUC ) values. In the training cohort, AUC values for 1-, 3-, and 5-year DFS predictions increased to 0.979, 0.957, and 0.871, while in the external testing cohort, the v alues r eached 0.851, 0.878, and 0.938 for 1-, 2-, and 3-year DFS pr edictions, r especti v el y. The DeepClinMed-PGM's robust discriminative capabilities were consistently evident across various cohorts, including the training cohort [hazard ratio ( HR ) 0.027, 95% confidence interval ( CI ) 0.0016-0.046, P < 0.0001], the internal validation cohort ( HR 0.117, 95% CI 0.041-0.334, P < 0.0001 ) , and the external cohort ( HR 0.061, 95% CI 0.017-0.218, P < 0.0001 ) . Additionally, the DeepClinMed-PGM model demonstrated C-index values of 0.925, 0.823, and 0.864 within the three cohorts, respectively. Conclusion: This study introduces an approach to breast cancer prognosis, inte gr ating imaging and molecular and clinical data for enhanced pr edicti v e accuracy, offering pr omise for personalized tr eatment str ate gies.