A Novel Risk-Scoring System to Identify the Potential Population Benefiting From Adjuvant Chemotherapy for Node-Negative TNBC Patients With Tumor Size Less Than 1 cm

Personalized chemotherapy selection for patients with triple-negative breast cancer using deep learning

Background

Potential uncertainties and overtreatment exist in adjuvant chemotherapy for triple-negative breast cancer (TNBC) patients.

Objectives

This study aims to explore the performance of deep learning (DL) models in personalized chemotherapy selection and quantify the impact of baseline characteristics on treatment efficacy.

Methods

Patients who received treatment recommended by models were compared to those who did not. Overall survival for treatment according to model recommendations was the primary outcome. To mitigate bias, inverse probability treatment weighting (IPTW) was employed. A mixed-effect multivariate linear regression was employed to visualize the influence of certain baseline features of patients on chemotherapy selection.

Results

A total of 10,070 female TNBC patients met the inclusion criteria. Treatment according to Self-Normalizing Balanced (SNB) individual treatment effect for survival data model recommendations was associated with a survival benefit (IPTW-adjusted hazard ratio: 0.53, 95% CI, 0.32-8.60; IPTW-adjusted risk difference: 12.90, 95% CI, 6.99-19.01; IPTW-adjusted the difference in restricted mean survival time: 5.54, 95% CI, 1.36-8.61), which surpassed other models and the National Comprehensive Cancer Network guidelines. No survival benefit for chemotherapy was seen for patients not recommended to receive this treatment. SNB predicted older patients with larger tumors and more positive lymph nodes are the optimal candidates for chemotherapy.

Conclusion

These findings suggest that the SNB model may identify patients with TNBC who could benefit from chemotherapy. This novel analytical approach may provide debiased individual survival information and treatment recommendations. Further research is required to validate these models in clinical settings with more features and outcome measurements.

Survival Contradiction in Stage II, IIIA, And IIIB Colon Cancer: A Surveillance, Epidemiology, and End Result-Based Analysis

There exists an inconsistency between stage and survival in the current American Joint Committee on Cancer (AJCC) staging system for colon cancer. In this study, we compared the clinicopathological characteristics and prognosis of colon cancer patients with stage II, IIIA, and IIIB disease based on the surveillance, epidemiology, and end results (SEER) database. Kaplan-Meier analysis was used to generate overall survival (OS) and cancer-specific survival (CSS) curves. The Cox regression was employed to identify risk factors. The competing risk model was completed by the cumulative incidence function and Gray's test. In the final population of 31,361 colon cancer patients, Kaplan-Meier curve analysis showed that stage IIIA had the highest OS and CSS, followed by stage IIA and IIIB, and IIB and IIC showed the worst OS and CSS. In the Cox model, the stage was proven to be an independent prognostic factor. In the competing risk model, stage IIIA colon cancer patients had the lowest 5-year cancer-specific death rate in stages II, IIIA, and IIIB. In conclusion, the prognosis of colon cancer patients in stage IIA was worse than that of patients in stage IIIA, while the survival rate of stage IIB and IIC was lower than that of stage IIIB.