Background/Objectives: Accurate and accessible perioperative health information empowers patients and enhances recovery outcomes. Artificial intelligence tools, such as ChatGPT, have garnered attention for their potential in health communication. This study evaluates the accuracy and readability of responses generated by ChatGPT to questions commonly asked about breast cancer. Methods: Fifteen simulated patient queries about breast cancer surgery preparation and recovery were prepared. Responses generated by ChatGPT (4o version) were evaluated for accuracy by a pool of breast surgeons using a 4-point Likert scale. Readability was assessed with the Flesch–Kincaid Grade Level (FKGL). Descriptive statistics were used to summarize the findings. Results: Of the 15 responses evaluated, 11 were rated as “accurate and comprehensive”, while 4 out of 15 were deemed “correct but incomplete”. No responses were classified as “partially incorrect” or “completely incorrect”. The median FKGL score was 11.2, indicating a high school reading level. While most responses were technically accurate, the complexity of language exceeded the recommended readability levels for patient-directed materials. Conclusions: The model shows potential as a complementary resource for patient education in breast cancer surgery, but should not replace direct interaction with healthcare providers. Future research should focus on enhancing language models’ ability to generate accessible and patient-friendly content.

Triple negative breast cancer (TNBC) is historically defined as oestrogen receptor (ER) < 1% and HER2-negative. Increasing evidence supports that ER-low breast cancer (BC) (ER 1-10%) shares similar clinical behaviour and biology with classic TNBC. However, how ER cut-off definitions have been applied as eligibility criteria in clinical trials for TNBC over time remains unclear. In August 2024, the Clinicaltrials.gov database was systematically queried using the following string: "breast cancer" AND "interventional studies" AND "phase II-III-not applicable". We included trials started from January, 1, 2010 to August, 7, 2024 restricted to TNBC, using either ER<1% or any other ER cut-off up to 10%. Differences across study descriptors were assessed using Mann-Whitney U and χ² tests. A total of 6747 studies were retrieved. Of 620 eligible trials, 474 (76.5%) restricted the inclusion to TNBC and 146 (23.5%) included ER-low tumours. The percentage of trials allowing ER-low was lower for phase III versus phase I and phase II (16.8%, 17.5%, and 27.2%, respectively; p = 0.018); in industry versus investigator-driven studies (11.6% vs 29.1%, p < 0.001), and in metastatic versus early-stage settings (18.0% vs 33.5%, p < 0.001). ER-low inclusion increased over time, particularly in investigator-driven trials (since 2015), while remaining limited in industry-sponsored studies. We evaluated the ER cut-off adopted in trials testing therapies for TNBC. Although more inclusive criteria have been applied in recent years, patients with ER-low disease remain largely excluded from registrational trials, particularly in the metastatic setting, potentially limiting access to effective therapies. Broadening inclusion criteria could improve treatment opportunities for this high-risk population.

Pathologic complete response after neoadjuvant treatment is considered a surrogate of cure in triple-negative breast cancer, yet around 10% of patients still relapse. Whether baseline stromal tumor-infiltrating lymphocytes can stratify this residual risk is unknown. Here, we report on GAMBIT, a multicentric real-world retrospective study of 2457 patients with triple-negative breast cancer or estrogen receptor-low disease, HER2-negative, of whom 1192 obtained a pathological complete response and 690 have evaluable tumor infiltrating lymphocytes. Among patients with pathological complete response, clinical nodal status and tumor infiltrating lymphocytes are independently prognostic and patients with clinical node-positive/low-tumor infiltrating lymphocytes tumors experience substantially worse outcomes, with five-year distant relapse-free survival of 83.4% and overall survival of 85.8%. In this high-risk subgroup, five-year cumulative incidence of central nervous system reaches 7.5%, including 6.9% presenting as isolated central nervous system relapse. In this work, we identify a high-risk subgroup despite pathologic complete response and provide a framework supporting risk-adapted trial design incorporating central nervous system-directed strategies.