The potential of Generative Pre-trained Transformer 4 (GPT-4) to analyse medical notes in three different languages: a retrospective model-evaluation study.

Background: Patient notes contain substantial information but are difficult for computers to analyse due to their unstructured format. Large-language models (LLMs), such as Generative Pre-trained Transformer 4 (GPT-4), have changed our ability to process text, but we do not know how effectively they handle medical notes. We aimed to assess the ability of GPT-4 to answer predefined questions after reading medical notes in three different languages.

Breast Implant-Associated Anaplastic Large Cell Lymphoma Awareness: An Analysis of the Responses to an Institutional Campaign and Global Recall.

Background: We performed an assessment of patient response rates and clinical outcomes to the global recall for textured breast implants and to our institution's letters informing them of their risk of breast implant-associated anaplastic large cell lymphoma (BIA-ALCL).

Methods: A retrospective review of patients who had textured implants placed at our institution was completed. Outcome measures included patient response rates to either the global recall or our institution's letters, rate of textured implant removal, and type of subsequent revision surgery.

Neoadjuvant Chemotherapy and Nipple-Sparing Mastectomy: Timing and Postoperative Complications.

Background: As the demand for nipple-sparing mastectomy (NSM) increases and surgeons expand the eligibility criteria, a subset of patients may become candidates following neoadjuvant chemotherapy (NACT). However, the impact of NACT on postoperative complications remains unclear as the current literature is discordant.

Methods: A single-institution, retrospective chart review was performed on patients undergoing NSM from 1989 to 2017.