The Transformative Potential of Large Language Models in Mining Electronic Health Records Data: Content Analysis.

Background: In this study, we evaluate the accuracy, efficiency, and cost-effectiveness of large language models in extracting and structuring information from free-text clinical reports, particularly in identifying and classifying patient comorbidities within oncology electronic health records. We specifically compare the performance of gpt-3.5-turbo-1106 and gpt-4-1106-preview models against that of specialized human evaluators.

Radiation for Awakening the Dormant Immune System, a Promising Challenge to be Explored.

Recent advances that have been made in our understanding of cancer biology and immunology show that infiltrated immune cells and cytokines in the tumor microenvironment may play different functions that appear tightly related to clinical outcomes. Strategies aimed at interfering with the cross-talk between microenvironment tumor cells and their cellular partners have been considered for the development of new immunotherapies. These novel therapies target different cell components of the tumor microenvironment and importantly, they may be coupled and boosted with classical treatments, such as radiotherapy.

Combined modulated electron and photon beams planned by a Monte-Carlo-based optimization procedure for accelerated partial breast irradiation.

The purpose of this study was to present a Monte-Carlo (MC)-based optimization procedure to improve conventional treatment plans for accelerated partial breast irradiation (APBI) using modulated electron beams alone or combined with modulated photon beams, to be delivered by a single collimation device, i.e. a photon multi-leaf collimator (xMLC) already installed in a standard hospital.