Protective ileostomy creation after anterior resection of the rectum (PICARR): a decision-making exploring international survey

In our previous survey of experts, surgeon’s decision-making process (DMP) about protective ileostomy (PI) creation after anterior resection was investigated. Based on our previous data, a multiple choice questionnaire has been developed. The aim is to perform a quantitative analysis of the results obtained from an international survey and to describe the clinical practice worldwide. Ten questions were related to participants’ demographics and, 20 questions (of which 17 Likert scale questions...

Efficient multi-task learning with instance selection for biomedical NLP

Background: Biomedical natural language processing (NLP) increasingly relies on large language models and extensive datasets, presenting significant computational challenges. Methods: We propose Blue5, a multi-task model based on SciFive that incorporates instance selection (IS) to enable efficient, multi-task learning (MTL) on biomedical data. We adapt the E2SC-IS framework for the biomedical domain, integrating a calibrated SVM classifier to reduce computational costs. Results: Our approach...

Deep reinforcement learning for Type 1 Diabetes: Dual PPO controller for personalized insulin management

Background: Managing blood glucose levels in Type 1 Diabetes Mellitus (T1DM) is essential to prevent complications. Traditional insulin delivery methods often require significant patient involvement, limiting automation. Reinforcement Learning (RL)-based controllers offer a promising approach for improving automated insulin administration. Methods: We propose a Dual Proximal Policy Optimization (Dual PPO) controller for personalized insulin delivery in a hybrid closed-loop system. The control...

Understanding Oxygen Concentrator Failures in Low Resource Settings: The Role of Dust and Humidity