Citations

Abstract Clinical empathy is essential for patient care, but physicians need continually balance emotional warmth with factual precision under the cognitive and emotional constraints of clinical practice. This study investigates how large language models (LLMs) can function as empathy editors, refining physicians’ written responses to enhance empathetic tone while preserving underlying medical information. More importantly, we introduce novel quantitative metrics, an Empathy Ranking Score and a MedFactChecking Score to systematically assess both emotional and factual quality of the responses. Experimental results show that LLM-edited responses significantly increase perceived empathy while preserving factual accuracy compared with fully LLM-generated outputs. These findings suggest that using LLMs as editorial assistants, rather than autonomous generators , offers a safer, more effective pathway to empathetic and trustworthy AI-assisted healthcare communication.

Amyotrophic lateral sclerosis (ALS) is a fatal disease affecting upper and lower motor neurons. Microglia directly interact with motor neurons and participate in the progression of ALS. Single-cell mass cytometry (CyTOF) analysis revealed prominent expression of α5 integrin in microglia and macrophages in a superoxide dismutase-1 G93A mouse model of ALS (SOD1 G93A ). In postmortem tissues from ALS patients with various clinical ALS phenotypes and disease duration, α5 integrin is prominent in motor pathways of the central and peripheral nervous system and in perivascular zones associated with the blood–brain barrier. In SOD1 G93A mice, administration of a monoclonal antibody against α5 integrin increased survival compared to an isotype control and improved motor function on behavioral testing. Together, these findings in mice and in humans suggest that α5 integrin is a potential therapeutic target in ALS.