A Dartmouth study finds that AI may cost doctors time when corresponding with patients by making them spend more time editing AI-drafted responses than it would take to write them. The researchers analyzed 146,000 conversations between patients and their primary care physicians from the online portal of a large healthcare system and found that automated responses frequently introduced errors and extraneous details. But the study provides a framework for generating "good" AI responses that align with how clinicians communicate and shows that adapting AI to individual physicians can reduce editing by 26%. The study was presented at the 64th Annual Meeting of the Association for Computational Linguistics.

To help healthcare facilities, clinicians, and public health agencies prepare for future Andes virus outbreaks, researchers from Mass General Brigham systematically surveyed the published literature for prior reports of Andes virus exposure in healthcare settings. Based on eight studies from seven Andes virus transmission events, the researchers concluded that incidents of Andes virus transmission to healthcare personnel were associated with delays in implementing transmission-based precautions or control measures. Their findings are published in Clinical Infectious Diseases.