A new study by investigators from Mass General Brigham demonstrates that large language models (LLMs), a type of generative AI, may help reduce physician workload and improve patient education when used to draft replies to patient messages.
Apr 24 2024Mass General Brigham A new study by investigators from Mass General Brigham demonstrates that large language models , a type of generative AI, may help reduce physician workload and improve patient education when used to draft replies to patient messages. The study also found limitations to LLMs that may affect patient safety, suggesting that vigilant oversight of LLM-generated communications is essential for safe usage.
Generative AI has the potential to provide a 'best of both worlds' scenario of reducing burden on the clinician and better educating the patient in the process. However, based on our team's experience working with LLMs, we have concerns about the potential risks associated with integrating LLMs into messaging systems. With LLM-integration into EHRs becoming increasingly common, our goal in this study was to identify relevant benefits and shortcomings.
For the study, the researchers used OpenAI's GPT-4, a foundational LLM, to generate 100 scenarios about patients with cancer and an accompanying patient question. No questions from actual patients were used for the study. Six radiation oncologists manually responded to the queries; then, GPT-4 generated responses to the questions. Finally, the same radiation oncologists were provided with the LLM-generated responses for review and editing.
Related StoriesNotably, LLM-generated/physician-edited responses were more similar in length and content to LLM-generated responses versus the manual responses. In many cases, physicians retained LLM-generated educational content, suggesting that they perceived it to be valuable. While this may promote patient education, the researchers emphasize that overreliance on LLMs may also pose risks, given their demonstrated shortcomings.
Research Cancer Doctor Education Electronic Health Record Hospital Language Medicine Oncology
日本 最新ニュース, 日本 見出し
Similar News:他のニュース ソースから収集した、これに似たニュース記事を読むこともできます。
Mass General Hospital develops clinical decision support tool for mpox diagnosisDiagnosing infectious conditions can be challenging. Diagnosis is especially challenging for uncommon and emerging infectious diseases for which there's limited clinical experience.
続きを読む »
4 Guatemalan nationals accused of participating in large-scale schemes in CT, Mass., RIFour Guatemalan nationals are accused of participating in a large-scale scheme to steal and resell high-value products from home improvement stores and other…
続きを読む »
Research identifies pitfalls and opportunities for generative AI in patient messaging systemsA new study by investigators from Mass General Brigham demonstrates that large language models (LLMs), a type of generative AI, may help reduce physician workload and improve patient education when used to draft replies to patient messages.
続きを読む »
Midlands conference discusses new opportunities for tenant farming sectorCreating opportunities for tenant farmers in a changing farming landscape was the theme of a national conference hosted by the NFU which was attended by Shropshire farmers.
続きを読む »
World Snooker Championship 2024: Snooker must 'embrace' new opportunities amid Crucible uncertaintyEddie Hearn says snooker must 'embrace' investment from different parts of the globe as the debate over whether the World Championship should leave its iconic Sheffield home continues.
続きを読む »
What I learnt about opportunities for Yorkshire from eye-opening visit to Pakistan: James MasonI've been very fortunate to travel extensively in my adult life. Since backpacking around the world after finishing university to business and leisure travel to China, the Middle East, US and Africa.
続きを読む »