Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384455669> ?p ?o ?g. }
- W4384455669 abstract "ABSTRACT Objective This study aimed to develop and assess the performance of fine-tuned large language models for generating responses to patient messages sent via an electronic health record patient portal. Methods Utilizing a dataset of messages and responses extracted from the patient portal at a large academic medical center, we developed a model (CLAIR-Short) based on a pre-trained large language model (LLaMA-65B). In addition, we used the OpenAI API to update physician responses from an open-source dataset into a format with informative paragraphs that offered patient education while emphasizing empathy and professionalism. By combining with this dataset, we further fine-tuned our model (CLAIR-Long). To evaluate the fine-tuned models, we used ten representative patient portal questions in primary care to generate responses. We asked primary care physicians to review generated responses from our models and ChatGPT and rated them for empathy, responsiveness, accuracy, and usefulness. Results The dataset consisted of a total of 499,794 pairs of patient messages and corresponding responses from the patient portal, with 5,000 patient messages and ChatGPT-updated responses from an online platform. Four primary care physicians participated in the survey. CLAIR-Short exhibited the ability to generate concise responses similar to provider’s responses. CLAIR-Long responses provided increased patient educational content compared to CLAIR-Short and were rated similarly to ChatGPT’s responses, receiving positive evaluations for responsiveness, empathy, and accuracy, while receiving a neutral rating for usefulness. Conclusion Leveraging large language models to generate responses to patient messages demonstrates significant potential in facilitating communication between patients and primary care providers." @default.
- W4384455669 created "2023-07-16" @default.
- W4384455669 creator A5004738173 @default.
- W4384455669 creator A5061326990 @default.
- W4384455669 creator A5079969497 @default.
- W4384455669 creator A5082251203 @default.
- W4384455669 creator A5084108623 @default.
- W4384455669 creator A5084194339 @default.
- W4384455669 creator A5086954690 @default.
- W4384455669 creator A5090773076 @default.
- W4384455669 creator A5091713549 @default.
- W4384455669 date "2023-07-16" @default.
- W4384455669 modified "2023-10-16" @default.
- W4384455669 title "Leveraging Large Language Models for Generating Responses to Patient Messages" @default.
- W4384455669 cites W2093274439 @default.
- W4384455669 cites W2327037637 @default.
- W4384455669 cites W2754518417 @default.
- W4384455669 cites W2795347911 @default.
- W4384455669 cites W2991399758 @default.
- W4384455669 cites W2996946491 @default.
- W4384455669 cites W3005890082 @default.
- W4384455669 cites W3006900481 @default.
- W4384455669 cites W3093164586 @default.
- W4384455669 cites W3205513304 @default.
- W4384455669 cites W4200043507 @default.
- W4384455669 cites W4293457270 @default.
- W4384455669 cites W4309791331 @default.
- W4384455669 cites W4313451803 @default.
- W4384455669 cites W4323655724 @default.
- W4384455669 cites W4366769280 @default.
- W4384455669 cites W4367310920 @default.
- W4384455669 cites W4380995257 @default.
- W4384455669 cites W4381185932 @default.
- W4384455669 cites W4381192815 @default.
- W4384455669 cites W4381893163 @default.
- W4384455669 cites W4381930847 @default.
- W4384455669 cites W4382246105 @default.
- W4384455669 cites W4382395040 @default.
- W4384455669 doi "https://doi.org/10.1101/2023.07.14.23292669" @default.
- W4384455669 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37503263" @default.
- W4384455669 hasPublicationYear "2023" @default.
- W4384455669 type Work @default.
- W4384455669 citedByCount "2" @default.
- W4384455669 countsByYear W43844556692023 @default.
- W4384455669 crossrefType "posted-content" @default.
- W4384455669 hasAuthorship W4384455669A5004738173 @default.
- W4384455669 hasAuthorship W4384455669A5061326990 @default.
- W4384455669 hasAuthorship W4384455669A5079969497 @default.
- W4384455669 hasAuthorship W4384455669A5082251203 @default.
- W4384455669 hasAuthorship W4384455669A5084108623 @default.
- W4384455669 hasAuthorship W4384455669A5084194339 @default.
- W4384455669 hasAuthorship W4384455669A5086954690 @default.
- W4384455669 hasAuthorship W4384455669A5090773076 @default.
- W4384455669 hasAuthorship W4384455669A5091713549 @default.
- W4384455669 hasBestOaLocation W43844556691 @default.
- W4384455669 hasConcept C137293760 @default.
- W4384455669 hasConcept C15744967 @default.
- W4384455669 hasConcept C159110408 @default.
- W4384455669 hasConcept C160735492 @default.
- W4384455669 hasConcept C162324750 @default.
- W4384455669 hasConcept C204321447 @default.
- W4384455669 hasConcept C2776153502 @default.
- W4384455669 hasConcept C2779885105 @default.
- W4384455669 hasConcept C2984752397 @default.
- W4384455669 hasConcept C2989236134 @default.
- W4384455669 hasConcept C41008148 @default.
- W4384455669 hasConcept C50522688 @default.
- W4384455669 hasConcept C509550671 @default.
- W4384455669 hasConcept C512399662 @default.
- W4384455669 hasConcept C71924100 @default.
- W4384455669 hasConcept C77805123 @default.
- W4384455669 hasConceptScore W4384455669C137293760 @default.
- W4384455669 hasConceptScore W4384455669C15744967 @default.
- W4384455669 hasConceptScore W4384455669C159110408 @default.
- W4384455669 hasConceptScore W4384455669C160735492 @default.
- W4384455669 hasConceptScore W4384455669C162324750 @default.
- W4384455669 hasConceptScore W4384455669C204321447 @default.
- W4384455669 hasConceptScore W4384455669C2776153502 @default.
- W4384455669 hasConceptScore W4384455669C2779885105 @default.
- W4384455669 hasConceptScore W4384455669C2984752397 @default.
- W4384455669 hasConceptScore W4384455669C2989236134 @default.
- W4384455669 hasConceptScore W4384455669C41008148 @default.
- W4384455669 hasConceptScore W4384455669C50522688 @default.
- W4384455669 hasConceptScore W4384455669C509550671 @default.
- W4384455669 hasConceptScore W4384455669C512399662 @default.
- W4384455669 hasConceptScore W4384455669C71924100 @default.
- W4384455669 hasConceptScore W4384455669C77805123 @default.
- W4384455669 hasLocation W43844556691 @default.
- W4384455669 hasLocation W43844556692 @default.
- W4384455669 hasLocation W43844556693 @default.
- W4384455669 hasOpenAccess W4384455669 @default.
- W4384455669 hasPrimaryLocation W43844556691 @default.
- W4384455669 hasRelatedWork W1998814105 @default.
- W4384455669 hasRelatedWork W2014447469 @default.
- W4384455669 hasRelatedWork W2064101415 @default.
- W4384455669 hasRelatedWork W2122241274 @default.
- W4384455669 hasRelatedWork W2359001871 @default.
- W4384455669 hasRelatedWork W2748952813 @default.
- W4384455669 hasRelatedWork W2899084033 @default.
- W4384455669 hasRelatedWork W2967416135 @default.