Yang Zhao , Chao Gao , Lu Zhang , Xiaopei Gao , Zheng Zhang
{"title":"The application of chatbot in gastroenterology nursing","authors":"Yang Zhao , Chao Gao , Lu Zhang , Xiaopei Gao , Zheng Zhang","doi":"10.1016/j.gande.2023.07.003","DOIUrl":null,"url":null,"abstract":"<div><h3>Objective</h3><p>The advent of large language models has triggered a wave of technological advancements in the global AI dialogue system, which has been widely adopted in various fields including medical care. This research aims to investigate the potential of chatbots in the field of gastroenterology nursing.</p></div><div><h3>Methods</h3><p>Two nurses compiled and categorized 20 relevant questions related to gastroenterology nursing, grouping them into four modules. Two chatbot-based AI language models were selected to answer all the questions. The satisfaction levels and satisfaction rates for each module were analyzed to evaluate the performance of the two chatbots.</p></div><div><h3>Results</h3><p>Chatbot A received an overall satisfaction rate of 85% (with 9 very satisfied, 8 satisfied, and 3 dissatisfied responses), while chatbot B had a lower satisfaction rate of 45% (with 0 very satisfied, 9 satisfied, and 11 dissatisfied responses). The satisfaction rates for module 1 (pre-hospital care) were 60% for chatbot A and 20% for chatbot B. In module 2 (health education during hospitalization), chatbot A's satisfaction rate was 100%, while chatbot B's satisfaction was only 60%. For module 3 (continuing care after discharge), chatbot A's satisfaction rate was 100%, while chatbot B's was 40%. Finally, in module 4 (nursing management), chatbot A received an 80% satisfaction rate, compared to chatbot B's 60% satisfaction rate.</p></div><div><h3>Conclusion</h3><p>The performance of chatbot in terms of health education and nursing management for patients during hospitalization is acceptable; Further optimization is needed in terms of pre hospitalization nursing interventions and post discharge continuity care. The performance of different chatbots varies, and intelligent large models need to be tailored to the medical or nursing fields to better apply in the field of digestive disease care.</p></div>","PeriodicalId":100571,"journal":{"name":"Gastroenterology & Endoscopy","volume":"1 3","pages":"Pages 136-138"},"PeriodicalIF":0.0000,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Gastroenterology & Endoscopy","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2949752323000377","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Objective
The advent of large language models has triggered a wave of technological advancements in the global AI dialogue system, which has been widely adopted in various fields including medical care. This research aims to investigate the potential of chatbots in the field of gastroenterology nursing.
Methods
Two nurses compiled and categorized 20 relevant questions related to gastroenterology nursing, grouping them into four modules. Two chatbot-based AI language models were selected to answer all the questions. The satisfaction levels and satisfaction rates for each module were analyzed to evaluate the performance of the two chatbots.
Results
Chatbot A received an overall satisfaction rate of 85% (with 9 very satisfied, 8 satisfied, and 3 dissatisfied responses), while chatbot B had a lower satisfaction rate of 45% (with 0 very satisfied, 9 satisfied, and 11 dissatisfied responses). The satisfaction rates for module 1 (pre-hospital care) were 60% for chatbot A and 20% for chatbot B. In module 2 (health education during hospitalization), chatbot A's satisfaction rate was 100%, while chatbot B's satisfaction was only 60%. For module 3 (continuing care after discharge), chatbot A's satisfaction rate was 100%, while chatbot B's was 40%. Finally, in module 4 (nursing management), chatbot A received an 80% satisfaction rate, compared to chatbot B's 60% satisfaction rate.
Conclusion
The performance of chatbot in terms of health education and nursing management for patients during hospitalization is acceptable; Further optimization is needed in terms of pre hospitalization nursing interventions and post discharge continuity care. The performance of different chatbots varies, and intelligent large models need to be tailored to the medical or nursing fields to better apply in the field of digestive disease care.