Identifying different phenotypes of symptomatic gastroesophageal reflux disease using artificial intelligence

Introduction The Lyon Consensus Conference proposed criteria for the clinical diagnosis of three different phenotypes of gastroesophageal reflux disease: nonerosive gastroesophageal reflux disease, Reflux Hypersensitivity, and Functional Heartburn. Methods In the present study, we examined the potential of ChatGPT, an artificial intelligence-based conversational large language model to describe how one can identify the different phenotypes as identified by the Lyon Consensus Conference, and to provide a diagnosis when given important clinical findings in a given patient with a particular phenotype. Results Although in our analyses ChatGPT captured correct information regarding symptoms, upper gastrointestinal endoscopy findings and response to gastric antisecretory agents when asked to describe different phenotypes, it failed, however, to return correct information on esophageal acid exposure time and the association of symptoms with esophageal reflux episodes. ChatGPT was even less effective in returning the correct diagnosis after being given specific clinical features of a particular phenotype. Conclusions Although it seems likely that the ability of ChatGPT to capture information from multiple sources will improve with future use and refinement, presently it is inadequate as a standalone tool for processing information for the description or diagnosis of different clinical disease states. On the other hand, artificial intelligence might prove useful to clinicians in performing tasks that involve obtaining data from a single source such as the electronic medical record and generating a document having a standardized format such as a discharge summary. ### Competing Interest Statement The authors have declared no competing interest. ### Funding Statement This study did not receive any funding ### Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes All data produced in the present work are contained in the manuscript