Currently submitted to: Journal of Medical Internet Research
Date Submitted: May 12, 2019
Open Peer Review Period: May 15, 2019 - Jul 10, 2019
(currently open for review and needs more reviewers - can you help?)
Patient Perspectives on Usefulness of an Artificial Intelligence Assisted Symptom-Checker: A Cross-Sectional Survey Study
Patients increasingly seek online symptom-checkers to obtain diagnoses. Little is known, however, about characteristics of patients who use these resources, their rationale for use, and whether patients find them accurate and useful.
To examine patients’ experiences using an artificial intelligence (AI) assisted online symptom-checker.
An online survey was administered to US users of Isabel Symptom Checker within 6 months of their use and occurring from March 2, 2018 through March 15, 2018. User characteristics, experiences of symptom-checker use, experiences discussing results with physicians, and prior personal history of experiencing a diagnostic error were collected.
329 usable/complete responses were obtained. Mean respondent age was 48.0 years (SD=16.7); most were women (n=230;75.7%) and white/Caucasian (n=271;89.1%). Patients used the symptom-checker to better understand their symptoms’ causes (n=232;76.3%), decide whether to seek care (n=101;33.2%) or where (e.g., primary or urgent care; n=63;20.7%), get medical advice without going to a doctor (n=48;15.8%), or better understand their diagnosis (n=39;12.8%). Most reported receiving useful information for their health problems (n=274;83.3%), with half reporting positive health effects (n=154;50.9%). Most perceived it to be useful as a diagnostic tool (n=253;76.9%), as providing insights leading them closer to correct diagnoses (n=231;70.2%), and reported they would use it again (n=278;84.5%). Patients who discussed findings with their physicians (n=103) sometimes felt physicians were disinterested (n=24;23.3%) and not open to discussing the tool’s results (n=21;20.4%). Patients who previously experienced diagnostic errors (missed or delayed diagnoses; n=181;55.0%) were more likely to use the symptom-checker to determine if they should seek care (26.5% vs 12.2%;p=.002), but more often felt physicians were disinterested in discussing the tool’s results (30.4% vs 8.8%;p=.04) than patients who had not previously experienced diagnostic errors.
Despite ongoing concerns about symptom-checker accuracy, a large patient-user group perceived an AI assisted symptom-checker as useful for diagnosis. Formal validation studies evaluating symptom-checker accuracy and effectiveness in real-world practice could provide additional useful information about their benefit.
Note: Per the author's request, please log in to view the PDF
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.