Previously submitted to: JMIR AI (no longer under consideration since Feb 24, 2025)
Date Submitted: Oct 3, 2023
Open Peer Review Period: Oct 2, 2023 - Nov 27, 2023
(closed for review but you can still tweet)
NOTE: This is an unreviewed Preprint
Warning: This is a unreviewed preprint (What is a preprint?). Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn (a note "no longer under consideration" will appear above).
Peer review me: Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period (in this case, a "Peer Review Me" button to sign up as reviewer is displayed above). All preprints currently open for review are listed here. Outside of the formal open peer-review period we encourage you to tweet about the preprint.
Citation: Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author).
Final version: If our system detects a final peer-reviewed "version of record" (VoR) published in any journal, a link to that VoR will appear below. Readers are then encourage to cite the VoR instead of this preprint.
Settings: If you are the author, you can login and change the preprint display settings, but the preprint URL/DOI is supposed to be stable and citable, so it should not be removed once posted.
Submit: To post your own preprint, simply submit to any JMIR journal, and choose the appropriate settings to expose your submitted version as preprint.
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Decoding Mediverse : Unveiling the Diagnostic Accuracy of a Medical AI Symptom Checker (DMAIS study)
ABSTRACT
Background:
Artificial intelligence is rapidly gaining traction in healthcare. Mediverse, an AI-symptom checker constructed using medical knowledge database, predictive algorithm, Bayesian inference, feedback loop and clinical validation, aimed to aid in the initial diagnosis and provide indications for referral for patients with common symptoms, thereby improving efficiency of triaging and diagnostic process with concurrent patient education.
Objective:
We conducted a study on the Mediverse AI Symptom Checker to assess its concordance rate with the diagnoses formulated by the physicians. Additionally, we assessed patients' and doctors' satisfaction with the system's patient education on diseases. User-friendliness and acceptance levels of the system were also evaluated among both patients and doctors.
Methods:
This is a prospective validation study. Patients presenting to both outpatient clinic and emergency department of Hospital Putrajaya, Malaysia, covering study period from 1st of January 2023 to 31st March 2023, were first assessed and treated by doctors. They were then given access to Mediverse AI symptom checker to key in their main presenting symptoms. Diagnosis accuracy was evaluated by comparing the AI generated diagnosis with the diagnosis of the treating doctor. An independent assessor evaluated the concordance of the diagnosis offered by Mediverse AI symptom checker and the doctor’s diagnosis and classified the results as “complete match” (the exact same diagnosis), “partial match” (not the exact same diagnosis but a similar diagnosis that would result in the same management strategy) and “mismatch” (different category of diagnosis that would result in a different management strategy). User’s satisfaction was also evaluated.
Results:
The study involved 75 doctors and 325 patients from general outpatient clinic and emergency department. In 90.5% of the encounters, the top three diagnoses offered by Mediverse AI symptom checker matched the doctor’s diagnosis, with 87.3% of complete match or partial match. Among the participating doctors, the majority (n=180, 55.4%) strongly agreed that the triage advice provided by the Mediverse AI symptom checker for each diagnosis was appropriate.
Conclusions:
The Mediverse AI symptom checker demonstrates promise as a tool for assisting initial diagnosis, exhibiting a high level of concordance with human diagnosis and receiving a high user satisfaction rate. Further research is warranted to assess its effectiveness in a diverse patient population encompassing a wide range of symptoms and conditions. Clinical Trial: nil
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© 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.