Brown Digital Repository | Item

Full Metadata

Overview

Year:: 2019
Contributor:: Koehler, Chris (Author); Fraser, Hamish (Author); Patena, John (Author); Ranney, Megan (Author); Brown University. Alpert Medical School. Scholarly Concentration Program. Non-Scholarly Concentrator (research program)
Subject:: Artificial intelligence--Medical applications; Emergency medicine; Cell phones; Triage (Medicine); Diagnosis

Files

Description

Abstract:: Background: There is increasing interest in Computerized Diagnostic Decision Support (CDDS) programs to reduce misdiagnosis rates. While originally directed at doctors, CDDS programs called “Symptom Checkers” are designed to directly assist patients by creating differential diagnoses and advising on the need for further care. Unfortunately, there is very little evidence of their performance and safety due to a lack of rigorous evaluation particularly of clinical use. Purpose: A pilot evaluation of a leading Symptom Checker in an observational study to measure diagnostic and triage accuracy, to assess user experience, and ease of use for a range of user backgrounds. Methods: Participants were recruited in the Rhode Island Hospital adult emergency department. Data analysis will take place in three stages. Firstly, by comparing differential diagnosis lists from the Ada app and one or more diagnoses from the physician using two validated metrics, Comprehensiveness and Relevance. Secondly the completeness of the Ada app’s history taking questions will also be analyzed. Thirdly vital sign data will be used to assess any improvement in diagnostic performance. Results: 40 patients were enrolled in this pilot study. On average, participants were satisfied with the application and found it easy to use. Limitations: As this is a pilot study there will be limited power to assess diagnostic accuracy, however it should provide essential data for the design of a larger scale study of approximately 400 patients. Conclusions: Participants were satisfied with the application and found it easy to use. The participants provided a broad range of medical concerns, experience levels, and backgrounds. This pilot study will offer unique insight if Symptom Checkers can provide accurate diagnosis and triage to people in distress in different settings.
Notes:: Scholarly concentration: Non-Scholarly Concentrator

Content

Access Conditions

Use and Reproduction: Attribution 4.0 International (CC BY 4.0)

Citation

Koehler, Chris, Fraser, Hamish, Patena, John, et al., "Triage and Diagnosis Using A Symptom Checker Mobile Application: A Pilot Study" (2019). Warren Alpert Medical School Academic Symposium. Brown Digital Repository. Brown University Library. https://repository.library.brown.edu/studio/item/bdr:957177/

Relations

Collection:

Warren Alpert Medical School Academic Symposium

The Warren Alpert Medical School Academic Symposium is an annual event at Warren Alpert Medical School of Brown University that provides Year II medical students a venue to present their summer research in a poster format. Participation in the Symposium …
...

Triage and Diagnosis Using A Symptom Checker Mobile Application: A Pilot Study