Comparison of physician and artificial intelligence-based symptom checker diagnostic accuracy.
Artificial intelligence
Diagnosis
Diagnostic decision support system
Rheumatology
Symptom checker
Telemedicine
Journal
Rheumatology international
ISSN: 1437-160X
Titre abrégé: Rheumatol Int
Pays: Germany
ID NLM: 8206885
Informations de publication
Date de publication:
12 2022
12 2022
Historique:
received:
19
07
2022
accepted:
29
08
2022
pubmed:
11
9
2022
medline:
12
10
2022
entrez:
10
9
2022
Statut:
ppublish
Résumé
Symptom checkers are increasingly used to assess new symptoms and navigate the health care system. The aim of this study was to compare the accuracy of an artificial intelligence (AI)-based symptom checker (Ada) and physicians regarding the presence/absence of an inflammatory rheumatic disease (IRD). In this survey study, German-speaking physicians with prior rheumatology working experience were asked to determine IRD presence/absence and suggest diagnoses for 20 different real-world patient vignettes, which included only basic health and symptom-related medical history. IRD detection rate and suggested diagnoses of participants and Ada were compared to the gold standard, the final rheumatologists' diagnosis, reported on the discharge summary report. A total of 132 vignettes were completed by 33 physicians (mean rheumatology working experience 8.8 (SD 7.1) years). Ada's diagnostic accuracy (IRD) was significantly higher compared to physicians (70 vs 54%, p = 0.002) according to top diagnosis. Ada listed the correct diagnosis more often compared to physicians (54 vs 32%, p < 0.001) as top diagnosis as well as among the top 3 diagnoses (59 vs 42%, p < 0.001). Work experience was not related to suggesting the correct diagnosis or IRD status. Confined to basic health and symptom-related medical history, the diagnostic accuracy of physicians was lower compared to an AI-based symptom checker. These results highlight the potential of using symptom checkers early during the patient journey and importance of access to complete and sufficient patient information to establish a correct diagnosis.
Identifiants
pubmed: 36087130
doi: 10.1007/s00296-022-05202-4
pii: 10.1007/s00296-022-05202-4
pmc: PMC9548469
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
2167-2176Informations de copyright
© 2022. The Author(s).
Références
Ann Rheum Dis. 2015 Mar;74(3):e12
pubmed: 24534758
JMIR Form Res. 2019 Oct 29;3(4):e13863
pubmed: 31663858
Orphanet J Rare Dis. 2019 Mar 21;14(1):69
pubmed: 30898118
RMD Open. 2019 Apr 3;5(1):e000870
pubmed: 31168406
Arthritis Res Ther. 2021 Sep 6;23(1):233
pubmed: 34488887
Front Med (Lausanne). 2022 Apr 25;9:774945
pubmed: 35547229
J Gen Intern Med. 2018 Jan;33(1):103-115
pubmed: 28936618
BMJ Open. 2020 Dec 16;10(12):e040269
pubmed: 33328258
Z Rheumatol. 2019 Oct;78(8):722-742
pubmed: 31468170
Semin Arthritis Rheum. 1991 Dec;21(3):156-69
pubmed: 1788552
Z Rheumatol. 2021 Dec;80(10):909-913
pubmed: 34605980
BMJ. 2015 Jul 08;351:h3480
pubmed: 26157077
Int J Rheumatol. 2014;2014:672714
pubmed: 25114683
Rheumatology (Oxford). 2018 Sep 1;57(9):1592-1601
pubmed: 29850885
BMC Musculoskelet Disord. 2016 Aug 24;17(1):362
pubmed: 27553253
Clin Med Insights Arthritis Musculoskelet Disord. 2016 Oct 02;9:181-187
pubmed: 27721659
Semin Arthritis Rheum. 2020 Oct;50(5):1015-1021
pubmed: 32911279
JMIR Mhealth Uhealth. 2020 May 15;8(5):e17507
pubmed: 32348258
Front Public Health. 2022 Feb 22;10:844669
pubmed: 35273944
Z Rheumatol. 2019 Oct;78(8):692-697
pubmed: 31468164
Arthritis Res Ther. 2021 Apr 13;23(1):112
pubmed: 33849654
J Med Internet Res. 2020 Jan 30;22(1):e14679
pubmed: 32012052