EUVIMEDEUVIMED entdecken
Vergleichsstudie

Comparison of Initial Artificial Intelligence (AI) and Final Physician Recommendations in AI-Assisted Virtual Urgent Care Visits

Dan Zeltzer iD, Zehavi Kugler, Lior Hayat, Tamar Brufman, Ran Ilan Ber, Keren Leibovich, Tom Beer iD, Ilan Frank, Ran Shaul, Caroline Goldzweig, Joshua Pevnick

Annals of Internal Medicine · 2025-04 · 178 (4) · 498-506

DOI: 10.7326/annals-24-03283 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift Annals of Internal Medicine, 2025-04. Verfasst von Dan Zeltzer und 10 weiteren Autor:innen. Beteiligte Einrichtung: Tel Aviv University, Tel Aviv, Israel (D.Z.). Hauptthemen laut MEDLINE: Artificial Intelligence, Ambulatory Care. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 19 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Whether artificial intelligence (AI) assistance is associated with quality of care is uncertain. OBJECTIVE: To compare initial AI recommendations with final recommendations of physicians who had access to the AI recommendations and may or may not have viewed them. DESIGN: Retrospective cohort study. SETTING: Cedars-Sinai Connect, an AI-assisted virtual urgent care clinic with intake questions via structured chat. When confidence is sufficient, AI presents diagnosis and management recommendations (prescriptions, laboratory tests, and referrals). PATIENTS: 461 physician-managed visits with AI recommendations of sufficient confidence and complete medical records for adults with respiratory, urinary, vaginal, eye, or dental symptoms from 12 June to 14 July 2024. MEASUREMENTS: Concordance of diagnosis and management recommendations of initial AI recommendations and final physician recommendations. Physician adjudicators scored all nonconcordant and a sample of concordant recommendations as optimal, reasonable, inadequate, or potentially harmful. RESULTS: Initial AI and final physician recommendations were concordant for 262 visits (56.8%). Among the 461 weighted visits, AI recommendations were more frequently rated as optimal (77.1% [95% CI, 72.7% to 80.9%]) compared with treating physician decisions (67.1% [CI, 62.9% to 71.1%]). Quality scores were equal in 67.9% (CI, 64.8% to 70.9%) of cases, better for AI in 20.8% (CI, 17.8% to 24.0%), and better for treating physicians in 11.3% (CI, 9.0% to 14.2%), respectively. LIMITATIONS: Single-center retrospective study. Adjudicators were not blinded to the source of recommendations. It is unknown whether physicians viewed AI recommendations. CONCLUSION: When AI and physician recommendations differed, AI recommendations were more often rated better quality. Findings suggest that AI performed better in identifying critical red flags and supporting guideline-adherent care, whereas physicians were better at adapting recommendations to changing information during consultations. Thus, AI may have a role in assisting physician decision making in virtual urgent care. PRIMARY FUNDING SOURCE: K Health.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceAmbulatory CareHumansRetrospective StudiesFemaleMaleMiddle AgedAdultAgedQuality of Health Care

Autor:innen und Institutionen

  • Tel Aviv University, Tel Aviv, Israel (D.Z.).
  • K Health, New York, New York (Z.K., L.H., T.Brufman, R.I.B., K.L., T.Beer, I.F., R.S.).
  • Department of Medicine, Cedars-Sinai Medical Center, Los Angeles, California (C.G., J.P.).

ORCID-Profile: Dan Zeltzer, Tom Beer

Zitieren

APA

Zeltzer, D., Kugler, Z., Hayat, L., Brufman, T., Ilan Ber, R., Leibovich, K., Beer, T., Frank, I., Shaul, R., Goldzweig, C., & Pevnick, J. (2025). Comparison of Initial Artificial Intelligence (AI) and Final Physician Recommendations in AI-Assisted Virtual Urgent Care Visits. Annals of Internal Medicine, 178(4), 498-506. https://doi.org/10.7326/annals-24-03283

Vancouver

Zeltzer D, Kugler Z, Hayat L, Brufman T, Ilan Ber R, Leibovich K, et al. Comparison of Initial Artificial Intelligence (AI) and Final Physician Recommendations in AI-Assisted Virtual Urgent Care Visits. Annals of Internal Medicine. 2025;178(4):498-506. doi:10.7326/annals-24-03283

BibTeX
@article{Zeltzer2025,
  author = {Zeltzer, Dan and Kugler, Zehavi and Hayat, Lior and Brufman, Tamar and Ilan Ber, Ran and Leibovich, Keren and Beer, Tom and Frank, Ilan and Shaul, Ran and Goldzweig, Caroline and Pevnick, Joshua},
  title = {Comparison of Initial Artificial Intelligence (AI) and Final Physician Recommendations in AI-Assisted Virtual Urgent Care Visits},
  journal = {Annals of Internal Medicine},
  year = {2025},
  volume = {178},
  number = {4},
  pages = {498--506},
  doi = {10.7326/annals-24-03283}
}
Kostenlos starten →