TUESDAY, Dec. 19, 2023 (HealthDay News) -- Standard artificial intelligence (AI) models improve diagnostic accuracy, but systematically biased AI models reduce this accuracy, according to a study published in the Dec. 19 issue of the Journal of the American Medical Association.

Sarah Jabbour, from the University of Michigan in Ann Arbor, and colleagues examined the impact of systematically biased AI on clinician diagnostic accuracy in a randomized clinical vignette survey study. Clinicians were shown nine clinical vignettes of patients hospitalized with acute respiratory failure and were asked to determine the likelihood of pneumonia, heart failure, or chronic obstructive pulmonary disease as the underlying cause. Clinicians were shown two vignettes without AI model input to establish baseline diagnostic accuracy and were then randomly assigned to see six vignettes with AI model input: three standard-model predictions and three systematically biased model predictions.

Overall, 457 clinicians were randomly assigned: 231 and 226 to AI model predictions without and with explanations, respectively. The researchers found that for the three diagnoses, clinicians' baseline diagnostic accuracy was 73.0 percent. Clinician accuracy increased over baseline by 2.9 and 4.4 percentage points when shown a standard AI model without and with explanations. Clinician accuracy was reduced by 11.3 percentage points with systematically biased AI model predictions compared with baseline; providing biased AI model predictions with explanations reduced accuracy by 9.1 percentage points, representing a nonsignificant improvement of 2.3 percentage points compared with the systematically biased model.

"Although the findings of the study suggest that clinicians may not be able to serve as a backstop against flawed AI, they can play an essential role in understanding AI's limitations," the authors write.

One author reported receiving royalties from a patent from Airstrip.

Abstract/Full Text (subscription or payment may be required)

Editorial (subscription or payment may be required)

Copyright © 2020 HealthDay. All rights reserved.

WEDNESDAY, Dec. 20, 2023 (HealthDay News) -- Burnout, lack of professional fulfillment, and other well-being-linked factors are associated with intention to leave (ITL) among physicians, according to a study published online Dec. 15 in JAMA Network Open.

Jennifer A. Ligibel, M.D., from the Dana-Farber Cancer Institute in Boston, and colleagues describe the prevalence of burnout, professional fulfillment, and ITL among physicians at academic-affiliated health care systems. Data were included from 18,719 academic physicians who responded to a survey.

The researchers found that 37.9 percent of the respondents met the criteria for burnout, 39.3 percent met the criteria for professional fulfillment, and 32.6 percent reported moderate or greater ITL, with variation across specialties. Each 1-point increase in burnout was associated with ITL after adjustment for demographics (odds ratio, 1.52), while there was an inverse association for each 1-point increase in professional fulfillment with ITL (odds ratio, 0.64). Inverse associations with ITL were seen for each 1-point increase in supportive leadership behaviors, peer support, personal-organizational values alignment, perceived gratitude, COVID-19 organizational support, and electronic health record helpfulness after adjustment for demographics, burnout, and professional fulfillment. Direct associations with ITL were seen for each 1-point increase in depression and negative impact of work on personal relationships.

"These results underscore the importance of the connections between academic physicians and both institutional leadership and mission, as well as point to the need for developing initiatives with a comprehensive approach that considers burnout, professional fulfillment, and other organizational and individual-level well-being factors to help prevent physician turnover," the authors write.

One author disclosed ties to Marvin Behavioral Health Inc.

Abstract/Full Text

Copyright © 2020 HealthDay. All rights reserved.