A free online case simulator tool called The Human Diagnosis Project may provide a valid measure of physicians' diagnostic performance, according to a study published in JAMA Network Open.
The Human Dx tool uses crowdsourced physician knowledge and machine learning to present users with a simulated medical case in which they must analyze a patient's symptoms and rule out dozens of possibilities to make a correct diagnosis.
For the study, researchers from Baltimore-based Johns Hopkins University analyzed the results of 11,023 case simulations solved by 1,738 physicians, residents and medical students nationwide between Jan. 21, 2016, and Jan. 15, 2017.
Researchers found clinicians with more experience and training scored higher on the simulator. Attending physicians had the most efficient and accurate diagnostic performances among all clinician types.
"Doctors are constantly trying to stay up to date on current best practices to better provide patients with high-value care," study co-author Reza Manesh, MD, assistant program director for clinical reasoning at Johns Hopkins' Osler Medical Training Program, said in a press release. "However, there is no way for doctors to self-assess how well they incorporate that new knowledge into how they make decisions for patients. There is an urgent need to objectively evaluate a physician's clinical reasoning and ensure they are making the right decisions for their patients."
More articles on clinical leadership & infection control:
Patient deaths after colorectal surgery declined from 2008 to 2017
Data-mining EHRs can detect hospital disease outbreaks, study finds
Researchers use AI to predict progression of neurodegenerative diseases