Sorry, you need to enable JavaScript to visit this website.
Skip to main content
Study

Automating detection of diagnostic error of infectious diseases using machine learning.

Peterson KS, Chapman AB, Widanagamaachchi W, et al. Automating detection of diagnostic error of infectious diseases using machine learning. PLOS Digit Health. 2024;3(6):e0000528. doi:10.1371/journal.pdig.0000528.

Save
Print
July 10, 2024
Peterson KS, Chapman AB, Widanagamaachchi W, et al. PLOS Digit Health. 2024;3(6):e0000528.
View more articles from the same authors.

Developing machine learning (ML) models to detect real time adverse events requires careful validation of proposed approaches. This article describes two ML models to detect diagnostic divergence (i.e., the deviation between predicted diagnosis and documented diagnosis, weighted by mortality) of pneumonia in the emergency department (ED). More than 6.5 million ED visits were analyzed by the models and 130 were analyzed by expert physicians for diagnostic divergence. Correlation between human and automatic reviewers was weak to moderate. The authors present potential reasons for this outcome and propose future research to improve ML accuracy.

Save
Print
Cite
Citation

Peterson KS, Chapman AB, Widanagamaachchi W, et al. Automating detection of diagnostic error of infectious diseases using machine learning. PLOS Digit Health. 2024;3(6):e0000528. doi:10.1371/journal.pdig.0000528.

Related Resources From the Same Author(s)
Related Resources