22 June 2022

An editorial published in the RACP’s peer reviewed scientific journal The Internal Medicine Journal highlights that artificial intelligence may significantly reduce diagnostic errors. 

The paper’s author, and RACP Fellow Professor Ian Scott says “Diagnostic errors are common, occurring in 5–15% of all clinical encounters and causing serious patient harm in up to 1.0% of hospital admissions and general practitioner visits. 

“Diagnostic error is the most frequent cause of malpractice claims, and between 70% and 80% errors are deemed potentially preventable. 

“Anything we can do to better support physicians and their patients to reduce diagnostic errors and improve patient outcomes should be closely considered. 

“We already have artificial intelligence tools that can help doctors to diagnose certain conditions in patients using data from electronic medical records. As examples, one system was able to reliably detect missed cases of pneumonia or heart failure in hospitalised patients, while another could diagnose appendicitis in children presenting with abdominal pain. These are significant results, but these tools are not being widely used in the healthcare system. 

“As a medical profession, we need to be looking at all the ways we can embrace technology to reduce errors and improve outcomes for patients.”