New study reveals machine learning outperforms surgeons in predicting knee replacement outcomes

Unicompartmental (partial) knee replacement (UKR) is a common procedure designed to relieve pain in patients with knee osteoarthritis. However, some patients experience poor outcomes, and it can be challenging for surgeons to determine why these issues arise. A new study from NDORMS, published in The Knee, has found that a machine learning model can better predict which patients will have poor outcomes after undergoing UKR surgery, compared to experienced orthopedic surgeons.