Artificial intelligence showed high predictive accuracy when selecting surgical candidates for lumbar spinal stenosis compared to a panel of spine experts, according to a study published in the European Spine Journal.
Researchers proposed a hybrid AI model that computes the chances of spinal surgical recommendations based on patient demographic factors, symptom manifestations and MRIs, according to the study published July 8. Sets of 400 and 100 medical vignettes reviewed by surgeons were used for training and testing.
The model had high predictive accuracy with a root mean square error between AI predictions and ground truth of 0.0964. The average RMSE between physician recommendations and ground truth was 0.1940. Other classification metrics showed similarities between AI and physician recommendations.
The study authors concluded, "Our results suggest that AI can be used to automate the evaluation of surgical candidacy for LSS with performance comparable to a multidisciplinary panel of physicians."