Performance of hybrid artificial intelligence in determining candidacy for lumbar stenosis surgery

Abstract

Purpose Lumbar spinal stenosis (LSS) is a condition affecting several hundreds of thousands of adults in the United States each year and is associated with significant economic burden. The current decision-making practice to determine surgical candidacy for LSS is often subjective and clinician specific. In this study, we hypothesize that the performance of artificial intelligence (AI) methods could prove comparable in terms of prediction accuracy to that of a panel of spine experts. Methods We propose a novel hybrid AI model which computes the probability of spinal surgical recommendations for LSS, based on patient demographic factors, clinical symptom manifestations, and MRI findings. The hybrid model combines a random forest model trained from medical vignette data reviewed by surgeons, with an expert Bayesian network model built from peer-reviewed literature and the expert opinions of a multidisciplinary team in spinal surgery, rehabilitation medicine, interventional and diagnostic radiology. Sets of 400 and 100 medical vignettes reviewed by surgeons were used for training and testing. Results The model demonstrated high predictive accuracy, with a root mean square error (RMSE) between model predictions and ground truth of 0.0964, while the average RMSE between individual doctor's recommendations and ground truth was 0.1940. For dichotomous classification, the AUROC and Cohen's kappa were 0.9266 and 0.6298, while the corresponding average metrics based on individual doctor's recommendations were 0.8412 and 0.5659, respectively. Conclusions 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.

Determining Prior Authorization Approval for Lumbar Stenosis Surgery With Machine Learning

“…In a previous article, Mourad et al found similar results for prediction error (AUROC and Cohen’s kappa were .9266 and .6298 respectively) using a hybrid AI model in determining candidates for lumbar surgery in LSS based on surgeon decisions on medical vignettes. 10 Similarly, another study showed similar prediction error (AUROC = .90) with a cohort of 387 patients. 11 Interestingly, Wilson et al obtained good predictions with ML on MRI imaging only, with AUROC = .88.…”

“…7,8 Other ML approaches included surgery decision making to identify surgical candidates based on surgeon's recommendation 9 or predicting postoperative outcomes. 10,11 Here, we propose a novel ML approach to compute the recommendation probability of spinal surgery for LSS based on MD decision making instead of surgeon's recommendation. The model consists of a random forest model trained to accurately estimate model parameters from medical vignette data reviewed by MDs.…”

“… 7 , 8 Other ML approaches included surgery decision making to identify surgical candidates based on surgeon’s recommendation 9 or predicting postoperative outcomes. 10 , 11 …”

Emerging Technologies within Spine Surgery

“…Mourad et al created a hybrid AI model that evaluated clinical symptoms, MRI, and demographic factors to determine surgical candidacy for lumbar spinal surgery. Their model performed in a similar way to a multidisciplinary team, which included five fellowship-trained spine surgeons [45]. A separate retrospective study had 86% agreement in its surgical plan, with the actual treatment course using demographics, medical history, patient-reported outcome measures, and radiographic parameters as guidance [46].…”