University of Toulouse, CNRS, UPS, 31062, Toulouse, France.
Remedy Logic, 1177 Avenue of the Americas, 5th Floor, New York, NY, 10036, USA.
Eur Spine J. 2022 Aug;31(8):2149-2155. doi: 10.1007/s00586-022-07307-7. Epub 2022 Jul 8.
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.
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.
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.
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.
腰椎管狭窄症（LSS）是美国每年影响数十万成年人的一种疾病，与巨大的经济负担有关。目前，确定 LSS 手术适应证的决策实践往往是主观的，且具有临床医生特异性。在这项研究中，我们假设人工智能（AI）方法的性能在预测准确性方面可以与一组脊柱专家相媲美。
我们提出了一种新的混合 AI 模型，该模型基于患者人口统计学因素、临床症状表现和 MRI 结果，计算 LSS 脊柱手术推荐的概率。该混合模型将基于外科医生审查的医学小插曲数据训练的随机森林模型，与基于同行评议文献和脊柱外科、康复医学、介入和诊断放射学多学科团队专家意见构建的专家贝叶斯网络模型相结合。使用 400 组和 100 组外科医生审查的医学小插曲进行训练和测试。
该模型表现出很高的预测准确性，模型预测与真实值之间的均方根误差（RMSE）为 0.0964，而单个医生建议与真实值之间的平均 RMSE 为 0.1940。对于二分类，AUROC 和 Cohen's kappa 分别为 0.9266 和 0.6298，而基于单个医生建议的相应平均指标分别为 0.8412 和 0.5659。
我们的研究结果表明，AI 可用于自动评估 LSS 的手术适应证，其性能可与多学科医生小组相媲美。
