Abel Frederik, Garcia Eugene, Andreeva Vera, Nikolaev Nikolai S, Kolisnyk Serhii, Sarbaev Ruslan, Novikov Ivan, Kozinchenko Evgeniy, Kim Jack, Rusakov Andrej, Mourad Raphael, Lebl Darren R
Department of Spine Surgery, Hospital for Special Surgery, New York, New York, USA.
Remedy Logic, New York, New York, USA.
World Neurosurg. 2024 Jan;181:e953-e962. doi: 10.1016/j.wneu.2023.11.020. Epub 2023 Nov 10.
Symptomatic lumbar spinal stenosis (LSS) leads to functional impairment and pain. While radiologic characterization of the morphological stenosis grade can aid in the diagnosis, it may not always correlate with patient symptoms. Artificial intelligence (AI) may diagnose symptomatic LSS in patients solely based on self-reported history questionnaires.
We evaluated multiple machine learning (ML) models to determine the likelihood of LSS using a self-reported questionnaire in patients experiencing low back pain and/or numbness in the legs. The questionnaire was built from peer-reviewed literature and a multidisciplinary panel of experts. Random forest, lasso logistic regression, support vector machine, gradient boosting trees, deep neural networks, and automated machine learning models were trained and performance metrics were compared.
Data from 4827 patients (4690 patients without LSS: mean age 62.44, range 27-84 years, 62.8% females, and 137 patients with LSS: mean age 50.59, range 30-71 years, 59.9% females) were retrospectively collected. Among the evaluated models, the random forest model demonstrated the highest predictive accuracy with an area under the receiver operating characteristic curve (AUROC) between model prediction and LSS diagnosis of 0.96, a sensitivity of 0.94, a specificity of 0.88, a balanced accuracy of 0.91, and a Cohen's kappa of 0.85.
Our results indicate that ML can automate the diagnosis of LSS based on self-reported questionnaires with high accuracy. Implementation of standardized and intelligence-automated workflow may serve as a supportive diagnostic tool to streamline patient management and potentially lower health care costs.
有症状的腰椎管狭窄症（LSS）会导致功能障碍和疼痛。虽然形态学狭窄程度的影像学特征有助于诊断，但它可能并不总是与患者症状相关。人工智能（AI）可能仅根据自我报告的病史问卷来诊断有症状的LSS患者。
我们评估了多个机器学习（ML）模型，以使用自我报告问卷来确定LSS在经历腰痛和/或腿部麻木的患者中的可能性。该问卷是根据同行评审文献和多学科专家小组编制的。对随机森林、套索逻辑回归、支持向量机、梯度提升树、深度神经网络和自动化机器学习模型进行了训练，并比较了性能指标。
回顾性收集了4827例患者的数据（4690例无LSS患者：平均年龄62.44岁，范围27 - 84岁，女性占62.8%；137例LSS患者：平均年龄50.59岁，范围30 - 71岁，女性占59.9%）。在评估的模型中，随机森林模型显示出最高的预测准确性，模型预测与LSS诊断之间的受试者操作特征曲线下面积（AUROC）为0.96，敏感性为0.94，特异性为0.88，平衡准确性为0.91，Cohen's kappa为0.85。
我们的结果表明，ML可以基于自我报告问卷高精度地自动诊断LSS。实施标准化和智能自动化工作流程可作为一种支持性诊断工具，以简化患者管理并可能降低医疗保健成本。
