Department of Neurosurgery, Bergman Clinics Amsterdam, Rijksweg 69, 1411 GE Naarden, The Netherlands; Amsterdam UMC, Vrije Universiteit Amsterdam, Neurosurgery, Amsterdam Movement Sciences, de Boelelaan 1117, 1081 HV Amsterdam, The Netherlands; Department of Neurosurgery, Clinical Neuroscience Center, University Hospital Zurich, University of Zurich, Frauenklinikstrasse 10, 8091 Zurich, Switzerland.
Department of Clinical Informatics, Bergman Clinics Amsterdam, Rijksweg 69, 1411 GE Naarden, The Netherlands.
Spine J. 2019 May;19(5):853-861. doi: 10.1016/j.spinee.2018.11.009. Epub 2018 Nov 16.
There is considerable variability in patient-reported outcome measures following surgery for lumbar disc herniation. Individualized prediction tools that are derived from center- or even surgeon-specific data could provide valuable insights for shared decision-making.
To evaluate the feasibility of deriving robust deep learning-based predictive analytics from single-center, single-surgeon data.
Derivation of predictive models from a prospective registry.
Patients who underwent single-level tubular microdiscectomy for lumbar disc herniation.
Numeric rating scales for leg and back pain severity and Oswestry Disability Index scores at 12 months postoperatively.
Data were derived from a prospective registry. We trained deep neural network-based and logistic regression-based prediction models for patient-reported outcome measures. The primary endpoint was achievement of the minimum clinically important difference (MCID) in numeric rating scales and Oswestry Disability Index, defined as a 30% or greater improvement from baseline. Univariate predictors of MCID were also identified using conventional statistics.
A total of 422 patients were included (mean [SD] age: 48.5 [11.5] years; 207 [49%] female). After 1 year, 337 (80%), 219 (52%), and 337 (80%) patients reported a clinically relevant improvement in leg pain, back pain, and functional disability, respectively. The deep learning models predicted MCID with high area-under-the-curve of 0.87, 0.90, and 0.84, as well as accuracy of 85%, 87%, and 75%. The regression models provided inferior performance measures for each of the outcomes.
Our study demonstrates that generating personalized and robust deep learning-based analytics for outcome prediction is feasible even with limited amounts of center-specific data. With prospective validation, the ability to preoperatively and reliably inform patients about the likelihood of symptom improvement could prove useful in patient counselling and shared decision-making.
腰椎间盘突出症手术后患者报告的结局存在很大差异。基于中心甚至外科医生特定数据的个体化预测工具可为共同决策提供有价值的见解。
评估从单中心、单外科医生数据中得出稳健的基于深度学习的预测分析的可行性。
从前瞻性登记处推导预测模型。
接受单节段管状微创椎间盘切除术治疗腰椎间盘突出症的患者。
术后 12 个月腿部和背部疼痛严重程度的数字评定量表和 Oswestry 残疾指数评分。
数据来自前瞻性登记处。我们使用基于深度神经网络和逻辑回归的预测模型对患者报告的结局进行训练。主要终点是达到数字评定量表和 Oswestry 残疾指数的最小临床重要差异（MCID），定义为与基线相比改善 30%或更多。使用常规统计学方法确定 MCID 的单变量预测因素。
共纳入 422 例患者（平均[标准差]年龄：48.5[11.5]岁；207[49%]女性）。1 年后，337（80%）、219（52%）和 337（80%）例患者腿部疼痛、背部疼痛和功能障碍分别报告有临床相关的改善。深度学习模型预测 MCID 的曲线下面积为 0.87、0.90 和 0.84，准确率为 85%、87%和 75%。回归模型在每种结局中提供了较低的性能指标。
我们的研究表明，即使在有限的中心特定数据量的情况下，生成个性化和稳健的基于深度学习的分析来进行结局预测也是可行的。通过前瞻性验证，术前可靠地告知患者症状改善的可能性可能有助于患者咨询和共同决策。
