Division of Brain, Imaging & Behaviour, Krembil Brain Institute, Toronto Western Hospital, University Health Network, Toronto, Ontario, Canada; Institute of Medical Science, Faculty of Medicine, University of Toronto, Toronto, Ontario, Canada.
Schulich School of Medicine & Dentistry, Western University, London, Ontario, Canada.
Neuroimage Clin. 2021;31:102706. doi: 10.1016/j.nicl.2021.102706. Epub 2021 May 25.
Trigeminal neuralgia, a severe chronic neuropathic pain disorder, is widely believed to be amenable to surgical treatments. Nearly 20% of patients, however, do not have adequate pain relief after surgery. Objective tools for personalized pre-treatment prognostication of pain relief following surgical interventions can minimize unnecessary surgeries and thus are of substantial benefit for patients and clinicians.
To determine if pre-treatment regional brain morphology-based machine learning models can prognosticate 1 year response to Gamma Knife radiosurgery for trigeminal neuralgia.
We used a data-driven approach that combined retrospective structural neuroimaging data and support vector machine-based machine learning to produce robust multivariate prediction models of pain relief following Gamma Knife radiosurgery for trigeminal neuralgia. Surgical response was defined as ≥ 75% pain relief 1 year post-treatment. We created two prediction models using pre-treatment regional brain gray matter morphology (cortical thickness or surface area) to distinguish responders from non-responders to radiosurgery. Feature selection was performed through sequential backwards selection algorithm. Model out-of-sample generalizability was estimated via stratified 10-fold cross-validation procedure and permutation testing.
In 51 trigeminal neuralgia patients (35 responders, 16 non-responders), machine learning models based on pre-treatment regional brain gray matter morphology (14 regional surface areas or 13 regional cortical thicknesses) provided robust a priori prediction of surgical response. Cross-validation revealed the regional surface area model was 96.7% accurate, 100.0% sensitive, and 89.1% specific while the regional cortical thickness model was 90.5% accurate, 93.5% sensitive, and 83.7% specific. Permutation testing revealed that both models performed beyond pure chance (p < 0.001). The best predictor for regional surface area model and regional cortical thickness model was contralateral superior frontal gyrus and contralateral isthmus cingulate gyrus, respectively.
Our findings support the use of machine learning techniques in subsequent investigations of chronic neuropathic pain. Furthermore, our multivariate framework provides foundation for future development of generalizable, artificial intelligence-driven tools for chronic neuropathic pain treatments.
三叉神经痛是一种严重的慢性神经性疼痛疾病，普遍认为其适合手术治疗。然而，近 20%的患者手术后疼痛缓解不充分。用于手术干预后疼痛缓解的个性化术前预测的客观工具可以最大限度地减少不必要的手术，因此对患者和临床医生都有很大的益处。
确定术前基于区域脑形态的机器学习模型是否可以预测伽玛刀放射外科治疗三叉神经痛的 1 年疗效。
我们采用了一种数据驱动的方法，结合回顾性结构神经影像学数据和基于支持向量机的机器学习，生成伽玛刀放射外科治疗三叉神经痛后疼痛缓解的稳健多元预测模型。手术反应定义为治疗后 1 年疼痛缓解≥75%。我们使用术前区域脑灰质形态（皮质厚度或表面积）创建了两个预测模型，以区分放射外科治疗的 responder 和 non-responder。通过顺序反向选择算法进行特征选择。通过分层 10 折交叉验证程序和置换测试来估计模型的样本外泛化能力。
在 51 例三叉神经痛患者（35 例 responder，16 例 non-responder）中，基于术前区域脑灰质形态（14 个区域表面积或 13 个区域皮质厚度）的机器学习模型提供了手术反应的可靠先验预测。交叉验证显示，区域表面积模型的准确率为 96.7%，敏感性为 100.0%，特异性为 89.1%，而区域皮质厚度模型的准确率为 90.5%，敏感性为 93.5%，特异性为 83.7%。置换测试表明，两个模型的表现均优于纯随机（p<0.001）。区域表面积模型和区域皮质厚度模型的最佳预测因子分别为对侧额上回和对侧扣带回峡部。
我们的发现支持在随后的慢性神经性疼痛研究中使用机器学习技术。此外，我们的多元框架为开发可推广的、基于人工智能的慢性神经性疼痛治疗工具提供了基础。
