1Mayo Clinic Neuro-Informatics Laboratory and.
2Department of Neurological Surgery, Mayo Clinic, Rochester, Minnesota.
Neurosurg Focus. 2023 Jun;54(6):E15. doi: 10.3171/2023.3.FOCUS22653.
Chordomas are rare tumors from notochordal remnants and account for 1%-4% of all primary bone malignancies, often arising from the clivus and sacrum. Despite margin-negative resection and postoperative radiotherapy, chordomas often recur. Further, immunohistochemical (IHC) markers have not been assessed as predictive of chordoma recurrence. The authors aimed to identify the IHC markers that are predictive of postoperative long-term (≥ 1 year) chordoma recurrence by using trained multiple tree-based machine learning (ML) algorithms.
The authors reviewed the records of patients who had undergone treatment for clival and spinal chordomas between January 2017 and June 2021 across the Mayo Clinic enterprise (Minnesota, Florida, and Arizona). Demographics, type of treatment, histopathology, and other relevant clinical factors were abstracted from each patient record. Decision tree and random forest classifiers were trained and tested to predict long-term recurrence based on unseen data using an 80/20 split.
One hundred fifty-one patients diagnosed and treated for chordomas were identified: 58 chordomas of the clivus, 48 chordomas of the mobile spine, and 45 chordomas sacrococcygeal in origin. Patients diagnosed with cervical chordomas were the oldest among all groups (58 ± 14 years, p = 0.009). Most patients were male (n = 91, 60.3%) and White (n = 139, 92.1%). Most patients underwent resection with or without radiation therapy (n = 129, 85.4%). Subtotal resection followed by radiation therapy (n = 51, 33.8%) was the most common treatment modality, followed by gross-total resection then radiation therapy (n = 43, 28.5%). Multivariate analysis showed that S100 and pan-cytokeratin are more likely to predict the increase in the risk of postoperative recurrence (OR 3.67, 95% CI 1.09-12.42, p= 0.03; and OR 3.74, 95% CI 0.05-2.21, p = 0.02, respectively). In the decision tree analysis, a clinical follow-up > 1897 days was found in 37% of encounters and a 90% chance of being classified for recurrence (accuracy = 77%). Random forest analysis (n = 500 trees) showed that patient age, type of surgical treatment, location of tumor, S100, pan-cytokeratin, and EMA are the factors predicting long-term recurrence.
The IHC and clinicopathological variables combined with tree-based ML tools successfully demonstrated a high capacity to identify recurrence patterns with an accuracy of 77%. S100, pan-cytokeratin, and EMA were the IHC drivers of recurrence. This shows the power of ML algorithms in analyzing and predicting outcomes of rare conditions of a small sample size.
脊索瘤是源自脊索残余的罕见肿瘤，占所有原发性骨恶性肿瘤的 1%-4%，通常起源于颅底和骶骨。尽管边缘阴性切除和术后放疗，脊索瘤仍经常复发。此外，免疫组织化学（IHC）标志物尚未被评估为预测脊索瘤复发的指标。作者旨在使用经过训练的多树基机器学习（ML）算法确定具有预测术后长期（≥1 年）脊索瘤复发的 IHC 标志物。
作者回顾了 2017 年 1 月至 2021 年 6 月期间在梅奥诊所企业（明尼苏达州、佛罗里达州和亚利桑那州）接受治疗的颅底和脊柱脊索瘤患者的记录。从每位患者的记录中提取人口统计学、治疗类型、组织病理学和其他相关临床因素。使用 80/20 分割，使用未见数据训练和测试决策树和随机森林分类器，以预测长期复发。
确定了 151 名被诊断和治疗脊索瘤的患者：58 例颅底脊索瘤、48 例活动脊柱脊索瘤和 45 例尾骨脊索瘤。诊断为颈椎脊索瘤的患者在所有组中年龄最大（58±14 岁，p=0.009）。大多数患者为男性（n=91，60.3%）和白人（n=139，92.1%）。大多数患者接受了手术切除联合或不联合放疗（n=129，85.4%）。次全切除后放疗（n=51，33.8%）是最常见的治疗方式，其次是大体全切除后放疗（n=43，28.5%）。多变量分析显示 S100 和泛细胞角蛋白更有可能预测术后复发风险增加（OR 3.67，95%CI 1.09-12.42，p=0.03；OR 3.74，95%CI 0.05-2.21，p=0.02）。在决策树分析中，37%的就诊患者的临床随访时间超过 1897 天，复发的概率为 90%（准确率=77%）。随机森林分析（n=500 棵树）显示，患者年龄、手术治疗类型、肿瘤位置、S100、泛细胞角蛋白和 EMA 是预测长期复发的因素。
IHC 和临床病理变量与基于树的 ML 工具相结合，成功地证明了具有 77%准确率的识别复发模式的高能力。S100、泛细胞角蛋白和 EMA 是复发的 IHC 驱动因素。这表明 ML 算法在分析和预测小样本量的罕见疾病结果方面具有强大的功能。
