脊索瘤是一类罕见的来源于脊索残留物的肿瘤，占所有原发性骨恶性肿瘤的1%至4%，常发生在颅骨和骶骨。尽管进行了边缘负性切除和术后放疗，脊索瘤往往会复发。此外，免疫组化（IHC）标记物尚未评估为预测脊索瘤复发的指标。本研究旨在利用经过训练的多树型机器学习（ML）算法，识别预测术后长期（≥1年）脊索瘤复发的IHC标记物。作者回顾了2017年1月至2021年6月期间，在Mayo Clinic的Minnesota、Florida和Arizona三个地点接受骨瘤和脊柱脊索瘤治疗的患者记录。从每个患者的记录中提取了人口统计学数据、治疗类型、组织病理学以及其他相关临床因素。使用80/20的比例拆分，训练和测试决策树和随机森林分类器，根据未见数据预测长期复发。共确定了151例诊断和治疗脊索瘤的患者：其中58例为颅骨脊索瘤、48例为移动脊柱脊索瘤，45例为骶尾椎脊索瘤。颈部脊索瘤患者是所有组中年龄最大的组（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%）。大多数患者进行了切除术或伴放射疗法（n=129，85.4%）。伴放疗的次全切除（n=51，33.8%）是最常见的治疗方式，其次是全切除再放疗（n=43，28.5%）。多变量分析表明，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；和OR 3.74，95% CI 0.05-2.21，p=0.02，分别）。在决策树分析中，37%的患者出现了>1897天的临床随访，并有90%的机会被分类为复发（准确率=77%）。随机森林分析（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和临床病理学变量与基于树的ML工具的结合成功地展示了识别复发模式的高能力，准确率为77%。S100、泛细胞角蛋白和EMA是复发的IHC驱动因素。这显示了ML算法在分析和预测小样本罕见疾病结果方面的能力。

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.