机器学习模型基于肿瘤负荷对结直肠癌肝转移切除术后预后分层
该国际多中心队列研究纳入2001至2018年1344例结直肠癌肝转移切除术患者,利用机器学习基于肿瘤数目和大小阈值定义肿瘤负荷(ML-TB),并在验证队列中将患者分为3个预后组。低、中、高ML-TB组5年总生存率分别为51.6%、40.9%和23.1%(p < 0.001),ML-TB分层效果优于Fong和GAME评分。
要点
- 机器学习基于肿瘤数目(3个)和最大病灶大小(1.3 cm)定义ML-TB。
- 低、中、高ML-TB组5年总生存率分别为51.6%、40.9%、23.1%。
- ML-TB对5年总生存的分层效果(d=2.73)优于Fong(d=1.61)和GAME(d=0.84)。
核心结论
- 机器学习基于总体肿瘤负荷可将结直肠癌肝转移切除术后患者分为3个预后不同的类别。
- ML-TB在预后分层方面优于其他常用的结直肠癌肝转移预后评分系统。
研究设计与样本
- 国际多中心队列分析,纳入2001至2018年接受肝切除术的结直肠癌肝转移患者,分为训练队列(n=672)和验证队列(n=672)。
- 使用机器学习基于与5年总生存相关的肿瘤数目和大小阈值定义肿瘤负荷(ML-TB)。
- 采用Cohen's d比较ML-TB与Fong评分和Genetic and Morphological Evaluation评分的预后区分能力。
主要发现
- 训练队列和验证队列的中位肿瘤数目(2,IQR 1-3)和大小(3 cm,IQR 2.0-5.0)可比;患者年龄(训练60.8 vs 验证61.0)和术前CEA(训练10.2 ng/mL vs 验证8.3 ng/mL)也相似(p > 0.05)。
- 机器学习在训练队列中得出肿瘤数目(3个)和最大病灶大小(1.3 cm)的最佳截断阈值。
- 验证队列中低、平均、高ML-TB组5年总生存率分别为51.6%、40.9%、23.1%(p < 0.001)。
- ML-TB对5年总生存的分层效果(低 vs 高ML-TB,d=2.73)优于Fong临床评分(d=1.61)和Genetic and Morphological Evaluation评分(d=0.84)。
关键数值与推荐
- ML-TB基于肿瘤数目阈值3个和最大病灶大小阈值1.3 cm定义。
- 验证队列中低、平均、高ML-TB组5年总生存率分别为51.6%、40.9%、23.1%(p < 0.001)。
- ML-TB低 vs 高组Cohen's d=2.73,Fong评分d=1.61,GAME评分d=0.84。
临床怎么用
- 基于肿瘤数目和最大病灶大小计算的ML-TB可用于结直肠癌肝转移切除术后患者的预后分层。
- ML-TB的预后区分能力优于Fong和GAME评分,或可作为现有评分系统的替代或补充工具。
局限性
- 原文未述局限性
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: Assessing overall tumor burden on the basis of tumor number and size may assist in prognostic stratification of patients after resection of colorectal liver metastases (CRLM). We sought to define the prognostic accuracy of tumor burden by using machine learning (ML) algorithms compared with other commonly used prognostic scoring systems. STUDY DESIGN: Patients who underwent hepatectomy for CRLM between 2001 and 2018 were identified from a multi-institutional database and split into training and validation cohorts. ML was used to define tumor burden (ML-TB) based on CRLM tumor number and size thresholds associated with 5-year overall survival. Prognostic ability of ML-TB was compared with the Fong and Genetic and Morphological Evaluation scores using Cohen's d. RESULTS: Among 1,344 patients who underwent resection of CRLM, median tumor number (2, interquartile range 1 to 3) and size (3 cm, interquartile range 2.0 to 5.0) were comparable in the training (n = 672) vs validation (n = 672) cohorts; patient age (training 60.8 vs validation 61.0) and preoperative CEA (training 10.2 ng/mL vs validation 8.3 ng/mL) was also similar (p > 0.05). ML empirically derived optimal cutoff thresholds for number of lesions (3) and size of the largest lesion (1.3 cm) in the training cohort, which were then used to categorize patients in the validation cohort into 3 prognostic groups. Patients with low, average, or high ML-TB had markedly different 5-year overall survival (51.6%, 40.9%, and 23.1%, respectively; p < 0.001). ML-TB was more effective at stratifying patients relative to 5-year overall survival (low vs high ML-TB, d = 2.73) vs the Fong clinical (d = 1.61) or Genetic and Morphological Evaluation (d = 0.84) scores. CONCLUSIONS: Using a large international cohort, ML was able to stratify patients into 3 distinct prognostic categories based on overall tumor burden. ML-TB was noted to be superior to other CRLM prognostic scoring systems.
引用
- Paro A, Hyer MJ, Tsilimigras DI, et al. Machine Learning Approach to Stratifying Prognosis Relative to Tumor Burden after Resection of Colorectal Liver Metastases: An International Cohort Analysis. J Am Coll Surg. 2022. PMID: 35290269. doi:10.1097/XCS.0000000000000094
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。