Fa'ak Faisal, Coudray Nicolas, Jour George, Ibrahim Milad, Illa-Bochaca Irineu, Qiu Shi, Claudio Quiros Adalberto, Yuan Ke, Johnson Douglas B, Rimm David L, Weber Jeffrey S, Tsirigos Aristotelis, Osman Iman
Division of Medical Oncology, Washington University School of Medicine, St. Louis, Missouri.
Laura and Isaac Perlmutter Cancer Center, NYU Langone Health, New York, New York.
Clin Cancer Res. 2025 Aug 14;31(16):3526-3536. doi: 10.1158/1078-0432.CCR-24-3720.
Cancer treatment has been revolutionized by immune checkpoint inhibitors (ICI). However, a subset of patients do not respond and/or they experience significant adverse events. Attempts to integrate reliable biomarkers of ICI response as part of standard care have been hampered by limited generalizability. We previously reported our supervised machine learning (ML) model in a retrospective cohort of metastatic melanoma.
In this study, we expanded our testing to include larger cohorts of patients with melanoma accrued at several sites, including patients enrolled in clinical trials in both adjuvant and metastatic settings. We examined pretreatment hematoxylin and eosin slides from 639 patients with stage III/IV melanoma treated with ICIs [anti-cytotoxic T-lymphocyte-associated protein 4 (n = 212), anti-programmed death 1 (n = 271), or the combination (n = 156)]. We tested the generalizability of our supervised ML algorithm to predict response to ICIs in the metastatic melanoma cohort and then developed a self-supervised ML model to identify the histologic morphologies associated with patients' survival following ICI use in adjuvant and metastatic melanoma cohorts.
We predicted the response to ICI treatment with an AUC of 0.72. The deep convolutional neural network classified patients into high and low risk based on their likelihood of progression-free survival (P < 0.0001). We uncovered a novel association of specific histomorphologic tumor features-epithelioid histology and a low tumor-stroma ratio-with survival following ICI treatment.
Our data support the generalizability of our developed ML algorithm in predicting response to ICI treatment in patients with metastatic unresectable melanoma. We also showed, for the first time, tumor features associated with patients' overall survival.
免疫检查点抑制剂（ICI）彻底改变了癌症治疗方式。然而，有一部分患者没有反应和/或会经历严重的不良事件。将可靠的ICI反应生物标志物纳入标准治疗的尝试因普遍适用性有限而受阻。我们之前在转移性黑色素瘤的回顾性队列中报告了我们的监督机器学习（ML）模型。
在本研究中，我们扩大了测试范围，纳入了在多个地点招募的更大规模的黑色素瘤患者队列，包括参加辅助和转移性治疗临床试验的患者。我们检查了639例接受ICI治疗的III/IV期黑色素瘤患者的治疗前苏木精和伊红染色切片[抗细胞毒性T淋巴细胞相关蛋白4（n = 212）、抗程序性死亡1（n = 271）或联合用药（n = 156）]。我们测试了我们的监督ML算法在转移性黑色素瘤队列中预测ICI反应的普遍适用性，然后开发了一种自监督ML模型，以识别在辅助和转移性黑色素瘤队列中使用ICI后与患者生存相关的组织形态学特征。
我们预测ICI治疗反应的AUC为0.72。深度卷积神经网络根据患者无进展生存的可能性将其分为高风险和低风险（P < 0.0001）。我们发现了特定组织形态学肿瘤特征——上皮样组织学和低肿瘤-基质比——与ICI治疗后生存之间的新关联。
我们的数据支持我们开发的ML算法在预测不可切除转移性黑色素瘤患者对ICI治疗反应方面的普遍适用性。我们还首次展示了与患者总生存相关的肿瘤特征。
