Department of Respiratory Medicine, Nagoya University Graduate School of Medicine, 65 Tsurumai-cho, Showa-ku, Nagoya, Aichi, 4668550, Japan.
Medical IT Center, Nagoya University Hospital, Nagoya, Japan.
BMC Cancer. 2024 Nov 18;24(1):1417. doi: 10.1186/s12885-024-13190-w.
Multiple first-line treatment options have been developed for advanced non-small cell lung cancer (NSCLC) in each subgroup determined by predictive biomarkers, specifically driver oncogene and programmed cell death ligand-1 (PD-L1) status. However, the methodology for optimal treatment selection in individual patients is not established. This study aimed to develop artificial intelligence (AI)-based personalized survival prediction model according to treatment selection.
The prediction model was built based on random survival forest (RSF) algorithm using patient characteristics, anticancer treatment histories, and radiomics features of the primary tumor. The predictive accuracy was validated with external test data and compared with that of cox proportional hazard (CPH) model.
A total of 459 patients (training, n = 299; test, n = 160) with advanced NSCLC were enrolled. The algorithm identified following features as significant factors associated with survival: age, sex, performance status, Brinkman index, comorbidity of chronic obstructive pulmonary disease, histology, stage, driver oncogene status, tumor PD-L1 expression, administered anticancer agent, six markers of blood test (sodium, lactate dehydrogenase, etc.), and three radiomics features associated with tumor texture, volume, and shape. The C-index of RSF model for test data was 0.841, which was higher than that of CPH model (0.775, P < 0.001). Furthermore, the RSF model enabled to identify poor survivor treated with pembrolizumab because of tumor PD-L1 high expression and those treated with driver oncogene targeted therapy according to driver oncogene status.
The proposed AI-based algorithm accurately predicted the survival of each patient with advanced NSCLC. The AI-based methodology will contribute to personalized medicine.
The trial design was retrospectively registered study performed in accordance with the Declaration of Helsinki and approved by the Institutional Review Board of Nagoya University Graduate School of Medicine (approval: 2020 - 0287).
在每个预测生物标志物（特别是驱动致癌基因和程序性死亡配体 1（PD-L1）状态）确定的亚组中，已经为晚期非小细胞肺癌（NSCLC）开发了多种一线治疗选择。然而，尚未建立针对个体患者的最佳治疗选择方法。本研究旨在根据治疗选择开发基于人工智能（AI）的个性化生存预测模型。
该预测模型是基于随机生存森林（RSF）算法构建的，该算法使用患者特征、抗癌治疗史和原发肿瘤的放射组学特征。使用外部测试数据验证了预测准确性，并与 Cox 比例风险（CPH）模型进行了比较。
共纳入 459 名晚期 NSCLC 患者（训练，n=299；测试，n=160）。该算法确定了以下特征为与生存相关的重要因素：年龄、性别、表现状态、Brinkman 指数、慢性阻塞性肺疾病合并症、组织学、分期、驱动致癌基因状态、肿瘤 PD-L1 表达、给予的抗癌药物、六项血液检查标志物（钠、乳酸脱氢酶等）以及与肿瘤纹理、体积和形状相关的三个放射组学特征。测试数据的 RSF 模型的 C 指数为 0.841，高于 CPH 模型（0.775，P<0.001）。此外，RSF 模型能够识别由于肿瘤 PD-L1 高表达而接受 pembrolizumab 治疗的生存较差的患者，以及根据驱动致癌基因状态接受驱动致癌基因靶向治疗的患者。
所提出的基于 AI 的算法准确预测了每个晚期 NSCLC 患者的生存情况。基于 AI 的方法将有助于个性化医学。
该试验设计是根据赫尔辛基宣言进行的回顾性注册研究，并得到名古屋大学研究生院医学伦理委员会的批准（批准号：2020-0287）。
