Ogliari Francesca Rita, Traverso Alberto, Barbieri Simone, Montagna Marco, Chiabrando Filippo, Versino Enrico, Bosco Antonio, Lin Alessia, Ferrara Roberto, Oresti Sara, Damiano Giuseppe, Viganò Maria Grazia, Ferrara Michele, Riva Silvia Teresa, Nuccio Antonio, Venanzi Francesco Maria, Vignale Davide, Cicala Giuseppe, Palmisano Anna, Cascinu Stefano, Gregorc Vanesa, Bulotta Alessandra, Esposito Antonio, Tacchetti Carlo, Reni Michele
Università Vita-Salute San Raffaele, Milan, Italy; Department of Medical Oncology, IRCCS Ospedale San Raffaele, Milan, Italy.
Università Vita-Salute San Raffaele, Milan, Italy.
Lung Cancer. 2025 Jan;199:108075. doi: 10.1016/j.lungcan.2024.108075. Epub 2024 Dec 31.
Artificial intelligence (AI) models are emerging as promising tools to identify predictive features among data coming from health records. Their application in clinical routine is still challenging, due to technical limits and to explainability issues in this specific setting. Response to standard first-line immunotherapy (ICI) in metastatic Non-Small-Cell Lung Cancer (NSCLC) is an interesting population for machine learning (ML), since up to 30% of patients do not benefit.
We retrospectively collected all consecutive patients with PD-L1 ≥ 50 % metastatic NSCLC treated with first-line ICI at our institution between 2017 and 2021. Demographic, laboratory, molecular and clinical data were retrieved manually or automatically according to data sources. Primary aim was to explore feasibility of ML models in clinical routine setting and to detect problems and solutions for everyday implementation. Early progression was used as preliminary endpoint to test our algorithm.
Out of 123 patients, 106 were included, 52/106 (49 %) had disease progression or died within 3 months of start of ICI. Early progression correlated with increased neutrophil percentage (>80 % of white blood cells), neutrophil/lymphocyte ratio (≥8) and lower-range PD-L1 status (<70 %) at baseline, which was consistent with literature. Automated ML (AutoML) models run on our dataset reached precision scores around 80 %, with Voting Ensemble emerging as best performing model, while white-box models (such as Shapley Additive exPlanations) provided better explainability. In all AutoML models, laboratory features were the top selected features, whilst clinical ones needed more pre-processing before gaining relevance, which was consistent with different data extraction (automatic versus manual) and missing data rates.
ML models' application is feasible in clinical practice and can trustworthily predict early progression during first-line ICI for metastatic NSCLC. Solving pre-analytical issues is key for future improvement, focusing on automatic tools for data extraction, collection and explainability.
人工智能（AI）模型正成为从健康记录数据中识别预测特征的有前景的工具。由于技术限制以及该特定环境下的可解释性问题，其在临床常规中的应用仍然具有挑战性。转移性非小细胞肺癌（NSCLC）对标准一线免疫治疗（ICI）的反应是机器学习（ML）的一个有趣研究对象，因为高达30%的患者无法从中获益。
我们回顾性收集了2017年至2021年间在我们机构接受一线ICI治疗的所有连续的PD-L1≥50%的转移性NSCLC患者。根据数据来源手动或自动检索人口统计学、实验室、分子和临床数据。主要目的是探索ML模型在临床常规环境中的可行性，并检测日常实施中的问题和解决方案。早期进展被用作测试我们算法的初步终点。
在123例患者中，106例被纳入研究，其中52/106（49%）在ICI开始后的3个月内出现疾病进展或死亡。早期进展与基线时中性粒细胞百分比增加（>白细胞的80%）、中性粒细胞/淋巴细胞比率（≥8）以及较低范围的PD-L1状态（<70%）相关，这与文献一致。在我们的数据集上运行的自动化ML（AutoML）模型达到了约80%的精确率得分，投票集成模型表现最佳，而白盒模型（如Shapley值加法解释）提供了更好的可解释性。在所有AutoML模型中，实验室特征是最常被选中的特征，而临床特征在获得相关性之前需要更多的预处理，这与不同的数据提取方式（自动与手动）和缺失数据率一致。
ML模型在临床实践中的应用是可行的，并且可以可靠地预测转移性NSCLC一线ICI治疗期间的早期进展。解决分析前问题是未来改进的关键，重点是数据提取、收集和可解释性的自动工具。
