Clinical decision support algorithm based on machine learning to assess the clinical response to anti–programmed death-1 therapy in patients with non–small-cell lung cancer. (August 2021)

• Record Type: Journal Article
• Authors: Ahn, Beung-Chul; So, Jea-Woo; Synn, Chun-Bong; Kim, Tae Hyung; Kim, Jae Hwan; Byeon, Yeongseon; Kim, Young Seob; Heo, Seong Gu; Yang, San-Duk; Yun, Mi Ran; Lim, Sangbin; Choi, Su-Jin; Lee, Wongeun; Kim, Dong Kwon; Lee, Eun Ji; Lee, Seul; Lee, Doo-Jae; Kim, Chang Gon; Lim, Sun Min; Hong, Min Hee; Cho, Byoung Chul; Pyo, Kyoung-Ho; Kim, Hye Ryun
• Is Part Of: European journal of cancer. Volume 153(2021)
• Page Start: 179
• Page End: 189
• Publication Date: 2021-08
• Subjects: Machine learning -- Clinical decision support system -- Lung cancer -- Immune checkpoint inhibitor -- Anti–programmed death-1 -- Non-invasive biomarker; Cancer -- Periodicals; Neoplasms -- Periodicals; Cancer -- Périodiques; Cancer; Tumors; Electronic journals; Periodicals; Electronic journals; 616.994
• DOI: 10.1016/j.ejca.2021.05.019
• Languages: English
• ISSNs: 0959-8049

Abstract

Abstract: Objective: Anti–programmed death (PD)-1 therapy confers sustainable clinical benefits for patients with non–small-cell lung cancer (NSCLC), but only some patients respond to the treatment. Various clinical characteristics, including the PD-ligand 1 (PD-L1) level, are related to the anti–PD-1 response; however, none of these can independently serve as predictive biomarkers. Herein, we established a machine learning (ML)–based clinical decision support algorithm to predict the anti–PD-1 response by comprehensively combining the clinical information. Materials and methods: We collected clinical data, including patient characteristics, mutations and laboratory findings, from the electronic medical records of 142 patients with NSCLC treated with anti–PD-1 therapy; these were analysed for the clinical outcome as the discovery set. Nineteen clinically meaningful features were used in supervised ML algorithms, including LightGBM, XGBoost, multilayer neural network, ridge regression and linear discriminant analysis, to predict anti–PD-1 responses. Based on each ML algorithm's prediction performance, the optimal ML was selected and validated in an independent validation set of PD-1 inhibitor–treated patients. Results: Several factors, including PD-L1 expression, tumour burden and neutrophil-to-lymphocyte ratio, could independently predict the anti–PD-1 response in the discovery set. ML platforms based on the LightGBM algorithm using 19 clinical features showed more significant prediction performance (area under the curve [AUC] 0.788) than on individual clinical features and traditional multivariate logistic regression (AUC 0.759). Conclusion: Collectively, our LightGBM algorithm offers a clinical decision support model to predict the anti–PD-1 response in patients with NSCLC. Graphical abstract: Image 1 Highlights: Programmed death-ligand 1 expression alone may not reflect the response to programmed cell death protein 1 (PD-1) inhibitors. Various clinical characteristics are related to the anti–PD-1 response. We established a machine learning–based algorithm to predict the anti–PD-1 response.