0 663

Cited 17 times in

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

 Beung-Chul Ahn  ;  Jea-Woo So  ;  Chun-Bong Synn  ;  Tae Hyung Kim  ;  Jae Hwan Kim  ;  Yeongseon Byeon  ;  Young Seob Kim  ;  Seong Gu Heo  ;  San-Duk Yang  ;  Mi Ran Yun  ;  Sangbin Lim  ;  Su-Jin Choi  ;  Wongeun Lee  ;  Dong Kwon Kim  ;  Eun Ji Lee  ;  Seul Lee  ;  Doo-Jae Lee  ;  Chang Gon Kim  ;  Sun Min Lim  ;  Min Hee Hong  ;  Byoung Chul Cho  ;  Kyoung-Ho Pyo  ;  Hye Ryun Kim 
 EUROPEAN JOURNAL OF CANCER, Vol.153 : 179-189, 2021-08 
Journal Title
Issue Date
Anti–programmed death-1 ; Clinical decision support system ; Immune checkpoint inhibitor ; Lung cancer ; Machine learning ; Non-invasive biomarker
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.
Full Text
Appears in Collections:
1. College of Medicine (의과대학) > BioMedical Science Institute (의생명과학부) > 1. Journal Papers
1. College of Medicine (의과대학) > Dept. of Internal Medicine (내과학교실) > 1. Journal Papers
Yonsei Authors
Kim, Young Seob(김영섭)
Kim, Jae Hwan(김재환)
Kim, Chang Gon(김창곤)
Kim, Hye Ryun(김혜련) ORCID logo https://orcid.org/0000-0002-1842-9070
Byeon, Yeongseon(변영선)
Ahn, Beung-Chul(안병철) ORCID logo https://orcid.org/0000-0002-2579-2791
Lim, Sun Min(임선민)
Cho, Byoung Chul(조병철) ORCID logo https://orcid.org/0000-0002-5562-270X
Pyo, Kyoung Ho(표경호) ORCID logo https://orcid.org/0000-0001-5428-0288
Heo, Seong Gu(허성구)
Hong, Min Hee(홍민희) ORCID logo https://orcid.org/0000-0003-3490-2195
사서에게 알리기


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.