Advancing predictive markers in lung adenocarcinoma: A machine learning‐based immunotherapy prognostic prediction signature

• DOI: 10.1002/tox.24284
• Publication Date: 2024-04-09T12:11:51Z
• Authors: Zhongyan Li; Shengbin Pei; Yanjuan Wang; Ge Zhang; Haoran Lin; Shiyang Dong
• Keywords: 03 medical and health sciences; 0302 clinical medicine

Abstract The prognosis of lung adenocarcinoma (LUAD) is generally poor. Immunotherapy has emerged as a promising therapeutic modality, demonstrating remarkable potential for substantially prolonging the overall survival individuals afflicted with LUAD. However, there currently lack reliable signatures identifying patients who would benefit from immunotherapy. We conducted comparative analysis two immunotherapy cohorts (OAK and POPLAR) utilized single‐factor COX regression to identify genes that significantly impact Based on TCGA‐LUAD dataset, we employed combination 101 machine learning algorithms construct model selected optimal model. was validated five GEO datasets compared 144 previously published assess its performance. Subsequently, explored underlying biological mechanisms through tumor mutation burden analysis, enrichment immune infiltration analysis. An prognostic prediction signature (IPPS) constructed based 13 genes, showing robust performance in dataset. IPPS exhibited consistent predictive accuracy validation cohorts. Compared signatures, consistently ranked among top terms C‐index values. Further exploration revealed differences between high low‐IPPS groups burden, pathway enrichment, infiltration. demonstrates strong capabilities LUAD patients, offering suitable candidates contribute precision treatment strategies