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

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