ABSTRACT
We conducted a comprehensive review of existing prediction models pertaining to the efficacy of immune-checkpoint inhibitor (ICI) and the occurrence of immune-related adverse events (irAEs). The predictive potential of neutrophil-to-lymphocyte ratio (NLR) and platelet-to-lymphocyte ratio (PLR) in determining ICI effectiveness has been extensively investigated, while limited research has been conducted on predicting irAEs. Furthermore, the combined model incorporating NLR and PLR, either with each other or in conjunction with additional markers such as carcinoembryonic antigen, exhibits superior predictive capabilities compared to individual markers alone. NLR and PLR are promising markers for clinical applications. Forthcoming models ought to incorporate established efficacious models and newly identified ones, thereby constituting a multifactor composite model. Furthermore, efforts should be made to explore effective clinical application approaches that enhance the predictive accuracy and efficiency.