Artificial intelligence in predicting efficacy and toxicity of Immunotherapy: Applications, challenges, and future directions

Abstract

Immune checkpoint inhibitors (ICIs) have revolutionized cancer treatment, becoming a standard approach for various tumor types. Consequently, accurately predicting their efficacy has become crucial in clinical practice. Artificial intelligence (AI) has emerged as a powerful tool for extracting meaningful insights from complex clinical datasets, showing immense potential to transform medical decision-making. Therefore, the integration of AI techniques into immunotherapy facilitates the development of predictive models for immunotherapeutic efficacy based on radiological, genomic, and pathological data, ultimately refining the precision treatment of tumors. In this review, we systematically summarize the application of AI in predicting the efficacy of ICIs, and briefly address the challenges and future directions in this field.