Artificial intelligence in cancer immunotherapy: current trends in predicting response and personalizing treatment

Sep 22, 2026

Upload by Kurz

Artificial intelligence (AI) can transform cancer immunotherapy by improving prediction of treatment responses, enabling targeted biomarker discovery, and supporting personalised treatment planning. Traditional single-marker biomarkers such as PD-L1, TMB, and MSI fall short for tumour heterogeneity and dynamic tumour microenvironment (TME) assessment. This review synthesises multimodal AI models combining genomics, transcriptomics, radiomics, digital pathology, circulating biomarkers, and clinical evidence to generate composite predictive signatures with stronger discrimination. It also highlights improved translational pipelines for adoptive cell therapy and emerging pathways toward generalisable, privacy-preserving systems, while noting barriers from data heterogeneity, bias, and limited explainability.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages15

Reading Time38 min

AccessFree to download

Introduction

Immunotherapy and therapeutic approaches

Limitations and need for response prediction

Abstract

Multimodal AI for predictive signatures

Applications in adoptive cell therapies

Clinical implementation challenges and future directions

Nosa-Ihaza et al. Journal of the Egyptian National Cancer Institute (2026) 38:30 [https://doi.org/10.1186/s43046-026-00371-w](https://doi.org/10.1186/s43046-026-00371-w) Journal of the Egyptian National Cancer Institute REVIEW Open Access Artificial intelligence in cancer immunotherapy: current trends in predicting response and personalizing treatment Eloghosa Aisosa Nosa-Ihaza1*, Emmanuel Chidera Edeh1, Wol Bol Geng1 and Ebenezer Okenwa1 Abstract Artificial intelligence (AI) can transform cancer immunotherapy by enabling more accurate prediction of treatment responses, the discovery of specific biomarkers, and the development of personalised treatment plans. Traditional single-marker biomarkers (PD-L1, TMB, MSI) lack consistency across tumour types and cannot be used to assess tumour heterogeneity or the dynamic tumour microenvironment (TME) . This review synthesises developments in multimodal AI models that combine genomics, transcriptomics, radiomics, digital pathology (pathomics), circulating biomarkers, and clinical evidence to create composite predictive signatures with significantly better discriminatory value. AUCs over 0.8 have been seen in a few retrospective studies with deep learning and ensemble modelson whole-slide images, CT/MRI/PET radiomics, spatial and single-cell omics, and multi-omics fusion models, but prospective and multicentre validation is scarce, and external validation often shows deterioration in performance. AI is also used to enhance the translational pipelines of adoptive cell therapies (e. g., CAR-T) by improving patientselection, manufacturing (e. g., digital twins), and early toxicity prediction (e. g., CRS, ICANS) . Nevertheless, clinical implementation remains hindered by data heterogeneity, bias, poor longitudinal validation, limited reproducibility, and a lack of transparency in most models, even though prospective, multicenter validation and explainable AI are crucial for clinician trust and regulatory acceptance. New systems such as federated learning, foundation models, spatial omics, digital twins, and wearable monitoring represent paths to generalizable, privacy-preserving, and actionable systems in clinical practice. To achieve the potential of AI, the generation of data will need to be standardized, reporting must be transparent, interdisciplinary, and regulatory frameworks must be strengthened focusing on the practical use of AI and patient safety. By taking these steps, AI could be shifted to prospective clinical decision support, which uses AI to meaningfully enhance personalization and outcomes in cancer immunotherapy based on a retrospective research tool. Keywords Cancer immunotherapy, Artificial intelligence, Treatment response prediction, Biomarker discovery, Tumor microenvironment, Precision oncology *Correspondence: Eloghosa Aisosa Nosa-Ihaza[nosa-ihazaeloghosaaisosa.120950@marwadiuniversity.ac.in](nosa-ihazaeloghosaaisosa.120950@marwadiuniversity.ac.in) Full list of author information is available at the end of the article © The Author(s) 2026. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit [http://creativecommons.org/licenses/by/4.0/](http://creativecommons.org/licenses/by/4.0/.)[.](http://creative

FAQs

How does AI improve cancer immunotherapy beyond traditional biomarkers?

AI supports more accurate prediction of treatment responses, enables discovery of specific biomarkers, and helps build personalised treatment plans. Multimodal signatures can better reflect tumour heterogeneity and the dynamic tumour microenvironment than single markers like PD-L1, TMB, or MSI.

Which data modalities are highlighted for multimodal predictive AI models?

The review highlights composite models combining genomics, transcriptomics, radiomics, digital pathology (pathomics), circulating biomarkers, and clinical evidence. It also discusses whole-slide images, CT/MRI/PET radiomics, spatial and single-cell omics, and multi-omics fusion.

What challenges hinder clinical implementation of AI in this field?

Clinical implementation is hindered by data heterogeneity, bias, poor longitudinal validation, limited reproducibility, and insufficient transparency or lack of explainability in many models. Prospective multicentre validation and external validation often show performance deterioration.

Sep 22, 2026

Upload by Kurz