{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T17:41:09Z","timestamp":1786642869239,"version":"build-2736575974"},"reference-count":44,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:00:00Z","timestamp":1786579200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82372762"],"award-info":[{"award-number":["82372762"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82073211"],"award-info":[{"award-number":["82073211"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangsu Province Capability Improvement Project through Science, Technology and Education, Jiangsu Provincial Medical Key Laboratory","award":["ZDXYS202203"],"award-info":[{"award-number":["ZDXYS202203"]}]},{"name":"Jiangsu Provincial Medical Innovation Center","award":["CXZX202224"],"award-info":[{"award-number":["CXZX202224"]}]},{"name":"Yishan Research Project of Jiangsu Cancer Hospital","award":["YSZD202403"],"award-info":[{"award-number":["YSZD202403"]}]},{"name":"Research Project of Jiangsu Cancer Hospital","award":["RCYQ202401"],"award-info":[{"award-number":["RCYQ202401"]}]},{"name":"Research Project of Jiangsu Cancer Hospital","award":["XHMS202406"],"award-info":[{"award-number":["XHMS202406"]}]},{"name":"Jiangsu Provincial Cadre Healthcare Research Project","award":["BJ24023"],"award-info":[{"award-number":["BJ24023"]}]},{"name":"Frontier Technologies R&D Program of Jiangsu","award":["BF2025617"],"award-info":[{"award-number":["BF2025617"]}]}],"content-domain":{"domain":["www.plosdigitalhealth.org"],"crossmark-restriction":false},"short-container-title":["PLOS Digit Health"],"abstract":"<jats:p>While effective against non-small cell lung cancer (NSCLC), PD-1 inhibitors can induce immune-related adverse events (irAEs), occurring in up to 15.2% of patients and potentially fatal. Currently, effective predictive biomarkers capable of simultaneously forecasting both irAEs and immune checkpoint inhibitor (ICI) responders remain elusive. This limitation hinders the safe clinical application of these agents. This study enrolled 333 advanced NSCLC patients treated with PD-1 inhibitor monotherapy or combination therapy. CT imaging features were extracted using radiomics and deep-learning approaches. Three unimodal and two multimodal models were constructed to predict irAEs (Grade \u22653) and ICI responders in parallel. The SHAP algorithm was used to identify clinical features contributing to the prediction of both irAEs and ICI responders. The CDML\u2013DenseNet model, integrating clinical features with deep-learning\u2013derived radiomics features (DenseNet), demonstrated superior performance in predicting irAEs (AUC\u2009=\u20090.85), outperforming single-modal radiomics models. For ICI responder prediction, the CDML\u2013DenseNet model achieved an AUC of 0.866. The Prognostic Nutritional Index (PNI) was identified as a key feature in both irAEs and ICI responder prediction models. Patients who were non-responders to ICIs but experienced irAEs had significantly lower PNI (46.8\u2009\u00b1\u20098.779, P\u2009&lt;\u20090.05) compared with ICI responders without irAEs. Our multimodal CDML\u2013DenseNet model effectively predicts both irAEs and ICI responders in NSCLC patients receiving PD-1 inhibitors. This approach provides a novel framework for balancing immunotherapy efficacy and toxicity. Furthermore, the readily available and cost-effective PNI offers clinicians a practical tool to identify potential non-responders experiencing irAEs and to refine treatment decisions.<\/jats:p>","DOI":"10.1371\/journal.pdig.0001568","type":"journal-article","created":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T17:21:40Z","timestamp":1786641700000},"page":"e0001568","update-policy":"https:\/\/doi.org\/10.1371\/journal.pdig.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["AI-driven dual-task prediction model for co-stratifying efficacy and toxicity in NSCLC immunotherapy"],"prefix":"10.1371","volume":"5","author":[{"given":"Hanlin","family":"Ding","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuting","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siqi","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuzhong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuemin","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yipeng","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjie","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuming","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rutao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qixing","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anpeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Qiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gaochao","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6569-5956","authenticated-orcid":true,"given":"Feng","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,8,13]]},"reference":[{"issue":"10299","key":"pdig.0001568.ref001","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1016\/S0140-6736(21)00312-3","article-title":"Lung cancer","volume":"398","author":"AA Thai","year":"2021","journal-title":"Lancet"},{"issue":"21","key":"pdig.0001568.ref002","doi-asserted-by":"crossref","first-page":"5309","DOI":"10.1016\/j.cell.2021.09.020","article-title":"Hallmarks of response, resistance, and toxicity to immune checkpoint blockade","volume":"184","author":"G Morad","year":"2021","journal-title":"Cell"},{"issue":"8","key":"pdig.0001568.ref003","doi-asserted-by":"crossref","DOI":"10.1136\/jitc-2022-006500","article-title":"Chronic immune-related adverse events in patients with cancer receiving immune checkpoint inhibitors: a systematic review","volume":"11","author":"CC Barron","year":"2023","journal-title":"J Immunother Cancer"},{"issue":"6","key":"pdig.0001568.ref004","doi-asserted-by":"crossref","DOI":"10.1136\/jitc-2021-002435","article-title":"Society for Immunotherapy of Cancer (SITC) clinical practice guideline on immune checkpoint inhibitor-related adverse events","volume":"9","author":"JR Brahmer","year":"2021","journal-title":"J Immunother Cancer"},{"issue":"36","key":"pdig.0001568.ref005","doi-asserted-by":"crossref","first-page":"4073","DOI":"10.1200\/JCO.21.01440","article-title":"Management of Immune-Related Adverse Events in Patients Treated With Immune Checkpoint Inhibitor Therapy: ASCO Guideline Update","volume":"39","author":"BJ Schneider","year":"2021","journal-title":"J Clin Oncol"},{"issue":"1","key":"pdig.0001568.ref006","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1186\/s40425-017-0300-z","article-title":"Managing toxicities associated with immune checkpoint inhibitors: consensus recommendations from the Society for Immunotherapy of Cancer (SITC) Toxicity Management Working Group","volume":"5","author":"I Puzanov","year":"2017","journal-title":"J Immunother Cancer"},{"issue":"7","key":"pdig.0001568.ref007","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1038\/s41573-021-00259-5","article-title":"Immune-related toxicities of checkpoint inhibitors: mechanisms and mitigation strategies","volume":"21","author":"RJ Sullivan","year":"2022","journal-title":"Nat Rev Drug Discov"},{"issue":"12","key":"pdig.0001568.ref008","doi-asserted-by":"crossref","first-page":"1721","DOI":"10.1001\/jamaoncol.2018.3923","article-title":"Fatal Toxic Effects Associated With Immune Checkpoint Inhibitors","volume":"4","author":"DY Wang","year":"2018","journal-title":"JAMA Oncol"},{"issue":"4","key":"pdig.0001568.ref009","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1038\/s41571-022-00600-w","article-title":"Immune-checkpoint inhibitors: long-term implications of toxicity","volume":"19","author":"DB Johnson","year":"2022","journal-title":"Nat Rev Clin Oncol"},{"key":"pdig.0001568.ref010","doi-asserted-by":"crossref","first-page":"107184","DOI":"10.1016\/j.lungcan.2023.107184","article-title":"Management, risk factors and prognostic impact of checkpoint-inhibitor pneumonitis (CIP) in lung cancer - A multicenter observational analysis","volume":"179","author":"N Frost","year":"2023","journal-title":"Lung Cancer"},{"issue":"12","key":"pdig.0001568.ref011","doi-asserted-by":"crossref","first-page":"1579","DOI":"10.1016\/S1470-2045(18)30608-9","article-title":"Cardiovascular toxicities associated with immune checkpoint inhibitors: an observational, retrospective, pharmacovigilance study","volume":"19","author":"J-E Salem","year":"2018","journal-title":"Lancet Oncol"},{"key":"pdig.0001568.ref012","doi-asserted-by":"crossref","first-page":"1662333","DOI":"10.3389\/fimmu.2025.1662333","article-title":"Immune checkpoint inhibitor therapy in advanced cancer: clinical association of irAEs type, inflammatory markers and efficacy","volume":"16","author":"M Qian","year":"2025","journal-title":"Front Immunol"},{"issue":"12","key":"pdig.0001568.ref013","doi-asserted-by":"crossref","first-page":"1930","DOI":"10.1016\/j.jtho.2018.08.2035","article-title":"Pneumonitis in Non-Small Cell Lung Cancer Patients Receiving Immune Checkpoint Immunotherapy: Incidence and Risk Factors","volume":"13","author":"K Suresh","year":"2018","journal-title":"J Thorac Oncol"},{"issue":"12","key":"pdig.0001568.ref014","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1001\/jamaoncol.2016.2453","article-title":"Incidence of Programmed Cell Death 1 Inhibitor\u2013Related Pneumonitis in Patients With Advanced Cancer","volume":"2","author":"M Nishino","year":"2016","journal-title":"JAMA Oncol"},{"issue":"1","key":"pdig.0001568.ref015","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1007\/s40487-026-00416-z","article-title":"Evaluating the Cost of Genomic Testing for Biomarker-Driven Therapies in Oncology","volume":"14","author":"JP Grossman","year":"2026","journal-title":"Oncol Ther"},{"key":"pdig.0001568.ref016","doi-asserted-by":"crossref","first-page":"1591359","DOI":"10.3389\/fimmu.2025.1591359","article-title":"Unveiling the dual role of circulating tumor cells in colorectal cancer immunotherapy: a comprehensive review of biomarker utility and immune microenvironment crosstalk","volume":"16","author":"Y Feng","year":"2025","journal-title":"Front Immunol"},{"issue":"10","key":"pdig.0001568.ref017","doi-asserted-by":"crossref","first-page":"101580","DOI":"10.1016\/j.isci.2020.101580","article-title":"Uncoupling Therapeutic Efficacy from Immune-Related Adverse Events in Immune Checkpoint Blockade","volume":"23","author":"W Hu","year":"2020","journal-title":"iScience"},{"issue":"1","key":"pdig.0001568.ref018","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1038\/s41746-025-01580-8","article-title":"Deep Gaussian process with uncertainty estimation for microsatellite instability and immunotherapy response prediction from histology","volume":"8","author":"S Park","year":"2025","journal-title":"NPJ Digit Med"},{"issue":"1","key":"pdig.0001568.ref019","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1186\/s12967-024-06057-y","article-title":"Habitat radiomics analysis for progression free survival and immune-related adverse reaction prediction in non-small cell lung cancer treated by immunotherapy","volume":"23","author":"Y Wu","year":"2025","journal-title":"J Transl Med"},{"issue":"7","key":"pdig.0001568.ref020","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1001\/jamaoncol.2025.0897","article-title":"Immunotherapy With or Without Chemotherapy in Advanced NSCLC-A Delicate Balance of Harm and Benefit","volume":"11","author":"G Mountzios","year":"2025","journal-title":"JAMA Oncol"},{"key":"pdig.0001568.ref021","article-title":"Harm-benefit balance of immune checkpoint inhibitors in non\u2013small cell lung cancer","author":"J Heyward","year":"2025","journal-title":"JAMA Oncol"},{"issue":"1","key":"pdig.0001568.ref022","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1158\/2326-6066.CIR-19-0476","article-title":"Changes in CT Radiomic Features Associated with Lymphocyte Distribution Predict Overall Survival and Response to Immunotherapy in Non-Small Cell Lung Cancer","volume":"8","author":"M Khorrami","year":"2020","journal-title":"Cancer Immunol Res"},{"issue":"6","key":"pdig.0001568.ref023","doi-asserted-by":"crossref","first-page":"998","DOI":"10.1093\/annonc\/mdz108","article-title":"Predicting response to cancer immunotherapy using noninvasive radiomic biomarkers","volume":"30","author":"S Trebeschi","year":"2019","journal-title":"Ann Oncol"},{"issue":"9","key":"pdig.0001568.ref024","doi-asserted-by":"crossref","first-page":"1180","DOI":"10.1016\/S1470-2045(18)30413-3","article-title":"A radiomics approach to assess tumour-infiltrating CD8 cells and response to anti-PD-1 or anti-PD-L1 immunotherapy: an imaging biomarker, retrospective multicohort study","volume":"19","author":"R Sun","year":"2018","journal-title":"Lancet Oncol"},{"issue":"10","key":"pdig.0001568.ref025","doi-asserted-by":"crossref","first-page":"1151","DOI":"10.1038\/s43018-022-00416-8","article-title":"Multimodal integration of radiology, pathology and genomics for prediction of response to PD-(L)1 blockade in patients with non-small cell lung cancer","volume":"3","author":"RS Vanguri","year":"2022","journal-title":"Nat Cancer"},{"issue":"4","key":"pdig.0001568.ref026","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1007\/s10637-017-0524-2","article-title":"Radiomics to predict immunotherapy-induced pneumonitis: proof of concept","volume":"36","author":"RR Colen","year":"2018","journal-title":"Invest New Drugs"},{"key":"pdig.0001568.ref027","article-title":"1381P Defining the optimal number of cycles of adjuvant treatment for metastatic nasopharyngeal carcinoma","volume":"36","author":"Z Luo","year":"2025","journal-title":"Annals of Oncology"},{"issue":"12","key":"pdig.0001568.ref028","doi-asserted-by":"crossref","first-page":"1217","DOI":"10.1016\/j.annonc.2022.10.001","article-title":"Management of toxicities from immunotherapy: ESMO Clinical Practice Guideline for diagnosis, treatment and follow-up","volume":"33","author":"J Haanen","year":"2022","journal-title":"Ann Oncol"},{"issue":"3","key":"pdig.0001568.ref029","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1007\/s10278-017-0037-8","article-title":"SimpleITK Image-Analysis Notebooks: a Collaborative Environment for Education and Reproducible Research","volume":"31","author":"Z Yaniv","year":"2018","journal-title":"J Digit Imaging"},{"key":"pdig.0001568.ref030","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic Minority Over-sampling Technique","volume":"16","author":"NV Chawla","year":"2002","journal-title":"jair"},{"issue":"21","key":"pdig.0001568.ref031","doi-asserted-by":"crossref","DOI":"10.1158\/0008-5472.CAN-17-0339","article-title":"Computational Radiomics System to Decode the Radiographic Phenotype","volume":"77","author":"JJM van Griethuysen","year":"2017","journal-title":"Cancer Res"},{"key":"pdig.0001568.ref032","first-page":"32","article-title":"Scikit-learn: Machine Learning in Python","volume":"6","author":"F Pedregosa","journal-title":"Machine Learning in Python"},{"key":"pdig.0001568.ref033","article-title":"MONAI: An open-source framework for deep learning in healthcare","author":"MJ Cardoso","year":"2022","journal-title":"arXiv"},{"key":"pdig.0001568.ref034","doi-asserted-by":"crossref","first-page":"729","DOI":"10.21105\/joss.00729","article-title":"PyCM: Multiclass confusion matrix library in Python","volume":"3","author":"S Haghighi","year":"2018","journal-title":"JOSS"},{"key":"pdig.0001568.ref035","article-title":"A Unified Approach to Interpreting Model Predictions","author":"S Lundberg","year":"2017","journal-title":"arXiv"},{"key":"pdig.0001568.ref036","doi-asserted-by":"crossref","first-page":"103046","DOI":"10.1016\/j.media.2023.103046","article-title":"Deep learning based synthesis of MRI, CT and PET: Review and analysis","volume":"92","author":"S Dayarathna","year":"2024","journal-title":"Med Image Anal"},{"key":"pdig.0001568.ref037","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep Residual Learning for Image Recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. 770\u20138. https:\/\/doi.org\/10.1109\/cvpr.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"pdig.0001568.ref038","first-page":"2261","volume-title":"Densely Connected Convolutional Networks","author":"G Huang","year":"2017"},{"issue":"1","key":"pdig.0001568.ref039","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1038\/s41698-025-00917-6","article-title":"A machine learning approach for multimodal data fusion for survival prediction in cancer patients","volume":"9","author":"N Nikolaou","year":"2025","journal-title":"NPJ Precis Oncol"},{"issue":"2","key":"pdig.0001568.ref040","doi-asserted-by":"crossref","first-page":"621","DOI":"10.7150\/ijbs.89376","article-title":"Uncovering the flip side of immune checkpoint inhibitors: a comprehensive review of immune-related adverse events and predictive biomarkers","volume":"20","author":"Y-D Miao","year":"2024","journal-title":"Int J Biol Sci"},{"key":"pdig.0001568.ref041","doi-asserted-by":"crossref","first-page":"553987","DOI":"10.3389\/frai.2021.553987","article-title":"Deep Learning and its Application for Healthcare Delivery in Low and Middle Income Countries","volume":"4","author":"D Williams","year":"2021","journal-title":"Front Artif Intell"},{"key":"pdig.0001568.ref042","doi-asserted-by":"crossref","DOI":"10.2196\/48633","article-title":"Barriers to and Facilitators of Artificial Intelligence Adoption in Health Care: Scoping Review","volume":"11","author":"M Hassan","year":"2024","journal-title":"JMIR Hum Factors"},{"issue":"1","key":"pdig.0001568.ref043","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1186\/s12916-024-03612-8","article-title":"Integration of clinical and blood parameters in risk prognostication for patients receiving immunochemotherapy for extensive stage small cell lung cancer: real-world data from two centers","volume":"22","author":"X Li","year":"2024","journal-title":"BMC Med"},{"issue":"8","key":"pdig.0001568.ref044","article-title":"Predictive value of the prognostic nutritional index in advanced non-small cell lung cancer patients treated with immune checkpoint inhibitors: A systematic review and meta-analysis","volume":"9","author":"H Xia","year":"2023","journal-title":"Heliyon"}],"container-title":["PLOS Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001568","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T17:21:49Z","timestamp":1786641709000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001568"}},"subtitle":[],"editor":[{"given":"Zasim Azhar","family":"Siddiqui","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8,13]]},"references-count":44,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8,13]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pdig.0001568","relation":{},"ISSN":["2767-3170"],"issn-type":[{"value":"2767-3170","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,13]]}}}