{"doi":"10.1200/cci.23.00207","title":"Prediction of Effectiveness and Toxicities of Immune Checkpoint Inhibitors Using Real-World Patient Data","abstract":"PURPOSE: Although immune checkpoint inhibitors (ICIs) have improved outcomes in certain patients with cancer, they can also cause life-threatening immunotoxicities. Predicting immunotoxicity risks alongside response could provide a personalized risk-benefit profile, inform therapeutic decision making, and improve clinical trial cohort selection. We aimed to build a machine learning (ML) framework using routine electronic health record (EHR) data to predict hepatitis, colitis, pneumonitis, and 1-year overall survival. METHODS: Real-world EHR data of more than 2,200 patients treated with ICI through December 31, 2018, were used to develop predictive models. Using a prediction time point of ICI initiation, a 1-year prediction time window was applied to create binary labels for the four outcomes for each patient. Feature engineering involved aggregating laboratory measurements over appropriate time windows (60-365 days). Patients were randomly partitioned into training (80%) and test (20%) sets. Random forest classifiers were developed using a rigorous model development framework. RESULTS: The patient cohort had a median age of 63 years and was 61.8% male. Patients predominantly had melanoma (37.8%), lung cancer (27.3%), or genitourinary cancer (16.4%). They were treated with PD-1 (60.4%), PD-L1 (9.0%), and CTLA-4 (19.7%) ICIs. Our models demonstrate reasonably strong performance, with AUCs of 0.739, 0.729, 0.755, and 0.752 for the pneumonitis, hepatitis, colitis, and 1-year overall survival models, respectively. Each model relies on an outcome-specific feature set, though some features are shared among models. CONCLUSION: To our knowledge, this is the first ML solution that assesses individual ICI risk-benefit profiles based predominantly on routine structured EHR data. As such, use of our ML solution will not require additional data collection or documentation in the clinic.","journal":"JCO Clinical Cancer Informatics","year":2024,"id":429715,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":25,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.955,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2024-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":462861,"name":"Kathleen F. Mittendorf","orcid":"0000-0003-1097-9171","position":1,"is_corresponding":false},{"id":625585,"name":"Zoltán Kiss","orcid":"0009-0009-8017-6770","position":2,"is_corresponding":false},{"id":351389,"name":"Michele L. Lenoue-Newton","orcid":"0000-0003-3469-3784","position":3,"is_corresponding":false},{"id":1232819,"name":"Pablo Napan-Molina","orcid":null,"position":4,"is_corresponding":false},{"id":411087,"name":"Protiva Rahman","orcid":"0000-0003-0000-8558","position":5,"is_corresponding":false},{"id":445508,"name":"Cheng Ye","orcid":"0009-0003-1113-6990","position":6,"is_corresponding":false},{"id":1232820,"name":"Balázs Laczi","orcid":null,"position":7,"is_corresponding":false},{"id":1232821,"name":"Eszter Csernai","orcid":null,"position":8,"is_corresponding":false},{"id":1232382,"name":"Neha Jain","orcid":"0000-0002-0168-7874","position":9,"is_corresponding":false},{"id":1232383,"name":"Marilyn Holt","orcid":"0000-0002-3164-869X","position":10,"is_corresponding":false},{"id":476275,"name":"C. Noel Maxwell","orcid":null,"position":11,"is_corresponding":false},{"id":1007584,"name":"Madeleine Ball","orcid":"0000-0002-4491-8548","position":12,"is_corresponding":false},{"id":503184,"name":"Yufang Ma","orcid":"0000-0001-6672-3875","position":13,"is_corresponding":false},{"id":1232384,"name":"Margaret B. Mitchell","orcid":"0000-0002-8723-7670","position":14,"is_corresponding":false},{"id":28327,"name":"Douglas B. Johnson","orcid":"0000-0002-6390-773X","position":15,"is_corresponding":false},{"id":1145213,"name":"David S. Smith","orcid":"0000-0002-1615-2231","position":16,"is_corresponding":false},{"id":2252,"name":"Ben Ho Park","orcid":"0000-0001-8119-2291","position":17,"is_corresponding":false},{"id":351391,"name":"Christine Micheel","orcid":"0000-0002-7744-9039","position":18,"is_corresponding":false},{"id":737395,"name":"Daniel Fabbri","orcid":"0000-0003-0530-2510","position":19,"is_corresponding":false},{"id":1232822,"name":"Jan Wolber","orcid":null,"position":20,"is_corresponding":false},{"id":501473,"name":"Travis Osterman","orcid":"0000-0002-2841-8121","position":21,"is_corresponding":false},{"id":1232381,"name":"Levente Lippenszky","orcid":"0009-0000-7835-2071","position":0,"is_corresponding":true}],"reference_count":35,"raw_metadata":null,"created_at":"2026-07-19T01:59:11.328802Z","pmid":"38427922","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}