{"doi":"10.1002/cpt.70118","title":"Model‐Informed Deep Q‐Networks to Guide Infliximab Dosing in Pediatric Crohn’s Disease","abstract":"Model-informed precision dosing (MIPD) utilizes pharmacokinetic/pharmacodynamic (PK/PD) models to optimize drug therapy. However, conventional MIPD often requires manual simulation and regimen selection, which are time-consuming and demand specialized expertise. Reinforcement learning (RL), in which an agent learns optimal decisions through iterative interactions with an environment, offers a scalable and automated alternative. In this study, we developed a model-informed Deep Q-Network (DQN) to personalize infliximab dosing for patients with Crohn's disease. The DQN was trained in a simulation environment incorporating a population PK model, inter-individual variability, and assay error. Virtual patients with randomly and independently sampled covariates from log-normal distributions were used to explore dosing strategies at Infusions 1, 3, and 4. Doses ranged from 1 to 10 mg/kg at Infusion 1 and from 1 to 20 mg/kg thereafter, with intervals of 4-12 weeks. The reward function prioritized achieving trough concentrations of 18-26 μg/mL before Infusion 3 and 5-10 μg/mL before Infusions 4 and 5, while penalizing overtreatment and additional infusions. The DQN policy converged after 80,000 episodes, yielding target attainment probabilities (PTAs) of 92.9% and 98.4% at Infusions 4 and 5, respectively, in 1000 virtual patients. High doses (11-20 mg/kg) were selected in only 0.2% of cases. At Infusion 4, 66.8% of patients received an 8-week interval, and 57.3% at Infusion 5. Retrospective real-world validation showed that patients whose actual doses matched DQN recommendations had trough levels significantly closer to target ranges. These findings support the feasibility of using DQN-based agents to enhance and automate infliximab individualized dosing in pediatric populations.","journal":"Clinical Pharmacology & Therapeutics","year":2025,"id":529248,"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":2,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.947,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2025-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":307304,"name":"Phillip Minar","orcid":"0000-0003-4223-4211","position":1,"is_corresponding":false},{"id":1103969,"name":"Jack Reifenberg","orcid":"0000-0001-7612-0349","position":2,"is_corresponding":false},{"id":365313,"name":"Brendan M. Boyle","orcid":null,"position":3,"is_corresponding":false},{"id":309635,"name":"Joshua D. Noe","orcid":null,"position":4,"is_corresponding":false},{"id":87738,"name":"Jeffrey S. Hyams","orcid":"0000-0002-9769-236X","position":5,"is_corresponding":false},{"id":295600,"name":"Tomoyuki Mizuno","orcid":"0000-0002-8471-9826","position":6,"is_corresponding":false},{"id":1256289,"name":"Kei Irie","orcid":"0000-0002-0820-1208","position":0,"is_corresponding":true}],"reference_count":24,"raw_metadata":null,"created_at":"2026-07-19T02:50:56.971987Z","pmid":"41189499","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":[]}