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 sampled covariates 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 to 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 1,000 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. Competing Interest Statement J. S. H. is on advisory boards for Janssen, Abbvie, Lilly, and Genentech and is a consultant for Takeda and Pfizer. The other authors report no conflicts of interest. Footnotes Funding: This work was supported by the National Institute of Diabetes and Digestive and Kidney Diseases at the National Institutes of Health [grant number DK132408], Crohn’s and Colitis Foundation, and the Cincinnati Children’s Research Foundation. Conflicts of Interest: J. S. H. is on advisory boards for Janssen, Abbvie, Lilly, and Genentech and is a consultant for Takeda and Pfizer. The other authors report no conflicts of interest. Data availability statements: The datasets analyzed in this study are accessible upon reasonable request by contacting the corresponding author. Code availability: The model codes are accessible upon reasonable request by contacting the corresponding author. Ethics approval: This study was conducted in accordance with the Declaration of Helsinki. The REFINE study received approval from multiple Institutional Review Boards (IRBs), including Cincinnati Children’s Hospital Medical Center (CCHMC), Nationwide Children’s Hospital, Medical College of Wisconsin, and Connecticut Children’s Medical Center. Additionally, the CCHMC IRB approved the APPDASH study. Consent to Participate: Written informed consent was obtained from each participant, or from a parent or legal guardian, as appropriate. A waiver of consent was granted when applicable. Consent for publication: Not applicable