A Computational Platform Integrating a Mechanistic Model of Crohn's Disease for Predicting Temporal Progression of Mucosal Damage and Healing.

INTRODUCTION: Physicians are often required to make treatment decisions for patients with Crohn's disease on the basis of limited objective information about the state of the patient's gastrointestinal tissue while aiming to achieve mucosal healing. Tools to predict changes in mucosal health with treatment are needed. We evaluated a computational approach integrating a mechanistic model of Crohn's disease with a responder classifier to predict temporal changes in mucosal health. METHODS: A hybrid mechanistic-statistical platform was developed to predict biomarker and tissue health time courses in patients with Crohn's disease. Eligible patients from the VERSIFY study (n = 69) were classified into archetypical response cohorts using a decision tree based on early treatment data and baseline characteristics. A virtual patient matching algorithm assigned a digital twin to each patient from their corresponding response cohort. The digital twin was used to forecast response to treatment using the mechanistic model. RESULTS: The responder classifier predicted endoscopic remission and mucosal healing for treatment with vedolizumab over 26 weeks, with overall sensitivities of 80% and 75% and overall specificities of 69% and 70%, respectively. Predictions for changes in tissue damage over time in the validation set (n = 31), a measure of the overall performance of the platform, were considered good (at least 70% of data points matched), fair (at least 50%), and poor (less than 50%) for 71%, 23%, and 6% of patients, respectively. CONCLUSION: Hybrid computational tools including mechanistic components represent a promising form of decision support that can predict outcomes and patient progress in Crohn's disease.

A long-term mechanistic computational model of physiological factors driving the onset of type 2 diabetes in an individual.

A computational model of the physiological mechanisms driving an individual's health towards onset of type 2 diabetes (T2D) is described, calibrated and validated using data from the Diabetes Prevention Program (DPP). The objective of this model is to quantify the factors that can be used for prevention of T2D. The model is energy and mass balanced and continuously simulates trajectories of variables including body weight components, fasting plasma glucose, insulin, and glycosylated hemoglobin among others on the time-scale of years. Modeled mechanisms include dynamic representations of intracellular insulin resistance, pancreatic beta-cell insulin production, oxidation of macronutrients, ketogenesis, effects of inflammation and reactive oxygen species, and conversion between stored and activated metabolic species, with body-weight connected to mass and energy balance. The model was calibrated to 331 placebo and 315 lifestyle-intervention DPP subjects, and one year forecasts of all individuals were generated. Predicted population mean errors were less than or of the same magnitude as clinical measurement error; mean forecast errors for weight and HbA1c were ~5%, supporting predictive capabilities of the model. Validation of lifestyle-intervention prediction is demonstrated by synthetically imposing diet and physical activity changes on DPP placebo subjects. Using subject level parameters, comparisons were made between exogenous and endogenous characteristics of subjects who progressed toward T2D (HbA1c > 6.5) over the course of the DPP study to those who did not. The comparison revealed significant differences in diets and pancreatic sensitivity to hyperglycemia but not in propensity to develop insulin resistance. A computational experiment was performed to explore relative contributions of exogenous versus endogenous factors between these groups. Translational uses to applications in public health and personalized healthcare are discussed.