Leveraging Real‐World Data for EMA Qualification of a Model‐Based Biomarker Tool to Optimize Type‐1 Diabetes Prevention Studies

Abstract

The development of therapies to prevent or delay the onset of type 1 diabetes (T1D) remains challenging, and there is a lack of qualified biomarkers to identify individuals at risk of developing T1D or to quantify the time‐varying risk of conversion to a diagnosis of T1D. To address this drug development need, the T1D Consortium (i) acquired, remapped, integrated, and curated existing patient‐level data from relevant observational studies, and (ii) used a model‐based approach to evaluate the utility of islet autoantibodies (AAs) against insulin/proinsulin autoantibody, GAD65, IA‐2, and ZnT8 as biomarkers to enrich subjects for T1D prevention. The aggregated dataset was used to construct an accelerated failure time model for predicting T1D diagnosis. The model quantifies presence of islet AA permutations as statistically significant predictors of the time‐varying probability of conversion to a diagnosis of T1D. Additional sources of variability that greatly improved the accuracy of quantifying the time‐varying probability of conversion to a T1D diagnosis included baseline age, sex, blood glucose measurements from the 120‐minute timepoints of oral glucose tolerance tests, and hemoglobin A1c. The developed models represented the underlying evidence to qualify islet AAs as enrichment biomarkers through the qualification of novel methodologies for drug development pathway at the European Medicines Agency (EMA). Additionally, the models are intended as the foundation of a fully functioning end‐user tool that will allow sponsors to optimize enrichment criteria for clinical trials in T1D prevention studies.

T1dCteGui: A User‐Friendly Clinical Trial Enrichment Tool to Optimize T1D Prevention Studies by Leveraging AI/ML Based Synthetic Patient Population

“…The TTE model for the CTE tool was developed using individual‐level data obtained from the TrialNet Pathway to Prevention study (TN01), the Environmental Determinants of Diabetes in the Young (TEDDY), and the Diabetes Auto Immunity Study in the Young (DAISY) 13–15 . TN01 and TEDDY data were used for model training, and DAISY data were used as the external test set 8 . To eliminate the risk of exposing patient‐level data through the open‐source CTE tool, synthetic individual‐level data were generated using a machine learning (ML) method, as discussed below.…”

“…The data curation and model building process are described in detail in Podichetty et al 8 . in 2022.…”

“…The T1DC acquired and curated existing patient‐level data from three observational studies and evaluated the utility of islet AAs as biomarkers to enrich T1D prevention trials. With these data, the T1DC developed open‐source time‐to‐event (TTE) models to quantify the time‐varying probability of reaching a diagnosis of T1D, which could be used to optimize enrichment strategies for clinical trials of therapies aiming to delay or prevent T1D 8 . In March 2020, the European Medicines Agency (EMA) issued a public Letter of Support 9 for “Islet autoantibodies as enrichment biomarkers for type 1 diabetes prevention studies, through a quantitative disease progression model.” The EMA letter of support reiterated the need for the collection and sharing of relevant data to “permit timely and robust development and validation of such a model” stating this would “facilitate development and validation of the proposed quantitative tool.” In March 2022, the T1DC received a final positive qualification opinion for islet AAs as enrichment biomarkers for T1D prevention clinical trials 10 .…”

Possible heterogeneity of initial pancreatic islet beta‐cell autoimmunity heralding type 1 diabetes

“…The Environmental Determinants of Diabetes in the Young (TEDDY) study, supported by the National Institutes of Health, used a common protocol and had enough statistical power to identify environmental factors that would trigger islet autoimmunity (IA) and show progression to the clinical onset of T1D [8,12]. These longitudinal natural history studies have been possible because T1D biomarkers have evolved over time from research biomarkers into specialized enhancement biomarkers in clinical prevention trials [13,14].…”

Disease progression joint model predicts time to type 1 diabetes onset: Optimizing future type 1 diabetes prevention studies

“…Over the past several decades, substantial progress has been made in the effort to better understand T1D pathogenesis. For example, a new disease progression staging paradigm that differentiates the development of T1D into three phases was proposed in 2015 5 and is widely accepted by the American Diabetes Association, International Society for Pediatric and Adolescent Diabetes, and other major diabetes organizations worldwide 6–8 . In this paradigm, stage 1 is characterized by the presence of two or more islet autoantibodies (AAbs) with normoglycemia and no clinical symptoms.…”