Official websites use .gov
A
.gov
website belongs to an official government organization in the
United States.
Secure .gov websites use HTTPS
A
lock
(
) or
https://
means you’ve safely connected to the .gov website. Share sensitive
information only on official, secure websites.
PubMed ID:
37326252
Public Release Type:
Journal
Publication Year: 2023
Affiliation: Critical Path Institute
DOI:
https://doi.org/10.1002/cpt.2976
Authors:
Pauley M,
Henscheid N,
David SE,
Karpen SR,
Romero K,
Podichetty JT
Request IDs:
21437
Studies:
Anti-CD3 Mab (Teplizumab) for Prevention of Diabetes in Relatives At-Risk for Type 1 Diabetes Mellitus
,
Diabetes Prevention Trial of Type 1 Diabetes
,
Oral Insulin for Prevention of Diabetes in Relatives at Risk for Type 1 Diabetes Mellitus
,
The Environmental Determinants of Diabetes in the Young
,
TrialNet Pathway To Prevention (formerly Natural History Study)
While islet autoantibodies (AAs) are well established risk factors for developing type 1 diabetes (T1D), there is a lack of biomarkers endorsed by regulators to enrich clinical trial populations for those at risk of developing type 1 diabetes (T1D). As such, the development of therapies that delay or prevent the onset of T1D remains challenging. To address this drug development need, the Critical Path Institute’s T1D Consortium acquired patient-level data from multiple observational studies and used a model-based approach to evaluate the utility of islet autoantibodies (AAs) as enrichment biomarkers in clinical trials. An accelerated failure time model was developed, which provided the underlying evidence required to receive a qualification opinion for islet autoantibodies as enrichment biomarkers from the European Medicines Agency in March of 2022. To further democratize the use of the model to scientists and clinicians, a T1D Clinical Trial Enrichment Graphical User Interface (GUI) was developed. The interactive tool allows users to specify trial participant characteristics, including the percentage of participants with a specific AA combination. Users can specify ranges for participant baseline age, sex, blood glucose measurement from the 120-minute timepoints of an oral glucose tolerance test, and hemoglobin A1c. The tool then applies the model to predict the mean probability of a T1D diagnosis for that trial population and renders the results to the user. To ensure adequate data privacy and to make the tool open-source, a deep learning-based generative model was used to generate a cohort of synthetic subjects that underpins the tool.
