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.

Educational/Instructional Information

This recording covers how to navigate and access resources, identify the appropriate data sets and biospecimens for your research, and submit requests for resources. Recorded at the NIDDK-CR 20th Anniversary Workshop.

This recording covers the NIDDK Data Centric Challenge, including an overview of the challenge prompt, how to enter, submission requirements, and a demonstration of the NIDDK-CR Analytics Workbench. During the Challenge, participants will be asked to enhance data on Type 1 Diabetes (T1D) from the NIDDK Central Repository for future artificial intelligence (AI) applications. Recorded at the NIDDK-CR 20th Anniversary Workshop.

NIDDK-CR Data Challenge Office Hours on AI-Readiness

This office hours session on Preparing Machine Learning Applications for your AI-Ready Dataset covers the criteria for selecting machine learning (ML) models for generative AI and example use cases, ML tools that are available through Amazon Web Services (AWS), and how to export and share SageMaker Jupyter notebooks. Recorded at the January 19, 2024 NIDDK-CR Data Challenge Office Hours on Al-readiness.

Presentation Slides (PDF) from January 19, 2024 NIDDK-CR Data Challenge Office Hours

This office hours session on Preparing Data Dictionaries for AI-Ready Datasets covers the importance of data dictionaries for fostering data re-use, characteristics of a human- and machine-readable data dictionary, and a demonstration of preparing a data dictionary for a Zika dataset using R programming language. Recorded at the January 12, 2024 NIDDK-CR Data Challenge Office Hours on Al-readiness.

Demonstration Materials (code script in R, Zika dataset, and output data dictionary in Excel format) from January 12, 2024, NIDDK-CR Data Challenge Office Hours
Presentation Slides (PDF) from January 12, 2024, NIDDK-CR Data Challenge Office Hours

Part 2 of this office hours session on Conducting Al-Research for Health Data covers an overview of Al-assisted biomedical research, biases in Al and how to mitigate them, and research design considerations to drive meaning Al insights. Recorded at the January 5, 2024 NIDDK-CR Data Challenge Office Hours on Al-readiness.

Presentation Slides (PDF) from December 29, 2023 and January 05, 2024 NIDDK-CR Data Challenge Office Hours

Part 1 of this office hours session on Conducting AI-Research for Health Data covers an overview of AI-assisted biomedical research, biases in AI and how to mitigate them, and research design considerations to drive meaning AI insights. Recorded at the December 29, 2023 NIDDK-CR Data Challenge Office Hours on AI-readiness.

Presentation Slides (PDF) from December 29, 2023 and January 05, 2024 NIDDK-CR Data Challenge Office Hours

Recording from the December 22nd, 2023, office hours session on the magic of dimensionality reduction.

Notebook of Principal Component Analysis in Python from December 22, 2023 NIDDK Data Challenge Office Hours

Presentation Slides (PDF) from December 22, 2023 NIDDK-CR Data Challenge Office Hours

December 15th, 2023, office hours session on continued discussion of performing pre-model processing and data quality checks using R to prepare AI-ready datasets.

Recording from the December 8th, 2023, office hours session on performing pre-model processing and data quality checks using R to prepare AI-ready datasets

Presentation Slides (PDF) from December 1 and December 8, 2023 NIDDK-CR Data Challenge Office Hours