Collections »

About this collection

Extent

1 digital object.

Cite This Work

Burks, Jamison H.; Joe, Leslie; Kanjaria, Karina; Monsivais, Carlos; Smarr, Benjamin L. (2025). Data from: Chronobiologically-Informed Features from CGM Data Provide Unique Information for XGBoost Prediction of Longer-Term Glycemic Dysregulation in 8,000 Individuals with Type-2 Diabetes. UC San Diego Library Digital Collections. https://doi.org/10.6075/J0BR8SK9

Description

This collection contains the tabulated data used to perform the machine learning components of the manuscript Chronobiologically-Informed Features from CGM Data Provide Unique Information for XGBoost Prediction of Longer-Term Glycemic Dysregulation in 8,000 Individuals with Type-2 Diabetes.

Creation Date

• 2022-04

Date Issued

• 2025

Author

• Burks, Jamison Henry

Principal Investigator

• Smarr, Benjamin Lee

Topics

• Algorithm: Supervised learning
• Biomedical engineering
• Continuous glucose monitoring
• Domain: Biomedical and clinical sciences
• Domain: Health sciences
• Domain: Information and computing sciences
• Engineering
• Feature engineering
• Machine learning
• Task: Classification
• Task: Dimensionality reduction
• Type 2 Diabetes Mellitus

Formats

View formats within this collection

• data
• software
• text

Language

• English

Identifier

Identifier: Benjamin Lee Smarr: https://orcid.org/0000-0003-4442-3956

Identifier: Jamison Henry Burks: https://orcid.org/0000-0003-4816-5704

Related Resources

Primary associated publication

• Burks JH, Joe L, Kanjaria K, Monsivais C, O'laughlin K, Smarr BL (2025) Chronobiologically-informed features from CGM data provide unique information for XGBoost prediction of longer-term glycemic dysregulation in 8,000 individuals with type-2 diabetes. PLOS Digit Health 4(4): e0000815. https://doi.org/10.1371/journal.pdig.0000815

Collection image

• Image credit: Jamison Henry Burks. "Performance improvement from adding chronobiological features."