Datasets
Standard Dataset
Model Parameters for Glucose Regulatory Measure (GRM)
- Citation Author(s):
-
EricNg
- Submitted by:
- Eric Ng
- Last updated:
- Mon, 07/08/2024 - 15:58
- DOI:
- 10.21227/bx9e-2b60
- Data Format:
- License:
33 Views- Categories:
- Keywords:
Abstract
This dataset contains parameter values of the model presented by the manuscript titled "Model-Based Extraction of T2D Diagnostic Information from Continuous Glucose Monitoring". The parameters are obtained by first extracting hyperglycemic excursions, i.e. peaks, from continuous glucose data. A simple mathematical model describing glucose homeostasis is fitted to each peak, resulting in a collection of model parameters for each peak. Each file in this dataset contains the parameter values for all extracted peaks for each individual, stored as a YAML file that can be read by large variety of programming languages. The data stored within the YAML files serve as the training and testing data used to tune and validate the accuracy of the Glucose Regulatory Measure (GRM) presented in the same manuscript.
The dataset contains YAML files that contains model parameter values for each participant in the study. Data located under the directory 'batch_params_klick150' is used to as the training set for the tuning of GRM, and the data under the directory 'batch_params_klick600' is used as the validation/testing set to evaluate the performance of GRM as outlined in the manuscript. The filename is the unique identifier assigned to each individual. The data should be imported into Python using the yaml with the yaml.safe_load() command, which will be stored in memory as a dictionary. The keys and values of the dictionary are the variable names and a list of length n, where n is the number of peaks extracted for that particular individual. If a key references a single value (e.g. average, standard deviation), then the corresponding value is stored as a scalar (double).
The CSV file 'participant_list.csv' contains a list of all participants recruited for the study including those who do not meet the inclusion criteria. This file is it contains the labels required for the tuning and validation steps for GRM.
