Datasets
Standard Dataset
Continuous glucose measurement for inpatient with type 2 diabetes
- Citation Author(s):
- Submitted by:
- Jiyoung Woo
- Last updated:
- Tue, 07/25/2023 - 18:06
- DOI:
- 10.21227/adzq-2y15
- Data Format:
- Research Article Link:
- License:
- Categories:
- Keywords:
Abstract
This dataset includes data from 43 hospitalized patients with type 2 diabetes mellitus. Dexcom G5 and Dexcom G6 mobile continuous glucose measurement (CGM) devices were used to measure continuous blood glucose levels. The data collection period is from April 2019 to January 2022. We selected 43 patients whose records with a more extended recording period of more than seven days. Data was collected for 7 to 10 days at 5-minute intervals. This data can be used for glucose level prediction or hypoglycemia occurrence prediction for patient with type 2 diabetes mellitus. The most common type of diabetes in adults is type 2 diabetes mellitus (T2DM), which occurs when the body becomes resistant to insulin or fails to produce sufficient insulin.
The data collection period is from April 2019 to January 2022. We selected 43 patients whose records with a more extended recording period of more than seven days. Data was collected for 7 to 10 days at 5-minute intervals. The collected continuous blood glucose ranges from 40 mg/dL to 400 mg/dL, and readings outside this range were recorded as high or low. The data from the first day could be erroneous. The patients are aged between 20~79. The very first data could be inaccurate due to the CGM device calibration.
The continuous blood glucose measurement was collected with the approval of the Institutional Review Board of Soonchunhyang University Cheonan Hospital (SCHCA IRB protocol number: SCHCA 2019-11-048).
For use cases for this dataset, please refer following papers.
1. Sang-Min Lee, Dae-Yeon Kim, and Jiyoung Woo. Glucose transformer: Forecasting glucose level and events of hyperglycemia and hypoglycemia. IEEE Journal of Biomedical and Health Informatics, 27(3):1600–1611, 2023.
2. Dae-Yeon Kim, Dong-Sik Choi, Jaeyun Kim, Sung Wan Chun, Hyo- Wook Gil, Nam-Jun Cho, Ah Reum Kang, and Jiyoung Woo. Developing an individual glucose prediction model using recurrent neural network. Sensors, 20(22), 2020.
3. Dae-Yeon Kim, Dong-Sik Choi, Ah Reum Kang, Jiyoung Woo, Yechan Han, Sung Wan Chun, and Jaeyun Kim. Intelligent Ensemble Deep Learning System for Blood Glucose Prediction Using Genetic Algo- rithms. Complexity, 2022:e7902418, October 2022.
Comments
Thank you. I'm testing how I can download the dataset.
谢谢,我正需要这样的数据集
Hi