View : 22 Download: 0

Development and Validation of a Deep Learning Based Diabetes Prediction System Using a Nationwide Population-Based Cohort

Title
Development and Validation of a Deep Learning Based Diabetes Prediction System Using a Nationwide Population-Based Cohort
Authors
Rhee, Sang YoulSung, Ji MinKim, SunheeCho, In-JeongLee, Sang-EunChang, Hyuk-Jae
Ewha Authors
조인정
SCOPUS Author ID
조인정scopusscopus
Issue Date
2021
Journal Title
DIABETES & METABOLISM JOURNAL
ISSN
2233-6079JCR Link

2233-6087JCR Link
Citation
DIABETES & METABOLISM JOURNAL vol. 45, no. 4, pp. 515 - 525
Keywords
Diabetes mellitustype 2Mass screeningPrediabetic statePrediction
Publisher
KOREAN DIABETES ASSOC
Indexed
SCIE; SCOPUS; KCI WOS
Document Type
Article
Abstract
Background: Previously developed prediction models for type 2 diabetes mellitus (T2DM) have limited performance. We devel-oped a deep learning (DL) based model using a cohort representative of the Korean population. Methods: This study was conducted on the basis of the National Health Insurance Service-Health Screening (NHIS-HEALS) co-hort of Korea. Overall, 335,302 subjects without T2DM at baseline were included. We developed the model based on 80% of the subjects, and verified the power in the remainder. Predictive models for T2DM were constructed using the recurrent neural net-work long short-term memory (RNN-LSTM) network and the Cox longitudinal summary model. The performance of both models over a 10-year period was compared using a time dependent area under the curve. Results: During a mean follow-up of 10.4 +/- 1.7 years, the mean frequency of periodic health check-ups was 2.9 +/- 1.0 per subject. During the observation period, T2DM was newly observed in 8.7% of the subjects. The annual performance of the model created using the RNN-LSTM network was superior to that of the Cox model, and the risk factors for T2DM, derived using the two mod-els were similar; however, certain results differed. Conclusion: The DL-based T2DM prediction model, constructed using a cohort representative of the population, performs bet-ter than the conventional model. After pilot tests, this model will be provided to all Korean national health screening recipients in the future.
DOI
10.4093/dmj.2020.0081
Appears in Collections:
의과대학 > 의학과 > Journal papers
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE