- Construction of Risk Prediction Model of Type 2 Diabetic Kidney Disease Based on Deep Learning (Diabetes Metab J 2024;48:771-9)
-
Chuan Yun, Fangli Tang, Qingqing Lou
-
Diabetes Metab J. 2024;48(5):1008-1011. Published online September 1, 2024
-
DOI: https://doi.org/10.4093/dmj.2024.0490
-
-
1,307
View
-
46
Download
-
2
Web of Science
-
2
Crossref
-
 PDF PubReader  ePub
-
Citations
Citations to this article as recorded by  - A nomograph model for predicting the risk of diabetes nephropathy
Moli Liu, Zheng Li, Xu Zhang, Xiaoxing Wei
International Urology and Nephrology.2025;[Epub] CrossRef - Prediction of outpatient visits for allergic rhinitis using an artificial intelligence LSTM model - a study in Eastern China
Xiaofeng Fan, Liwei Chen, Wei Tang, Lixia Sun, Jie Wang, Shuhan Liu, Sirui Wang, Kaijie Li, Mingwei Wang, Yongran Cheng, Lili Dai
BMC Public Health.2025;[Epub] CrossRef
- Complications
- Construction of Risk Prediction Model of Type 2 Diabetic Kidney Disease Based on Deep Learning
-
Chuan Yun, Fangli Tang, Zhenxiu Gao, Wenjun Wang, Fang Bai, Joshua D. Miller, Huanhuan Liu, Yaujiunn Lee, Qingqing Lou
-
Diabetes Metab J. 2024;48(4):771-779. Published online April 30, 2024
-
DOI: https://doi.org/10.4093/dmj.2023.0033
-
-
3,807
View
-
290
Download
-
3
Web of Science
-
1
Crossref
-
 Abstract
PDFPubReader ePub
- Background
This study aimed to develop a diabetic kidney disease (DKD) prediction model using long short term memory (LSTM) neural network and evaluate its performance using accuracy, precision, recall, and area under the curve (AUC) of the receiver operating characteristic (ROC) curve.
Methods
The study identified DKD risk factors through literature review and physician focus group, and collected 7 years of data from 6,040 type 2 diabetes mellitus patients based on the risk factors. Pytorch was used to build the LSTM neural network, with 70% of the data used for training and the other 30% for testing. Three models were established to examine the impact of glycosylated hemoglobin (HbA1c), systolic blood pressure (SBP), and pulse pressure (PP) variabilities on the model’s performance.
Results
The developed model achieved an accuracy of 83% and an AUC of 0.83. When the risk factor of HbA1c variability, SBP variability, or PP variability was removed one by one, the accuracy of each model was significantly lower than that of the optimal model, with an accuracy of 78% (P<0.001), 79% (P<0.001), and 81% (P<0.001), respectively. The AUC of ROC was also significantly lower for each model, with values of 0.72 (P<0.001), 0.75 (P<0.001), and 0.77 (P<0.05).
Conclusion
The developed DKD risk predictive model using LSTM neural networks demonstrated high accuracy and AUC value. When HbA1c, SBP, and PP variabilities were added to the model as featured characteristics, the model’s performance was greatly improved.
-
Citations
Citations to this article as recorded by - Trends and analysis of risk factor differences in the global burden of chronic kidney disease due to type 2 diabetes from 1990 to 2021: A population‐based study
Yifei Wang, Ting Lin, Jiale Lu, Wenfang He, Hongbo Chen, Tiancai Wen, Juan Jin, Qiang He
Diabetes, Obesity and Metabolism.2025; 27(4): 1902. CrossRef
|
KDA
