Construction of Risk Prediction Model of Type 2 Diabetic Kidney Disease Based on Deep Learning

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.PMID:38685670 | DOI:10.4093/dmj.2023.0033

Source: Diabetes and Metabolism Journal - April 30, 2024 Category: Endocrinology Authors: Chuan Yun Fangli Tang Zhenxiu Gao Wenjun Wang Fang Bai Joshua D Miller Huanhuan Liu Yaujiunn Lee Qingqing Lou Source Type: research