Prediction of Nephropathy in Type 2 Diabetes: An Analysis of the ACCORD Trial Applying Machine Learning Techniques

Abstract

Applying data mining and machine learning (ML) techniques to clinical data might identify predictive biomarkers for diabetic nephropathy (DN), a common complication of type 2 diabetes mellitus (T2DM). A retrospective analysis of the Action to Control Cardiovascular Risk in Diabetes (ACCORD) trial was intended to identify such factors using ML. The longitudinal data were stratified by time after patient enrollment to differentiate early and late predictors. Our results showed that Random Forest and Simple Logistic Regression methods exhibited the best performance among the evaluated algorithms. Baseline values for glomerular filtration rate (GFR), urinary creatinine, urinary albumin, potassium, cholesterol, low‐density lipoprotein, and urinary albumin to creatinine ratio were identified as DN predictors. Early predictors were the baseline values of GFR, systolic blood pressure, as well as fasting plasma glucose (FPG) and potassium at month 4. Changes per year in GFR, FPG, and triglycerides were recognized as predictors of late development. In conclusion, ML‐based methods successfully identified predictive factors for DN among patients with T2DM.

Predicting adverse outcomes due to diabetes complications with machine learning using administrative health data

“…It was not our goal for this model to be used for individual level patient care. Our model was trained on data from over 1.5 million patients from Ontario, which is among one of the most diverse populations in the world and, to our knowledge, one of the largest prediction modelling studies that takes into account multiple types of diabetes complications [22][23][24][25][26][27][28][29][30][31][32][33][34][51][52][53] . Our model was also wellcalibrated and showed good discrimination.…”

“…Many prognostic models have been developed for diabetes complications in the clinical setting [22][23][24] , including more recent applications of machine learning approaches [25][26][27][28][29][30][31][32][33][34] . These models generally have made use of rich suites of features (e.g., body mass index, smoking status, biomarkers ranging from commonly ordered lipids to extensive genetic panels) extracted from electronic medical records (EMRs) 25,27,[31][32][33] or clinical trials 28,30 . However, while these models are important for clinical level risk prediction, they are not easily deployed by governments or private health insurance providers at the population level-which is precisely what is needed for addressing the aforementioned systemic barriers to diabetes complications care 35,36 .…”

Development of Machine Learning Models for Prediction of Smoking Cessation Outcome

“…Health outcome prediction models had been developed using methods of machine learning over recent years [ 14 , 15 ]. Some examples included prediction of postoperative in-hospital mortality [ 16 ], complications in patients with diabetes mellitus [ 17 ], and occurrence of cardiovascular diseases in patients on dialysis [ 18 ]. For smoking cessation, a decision tree model developed with machine learning to predict smoking cessation treatment outcome was proposed by Coughlin et al in 2018 [ 19 ].…”

Poor Control of Plasma Triglycerides Is Associated with Early Decline of Estimated Glomerular Filtration Rates in New-Onset Type 2 Diabetes in China: Results from a 3-Year Follow-Up Study

“…Previous studies had shown that dyslipidemia was a well-established risk factor for the renal impairment in diabetes; it is not only associated with the occurrence [ 2 , 10 , 19 ] but also the deterioration [ 4 , 11 ] of DKD. A cross-sectional study published in 2014 involving 13 countries reported the plasma lipid's contribution to the occurrence of DKD; hypertriglyceridemia significantly increased the risk of DKD, and high HDL-C was a protective factor [ 10 ].…”