Comprehensive risk management of diabetic kidney disease in patients with type 2 diabetes mellitus

Significance of SGLT2 inhibitors: lessons from renal clinical outcomes in patients with type 2 diabetes and basic researches

Diabetic kidney disease (DKD), a microvascular complication of diabetes, has been the leading cause of end-stage kidney disease (ESKD). Accordingly, patients with type 2 diabetes mellitus (T2DM) develop renal damage due to multiple metabolic and cardiorenal disease-related risk factors, including hyperglycemia, hypertension, dyslipidemia, hyperuricemia, and overnutrition/obesity. Despite multifactorial management including the administration of renin-angiotensin system inhibitors, patients often do not experience sufficient suppression of DKD progression and, thus, remain at risk for ESKD. Recent studies on cardiovascular outcomes among patients with T2DM have clearly shown that sodium-glucose cotransporter 2 (SGLT2) inhibitors, such as empagliflozin, canagliflozin, and dapagliflozin, have cardiorenal protective effects apart from their glucose-lowering effects. In particular, SGLT2 inhibitors have been found to improve renal outcomes, including ESKD, by slowing renal function decline and reducing urinary albumin excretion through their class effect. The proposed mechanisms for the renoprotective effects of SGLT2 inhibitors include the action of tubulo-glomerular feedback system and attenuation of hypoxia and metabolic stress in proximal tubular cells mediated through the inhibition of excessive glucose and sodium reabsorption, increased erythropoiesis, or increased ketone body production.

Artificial intelligence predicts the progression of diabetic kidney disease using big data machine learning

Artificial intelligence (AI) is expected to support clinical judgement in medicine. We constructed a new predictive model for diabetic kidney diseases (DKD) using AI, processing natural language and longitudinal data with big data machine learning, based on the electronic medical records (EMR) of 64,059 diabetes patients. AI extracted raw features from the previous 6 months as the reference period and selected 24 factors to find time series patterns relating to 6-month DKD aggravation, using a convolutional autoencoder. AI constructed the predictive model with 3,073 features, including time series data using logistic regression analysis. AI could predict DKD aggravation with 71% accuracy. Furthermore, the group with DKD aggravation had a significantly higher incidence of hemodialysis than the non-aggravation group, over 10 years (N = 2,900). The new predictive model by AI could detect progression of DKD and may contribute to more effective and accurate intervention to reduce hemodialysis.