Predicting rapid decline in kidney function among type 2 diabetes patients: A machine learning approach.

Background: Diabetic kidney disease (DKD) is one of the typical complications of type 2 diabetes (T2D), with approximately 10 % of DKD patients experiencing a Rapid decline (RD) in kidney function. RD leads to an increased risk of poor outcomes such as the need for dialysis. Albuminuria is a known kidney damage biomarker for DKD, yet RD cases do not always show changes in albuminuria, and the exact mechanism of RD remains unclear.

Calcineurin inhibition deactivates pyruvate dehydrogenase and induces proximal tubule cell metabolic dysfunction, causing profibrotic phenotype.

Calcineurin inhibitors (CNIs) are indispensable immunosuppressants for transplant recipients and patients with autoimmune diseases, but chronic use causes nephrotoxicity, including kidney fibrosis. Why inhibiting calcineurin, a serine/threonine phosphatase, causes kidney fibrosis remains unknown. We performed single-nucleus RNA sequencing of the kidney from a chronic CNI nephrotoxicity mouse model and found an increased proportion of injured proximal tubule cells, which exhibited altered expression of genes associated with oxidative phosphorylation, cellular senescence and fibrosis.

Cost-Effectiveness of Empagliflozin in CKD with or without Albuminuria.

Key Points: Empagliflozin is cost-effective for the treatment of CKD in patients with an urine albumin-to-creatinine ratio of 30 mg/g or more. Empagliflozin is not cost-effective for the treatment of CKD in patients with an urine albumin-to-creatinine ratio <30 mg/g.

Background: The Study of Heart and Kidney Protection with Empagliflozin (EMPA-KIDNEY) expanded the CKD population that may benefit from sodium-glucose cotransporter 2 inhibitors in terms of eGFR and urine albumin-to-creatinine ratio.

Using One-Shot Prompting of Non-Fine-Tuned Commercial Artificial Intelligence to Assess Nutrients from Photographs of Japanese Meals.

Background: Diet interventions often have poor adherence due to burdensome food logging. Approaches using photographs assessed by artificial intelligence (AI) may make food logging easier, if they are adequately accurate.

Method: We used OpenAI's GPT-4o model with one-shot prompts and no fine-tuning to assess energy, fat, protein, carbohydrate, fiber, and salt through photographs of 22 meals, comparing assessments to weighed food records for each meal and to assessments of dieticians.