Dataset Information

Artificial intelligence-guided precision treatment of chronic kidney disease-mineral bone disorder.

ABSTRACT: Chronic kidney disease (CKD)-mineral bone disorder (MBD) is a complex clinical syndrome that begins early during CKD and evolves into one of the deadliest complications of CKD through its effects on the cardiovascular and skeletal systems. Achievement of treatment goals to decrease the risk of accelerated cardiovascular events and fractures has been challenging. We hypothesized that application of quantitative systems pharmacology (QSP) modeling combined with artificial intelligence techniques could improve the management of CKD-MBD with the goal of improving outcomes for patients with CKD. We present the implementation of a reinforcement learning (RL) approach to achieve the prescribed goals for serum calcium, phosphorus, and parathyroid hormone through concurrent dosing of phosphate binders, vitamin D analogs, and calcimimetics by simulation in 80 subjects in Matlab. In silico simulation results demonstrate that the application of a QSP model coupled with RL more effectively and quickly achieves treatment goals even in the setting of inferior simulated subject compliance with medical therapy and identifies key decision variables for therapeutic recommendations.

SUBMITTER: Gaweda AE

PROVIDER: S-EPMC9574726 | biostudies-literature | 2022 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Artificial intelligence-guided precision treatment of chronic kidney disease-mineral bone disorder.

Gaweda Adam E AE Lederer Eleanor D ED Brier Michael E ME

CPT: pharmacometrics & systems pharmacology 20220803 10

Chronic kidney disease (CKD)-mineral bone disorder (MBD) is a complex clinical syndrome that begins early during CKD and evolves into one of the deadliest complications of CKD through its effects on the cardiovascular and skeletal systems. Achievement of treatment goals to decrease the risk of accelerated cardiovascular events and fractures has been challenging. We hypothesized that application of quantitative systems pharmacology (QSP) modeling combined with artificial intelligence techniques c ...[more]

PMID: 35920131

Similar Datasets

Project description:Objective: The aim of this study is to establish a suitable animal model of chronic kidney disease-mineral and bone disorder (CKD-MBD) by comparing CKD-MBD rat models induced by 5/6 Nx, AN, and UUO, accompanied by a low-calcium and high-phosphorus diet. Methods: Sprague‒Dawley rats were randomly divided into four groups: control group, 5/6 nephrectomy (5/6 Nx) group, Adriamycin nephropathy (AN) group, and unilateral ureteral obstruction (UUO) group. Serum biochemical indices were measured to evaluate renal function, mineral and bone metabolism, the severity of CKD-MBD, and the status of bone transformation. Hematoxylin-eosin staining (HE) and Masson's trichrome (Masson) staining were used for histopathological analysis of the kidney. Goldner's trichrome (Goldner) and tartrate-resistant acid phosphatase (TRAP) staining were utilized to observe bone mineralization and osteoclasts in the femur, respectively. Micro-CT images were applied to study the structure of the femur. The expression levels of osterix and cathepsin K in the femur were measured by immunohistochemistry (IHC) to confirm the status of bone transformation. Results: The levels of serum creatinine (Scr) and blood urea nitrogen (BUN) in the 5/6 Nx and AN group rats were significantly higher than those in the control rats, and this change was accompanied by marked changes in the levels of calcium (Ca), phosphate (Pi), intact parathyroid hormone (i-PTH), fibroblast growth factor 23 (FGF23), osteocalcin (OC), and cross-linked C-telopeptide of type 1 collagen (CTX-1); UUO group rats exhibited slight and inconsistent variations in the levels of Scr, BUN, Ca, Pi, i-PTH, FGF23, OC, and CTX-1 in serum. Histopathological analysis of the kidney showed that the UUO group rats suffered serious fibrosis and 5/6 Nx group rats exhibited severe focal calcification. Histopathological analysis of the femur showed that the AN group rats had minimal bone mineralization and that the 5/6 Nx group rats had overactive osteoclasts. Micro-CT revealed that the AN model had the most severe bone destruction and that the 5/6 Nx model had the least severe bone loss among the three models. The expression of cathepsin K in the femur was significantly increased in all models, while the expression of osterix in the femur was only significantly increased in the 5/6 Nx model. Conclusion: 5/6 Nx, AN, and UUO accompanied by a low-calcium and high-phosphorus diet successfully induced CKD-MBD in rats. The 5/6 NX model presented the progression of high-turnover bone disease, with consistency between biochemical indices in serum and histomorphometric analysis of the femur, and the AN and UUO models developed a severe deterioration in bone quantity and severe bone resorption; however, the changes in biochemical indices were subtle in the UUO model, and liver injury was obvious in the AN model.

Project description:BackgroundChronic kidney disease-mineral and bone disorder (CKD-MBD) in dogs is associated with hypovitaminosis D, increased parathyroid hormone (PTH), and increased fibroblast growth factor-23 (FGF-23) concentrations. Best practice for vitamin D metabolite supplementation in CKD-MBD remains unknown.ObjectiveTo provide an extended-release calcifediol supplement to dogs with CKD and to measure its effects on variables indicative of CKD-MBD.AnimalsTen dogs with International Renal Interest Society stages 2 and 3 CKD.MethodsIn a prospective study, dogs received a calcifediol supplement for 84 days. Serum 25-hydroxyvitamin D (25[OH]D), 1,25-dihydroxyvitamin D (1,25[OH]2 D), 24,25-dihydroxyvitamin D (24,25[OH]2 D), creatinine, calcium, phosphorus, PTH, plasma FGF-23 concentrations, and urine profiles were measured monthly during supplementation. Urine calcium to creatinine (UCa/Cr) ratios and fractional excretion of calcium, phosphorus, and sodium were determined.ResultsAll serum vitamin D metabolite concentrations increased significantly by day 84 (P < .001): [25(OH)D (median 249.9 ng/mL; range, 149.7-469.9 ng/mL) compared to baseline (median 50.2 ng/mL; range, 31.3-66.0 ng/mL); 1,25(OH)2 D (median 66.1 pg/mL; range, 56.9-88.1 pg/mL) compared to baseline (median 37.3 pg/mL; range, 29.3-56.7 pg/mL); 24,25(OH)2 D (median 81.4 ng/mL; range, 22.1-151.7 ng/mL) compared to baseline (median 15.4 ng/mL; range, 6.9-40.6 ng/mL)]. There were no significant differences in calcium, phosphorus, PTH concentrations, UCa/Cr or fractional excretion of calcium. No dog developed ionized hypercalcemia. Plasma FGF-23 concentrations increased by day 84 (median 1219 pg/mL; range, 229-8824 pg/mL) compared to baseline (median 798 pg/mL; range, 103-4.145 pg/mL) (P < .01).Conclusions and clinical importanceCalcifediol supplementation for 84 days was well-tolerated in dogs with IRIS stages 2 and 3 CKD. It remains to be determined how long-term supplementation would affect CKD progression and QOL.

Dataset Information

Artificial intelligence-guided precision treatment of chronic kidney disease-mineral bone disorder.

Publications

Artificial intelligence-guided precision treatment of chronic kidney disease-mineral bone disorder.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets