RESUMEN
BACKGROUNDA treatment option for autosomal dominant polycystic kidney disease (ADPKD) has highlighted the need to identify rapidly progressive patients. Kidney size/age and genotype have predictive power for renal outcomes, but their relative and additive value, plus associated trajectories of disease progression, are not well defined.METHODSThe value of genotypic and/or kidney imaging data (Mayo Imaging Class; MIC) to predict the time to functional (end-stage kidney disease [ESKD] or decline in estimated glomerular filtration rate [eGFR]) or structural (increase in height-adjusted total kidney volume [htTKV]) outcomes were evaluated in a Mayo Clinic PKD1/PKD2 population, and eGFR and htTKV trajectories from 20-65 years of age were modeled and independently validated in similarly defined CRISP and HALT PKD patients.RESULTSBoth genotypic and imaging groups strongly predicted ESKD and eGFR endpoints, with genotype improving the imaging predictions and vice versa; a multivariate model had strong discriminatory power (C-index = 0.845). However, imaging but not genotypic groups predicted htTKV growth, although more severe genotypic and imaging groups had larger kidneys at a young age. The trajectory of eGFR decline was linear from baseline in the most severe genotypic and imaging groups, but it was curvilinear in milder groups. Imaging class trajectories differentiated htTKV growth rates; severe classes had rapid early growth and large kidneys, but growth later slowed.CONCLUSIONThe value of imaging, genotypic, and combined data to identify rapidly progressive patients was demonstrated, and reference values for clinical trials were provided. Our data indicate that differences in kidney growth rates before adulthood significantly define patients with severe disease.FUNDINGNIDDK grants: Mayo DK058816 and DK090728; CRISP DK056943, DK056956, DK056957, and DK056961; and HALT PKD DK062410, DK062408, DK062402, DK082230, DK062411, and DK062401.
Asunto(s)
Procesamiento de Imagen Asistido por Computador/métodos , Fallo Renal Crónico/patología , Riñón/patología , Mutación , Riñón Poliquístico Autosómico Dominante/fisiopatología , Canales Catiónicos TRPP/genética , Adulto , Anciano , Estudios de Cohortes , Progresión de la Enfermedad , Femenino , Genotipo , Tasa de Filtración Glomerular , Humanos , Riñón/metabolismo , Fallo Renal Crónico/diagnóstico por imagen , Fallo Renal Crónico/genética , Masculino , Persona de Mediana Edad , Riñón Poliquístico Autosómico Dominante/diagnóstico por imagen , Riñón Poliquístico Autosómico Dominante/genética , Tomografía Computarizada por Rayos XRESUMEN
The major risk factor for kidney stone disease is idiopathic hypercalciuria. Recent evidence implicates a role for defective calcium reabsorption in the renal proximal tubule. We hypothesized that claudin-2, a paracellular cation channel protein, mediates proximal tubule calcium reabsorption. We found that claudin-2-null mice have hypercalciuria due to a primary defect in renal tubule calcium transport and papillary nephrocalcinosis that resembles the intratubular plugs in kidney stone formers. Our findings suggest that a proximal tubule defect in calcium reabsorption predisposes to papillary calcification, providing support for the vas washdown hypothesis. Claudin-2-null mice were also found to have increased net intestinal calcium absorption, but reduced paracellular calcium permeability in the colon, suggesting that this was due to reduced intestinal calcium secretion. Common genetic variants in the claudin-2 gene were associated with decreased tissue expression of claudin-2 and increased risk of kidney stones in 2 large population-based studies. Finally, we describe a family in which males with a rare missense variant in claudin-2 have marked hypercalciuria and kidney stone disease. Our findings indicate that claudin-2 is a key regulator of calcium excretion and a potential target for therapies to prevent kidney stones.
Asunto(s)
Claudinas , Regulación de la Expresión Génica , Variación Genética , Hipercalciuria , Cálculos Renales , Túbulos Renales Proximales , Animales , Calcio/orina , Claudinas/deficiencia , Claudinas/metabolismo , Hipercalciuria/genética , Hipercalciuria/patología , Hipercalciuria/orina , Cálculos Renales/genética , Cálculos Renales/patología , Cálculos Renales/orina , Túbulos Renales Proximales/metabolismo , Túbulos Renales Proximales/patología , Ratones , Ratones NoqueadosRESUMEN
BACKGROUND: Artificial intelligence-enabled electronic health record (EHR) analysis can revolutionize medical practice from the diagnosis and prediction of complex diseases to making recommendations in patient care, especially for chronic conditions such as chronic kidney disease (CKD), which is one of the most frequent complications in patients with diabetes and is associated with substantial morbidity and mortality. OBJECTIVE: The longitudinal prediction of health outcomes requires effective representation of temporal data in the EHR. In this study, we proposed a novel temporal-enhanced gradient boosting machine (GBM) model that dynamically updates and ensembles learners based on new events in patient timelines to improve the prediction accuracy of CKD among patients with diabetes. METHODS: Using a broad spectrum of deidentified EHR data on a retrospective cohort of 14,039 adult patients with type 2 diabetes and GBM as the base learner, we validated our proposed Landmark-Boosting model against three state-of-the-art temporal models for rolling predictions of 1-year CKD risk. RESULTS: The proposed model uniformly outperformed other models, achieving an area under receiver operating curve of 0.83 (95% CI 0.76-0.85), 0.78 (95% CI 0.75-0.82), and 0.82 (95% CI 0.78-0.86) in predicting CKD risk with automatic accumulation of new data in later years (years 2, 3, and 4 since diabetes mellitus onset, respectively). The Landmark-Boosting model also maintained the best calibration across moderate- and high-risk groups and over time. The experimental results demonstrated that the proposed temporal model can not only accurately predict 1-year CKD risk but also improve performance over time with additionally accumulated data, which is essential for clinical use to improve renal management of patients with diabetes. CONCLUSIONS: Incorporation of temporal information in EHR data can significantly improve predictive model performance and will particularly benefit patients who follow-up with their physicians as recommended.