Predicting mortality in hemodialysis patients using machine learning analysis.

BACKGROUND: Besides the classic logistic regression analysis, non-parametric methods based on machine learning techniques such as random forest are presently used to generate predictive models. The aim of this study was to evaluate random forest mortality prediction models in haemodialysis patients. METHODS: Data were acquired from incident haemodialysis patients between 1995 and 2015. Prediction of mortality at 6 months, 1 year and 2 years of haemodialysis was calculated using random forest and the accuracy was compared with logistic regression. Baseline data were constructed with the information obtained during the initial period of regular haemodialysis. Aiming to increase accuracy concerning baseline information of each patient, the period of time used to collect data was set at 30, 60 and 90 days after the first haemodialysis session. RESULTS: There were 1571 incident haemodialysis patients included. The mean age was 62.3 years and the average Charlson comorbidity index was 5.99. The mortality prediction models obtained by random forest appear to be adequate in terms of accuracy [area under the curve (AUC) 0.68-0.73] and superior to logistic regression models (ΔAUC 0.007-0.046). Results indicate that both random forest and logistic regression develop mortality prediction models using different variables. CONCLUSIONS: Random forest is an adequate method, and superior to logistic regression, to generate mortality prediction models in haemodialysis patients.

La corrección del déficit de 25-OH-vitamina D mejora el control del hiperparatiroidismo secundario y el estado inflamatorio de pacientes estables en hemodiálisis / Correction of 25-OH-vitamin D deficiency improves control of secondary hyperparathyroidism and reduces the inflammation in stable haemodialysis patients

Introducción: El déficit de 25-OH-vitamina D (25-OH-D) es común en los pacientes en hemodiálisis (HD). Por otra parte, es bien conocida la elevada incidencia de hiperparatiroidismo secundario en este grupo de pacientes, y lo importante que es su adecuado control. La 25-OH-D está implicada en la regulación de la homeostasis del calcio, por lo que tener niveles adecuados puede contribuir en el control del metabolismo óseo-mineral. Objetivos: Evaluar el efecto de la repleción de 25-OH-D en pacientes en HD con déficit vitamínico (niveles<20ng/ml), en el control del hiperparatiroidismo secundario y en el estado de microinflamación. Pacientes y métodos: Estudio observacional, prospectivo en el que se trataron pacientes estables en HD con déficit de 25-OH-D (<20ng/ml), con calcifediol 0,266mcg/15 días vía oral durante 3 meses. Los datos de HD, parámetros bioquímicos y las dosis de fármacos administrados fueron analizados antes y después de la corrección del déficit. Resultados: Un total de 45 pacientes estables en HD con edad media 74,08±12,49 años completaron el tratamiento. Del total, 27 pacientes (60%) alcanzaron niveles de 25-OH-D>20ng/ml (en 23 fueron>30ng/ml, y 4 entre 20-30ng/ml). Las cifras de hormona paratiroidea descendieron en 32 de los 45 pacientes, alcanzando en 23 (51% de tratados) un descenso>30% respecto al valor basal. En cuanto al tratamiento concomitante, se objetivó un descenso significativo de la dosis de activador selectivo del receptor de vitamina D; sin evidenciarse cambios en la dosis de calcimimético ni de quelantes. Respecto al estado de malnutrición-inflamación, destaca un descenso de la proteína C reactiva, aunque no se modificaron otros parámetros de microinflamación como los monocitos activados (CD14+/CD16+ y CD 14++/CD16+). Tampoco se observaron cambios en los niveles de FGF-23. Conclusiones: La corrección del déficit de 25-OH-D en pacientes en HD se asocia a un mejor control del hiperparatiroidismo secundario con menores dosis de análogos de vitamina D y a una mejoría en el estado inflamatorio de estos pacientes. Nuestros resultados apoyan la recomendación de determinar niveles de 25-OH-D y corregir el déficit en pacientes en HD (AU)

Introduction: Patients on haemodialysis (HD) have a high prevalence of 25-OH-vitamin D (25-OH-D)deficiency. Secondary hyperparathyroidismis a common condition in these patients, which is very important to control. 25-OH-D is involved in regulating calcium homeostasis. As such, appropriate levels of this vitamin could help to control bone mineral metabolism. Objective: To evaluate the effect 25-OH-D repletion in HD patients with 25-OH-D deficiency (<20ng/ml) on the control of secondary hyperparathyroidism and microinflammation status. Patients and methods: Prospective observational study in which stable patients on HD with 25-OH-D deficiency (<20ng/ml) were treated with oral calcifediol 0.266mcg/every 2 weeks for three months. Dialysis characteristics, biochemical parameters and drug doses administered were analysed before and after the correction of the deficiency. Results: Forty-five stable HD patients with a mean age of 74.08±12.49 years completed treatment. Twenty-seven patients (60%) achieved 25-OH-D levels above 20ng/ml (23 with levels>30ng/ml and 4 between 20-30ng/ml). Parathyroid hormone levels decreased in 32 of the 45 patients, 23 of which (51%) achieved a>30% decrease from baseline. In terms of concomitant treatment, we observed a significant reduction in the selective vitamin D receptor activator dose, but no changes in calcimimetic or phosphate binders administration. In terms of malnutrition-inflammation status, a decrease in C-reactive protein was noted, although other microinflammation parameters, such as activated monocytes (CD14+/CD16+ and CD 14++/CD16+) were unchanged. No changes were observed in the levels of FGF-23. Conclusions: Correcting 25-OH-D deficiency in HD patients is associated with better secondary hyperparathyroidism control with lower doses of vitamin D analogues, as well as an improvement in inflammatory status. Our results support the recommendation to determine 25-OH-D levels and correct its deficiency in these patients (AU)

Correction of 25-OH-vitamin D deficiency improves control of secondary hyperparathyroidism and reduces the inflammation in stable haemodialysis patients. / La corrección del déficit de 25-OH-vitamina D mejora el control del hiperparatiroidismo secundario y el estado inflamatorio de pacientes estables en hemodiálisis.

INTRODUCTION: Patients on haemodialysis (HD) have a high prevalence of 25-OH-vitamin D (25-OH-D)deficiency. Secondary hyperparathyroidismis a common condition in these patients, which is very important to control. 25-OH-D is involved in regulating calcium homeostasis. As such, appropriate levels of this vitamin could help to control bone mineral metabolism. OBJECTIVE: To evaluate the effect 25-OH-D repletion in HD patients with 25-OH-D deficiency (<20ng/ml) on the control of secondary hyperparathyroidism and microinflammation status. PATIENTS AND METHODS: Prospective observational study in which stable patients on HD with 25-OH-D deficiency (<20ng/ml) were treated with oral calcifediol 0.266mcg/every 2 weeks for three months. Dialysis characteristics, biochemical parameters and drug doses administered were analysed before and after the correction of the deficiency. RESULTS: Forty-five stable HD patients with a mean age of 74.08±12.49 years completed treatment. Twenty-seven patients (60%) achieved 25-OH-D levels above 20ng/ml (23 with levels>30ng/ml and 4 between 20-30ng/ml). Parathyroid hormone levels decreased in 32 of the 45 patients, 23 of which (51%) achieved a>30% decrease from baseline. In terms of concomitant treatment, we observed a significant reduction in the selective vitamin D receptor activator dose, but no changes in calcimimetic or phosphate binders administration. In terms of malnutrition-inflammation status, a decrease in C-reactive protein was noted, although other microinflammation parameters, such as activated monocytes (CD14+/CD16+ and CD 14++/CD16+) were unchanged. No changes were observed in the levels of FGF-23. CONCLUSIONS: Correcting 25-OH-D deficiency in HD patients is associated with better secondary hyperparathyroidism control with lower doses of vitamin D analogues, as well as an improvement in inflammatory status. Our results support the recommendation to determine 25-OH-D levels and correct its deficiency in these patients.

Efficiency of Original versus Generic Intravenous Iron Formulations in Patients on Haemodialysis.

AIMS: The appropriate use of intravenous (i.v.) iron is essential to minimise the requirements for erythropoiesis-stimulating agents (ESAs). The clinical efficacy of generic i.v. iron compared to the original formulation is controversial. We evaluated the changes that were induced after switching from a generic i.v. iron to an original formulation in a stable, prevalent haemodialysis (HD) population. METHODS: A total of 342 patients were included, and the follow-up period was 56 weeks for each formulation. Anaemia parameters and doses of ESA and i.v. iron were prospectively recorded before and after the switch from generic to original i.v. iron. RESULTS: To maintain the same haemoglobin (Hb) levels after switching from the generic to the original formulation, the requirements for i.v. iron doses were reduced by 34.3% (from 52.8±33.9 to 34.7±31.8 mg/week, p<0.001), and the ESA doses were also decreased by 12.5% (from 30.6±23.6 to 27±21 µg/week, p<0.001). The erythropoietin resistance index declined from 8.4±7.7 to 7.4±6.7 IU/kg/week/g/dl after the switch from the generic to the original drug (p = 0.001). After the switch, the transferrin saturation ratio (TSAT) and serum ferritin levels rose by 6.8% (p<0.001) and 12.4% (p = 0.001), respectively. The mortality rate was similar for both periods. CONCLUSIONS: The iron and ESA requirements are lower with the original i.v. iron compared to the generic drug. In addition, the uses of the original formulation results in higher ferritin and TSAT levels despite the lower dose of i.v. iron. Further studies are necessary to analyse the adverse effects of higher i.v. iron dosages.