RESUMEN
INTRODUCTION: High body mass index (BMI) is associated with increased cardiovascular mortality and risk of progression to end-stage renal disease both among the general population and among renal transplant patients. However, in the latter condition no unequivocal studies have been reported in the literature. The aim of our study was to investigate continuous versus categorical values of BMI (World Health Organization classification) as an independent risk factor in renal transplantation. PATIENTS AND METHODS: We retrospectively studied 194 renal transplant patients (128 males and 66 females) whose mean age at transplant was 43.9 years. They had 5 years follow-up. To investigate the association between BMI and graft survival, we performed univariate and multivariate analyses using the Cox regression model. This model was adjusted both for classical covariates (age, gender, time on dialysis, HLA mismatches, donor status) and other covariates as delayed graft function (DGF), acute rejection episodes (AR), and chronic allograft nephropathy (CAN), which are universally recognized to be predictors of graft loss as evidenced by a need for dialysis treatments. RESULTS: At the time of transplantation, the BMI averaged 24.4 +/- 2.65 kg/m(2). Upon univariate analysis, age (P = .049), BMI (P = .005), DGF (P = .009), ARE (P < .0001), and CAN (P = .001) were significantly related to poor transplant outcomes. Upon multivariate analysis, only the BMI value, considered as continuous value (P = .013), DGF (P = .030), and ARE (P < .0001) were significantly related to graft loss. CONCLUSIONS: BMI as a continuous value represented an independent risk factor for renal transplant loss at 5 years. Correction of pretransplant body weight both in overweight (25 Asunto(s)
Índice de Masa Corporal
, Trasplante de Riñón/fisiología
, Sobrepeso/fisiopatología
, Adulto
, Cadáver
, Femenino
, Estudios de Seguimiento
, Antígenos HLA/inmunología
, Prueba de Histocompatibilidad
, Humanos
, Trasplante de Riñón/inmunología
, Donadores Vivos
, Masculino
, Persona de Mediana Edad
, Estudios Retrospectivos
, Donantes de Tejidos
, Pérdida de Peso
RESUMEN
INTRODUCTION: For its intrinsic potential to mine causal relations, machine learning techniques are useful to identify new risk indicators. In this work, we have shown two classification trees to predict chronic allograft nephropathy (CAN), through an evaluation of routine blood and urine tests. METHODS: We retrospectively analyzed 80 renal transplant patients with 60-month follow-up (mean = 55.20 +/- 12.74) including 52 males and 28 females of overall average age of 41.65 +/- 12.52 years. The primary endpoint was biopsy-proven CAN within 5 years from transplantation (n = 16). Exclusion criteria were multiorgan transplantations, patients aged less than 18 years, graft failure, or patient death in the first 6 months posttransplantation. Classification trees based on the C 4.8 algorithm were used to predict CAN development starting from patient features at transplantation and biochemical test at 6-month follow-up. Model performance was showed as sensitivity (S), false-positive rate (FPR), and area under the receiver operating characteristic curve (AUC). RESULTS: The two class of patients (no CAN versus CAN) showed significant differences in serum creatinine, estimated Glomerular Filtration Rate with Modification of Diet in Renal Disease study formula (MDRD), serum hemoglobin, hematocrit, blood urea nitrogen, and 24-hour urine protein excretion. Among the 23 evaluated variables, the first model selected six predictors of CAN, showing S = 62.5%, TFP = 7.2%, and AUC = 0.847 (confidence interval [CI] 0.749-0.945). The second model selected four variables, showing S = 81.3%, TFP = 25%, and AUC = 0.824 (CI 0.713-0.934). CONCLUSIONS: Identification models have predicted the onset of multifactorial, complex pathology, like CAN. The use of classification trees represent a valid alternative to traditional statistical models, especially for the evaluation of interactions of risk factors.
Asunto(s)
Enfermedades Renales/clasificación , Enfermedades Renales/patología , Trasplante de Riñón/patología , Adulto , Algoritmos , Biopsia , Nitrógeno de la Urea Sanguínea , Creatinina/sangre , Femenino , Estudios de Seguimiento , Antígenos HLA , Hematócrito , Hemoglobinas/metabolismo , Prueba de Histocompatibilidad , Humanos , Trasplante de Riñón/inmunología , Trasplante de Riñón/fisiología , Masculino , Persona de Mediana Edad , Complicaciones Posoperatorias/clasificación , Complicaciones Posoperatorias/patología , Valor Predictivo de las Pruebas , ProteinuriaRESUMEN
INTRODUCTION: The predictive potentialities of application of data mining algorithms to medical research are well known. In this article, we have applied to a transplant population classification trees to build predictive models of graft failure, evaluating the interactions between body mass index (BMI) and other risk factors. The decision trees have been widely used to represent classification rules in a population by a hierarchical sequential structure. PATIENTS AND METHODS: We retrospectively studied 194 renal transplant patients with 5 years of follow-up (128 males, 66 females, mean age at time of transplant of 43.9 +/- 12.5 years). Exclusion criteria were: age < 18 years, multiorgan transplant, and retransplant. The BMI was calculated at the time of transplantation. In the classification algorithm, we considered the following parameters: age, sex, time on dialysis, donor type, donor age, HLA mismatches, delayed graft function (DGF), acute rejection episode (ARE), and chronic allograft nephropathy (CAN). The primary endpoint was graft loss within 5-years follow-up. RESULTS: The classification algorithm produced a decision tree that allowed us to evaluate the interactions between ARE, DGF, CAN, and BMI on graft outcomes, producing a validation set with 88.2% sensitivity and 73.8% specificity. Our model was able to highlight that subjects at risk of graft loss experienced one or more events of ARE, developed DGF and CAN, or has a BMI > 24.8 kg/m(2) and CAN. CONCLUSIONS: The use of decision trees in clinical practice may be a suitable alternative to the traditional statistical methods, since it may allow one to analyze interactions between various risk factors beyond the previous knowledge.