Predictors of shorter- and longer-term mortality after COVID-19 presentation among dialysis patients: parallel use of machine learning models in Latin and North American countries

Abstract

Background We developed machine learning models to understand the predictors of shorter-, intermediate-, and longer-term mortality among hemodialysis (HD) patients affected by COVID-19 in four countries in the Americas. Methods We used data from adult HD patients treated at regional institutions of a global provider in Latin America (LatAm) and North America who contracted COVID-19 in 2020 before SARS-CoV-2 vaccines were available. Using 93 commonly captured variables, we developed machine learning models that predicted the likelihood of death overall, as well as during 0–14, 15–30, > 30 days after COVID-19 presentation and identified the importance of predictors. XGBoost models were built in parallel using the same programming with a 60%:20%:20% random split for training, validation, & testing data for the datasets from LatAm (Argentina, Columbia, Ecuador) and North America (United States) countries. Results Among HD patients with COVID-19, 28.8% (1,001/3,473) died in LatAm and 20.5% (4,426/21,624) died in North America. Mortality occurred earlier in LatAm versus North America; 15.0% and 7.3% of patients died within 0–14 days, 7.9% and 4.6% of patients died within 15–30 days, and 5.9% and 8.6% of patients died > 30 days after COVID-19 presentation, respectively. Area under curve ranged from 0.73 to 0.83 across prediction models in both regions. Top predictors of death after COVID-19 consistently included older age, longer vintage, markers of poor nutrition and more inflammation in both regions at all timepoints. Unique patient attributes (higher BMI, male sex) were top predictors of mortality during 0–14 and 15–30 days after COVID-19, yet not mortality > 30 days after presentation. Conclusions Findings showed distinct profiles of mortality in COVID-19 in LatAm and North America throughout 2020. Mortality rate was higher within 0–14 and 15–30 days after COVID-19 in LatAm, while mortality rate was higher in North America > 30 days after presentation. Nonetheless, a remarkable proportion of HD patients died > 30 days after COVID-19 presentation in both regions. We were able to develop a series of suitable prognostic prediction models and establish the top predictors of death in COVID-19 during shorter-, intermediate-, and longer-term follow up periods.

Development and validation of a machine learning-based predictive model for secondary post-tonsillectomy hemorrhage

“…For an overview of the XGBoost logic, this non-linear machine learning model used the input (independent) variables in the training dataset to construct an array of decision trees in every possible combination to establish a series of thresholds that split variables to maximize the information gain ( 19 ). In our study, the XGBoost model predicted patient risk with excellent calibration and good validation.…”

Systemic Immune Inflammation Index as a Key Predictor of Dialysis in Pediatric Chronic Kidney Disease with the Use of Random Forest Classifier

“…Another step is the analysis of risk factors, with an emphasis on the use of Gini feature importance as a parameter indicating critical factors for classifying patients and discrimination in risk models. Other authors mention its use in the assessment of unrelated and COVID-19-related mortality in dialysis patients [43,44]. It was also used in predicting the outcome in patients with lupus nephritis [42] and in estimating graft function in patients after kidney transplantation [45].…”

Impacto de la hemodiafiltración de alto volumen en sobrevida de pacientes en hemodiálisis de Argentina

“…Un enfoque más novedoso para controlar el sesgo por selección fue presentado recientemente por Guinsburg et al 2 y se basó en el uso de una herramienta de machine-learning llamada DoWhy. DoWhy es una librería de Python de código abierto creada con suposiciones causales, organizada en torno a los cuatro pasos clave necesarios para cualquier análisis causal: modelar, identificar, estimar y refutar.…”