#460 Digital twin in hemodialysis model, with machine learning algorithms. Data from the Andalusian Hemodialysis Registry. SICATA

Abstract

Abstract Background and Aims Orthodoxly, a digital twin is a computer simulation of an individual, “in silico”, and in real time. A digital twin can also be created with BIG DATA. The Objective It is the development of a survival digital twin model using Machine Learning algorithms using data from the Andalusian SICATA registry. Method The database was composed of 29,189 records at the time of analysis and contains variables in the areas of comorbidity, anemia, efficacy of renal replacement therapy (RRT), and renal bone disease. The algorithms used were: - XG Boost, AdaBoost, Cat boost. KNN, Random Forest, Decision Trees, Logistic Regression. A survival model was developed with each Machine Learning (ML) algorithm . The metrics of the models were taken into account: precision, calibration, accuracy. The software used was Orange based on Python and Rattle based on R. An explanation of the “black box” type models was carried out using SHAP (Shapley values) based on game theory. Results The characteristics that the digital twin that we have modeled with the greatest survival would have are: 1. Age equal to or less than 45 years, 2. Being included in the kidney transplant waiting list. 3. Longer duration of the hemodialysis session. 4. Low doses of Erythropoietin. 5. Normal or high serum albumin levels. 6. BMI > 21.The sample was stratified according to the Ultrafiltration (UF) ratio during the Hemodialysis session in ml/kg/hour. Group1: UF <4 ml/kg/hour. Group2: UF 5-9 ml/kg/hour. Group3: UF>9 ml/kg/hour. And a mortality study was carried out using multivariate Logistic Regression. We found that the OR for mortality in groups 2 and 3 was 17% and 24% in relation to group 1, which had the lowest mortality. Conclusion ML has revealed that the UF ratio (ml/kg/hour) is an important predictor variable of mortality. In our studio a UF ratio<4 ml/kg/hour is safe ML has found an answer to a question that we had not asked ourselves when beginning the study: What is the optimal UF rate in the hemodialysis session?