Proposal of a new equation for estimating resting energy expenditure for acute kidney injury patients on dialysis. A Machine Learning Approach.

The objective of this study was, therefore, to develop a new predictive equation of resting energy expenditure (REE) for acute kidney injury patients (AKI) on dialysis. Material and methods: A cross-sectional descriptive study has been carried out in 114 AKI patients on dialysis and mechanical ventilation consecutively selected, aged between 19 and 95 years. For the construction of the predictive model, 80% of the cases were randomly separated to train and 20% of unused cases for validation. Several machine learning models were tested in the training data: linear regression with Stepwise, rpart, support vector machine with radial kernel, generalized boosting machine, and random forest. The models were selected by 10-fold cross-validation and the performances evaluated by the root mean square error (RMSE). Results: There were 364 indirect calorimetry (IC) measurements in 114 patients, mean age of 60.65 ± 16.9 years and 68.4% were males. The average REE was 2081 ± 645 kcal. REE was positively correlated with C-reactive protein, minute volume (MV), expiratory positive airway pressure, serum urea, body mass index and inversely with age. The principal variables included in the selected model were age, BMI, use of vasopressors, expiratory positive airway pressure, minute volume, C-reactive protein, temperature, and serum urea. The final r-value in the validation set was 0.69. Conclusion: We propose a new predictive equation for estimating the REE for AKI patients on dialysis that use a non-linear approach with better performance than actual models.