Proposal of a new equation for estimating resting energy expenditure of acute kidney injury patients on dialysis: a mach
- PDF / 1,623,170 Bytes
- 8 Pages / 595.276 x 790.866 pts Page_size
- 88 Downloads / 164 Views
Open Access
RESEARCH
Proposal of a new equation for estimating resting energy expenditure of acute kidney injury patients on dialysis: a machine learning approach Daniela Ponce* , Cassiana Regina de Goes and Luis Gustavo Modelli de Andrade
Abstract Background: The objective of this study was to develop a new predictive equation of resting energy expenditure (REE) for acute kidney injury patients (AKI) on dialysis. Materials and methods: A cross-sectional descriptive study was carried out of 114 AKI patients, consecutively selected, on dialysis and mechanical ventilation, aged between 19 and 95 years. For construction of the predictive model, 80% of cases were randomly separated to training and 20% of unused cases to validation. Several machine learning models were tested in the training data: linear regression with stepwise, rpart, support vector machine with radial kernel, generalised boosting machine and random forest. The models were selected by ten-fold cross-validation and the performances evaluated by the root mean square error. Results: There were 364 indirect calorimetry 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, body mass index, use of vasopressors, expiratory positive airway pressure, MV, 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 of AKI patients on dialysis that uses a nonlinear approach with better performance than actual models. Keywords: Energy metabolism, Resting energy expenditure, Machine learning, Acute kidney injury, Sepsis, Dialysis Introduction Acute kidney injury (AKI) occurs in approximately 3–15% of hospitalised patients and can affect 30–50% of patients admitted to intensive care units (ICU). It is associated with extremely high mortality rates, ranging from 20 to 50% [1]. Previous observational studies reported that malnourished and hospitalised AKI patients have higher rates of morbidity and mortality *Correspondence: [email protected] Department of Internal Medicine ‑ UNESP, Univ Estadual Paulista, Rubião Jr, s/n – Botucatu/SP18.618‑970, São Paulo, Brazil
than well-nourished patients [2, 3] and an association between cumulative caloric deficits and poor outcome in ICU patients [4, 5]. Accurate determination of energy needs is obviously important in critically ill patients as both over and underfeeding may be associated with complications and undesired consequences [6]. Determining energy requirements in critically ill patients via indirect calorimetry (IC) has long been considered the gold standard [7]. Limitations for using IC include time constraints, equipment availability, staffing and cost. Therefore, many predictive equations exist for predict
Data Loading...
