Estimating resting energy expenditure of patients on dialysis: Development and validation of a predictive equation

Machine learning models using non-linear techniques improve the prediction of resting energy expenditure in individuals receiving hemodialysis

PURPOSE

Approximately 700,000 people in the USA have chronic kidney disease requiring dialysis. Protein-energy wasting (PEW), a condition of advanced catabolism, contributes to three-year survival rates of 50%. PEW occurs at all levels of Body Mass Index (BMI) but is devastating for those people at the extremes. Treatment for PEW depends on an accurate understanding of energy expenditure. Previous research established that current methods of identifying PEW and assessing adequate treatments are imprecise. This includes disease-specific equations for estimated resting energy expenditure (eREE). In this study, we applied machine learning (ML) modelling techniques to a clinical database of dialysis patients. We assessed the precision of the ML algorithms relative to the best-performing traditional equation, the MHDE.

METHODS

This was a secondary analysis of the Rutgers Nutrition and Kidney Database. To build the ML models we divided the population into test and validation sets. Eleven ML models were run and optimized, with the best three selected by the lowest root mean squared error (RMSE) from measured REE. Values for eREE were generated for each ML model and for the MHDE. We compared precision using Bland-Altman plots.

RESULTS

Individuals were 41.4% female and 82.0% African American. The mean age was 56.4 ± 11.1 years, and the median BMI was 28.8 (IQR = 24.8 - 34.0) kg/m2. The best ML models were SVR, Linear Regression and Elastic net with RMSE of 103.6 kcal, 119.0 kcal and 121.1 kcal respectively. The SVR demonstrated the greatest precision, with 91.2% of values falling within acceptable limits. This compared to 47.1% for the MHDE. The models using non-linear techniques were precise across extremes of BMI.

CONCLUSION

ML improves precision in calculating eREE for dialysis patients, including those most vulnerable for PEW. Further development for clinical use is a priority.

Current methods for developing predictive energy equations in maintenance dialysis are imprecise

PURPOSE

For individuals receiving maintenance dialysis, estimating accurate resting energy expenditure (REE) is essential for achieving energy balance, and preventing protein-energy wasting. Dialysis-specific, predictive energy equations (PEEs) offer a practical way to calculate REE. Three PEEs have been formulated via similar methods in different demographic samples; the Maintenance Haemodialysis Equation (MHDE REE), Vilar et al. Equation (Vilar REE) and the Fernandes et al. Equation (Cuppari REE). We compared them in a US cohort and assessed precision relative to measured REE (mREE) from indirect calorimetry. Because of expected imprecision at the extremes of the weight distribution, we also assessed the PEEs stratified by body mass index (BMI) subgroups.

METHODS

This analysis comprised of 113 individuals from the Rutgers Nutrition and Kidney Database. Estimated REE (eREE) was calculated for each PEE, and agreement with mREE was set at > 50% of values within the limits of ±10%. Reliability and accuracy were determined using intraclass correlation (ICC) and a Bland Altman plot, which analysed the percentage difference of eREE form mREE.

RESULTS

Participants were 58.4% male and 81.4% African American. Mean age was 55.8 ± 12.2 years, and the median BMI was 28.9 (IQR = 25.3 - 34.4) kg/m2. The MHDE REE achieved 58.4% of values within ±10% from mREE; Cuppari REE achieved 47.8% and Vilar REE achieved 46.0% agreement. Reliability was good for the MHDE REE (ICC = 0.826) and Cuppari REE (ICC = 0.801), and moderate for the Vilar REE (ICC = 0.642) (p < .001 for all). The equations performed poorly at the lowest and highest BMI categories.

CONCLUSION

Dialysis-specific energy equations showed variable accuracy. When categorized by BMI, the equations performed poorly at the extremes, where individuals are most vulnerable. Innovation is needed to understand these variances and correct the imprecision in PEEs for clinical practice.KEY MESSAGESPotentially impacting over millions of patients worldwide, our long-term goal is to understand energy expenditure (EE) across the spectrum of CKD (stages 1-5) in adults and children being treated with dialysis or transplantation, with the intent of providing tools for the health professional that will improve the delivery of quality care.Our research has identified and focussed on disease-specific factors which account for 60% of the variance in predicting EE in patients on MHD, but significant gaps remain.Thus, our central hypotheses are that (1) there are unique disease-specific determinants of EE and (2) prediction of EE for individuals diagnosed with CKD can be vastly improved with a model that combines these factors with more sophisticated approaches.

Novel equation for estimating resting energy expenditure in patients with chronic kidney disease

BACKGROUND

In chronic kidney disease (CKD), determining energy expenditure is the precondition for recommending energy intake in nutrition management.

OBJECTIVES

We aimed to develop and validate a resting energy expenditure (REE) equation for patients with CKD.

METHODS

This cross-sectional study enrolled 300 patients with CKD (stages 3-5) according to inclusion and exclusion criteria. Stepwise linear regression analysis was used to derive a new REE equation (eREE-CKD) according to actual REE (aREE) measured using indirect calorimetry in the development dataset. The eREE-CKD value was then validated with aREE in the validation dataset and compared with values from existing equations obtained in general populations, namely, the Harris-Benedict, Mifflin, WHO, and Schofield equations in terms of bias, precision, and accuracy.

RESULTS

The eREE-CKD equation: eREE-CKD (kcal) = (1 if male; 0 if female) × 106.0 - [1 if diabetes mellitus (DM); 0 if non-DM] × 51.6 - 4.7 × age (y) + 13.1 × weight (kg) + 645.5 (R2 = 0.779).The bias, precision, and accuracy (percentage of estimates that differed >20% from the measured REE) of the eREE-CKD equation were -0.4 (IQR: -29.8, 23.8) kcal, 98.4 (IQR: 79.5, 116.6) kcal, and 5.4%, respectively with indirect calorimetry as the reference method. Both bias and precision of the eREE-CKD were significantly better than the Harris-Benedict, WHO, and Schofield equations (P < 0.001) and similar to the Mifflin equation (P = 0.125 for bias and 0.268 for precision). Accuracy of the eREE-CKD was significantly better than the Harris-Benedict, WHO, Mifflin, and Schofield equations (P < 0.001). Bias, precision, and accuracy of the eREE-CKD equation were consistent when applied to subgroups categorized according to high-sensitivity C-reactive protein concentrations and CKD stages, respectively.

CONCLUSIONS

The eREE-CKD equation using age, sex, weight, and DM data could serve as a reliable tool for estimating REE in patients with CKD. This trial was registered at clinicaltrials.gov as NCT03377413.

Resting energy expenditure in HIV/AIDS patients: Development and validation of a predictive equation

BACKGROUND

Accurate measurements of resting energy expenditure (REE) are important for determining nutritional needs in HIV patients. Indirect calorimetry (IC) is a noninvasive method that reflects REE but can be costly and is frequently calculated with predictive equations. Research suggests that REE obtained by predictive equations in people living with HIV/AIDS (PLWH) is inaccurate. The aim of the study is to develop and validate a new predictive equation of REE based on a population of PLWH.

METHODS

Cross-sectional study including 164 PLWH (82 to develop and 82 to validate the equation). Multiple linear regression was used to determine the relationship between variables and to develop the new predictive equation. Intraclass correlation coefficient (ICC) and Bland-Altman methods were used to evaluate agreement between the new predictive equation and indirect calorimetry.

RESULTS

A new predictive equation with an accuracy of 67% when compared with IC was developed. This equation included as covariates: fat free mass, antiretroviral therapy status and age.

CONCLUSION

A new equation to predict energy expenditure in PLWH was developed and validated. This formula can be used to estimate REE if IC is not available.