METHODS: Using indirect calorimetry, REE was measured at acute (≤5 days; n = 294) and late (≥6 days; n = 180) phases of intensive care unit admission. PEs were developed by multiple linear regression. A multi-fold cross-validation approach was used to validate the PEs. The best PEs were selected based on the highest coefficient of determination (R2), the lowest root mean square error (RMSE) and the lowest standard error of estimate (SEE). Two PEs developed from paired 168-patient data were compared with measured REE using mean absolute percentage difference.
RESULTS: Mean absolute percentage difference between predicted and measured REE was <20%, which is not clinically significant. Thus, a single PE was developed and validated from data of the larger sample size measured in the acute phase. The best PE for REE (kcal/day) was 891.6(Height) + 9.0(Weight) + 39.7(Minute Ventilation)-5.6(Age) - 354, with R2 = 0.442, RMSE = 348.3, SEE = 325.6 and mean absolute percentage difference with measured REE was: 15.1 ± 14.2% [acute], 15.0 ± 13.1% [late].
CONCLUSIONS: Separate PEs for acute and late phases may not be necessary. Thus, we have developed and validated a PE from acute phase data and demonstrated that it can provide optimal estimates of REE for patients in both acute and late phases.
TRIAL REGISTRATION: ClinicalTrials.gov NCT03319329.
MATERIALS & METHODS: A total of 50 participants with T2DM with peripheral neuropathy were included. Age group of 30-75 years were selected for the study. Participants with a known history of neurological disease, locomotor disability, and pregnancy were excluded from the study. Demographic details of the participants like duration of diabetes mellitus, age, Fasting Blood Glucose, Fasting Insulin, HOMA-IR, Glycated Haemoglobin (HBA1c), Neuropathy and Blood pressure values were noted. We measured Basal Metabolic Rate (BMR) by using Mifflin-St Jeor predictive equation in T2DM with peripheral neuropathy.
RESULTS: The mean age of the participants is 60.16 ± 10.62. The mean duration of T2DM 13.44 ± 11.92. In the present study we found a statistical significant correlation between BMR and HOMA IR (r = 0.913*; p = 0.000), BMR & Fasting blood sugar (FBS) (r = 0.281*; p = 0.048), BMR and Visceral fat (VF) (r = 0.332*; p = 0.018).
CONCLUSION: Basal metabolic rate is correlated to Homa-IR, visceral fat, fasting blood sugar and musculoskeletal mass among T2DM with peripheral neuropathy.
METHODOLOGY: This prospective study compared the performance of nine commonly used PEs, including the Harris-Benedict (H-B1919), Penn State, and TAH equations, with ML models (XGBoost, Random Forest Regressor [RFR], Support Vector Regression), and DL models (Convolutional Neural Networks [CNN]) in estimating REE in critically ill patients. A dataset of 300 IC measurements from an intensive care unit (ICU) was used, with REE measured by both IC and PEs. The ML/DL models were trained using a combination of static (i.e., age, height, body weight) and dynamic (i.e., minute ventilation, body temperature) variables. A five-fold cross validation was performed to assess the model prediction performance using the root mean square error (RMSE) metric.
RESULTS: Of the PEs analysed, H-B1919 yielded the lowest RMSE at 362 calories. However, the XGBoost and RFR models significantly outperformed all PEs, achieving RMSE values of 199 and 200 calories, respectively. The CNN model demonstrated the poorest performance among ML models, with an RMSE of 250 calories. The inclusion of additional categorical variables such as body mass index (BMI) and body temperature classes slightly reduced RMSE across ML and DL models. Despite data augmentation and imputation techniques, no significant improvements in model performance were observed.
CONCLUSION: ML models, particularly XGBoost and RFR, provide more accurate REE estimations than traditional PEs, highlighting their potential to better capture the complex, non-linear relationships between physiological variables and REE. These models offer a promising alternative for guiding nutritional therapy in clinical settings, though further validation on independent datasets and across diverse patient populations is warranted.