OBJECTIVE:: To compare, in patients with cancer and in healthy subjects, measured resting energy expenditure (REE) from traditional indirect calorimetry to a new portable device (MedGem™) and predicted REE. DESIGN:: Cross-sectional clinical validation study. SETTING:: Private radiation oncology centre, Brisbane, Australia. SUBJECTS:: Cancer patients (n=18) and healthy subjects (n=17) aged 37-86?y, with body mass indices ranging from 18 to 42?kg/m2. INTERVENTIONS:: Oxygen consumption (VO2) and REE were measured by VMax229 (VM) and MedGem (MG) indirect calorimeters in random order after a 12-h fast and 30-min rest. REE was also calculated from the MG without adjustment for nitrogen excretion (MGN) and estimated from Harris-Benedict prediction equations. Data were analysed using the Bland and Altman approach, based on a clinically acceptable difference between methods of 5%. RESULTS:: The mean bias (MGN-VM) was 10%and limits of agreement were-42 to 21%for cancer patients; mean bias-5%with limits of-45 to 35%for healthy subjects. Less than half of the cancer patients (n=7, 46.7%) and only a third (n=5, 33.3%) of healthy subjects had measured REE by MGN within clinically acceptable limits of VM. Predicted REE showed a mean bias (HB-VM) of-5%for cancer patients and 4%for healthy subjects, with limits of agreement of-30 to 20%and-27 to 34%, respectively. CONCLUSIONS:: Limits of agreement for the MG and Harris Benedict equations compared to traditional indirect calorimetry were similar but wide, indicating poor clinical accuracy for determining the REE of individual cancer patients and healthy subjects.European Journal of Clinical Nutrition (2005) 59, 603-610. doi:10.1038/sj.ejcn.1602114 Published online 2 March 2005 [ABSTRACT FROM AUTHOR]