Validity of two weight prediction models for community-living patients participating in a weight loss program.

Models predicting individual body weights over time clarify patient expectations in weight loss programs. The accuracy of two commonly used weight prediction models in community living people is unclear. All eligible people entering a weight management program between 1992 and 2015 were included. Patients' diet was 1200 kcal/day for week 0 followed by 900 kcal/day for weeks 1-7 and were excluded from the analysis if they were nonadherent. We generated expected weights using the National Institutes of Health Body Weight Planner (NIH-BWP) and the Pennington Biomedical Research Center Weight Loss Predictor (PBRC-WLP). 3703 adherent people were included (mean age 46 years, 72.6% women, mean [SD] weight 262.3 pounds [54.2], mean [SD] BMI 42.4 [7.6]). Mean (SD) relative body weight differences (100*[observed-expected]/expected) for NIH-BWP and PBRC-WLP models was - 1.5% (3.8) and - 2.9% (3.2), respectively. At week 7, mean squared error with NIH-BWP (98.8, 83%CI 89.7-108.8) was significantly lower than that with PBRC-WLP (117.7, 83%CI 112.4-123.4). Notable variation in relative weight difference were seen (for NIH-BWP, 5th-95th percentile was - 6.2%, + 3.7%; Δ 9.9%). During the first 7 weeks of a weight loss program, both weight prediction models returned expected weights that were very close to observed values with the NIH-BWP being more accurate. However, notable variability between expected and observed weights in individual patients were seen. Clinicians can monitor patients in weight loss programs by comparing their progress with these data.