We hypothesised that an exposure–response weight predictor algorithm developed from randomised controlled trial data can predict long-term individual body weight changes in both men and women in response to subcutaneous semaglutide treatment for weight management using self-reported, real-world data, collected through a digital patient support program (PSP). An exposure–response body weight prediction model developed from clinical trials with semaglutide in people with overweight or obesity was applied to a real-world dataset from patients prescribed semaglutide (0.25–2.4 mg) by their treating healthcare provider (HCP) and enrolled into an app-based PSP. Model variables were baseline sex and body weight, and self-reported dosing and body weight during semaglutide treatment. Predictions were assessed in two scenarios. In the first scenario, body weight at 26 ± 4 weeks was predicted from baseline data with model updates at weeks 4, 8, and 16. In the second scenario, body weight at 52 ± 4 weeks was predicted from baseline data with updates at weeks 8, 16, and 28. Model bias was calculated as the difference between predicted and self-reported body weight, while precision for predicting categorical weight loss (≥ 10%, ≥ 15%, ≥ 20%) was assessed using area under the curve (AUC). The study included 1797 WegovyCare® app users, predominantly women (81%), with a mean (SD) age of 48.0 (11.8) years. Mean (SD) self-reported body weight in the entire population was 105 (19.5) kg at baseline. In the half-year scenario, users lost an average of 15% (15.6 kg). Model bias was low (0.7–1.4 kg) and precision for predicting categorical weight loss was high (AUC 0.74–0.95). In the full-year scenario, average weight decreased by 21% (22.0 kg) with similarly low bias (−0.6 to 0.6 kg) and high prediction precision for categorical weight loss (AUC 0.75–0.92). This study successfully applied an exposure–response weight predictor algorithm to self-reported data collected from users in the real world. Integrating weight predictors into digital PSPs may be valuable for both patients and HCPs in managing weight loss and setting or monitoring treatment targets. This study tested whether a statistical model, originally developed using clinical trial data, can accurately predict how much weight people will lose when using semaglutide in real-world settings. The researchers used self-reported data from 1797 patients with overweight or obesity who were prescribed subcutaneous semaglutide for weight management and used a digital patient support app. They were on average 48 years of age and had a starting weight of 105 kg. Access to the app was facilitated by healthcare providers in primary care practices, online clinics, or community pharmacies. The statistical model included information on the users’ sex, starting body weight, as well as their reported semaglutide doses and weight changes over time. The researchers evaluated body weight predictions in two scenarios. In scenario 1, weight at approximately 26 weeks was predicted from baseline data, with model updates at weeks 4, 8, and 16. In scenario 2, weight at approximately 52 weeks was predicted from baseline data, with updates at weeks 8, 16, and 28. Accuracy of the model was measured by comparing the predicted weight loss to what users actually reported and by how well it could predict whether users would lose 10%, 15%, or 20% of their body weight. After 6 months, patients who continued to use the app lost on average 15% of their body weight, and after 12 months, patients with continued app use had lost on average 21%. The model’s predictions were very close to the actual weight change, with only small differences. Predictions improved as more time points were included in the model.
Kristine et al. (Fri,) studied this question.