Factors postulated to predict weight loss after gastric bypass surgery, include race, age, gender, technique, height, and initial weight. This paper contained 1551 gastric bypass patients (85.9% female). Operations were performed by one surgeon (MLO) at community hospitals in Southern California from 1989 to 2008 with 314 being laparoscopic and 1237 open. We created the following equation: In[percent weight] = At(2) - Bt, where t was the time after operation (days) and A and B are constants. Analysis was completed on R-software. The model fits with R(2) value 0.93 and gives patients a realistic mean target weight with a confidence interval of 95% for the first year. Conclusion. We created a curve predicting weight loss after surgery as a percentage of initial weight. Initial weight was the single most important predictor of weight loss after surgery. Other recorded variables accounted for less than 1% of variability. Unknown factors account for the remaining 6-7%.

Although machine learning (ML) has shown promise across disciplines, out-of-sample generalizability is concerning. This is currently addressed by sharing multi-site data, but such centralization is challenging/infeasible to scale due to various limitations. Federated ML (FL) provides an alternative paradigm for accurate and generalizable ML, by only sharing numerical model updates. Here we present the largest FL study to-date, involving data from 71 sites across 6 continents, to generate an automatic tumor boundary detector for the rare disease of glioblastoma, reporting the largest such dataset in the literature (n = 6, 314). We demonstrate a 33% delineation improvement for the surgically targetable tumor, and 23% for the complete tumor extent, over a publicly trained model. We anticipate our study to: 1) enable more healthcare studies informed by large diverse data, ensuring meaningful results for rare diseases and underrepresented populations, 2) facilitate further analyses for glioblastoma by releasing our consensus model, and 3) demonstrate the FL effectiveness at such scale and task-complexity as a paradigm shift for multi-site collaborations, alleviating the need for data-sharing.