Federated learning enables big data for rare cancer boundary detection

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.

Assaults on staff by psychiatric patients in community residences

The study examined assaultive behavior directed toward staff of community-based residential facilities by patients who had been discharged to these facilities from Massachusetts state psychiatric hospitals in the early 1990s. Observed rates of assault declined by 61 percent over a six-and-a-half-year period. Early in the study period, male patients were more likely than female patients to be assaultive, but men and women had similar rates of assaultiveness later in the study period, after they had been in residential placements for several years. The most common diagnosis among assaultive patients was schizophrenia.