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.

No abstract

No abstract

Terbinafine has proved to treat numerous fungal infections, including onychomycosis, successfully. Due to its liver metabolization and dependency on the cytochrome P450 enzyme complex, undesirable drug interaction are highly probable. Additionally to drug interactions, the treatment is long, rising the chances of the appearance of side effects and abandonment. Pharmacokinetic data suggest that terbinafine maintains a fungicidal effect within the nail up to 30 weeks after its last administration, which has aroused the possibility of a pulse therapy to reduce the side effects while treating onychomycosis. This study’s goal was to evaluate the effectiveness of three different oral terbinafine regimens in treating onychomycosis due to dermatophytes. Sixty-three patients with onychomycosis were sorted by convenience in three different groups. Patients from group 1 received the conventional terbinafine dose (250 mg per day for 3 months). Group 2 received a monthly week-long pulse-therapy dose (500 mg per day for 7 days a month, for 4 months) and group 3 received a 500 mg/day dose for 7 days every 3 months, totaling four treatments. There were no statistical differences regarding the effectiveness or side effects between the groups. Conclusion: A quarterly terbinafine pulse regimen can be a possible alternative for treating onychomycosis caused by dermatophytes.

No abstract