Scalable federated learning for emergency care using low cost microcomputing: Real-world, privacy preserving development and evaluation of a COVID-19 screening test in UK hospitals

Abstract

Background Tackling biases in medical artificial intelligence requires multi-centre collaboration, however, ethical, legal and entrustment considerations may restrict providers' ability to participate. Federated learning (FL) may eliminate the need for data sharing by allowing algorithm development across multiple hospitals without data transfer. Previously, we have shown an AI-driven screening solution for COVID-19 in emergency departments using clinical data routinely available within 1h of arrival to hospital (vital signs & blood tests; CURIAL-Lab). Here, we aimed to extend and federate our COVID-19 screening test, demonstrating development and evaluation of a rapidly scalable and user-friendly FL solution across 4 UK hospital groups. Methods We supplied a Raspberry Pi 4 Model B device, preloaded with our end-to-end FL pipeline, to 4 NHS hospital groups or their locally-linked research university (Oxford University Hospitals/University of Oxford (OUH), University Hospitals Birmingham/University of Birmingham (UHB), Bedfordshire Hospitals (BH) and Portsmouth Hospitals University (PUH) NHS trusts). OUH, PUH and UHB participated in federated training and calibration, training a deep neural network (DNN) and logistic regressor to predict COVID-19 status using clinical data for pre- pandemic (COVID-19-negative) admissions and COVID-19-positive cases from the first wave. We performed federated prospective evaluation at PUH & OUH, and external evaluation at BH, evaluating the resultant global and site-tuned models for admissions to the respective sites during the second pandemic wave. Removable microSD storage was destroyed on study completion. Findings Routinely collected clinical data from a total 130,941 patients (1,772 COVID-19 positive) across three hospital groups were included in federated training. OUH, PUH and BH participated in prospective federated evaluation, with sets comprising 32,986 patient admissions (3,549 positive) during the second pandemic wave. Federated training improved DNN performance by a mean of 27.6% in terms of AUROC when compared to models trained locally, from AUROC of 0.574 & 0.622 at OUH & PUH to 0.872 & 0.876 for the federated global model. Performance improvement was more modest for a logistic regressor with a mean AUROC increase of 13.9%. During federated external evaluation at BH, the global DNN model achieved an AUROC of 0.917 (0.893-0.942), with 89.7% sensitivity (83.6-93.6) and 76.7% specificity (73.9- 79.1). Site-personalisation of the global model did not give a significant improvement in overall performance (AUROC improvement <0.01), suggesting high generalisability. Interpretations We present a rapidly scalable hardware and software FL solution, developing a COVID-19 screening test across four UK hospital groups using inexpensive micro- computing hardware. Federation improved model performance and generalisability, and shows promise as an enabling technology for deep learning in healthcare. Funding University of Oxford Medical & Life Sciences Translational Fund/Wellcome

Multiclass Classification of Autism Spectrum Disorder, Attention Deficit Hyperactivity Disorder, and Typically Developed Individuals Using fMRI Functional Connectivity Analysis

“…Further, we propose integrating our methodology with federated learning techniques as a promising avenue for advancing diagnostics and drug trials in neurodevelopmental conditions [161,162,163]. Federated learning offers a solution to data privacy and scalability challenges, allowing for collaborative model training across multiple datasets while preserving data decentralization [164,165,166]. This approach holds immense potential for improving diagnostic accuracy and guiding personalized treatment strategies tailored to specific demographics or clinical settings [167].…”

Unleashing the Power of Federated Learning in Fragmented Digital Healthcare Systems: A Visionary Perspective

“…FL exhibited remarkable utility during the COVID-19 pandemic. Soltan et al introduced an FL approach to COVID-19 screening across multiple UK hospitals [10]. Using clinical data, a global model was developed and improved using federated training.…”

The Holy Grail of obstetric ultrasound: can artificial intelligence detect hard‐to‐identify fetal cardiac anomalies?

“…Another approach for large-scale AI training is federated learning. In this method, training occurs locally in each site without sharing patient data 37 . Ultimately, these initiatives should allow the creation of large-scale datasets for rigorous AI assessments across diverse populations and settings 36 .…”