Spatio-Temporal Split Learning for Privacy-Preserving Medical Platforms: Case Studies with COVID-19 CT, X-Ray, and Cholesterol Data

Machine learning requires a large volume of sample data, especially when it is used in high-accuracy medical applications. However, patient records are one of the most sensitive private information that is not usually shared among institutes. This paper presents spatio-temporal split learning, a distributed deep neural network framework, which is a turning point in allowing collaboration among privacy-sensitive organizations. Our spatio-temporal split learning presents how distributed machine learning can be efficiently conducted with minimal privacy concerns. The proposed split learning consists of a number of clients and a centralized server. Each client has only has one hidden layer, which acts as the privacy-preserving layer, and the centralized server comprises the other hidden layers and the output layer. Since the centralized server does not need to access the training data and trains the deep neural network with parameters received from the privacy-preserving layer, privacy of original data is guaranteed. We have coined the term, spatio-temporal split learning, as multiple clients are spatially distributed to cover diverse datasets from different participants, and we can temporally split the learning process, detaching the privacy preserving layer from the rest of the learning process to minimize privacy breaches. This paper shows how we can analyze the medical data whilst ensuring privacy using our proposed multi-site spatio-temporal split learning algorithm on Coronavirus Disease-19 (COVID-19) chest Computed Tomography (CT) scans, MUsculoskeletal RAdiographs (MURA) X-ray images, and cholesterol levels. Author

Reliability Assessment of Telemedicine Data by Analyzing Photoplethysmography with Deep Neural Network Technology

Photoplethysmography (PPG) is often used in telemedicine because it enables convenient measurement and provides data related to cardiopulmonary function. However PPG is difficult analyze using an automated algorithm because of its vulnerability to motion artefacts and the diversity of the waveforms according to the characteristics of individuals and diseases. Recently, as the use of telemedicine has become more frequent due to the outbreak of COVID19, the application of deep neural network (DNN) technology in the analysis of PPG and selection of reliable data has increased. In this study, PPG was analyzed using DNN techniques to reproduce the long-term potential (LTP) phenomenon in the brain. Moreover, the reliability of measuring saturation pulse oxymetry (SPO2) simultaneously was evaluated using the LTP-DNN. The LTP-DNN was able to evaluate faultless data by inspecting 58 PPG datasets, including 29 fault data, and could determine the possibility of failure in SPO2 measurement as well. Even in a moving situation, the LTP-DNN provides more accurate heartrate (HR) measurements than commercial SPO2 devices do. It can also be used to normalize the PPG waveform to identify waveform differences between individuals.