Feasibility of Remote Mapping and Clinical Support Using Novel Software

Background: Covid redefined how the world functions. The electrophysiology (EP) community identified multiple needs that arose due to this paradigm and redefined workflows. The geographic paucity of experienced clinical mapping support was a crucial issue that limited the worldwide adoption of complex ablation procedures. Objective(s): To ascertain the feasibility and safety of utilizing a novel software for remote mapping and remote clinical support for all spectrums of cardiac ablation procedures and to compare the adoption of ablation technology in that geography. Method(s): Ablation procedures performed at Metromed International Cardiac Centre (MICC), India were included in this early feasibility analysis (EFA). All procedures were performed by a single EP operator. Remote Clinical support was provided by an EP physician (primary operator's sibling) in the USA. All mapping was performed by an experienced mapper from a remote location 400 miles away from the primary EP operator in India. The mapping system utilized was Ensite Precision with SJM Connect software. Result(s): 300 contiguous ablation procedures from 2020 to 2022 were included in this EFA. The proprietory SJM Connect software allows remote access to the Ensite console via a secured connection. The software requires the operator to be granted access to the Ensite console via a permission request that must be acknowledged on the Ensite Console. The software will then allow the remote operator to levels of access to the system, view-only access, or complete control of the console to provide full remote support. Communication occurs between the remote user and the console via a chat function and over a voice call. This remote connection can be terminated at any time from either the console or the remote operator. There is no PHI displayed. Results detailing case demographics and acute procedural success and safety will be presented. Results comparing the adoption of ablation technology with the previous 3 years in this geography will be presented. Conclusion(s): This EFA demonstrates the safety and efficacy of using remote clinical support and remote mapping for ablation procedures. This opens a world of possibilities including the expansion of ablation technology to all corridors of the world with experienced clinical and mapping support connecting the EP community on a worldwide platform. Additional studies and strategies are needed to further understand the implication of remote support algorithms in bridging the healthcare gaps in the field of cardiac EP. [Formula presented]Copyright © 2023

Exploring SVM for Federated Machine Learning Applications

The traditional machine learning algorithms focus on centralised data repository where the aggregate data used for training is stored in a common location and processed. This approach is not suitable when data is stored in different locations and owned by different entities. Many crucial machine learning applications need computationally efficient and privacy-preserving solution. Also the central data repository has the risk of single point of failure. Federated learning is an emerging field in machine learning where the centralised concept is changed to distributed. Federated learning approach helps to train a model in machine learning without really sharing the data to a common server. In this approach, training is done locally at client side. A technique called federated averaging is applied at server side, where the model parameters from clients are aggregated and the updated parameters are computed. We propose a federated SVM architecture for solving a binary supervised classification problem. Here the experiments are done for MNIST dataset and COVID-19 dataset. Also the results are compared with centralised training approach. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Intelligent System for Social Distance Monitoring with Human Detection and Tracking using YOLOv3

Everyday life and the global economy have been negatively impacted by COVID-19 (Coronavirus). Slowing the spread of coronaviruses through social distance is proven to be an effective strategy in the war against COVID-19. The social distancing is the best way to stop the spread of COVID-19, as it prevents people from coming into intimate touch with each other. Recently, due to the fast spreading outbreak of the COVID-19, one of the obligatory preventive measures to avoid physical contact has become social distance. Surveillance methods that use Deep Learning, Open-CV and Computer vision to follow pedestrians and prevent congestion are the focus of this article. Closed-circuit television (CCTV) and drones can be used for implementation, where the camera will use object detection to identify the crowd and compute the distance between the humans. Local law enforcement will be notified if the Euclidean distance between two persons is less than the standard distance, which is determined by converting it to pixels and comparing it to that value.