Edge computing for smart disease prediction treatment therapy

Title

Edge computing for smart disease prediction treatment therapy

Creator

Nanjundan P.; Jaisingh W.; George J.P.

Description

Healthcare systems are increasingly seeking to match patients' pace of life and be personalized, as they are demanding more advanced products and services. The only solution for collecting and analyzing health data in realtime is an edge computing (EC) environment, coupled with 5G speeds and modern computing techniques. The technology in healthcare is currently being used to develop smart systems that can expedite the diagnosis of disease and provide precise and timely treatment. The automated hospital monitoring system and medical diagnosis system enable doctors to monitor and diagnose patients from a variety of locations, including hospitals, workplaces, and homes and provide transportation options. As a result, overall doctor visits are reduced as well as patient care is improved. More than 162 billion healthcare IoT devices are expected to be used worldwide by 2021 thanks to the internet of things (IoT) sensors and applications for general healthcare. With edge intelligence (EI), wearable devices with sensors, like smartwatches or smartphones, and gateway devices, such as microcontrollers, can form edge nodes: smart devices with sensors, as well as gateway devices with sensors, can act as edge nodes. Smart sensor devices are typically installed at a greater distance from personal computers (PCs) and servers, which can be utilized in fog computing (FC). In healthcare, EC and FC are used to deliver reliable, low-latency, and location-aware healthcare services by utilizing sensors located within users' reach. Recently, many researchers have proposed using hierarchical computing for the distribution and allocation of inference-based tasks among edge devices and fog nodes, which could lead to an increase in computing power and compute capability of edge devices. For disease prediction, this chapter discusses a variety of EC techniques. 2024 Apple Academic Press, Inc. All rights reserved.

Source

Reconnoitering the Landscape of Edge Intelligence in Healthcare, pp. 89-114.

Date

2024-01-01

Publisher

Apple Academic Press

Subject

Aautomated medical diagnosis systems; Cardio-vascular diseases; Deep learning; Edge computing; Healthcare system; Machine learning; Sensors; Smart devices; Surveillance frameworks

Coverage

Nanjundan P., Department of Data Science, Christ University, Lavasa, Pune, Maharashtra, India; Jaisingh W., School of Computing Science and Engineering, VIT Bhopal University, Bhopal, Madhya Pradesh, India; George J.P., Department of Data Science, Christ University, Lavasa, Pune, Maharashtra, India

Rights

Restricted Access

Relation

ISBN: 978-100089493-6; 978-177491436-6

Format

Online

Language

English

Type

Book chapter

Identifier

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85185094359&partnerID=40&md5=21c020c5c7134f5c43794d07b3ef1726