Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
March 4, 2026Future InternetOpen Access

Edge-centric IoT system achieves ~92% ECG classification accuracy and reduces patient evaluation time.

View Full Paper
Ask AI
Bookmark
Share

Why the study?

Continuous monitoring of cardiac patients in general hospital wards remains challenging due to manual charting systems and slow clinical responses to physiological deterioration.

Does an edge- and fog-based IoT healthcare system improve ECG classification precision and reduce alert latency in cardiac patients in hospital wards?

Population

PhysioNet datasets and patients in real wards

Comparison

Edge- and fog-based IoT monitoring system vs conventional threshold and manual charting systems

Design

System development and validation study

Key result

Edge-centric IoT system achieved 91.96% ECG classification accuracy and reduced patient evaluation time to 15.23 ± 2.71 seconds in real hospital wards.

Authors

TBTehseen BaigNCNauman Riaz ChaudhryRCReema Choudhary

Discussion

Loading...

Member takes

Overview

Supports rapid response in hospitalized cardiac patients; extends evidence for edge-centric IoT in clinical cardiology.

Key Points

  • The aim is to develop an IoT system that monitors cardiac patients in real-time to enhance clinical response times.
  • Developed an edge- and fog-based IoT system for cardiac monitoring.
  • Utilized wearable ECG sensors to collect vital signs wirelessly.
  • Implemented machine learning algorithms for ECG classification and triage.
  • Analyzed data in real-time with mobile app integration for clinician alerts.
  • Achieved ECG classification precision of 91.96 percent.
  • Reduced routine patient evaluation time to an average of 15.23 ± 2.71 seconds.
  • Demonstrated effectiveness in latency-sensitive hospital environments.

Structured PICO

Does an edge- and fog-based IoT healthcare system improve ECG classification precision and reduce alert latency in cardiac patients in hospital wards?

P
Population
Cardiac patients in general hospital wards and PhysioNet datasets
I
Intervention
Edge- and fog-based IoT healthcare system with wearable 12-lead ECG sensors and machine learning classification
C
Comparator
Manual charting system and conventional threshold systems
O
Outcome
ECG classification precision and alert latency

An edge-centric IoT system with machine learning can achieve high ECG classification precision and significantly reduce alert latency in hospital settings.

Cite This Study

Baig et al. (2026) studied this question. Edge-centric IoT system achieved 91.96% ECG classification accuracy and reduced patient evaluation time to 15.23 ± 2.71 seconds in real hospital wards.

synapsesocial.com/papers/69a7cd1dd48f933b5eed9244https://doi.org/10.3390/fi18030130
View Full Paper
Ask AI
Bookmark
Share