iCordisX: SmartPhone-Based Personalized Cardiac Monitoring Using Computer Vision and Bluetooth Low Energy
CSEF · 2018 Computational Systems & Analysis
Overview
Objectives/Goals iCordisX aims to provide a personalized and data-driven supplement for cardiac anomalies that acts as a dependable healthcare interface for wireless ECG monitors. Targeted Features: User-based system, daily symptom tracker, BLE functionality, diagnosis/monitoring mode. Methods/Materials Drew out and implemented project system: sensors + hardware. Developed algorithm for "diagnosis" of ECG. - Machine learning for extraction of baseline features from MIT-BIH Database, and object detection. Designed app interface: screens, user input, data flow and models. Tested fully-functional app system, review data output, compare accuracy to MATLAB algorithm, receive feedback from cardiologists/entrepreneurs. Create hardware casing (acryllic) and 3D shell. ECG Circuit - 1 x Arduino Pro Mini and Cable - 1 x AD8232 board 3 x TENS electrodes Computer + Software: Arduino IDE, Processing 3 Software, Anaconda-Navigator (Jupiter-Notebook), MATLAB R2016B, node.js, Visual Studio Code, XCode, AWS EC2 Instance Results Smoothing/peak detection method in MATLAB resulted in detrended signal, color-coded blue and red to distinguish the original signal.The Python algorithm was able to successfully filter, calculate specific intervals, and calculate heart rate, as seen by its percent error of only 8.08% for averaged features when compared to the MATLAB analysis. Average Signal Quality should be at least approximately .94. iCordisX has a calculated net price of $131 dollars (excluding the mobile device), an impressive feat for all it's capabilities. Conclusions/Discussion CordisX provides a unique value proposition: a personalized, simplistic monitoring system that is appealing to the aging society. The feature extraction algorithm is comparable to the accuracy of a standalone MATLAB program, which also verifies the device's accuracy of data output. The app is flexibility with data management and real-time data streaming, whether it be via monitoring or diagnosis. Users will receive a data-driven supplement for their daily heart health, all while logging it in the database for their personal physicians to see. Survival rates from heart attack may be increased from early detection in irregular heart rhythm, where the emergency protocol may be activated. All of iCordisX's features are driven by the user's information, and allows the user to view trends over a large period of time.
Summary statement
iCordisX aims to provide a personalized and data-driven supplement for cardiac anomalies that acts as a dependable healthcare interface for wireless ECG monitors.
Help received
Received resources at beginning of project from Nitish Nag (PhD Student @UCI) to begin algorithm engineering.
Competition history
- CSEF 2018
Resources
Related projects
ISEF · 2018
iCordisX: SmartPhone-Based Personalized Cardiac Monitoring Using Computer Vision and Bluetooth Low Energy
CSEF · 2017
CordisX: Personalized Cardiac Monitor
AJAS · 2018
CordisX: Personalized Cardiac Monitoring Through Low-Cost Sensor Systems and Real-Time Statistical Analysis Algorithms
AJAS · 2019
iCordisX: Smartphone-Based Personalized Cardiac Monitoring
CSEF · 2016
Project POE: Tri-Sensor Cardiac Monitoring System
CSEF · 2017
CardioWatch
ISEF · 2019
Engineering a Novel Wearable Biosensing Mechanism through the Implementation of Microelectromechanical Systems and Machine Learning to Realize Anomalies Hinting towards Future Cardiac Episodes
CSEF · 2017
Combatting Cardiac Arrest through a Compact and Portable Heart Rate Monitor and Analyzer
Closest projects by meaning, across every fair and year in the corpus.
Browse more like this
Source: California Science & Engineering Fair public projects