Understanding ECG signals in the MIMIC II database
0 likes530 views
This document discusses understanding ECG signals in a database and building a computer model to analyze them. It notes that ECGs can reveal many heart problems and challenges include missing data, incomplete records, and abnormal data. It proposes extracting features from records and using techniques like PCA. A referenced study describes a dynamical model for generating synthetic ECG signals that models the placement and shape of peaks, breathing, and heartbeat variations. The goal is to understand normal behavior before detecting abnormalities.
Understanding ECG signals in the MIMIC II database
- 1. Understanding ECG signals in the MIMIC II database Jiahao Chen and Jake Bolewski, MIT jiahao.github.io
- 2. From: Chapter 3, Conquering the ECG, Cardiology Explained. Ashley EA, Niebauer J. London: Remedica; 2004. ECG signals are very structured
- 3. From: Chapter 3, Conquering the ECG, Cardiology Explained. Ashley EA, Niebauer J. London: Remedica; 2004. ECG signals are very structured
- 4. From: Chapter 3, Conquering the ECG, Cardiology Explained. Ashley EA, Niebauer J. London: Remedica; 2004. ECGs can reveal many heart problems normal first-degree heart block atrial fibrillation atrial flutter left bundle bunch block etc… How can we build a computer model for all of these?
- 5. Characterization strategy database waveform record features statistics convert file formats find valid records PCA, etc.
- 6. Challenges - Missing data - Not all 12 leads present - some symptoms cannot be diagnosed - Incomplete waveforms - ignore for now - Weird data - data acquisition problem? coding error? our own ignorance?
- 7. Characterization strategy database waveform record features statistics ???
- 8. What features are we after? Some criteria for pathology are known precisely. More generally, we want to find abnormalities. But we need to understand normal behavior first. Others are more vague.
- 9. A model for normal behavior Patrick E. McSharry, Gari D. Clifford, Lionel Tarassenko, and Leonard A. Smith, "A Dynamical Model for Generating Synthetic Electrocardiogram Signals", IEEE Transactions in Biomedical Engineering, 50(3), 2003, 289--294.* doi:10.1109/TBME.2003.808805
- 10. A model for normal behavior Patrick E. McSharry, Gari D. Clifford, Lionel Tarassenko, and Leonard A. Smith, "A Dynamical Model for Generating Synthetic Electrocardiogram Signals", IEEE Transactions in Biomedical Engineering, 50(3), 2003, 289--294.* doi:10.1109/TBME.2003.808805 place and shape of P, Q, R, S, T peaks breathing three different sets of physiological features heartbeat variations described by another model…
- 11. http://nbviewer.ipython.org/urls/raw.github.com/jiahao/ijulia-notebooks-assorted/ master/ECG%20model.ipynb References: - Patrick E. McSharry, Gari D. Clifford, Lionel Tarassenko, and Leonard A. Smith, "A Dynamical Model for Generating Synthetic Electrocardiogram Signals", IEEE Transactions in Biomedical Engineering, 50(3), 2003, 289--294. doi:10.1109/TBME.2003.808805 Barbara J Aehlert, "ECGs Made Easy", 5/e, 2012, Mosby/JEMS. "Chapter 3: Conquering the ECG". In Ashley EA, Niebauer J, "Cardiology Explained", London: Remedica; 2004. http://www.ncbi.nlm.nih.gov/books/ NBK2214/ physionet.org IPython notebook