Human ecg indicators for fast screening and evaluation.

mgr inż. Marcin Maciejewski
dr inż. Wojciech Surtel

Lublin University of Technology, Institute of Electronics and Information Technology

Telemedical system design and implementation requires numerous steps. The research is a part of a longer study in the field of patient diagnosis using mobile devices. It is necessary to evaluate the operation of algorithms responsible for analysis and detection of life-threatening situations. By performing ECG analysis it is possible to obtain information about the overall patient health condition as well as detailed information about the circulatory system condition. To achieve that goal one must gather, filter and process data. Appropriate models must be constructed using extracted information. ECG carries a wide array of information both in time and frequency domain. To achieve functionality and accuracy a reduction in system inputs must be performed.

Available dataset was processed to obtain information about the patients condition. Pan-Tompkins algorithm was used to detect R peaks. Afterwards the rest of parameters was extracted in time and frequency domain. Correlation between parameters was performed for stationary and physically active patients and results were compared. The chosen vector of independent parameters will later be used for building classifiers necessary for obtaining valid and precise diagnosis.

Author: Marcin Maciejewski
Conference: Title