Coronary artery disease detection using photoplethysmography.

This paper presents a technique for coronary artery disease (CAD) detection through photoplethysmography (PPG). This work is aimed at developing a non-invasive, inexpensive screening technique suitable for home monitoring. Time domain analysis of PPG signal and its second derivative has been carried out to extract distinguishing features. Support Vector Machine based classifier has been used to classify CAD patients. ICU patient data from MIMIC-II dataset has been used for performance evaluation. Sensitivity of 85% and specificity of 78% has been achieved for the analysed data.

Cardiac arrhythmia detection using photoplethysmography.

Cardiovascular Diseases (CVDs) cause a very large number of casualties around the world every year and cardiac arrhythmias contribute to significant proportion of CVD related deaths. Bedside cardiac activity monitors in hospitals are based on electrocardiogram (ECG) processing and are known to produce too many false alarms. Moving beyond bedside care, ECG is not very suitable for use in wearable devices. Photoplethysmography (PPG) on the other hand provides an inexpensive and more wearable device-friendly alternative. This work presents a technique to detect life threatening arrhythmias using only PPG waveforms. PhysioNet Challenge 2015 data is used to detect five types of arrhythmias namely, tachycardia, bradycardia, asystole, ventricular tachycardia and ventricular fibrillation. A novel technique is employed to assign pulse quality index to every PPG pulse and highest quality portion of the signal is used for detection. Results indicate that PPG provides a viable alternative for conventional ECG based detection. An overall true positive rate (TPR) of 93% was achieved with true negative rate (TNR) of 53.78% suggesting that PPG is a viable option for arrhythmia detection.

Primary study for detection of arterial blood pressure waveform components.

The paper presents a technique to detect significant systolic peaks, the percussion (P) and tidal peak (T) and diastolic peak (D) from the arterial blood pressure (ABP) waveform. The technique is aimed at robust detection even in presence of significant noise. Singular Value Decomposition (SVD) based dominant period extraction of the ABP waveform followed by wavelet transform and local peak detection is applied to detect the points of interest. MIMIC-II ABP databse serves as a training dataset to select SVD and wavelet transform parameters and CSL Benchmark database is used to analyze the technique. Salient systolic peak detection for the CSL dataset was performed with positive predictive value and sensitivity figures of 98.48% and 99.24% respectively.

Fuzzy entropy based motion artifact detection and pulse rate estimation for fingertip photoplethysmography.

The paper presents a fingertip photoplethysmography (PPG) based technique to estimate the pulse rate of the subject. The PPG signal obtained from a pulse oximeter is used for the analysis. The input samples are corrupted with motion artifacts due to minor motion of the subjects. Entropy measure of the input samples is used to detect the motion artifacts and estimate the pulse rate. A three step methodology is adapted to identify and classify signal peaks as true systolic peaks or artifact. CapnoBase database and CSL Benchmark database are used to analyze the technique and pulse rate estimation was performed with positive predictive value and sensitivity figures of 99.84% and 99.32% respectively for CapnoBase and 98.83% and 98.84% for CSL database respectively.