A Supervised Approach to Robust Photoplethysmography Quality Assessment
| Autor: | Kais Gadhoumi, Tania Pereira, Karl Meisel, Rene A. Colorado, Xiuyun Liu, Xiao Hu, Kevin J Keenan, Mitchell Ma, Ran Xiao |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Support Vector Machine
Computer science Signal Quality Wearable computer Rhythm 02 engineering and technology 030204 cardiovascular system & hematology Cardiovascular Medical and Health Sciences Pulse Oximetry Electrocardiography Computer-Assisted Engineering 0302 clinical medicine Health Information Management Atrial Fibrillation 80 and over Oximetry Wearable technology Aged 80 and over Signal processing medicine.diagnostic_test Signal Processing Computer-Assisted Middle Aged Computer Science Applications Stroke Heart Disease Annotated Data Supervised Machine Learning Algorithms Biotechnology Adult Monitoring 0206 medical engineering Bioengineering Article Wearable Electronic Devices Young Adult 03 medical and health sciences Clinical Research Information and Computing Sciences Photoplethysmogram Intensive care medicine Humans Electrical and Electronic Engineering Photoplethysmography Aged business.industry Pattern recognition 020601 biomedical engineering Brain Disorders Support vector machine Pulse oximetry Test set Signal Processing Artificial intelligence business Biomedical monitoring Medical Informatics Quality assessment |
| Zdroj: | IEEE J Biomed Health Inform IEEE journal of biomedical and health informatics, vol 24, iss 3 |
| ISSN: | 2168-2208 2168-2194 |
| DOI: | 10.1109/jbhi.2019.2909065 |
| Popis: | Early detection of Atrial Fibrillation (AFib) is crucial to prevent stroke recurrence. New tools for monitoring cardiac rhythm are important for risk stratification and stroke prevention. As many of new approaches to long-term AFib detection are now based on photoplethysmogram (PPG) recordings from wearable devices, ensuring high PPG signal-to-noise ratios is a fundamental requirement for a robust detection of AFib episodes. Traditionally, signal quality assessment is often based on the evaluation of similarity between pulses to derive signal quality indices. There are limitations to using this approach for accurate assessment of PPG quality in the presence of arrhythmia, as in the case of AFib, mainly due to substantial changes in pulse morphology. In this paper, we first tested the performance of algorithms selected from a body of studies on PPG quality assessment using a dataset of PPG recordings from patients with AFib. We then propose machine learning approaches for PPG quality assessment in 30-s segments of PPG recording from 13 stroke patients admitted to the University of California San Francisco (UCSF) neuro intensive care unit and another dataset of 3764 patients from one of the five UCSF general intensive care units. We used data acquired from two systems, fingertip PPG (fPPG) from a bedside monitor system, and radial PPG (rPPG) measured using a wearable commercial wristband. We compared various supervised machine learning techniques including k-nearest neighbors, decisions trees, and a two-class support vector machine (SVM). SVM provided the best performance. fPPG signals were used to build the model and achieved 0.9477 accuracy when tested on the data from the fPPG exclusive to the test set, and 0.9589 accuracy when tested on the rPPG data. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|