PhysOnline: An Open Source Machine Learning Pipeline for Real-Time Analysis of Streaming Physiological Waveform

Real-time analysis of streaming physiological data to identify earlier abnormal conditions is an important aspect of precision medicine. However, open-source systems supporting this workflow are lacking. In this paper, we present PhysOnline, a pipeline built on the open-source Apache Spark platform...

Full description

Saved in:
Bibliographic Details
Published inIEEE journal of biomedical and health informatics Vol. 23; no. 1; pp. 59 - 65
Main Authors Sutton, Jacob R., Mahajan, Ruhi, Akbilgic, Oguz, Kamaleswaran, Rishikesan
Format Journal Article
LanguageEnglish
Published United States IEEE 01.01.2019
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Artificial intelligence
Case studies
Classification
Domains
ECG
EKG
Electrocardiography
Feature extraction
Feature recognition
Fibrillation
Identification methods
Internet
Learning algorithms
Machine learning
online analysis
Open source software
Pattern matching
Pattern recognition
Physical characteristics
Physiology
Pipelines
point of care
Precision medicine
Real time
Real-time feature extraction
Real-time systems
scalable analysis
sensors
Sparks
Streaming
Workflow
Online AccessGet full text

Cover

More Information
Summary:Real-time analysis of streaming physiological data to identify earlier abnormal conditions is an important aspect of precision medicine. However, open-source systems supporting this workflow are lacking. In this paper, we present PhysOnline, a pipeline built on the open-source Apache Spark platform to ingest streaming physiological data for online feature extraction and machine learning. We consider scalability factors for horizontal deployment to support growing analysis requirements. We further integrate real-time feature extraction, including pattern recognition methods as well as descriptive statistical components to identify temporal characteristics of waveform signals. These generated features are then used for machine learning and for real-time classification of abnormal conditions. As a case study, we present the online classification of electrocardiography recordings for screening Paroxysmal Atrial Fibrillation (PAF) and demonstrate that our pipeline can predict persons developing PAF at least 45 min. before an episode of that condition. This pipeline can be applied in domains where pattern matching, temporal abstractions, and morphological characteristics can be used for real-time classification of streaming time-series data. 1
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2168-2194
2168-2208
DOI:10.1109/JBHI.2018.2832610