A practical approach to storage and retrieval of high-frequency physiological signals

Abstract

Objective: Storage of physiological waveform data for retrospective analysis presents significant challenges. Resultant data can be very large, and therefore becomes expensive to store and complicated to manage. Traditional database approaches are not appropriate for large scale storage of physiological waveforms. Our goal was to apply modern time series compression and indexing techniques to the problem of physiological waveform storage and retrieval. Approach: We deployed a vendor-agnostic data collection system and developed domain-specific compression approaches that allowed long term storage of physiological waveform data and other associated clinical and medical device data. The database (called AtriumDB) also facilitates rapid retrieval of retrospective data for high-performance computing and machine learning applications. Main results: A prototype system has been recording data in a 42-bed pediatric critical care unit at The Hospital for Sick Children in Toronto, Ontario since February 2016. As of December 2019, the database contains over 720,000 patient-hours of data collected from over 5300 patients, all with complete waveform capture. One year of full resolution physiological waveform storage from this 42-bed unit can be losslessly compressed and stored in less than 300 GB of disk space. Retrospective data can be delivered to analytical applications at a rate of up to 50 million time-value pairs per second. Significance: Stored data are not pre-processed or filtered. Having access to a large retrospective dataset with realistic artefacts lends itself to the process of anomaly discovery and understanding. Retrospective data can be replayed to simulate a realistic streaming data environment where analytical tools can be rapidly tested at scale.

Hemodynamic Patterns Before Inhospital Cardiac Arrest in Critically Ill Children: An Exploratory Study

“…Patient and IHCA event characteristics were obtained from an established IHCA database documenting all ICU-based IHCA events, maintained as part of a continuous quality improvement review and kept in accordance with Utstein guidelines ( 11 ). Event waveforms were extracted from a physiologic waveform database known as “AtriumDB.” Waveform capture for analysis occurs pervasively for all patients at all times in the Critical Care Units at the Hospital for Sick Children, and data are stored for secondary use ( 12 ). Waveform signals associated with a patient are archived in a compressed and time-aligned format for subsequent analysis, as described by Goodwin et al ( 12 ).…”

“…Event waveforms were extracted from a physiologic waveform database known as “AtriumDB.” Waveform capture for analysis occurs pervasively for all patients at all times in the Critical Care Units at the Hospital for Sick Children, and data are stored for secondary use ( 12 ). Waveform signals associated with a patient are archived in a compressed and time-aligned format for subsequent analysis, as described by Goodwin et al ( 12 ). The IHCA documentation database is manually synchronized to AtriumDB by the institution’s Cardiac Arrest Review Committee.…”

Sharing and learning through the Pediatric Cardiac Critical Care Consortium: Moving toward precision care

“…It is noteworthy that predictive data analytics are used in less than 20% of pediatric cardiac ICUs. 24 In this era of ubiquitous electronic healthcare records and emerging methods for capturing high-frequency physiologic data, 25 this is a deficiency. Time-series continuous physiologic data generated from patients in the operating room, ICU, and ward settings must be captured and stored permanently; analysis will allow better understanding of physiologic states and risks for an event within that state.…”

Graph Representation Integrating Signals for Emotion Recognition and Analysis

“…Several studies have focused on the storage and integration of biosignals, although these are not related to emotion recognition [23][24][25][26]. For example, approach proposed by Kokkinaki et al [27] is built on the definition of a global ontology that manipulates the source similarities and differences and thus creates mappings or enhances its structure.…”