Towards Health Data Stream Analytics

Data streams, or data sets which continuously and rapidly grow over time, are a prominent form of clinical data generated during the monitoring and treatment of patients in the health care industry. We propose the name Health Data Stream Analytics (HDSA) to the application of stream data processing to clinical data. Our work in this area is demonstrating the useful role Health Data Stream Analytics can play in clinical decision support, patient safety improvement and early detection of adverse patient outcomes. Two major challenges in applying stream data processing to heath care are tailoring query support for the clinical context and dealing with the clinical requirement of online query processing. In this paper, we propose the Anaesthetic Data Analyser (ADA) as a Health Data Stream Analytics System for the anaesthetics specialty and describe how it addresses these challenges. ADA differentiates from current approaches by looking at trends in the data stream rather than a single data value against a preset threshold. The trend analysis supported by ADA is a novel application in this area, and enables support for adverse symptoms monitoring in physiological stream data, alerting clinicians when a pre-defined adverse data pattern is detected in the physiological signals. This paper also describes an online query processing algorithm and the results of experiments on “real world” physiological steam data which indicate the algorithms has sub-second response times for trend queries.

[1]  David J. DeWitt,et al.  The Niagara Internet Query System , 2001, IEEE Data Eng. Bull..

[2]  Chaoyi Pang,et al.  Unrestricted wavelet synopses under maximum error bound , 2009, EDBT '09.

[3]  Charu C. Aggarwal,et al.  Data Streams - Models and Algorithms , 2014, Advances in Database Systems.

[4]  Jennifer Widom,et al.  The CQL continuous query language: semantic foundations and query execution , 2006, The VLDB Journal.

[5]  Eamonn J. Keogh,et al.  A symbolic representation of time series, with implications for streaming algorithms , 2003, DMKD '03.

[6]  David J. DeWitt,et al.  NiagaraCQ: a scalable continuous query system for Internet databases , 2000, SIGMOD 2000.

[7]  Michael Stonebraker,et al.  Aurora: a new model and architecture for data stream management , 2003, The VLDB Journal.

[8]  Jeffrey F. Naughton,et al.  Estimating the Selectivity of XML Path Expressions for Internet Scale Applications , 2001, VLDB.

[9]  Douglas B. Terry,et al.  Continuous queries over append-only databases , 1992, SIGMOD '92.

[10]  Frederick Reiss,et al.  TelegraphCQ: An Architectural Status Report , 2003, IEEE Data Eng. Bull..

[11]  Michael Stonebraker,et al.  Load Shedding in a Data Stream Manager , 2003, VLDB.

[12]  Joseph M. Hellerstein,et al.  Eddies: continuously adaptive query processing , 2000, SIGMOD 2000.

[13]  Philippe Bonnet,et al.  Towards Sensor Database Systems , 2001, Mobile Data Management.

[14]  Frederick Reiss,et al.  TelegraphCQ: continuous dataflow processing , 2003, SIGMOD '03.

[15]  Frederick Reiss,et al.  TelegraphCQ: Continuous Dataflow Processing for an Uncertain World , 2003, CIDR.

[16]  Michael Stonebraker,et al.  Aurora: a data stream management system , 2003, SIGMOD '03.

[17]  Ira J. Haimowitz,et al.  Clinical monitoring using regression-based trend templates , 1995, Artif. Intell. Medicine.

[18]  Joseph M. Hellerstein,et al.  Flux: an adaptive partitioning operator for continuous query systems , 2003, Proceedings 19th International Conference on Data Engineering (Cat. No.03CH37405).

[19]  David J. DeWitt,et al.  On supporting containment queries in relational database management systems , 2001, SIGMOD '01.

[20]  Jeffrey F. Naughton,et al.  Rate-based query optimization for streaming information sources , 2002, SIGMOD '02.

[21]  Chaoyi Pang,et al.  On Multidimensional Wavelet Synopses for Maximum Error Bounds , 2009, DASFAA.

[22]  Jennifer Widom,et al.  Models and issues in data stream systems , 2002, PODS.

[23]  I S Kohane,et al.  Hypothesis-driven data abstraction with trend templates. , 1993, Proceedings. Symposium on Computer Applications in Medical Care.

[24]  Jennifer Widom,et al.  Query Processing, Resource Management, and Approximation ina Data Stream Management System , 2002 .

[25]  Rajeev Motwani,et al.  Chain: operator scheduling for memory minimization in data stream systems , 2003, SIGMOD '03.

[26]  Jennifer Widom,et al.  Continuous queries over data streams , 2001, SGMD.

[27]  Lukasz Golab,et al.  Data Stream Management Issues { A Survey , 2003 .

[28]  Samuel Madden,et al.  Fjording the stream: an architecture for queries over streaming sensor data , 2002, Proceedings 18th International Conference on Data Engineering.