<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2 Final//EN">
<!--Converted with LaTeX2HTML 2K.1beta (1.47)
original version by: Nikos Drakos, CBLU, University of Leeds
* revised and updated by: Marcus Hennecke, Ross Moore, Herb Swan
* with significant contributions from:
Jens Lippmann, Marek Rouchal, Martin Wilck and others -->
<HTML>
<HEAD>
<TITLE>lt03</TITLE>
<META NAME="description" CONTENT="lt03">
<META NAME="keywords" CONTENT="lt03">
<META NAME="resource-type" CONTENT="document">
<META NAME="distribution" CONTENT="global">
<META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=iso-8859-1">
<META NAME="Generator" CONTENT="LaTeX2HTML v2K.1beta">
<META HTTP-EQUIV="Content-Style-Type" CONTENT="text/css">
<LINK REL="STYLESHEET" HREF="lt03.css">
<LINK REL="next" HREF="node1.html">
</HEAD>
<body bgcolor=white>
<!--#include virtual="/links-physiobank.html"-->
<A NAME="tex2html17"
HREF="node1.html">
<IMG WIDTH="37" HEIGHT="24" ALIGN="BOTTOM" BORDER="0" ALT="next" SRC="next.png"></A>
<a href="../">
<IMG WIDTH="26" HEIGHT="24" ALIGN="BOTTOM" BORDER="0" ALT="up" SRC="up.png"></a>
<IMG WIDTH="63" HEIGHT="24" ALIGN="BOTTOM" BORDER="0" ALT="previous" SRC="prev_gr.png"> <BR>
<B> Next:</B> <A NAME="tex2html18"
HREF="node1.html">Bibliography</A>
<B> Up:</B> <a href="../">Long-Term ST Database</a>
<BR> <P>
<!--End of Navigation Panel-->
<P>
<DIV ALIGN="CENTER">
<FONT SIZE="+2"><B>Long-term ST database: a reference for the development and evaluation
of automated ischaemia detectors and for the study of the dynamics of myocardial
ischaemia</B></FONT>
</DIV>
<P>
<DIV ALIGN="CENTER">
<FONT SIZE="+1"><B>F. Jager<IMG
WIDTH="32" HEIGHT="25" ALIGN="BOTTOM" BORDER="0"
SRC="img1.png"
ALT="$^{\:1,2}$"> A. Taddei<IMG
WIDTH="18" HEIGHT="25" ALIGN="BOTTOM" BORDER="0"
SRC="img2.png"
ALT="$^{\:3}$"> G. B. Moody<IMG
WIDTH="32" HEIGHT="25" ALIGN="BOTTOM" BORDER="0"
SRC="img3.png"
ALT="$^{\:2,4}$">
M. Emdin<IMG
WIDTH="18" HEIGHT="25" ALIGN="BOTTOM" BORDER="0"
SRC="img2.png"
ALT="$^{\:3}$"> G. Antolic<IMG
WIDTH="18" HEIGHT="25" ALIGN="BOTTOM" BORDER="0"
SRC="img4.png"
ALT="$^{\:5}$">
<BR>
R. Dorn<IMG
WIDTH="18" HEIGHT="25" ALIGN="BOTTOM" BORDER="0"
SRC="img5.png"
ALT="$^{\:1}$"> A. Smrdel<IMG
WIDTH="18" HEIGHT="25" ALIGN="BOTTOM" BORDER="0"
SRC="img5.png"
ALT="$^{\:1}$">
C. Marchesi<IMG
WIDTH="32" HEIGHT="25" ALIGN="BOTTOM" BORDER="0"
SRC="img6.png"
ALT="$^{\:3,6}$"> and R. G. Mark<IMG
WIDTH="32" HEIGHT="25" ALIGN="BOTTOM" BORDER="0"
SRC="img3.png"
ALT="$^{\:2,4}$"></B></FONT>
<BR>
</DIV>
<P>
<DIV ALIGN="LEFT">
</DIV><PRE><TT>
<BR><IMG
WIDTH="15" HEIGHT="25" ALIGN="BOTTOM" BORDER="0"
SRC="img7.png"
ALT="$^{1}$"> Faculty of Computer & Information Science, University of Ljubljana, Ljubljana, Slovenia
<BR><IMG
WIDTH="15" HEIGHT="25" ALIGN="BOTTOM" BORDER="0"
SRC="img8.png"
ALT="$^{2}$"> Harvard-MIT Division of Health Sciences & Technology, Cambridge, MA, USA
<BR><IMG
WIDTH="15" HEIGHT="25" ALIGN="BOTTOM" BORDER="0"
SRC="img9.png"
ALT="$^{3}$"> National Research Council (CNR) Institute of Clinical Physiology, Pisa, Italy
<BR><IMG
WIDTH="15" HEIGHT="25" ALIGN="BOTTOM" BORDER="0"
SRC="img10.png"
ALT="$^{4}$"> Cardiology Division, Beth Israel Deaconess Medical Center, Boston, MA, USA
<BR><IMG
WIDTH="15" HEIGHT="25" ALIGN="BOTTOM" BORDER="0"
SRC="img11.png"
ALT="$^{5}$"> Department of Cardiology, University Medical Center, Ljubljana, Slovenia
<BR><IMG
WIDTH="15" HEIGHT="25" ALIGN="BOTTOM" BORDER="0"
SRC="img12.png"
ALT="$^{6}$"> Department of Systems & Informatics, University of Firenze, Italy
<BR>
<BR>
</TT></PRE>
<DIV ALIGN="LEFT">
</DIV>
<center><table bgcolor="lightblue">
<tr><td>
This article originally appeared in <em>Medical & Biological Engineering
& Computing</em> 41(2):172-182 (2003). Please cite this publication when
referencing this material. A <a href="lt03.pdf">PDF</a> version of this
article is also available.
</td></tr>
</table></center>
<P>
<DIV ALIGN="CENTER">
<FONT SIZE="+2"><B>Abstract</B></FONT>
</DIV>
<EM>The long-term ST database is the result of a multinational research effort. The
goal was to develop a challenging and realistic research resource for development and
evaluation of automated systems to detect transient ST segment changes in electrocardiograms
and for supporting basic research into the mechanisms and dynamics of transient myocardial
ischaemia. Twenty-four hour ambulatory ECG records were selected from routine clinical
practice settings in the USA and Europe, between 1994 and 2000, on the basis of occurrence
of ischaemic and non-ischaemic ST segment changes. Human expert annotators used newly
developed annotation protocols and a specially developed interactive graphic editor tool
(S<SMALL>EMIA)</SMALL> that supported paperless editing of annotations and facilitated international
co-operation via the Internet. The database contains 86 two- and three-channel 24 h
annotated ambulatory records from 80 patients and is stored on DVD-ROMs. The database
annotation files contain ST segment annotations of transient ischaemic (1155) and
heart-rate related ST episodes and annotations of non-ischaemic ST segment events related
to postural changes and conduction abnormalities. The database is intended to complement
the European Society of Cardiology ST-T database and the MIT-BIH and AHA arrhythmia
databases. It provides a comprehensive representation of `real-world' data, with numerous
examples of transient ischaemic and non-ischaemic ST segment changes, arrhythmias, conduction
abnormalities, axis shifts, noise and artifacts.</EM>
<BR>
<BR><B>Keywords -</B> <EM>Myocardial ischaemia, ST-segment change analysis, Non-ischaemic
ST segment changes, Annotated ECG database, Performance evaluation of instrumentation,
Mechanisms of transient myocardial ischaemia</EM>
<BR>
<BR>
<BR>(Med. Biol. Eng. Comput., 2003, <B>41</B>, 172-182)
<BR>
<P>
<P>
<DIV ALIGN="LEFT">
<FONT SIZE="+2"><B>1 Introduction</B></FONT>
</DIV>
<P>
A<SMALL>MBULATORY ELECTROCARDIOGRAPHIC</SMALL> (AECG) and intensive care unit (ICU) monitoring
are widely used diagnostic approaches in clinical practice for evaluating patients
with suspected or known coronary artery disease. Owing to the long duration of these
electrocardiogram (ECG) records, automated detection techniques are required to help
in interpretation of relevant clinical events.
<P>
Standardised reference ECG databases are important research resources that permit
developers of automated detectors and ECG analysers to assess the quality of their
instrumentation on the same reference database. Thus the performance of different
analysers can be compared. In the early 1980s, the <EM>MIT-BIH arrhythmia database</EM>
[<A
HREF="node1.html#Mark-82">M<SMALL>ARK</SMALL> <EM>et al.</EM>, 1982</A>] and the <EM>American Heart Association database</EM> [<A
HREF="node1.html#Hermes-80">H<SMALL>ERMES</SMALL> <EM>et al.</EM>, 1981</A>]
were released. They made it possible to develop, evaluate and compare reproducibly
the quantitative performance of automated arrhythmia detectors.
<P>
Another important task during AECG and ICU monitoring is the analysis of transient ST
segment and T-wave changes due to myocardial ischaemia. Improvements in recording technology
since the early 1980s made it possible to begin analysis of transient ST changes during
AECG. Standardising the approach to the detection and interpretation of ST segment and
T-wave changes was initiated by a `concerted action' on ambulatory monitoring set up by
the European Community in 1985 [<A
HREF="node1.html#Marchesi-86">M<SMALL>ARCHESI</SMALL>, 1986</A>]. The goal was to develop an ECG
database as a reference for assessing the quality of AECG analysis systems. Funding from
the European Community supported development of an annotation protocol and of a small
prototype database.
<P>
Development of the database was continued by the joint efforts of the Institute of
Clinical Physiology of the National Research Council (CNR) in Pisa and of the Thoraxcenter
of Erasmus University, in Rotterdam, with the voluntary participation of 13 research groups
from eight countries that provided ECG recordings and contributed to the demanding work
of annotating them. The European Society of Cardiology provided both financial and
scientific backing, so as to enable completion of the <EM>European Society of Cardiology
ST-T database</EM> (ESC DB) [<A
HREF="node1.html#Taddei-921">T<SMALL>ADDEI</SMALL> <EM>et al.</EM>, 1992b</A>], which was first released in 1990. It was the
first standard, generally available set of AECG records with documented `significant'
(<IMG
WIDTH="22" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img13.png"
ALT="$>$"> 100 <IMG
WIDTH="18" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img14.png"
ALT="$\mu$">V) transient ST segment episodes of depression or elevation and significant
transient T-wave episodes (<IMG
WIDTH="22" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img13.png"
ALT="$>$"> 200 <IMG
WIDTH="18" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img14.png"
ALT="$\mu$">V) of depression or elevation.
<P>
The ESC DB contains 90 2 h, well-characterised, representative records, with manually
annotated transient ST segment (368) and T-wave (401) episodes compatible with myocardial
ischaemia. Episodes are annotated in each lead separately, and each heart-beat is also
annotated manually in terms of QRS complex onset, beat type, rhythm change and signal
quality. The ESC DB promoted further investigations in the analysis of ST-T changes in
the ECG and has proven to be an invaluable resource for the development and evaluation
of ECG analysers.
<P>
During the past few years, it has been a reference for companies developing biomedical
equipment and has stimulated extensive research and publications
[<A
HREF="node1.html#Cerutti-92">C<SMALL>ERUTTI</SMALL> <EM>et al.</EM>, 1992</A>,<A
HREF="node1.html#Laguna-963">L<SMALL>AGUNA</SMALL> <EM>et al.</EM>, 1996</A>,<A
HREF="node1.html#Presedo-962">P<SMALL>RESEDO</SMALL> <EM>et al.</EM>, 1996a</A>,<A
HREF="node1.html#Emdin-97">E<SMALL>MDIN</SMALL> <EM>et al.</EM>, 1997</A>,<A
HREF="node1.html#Taddei-97">T<SMALL>ADDEI</SMALL> <EM>et al.</EM>, 1997</A>]
<BR>[<A
HREF="node1.html#Laguna-97">L<SMALL>AGUNA</SMALL> <EM>et al.</EM>, 1997</A>].
Techniques to classify QRS complex morphology were developed and evaluated
[<A
HREF="node1.html#Morabito-92">M<SMALL>ORABITO</SMALL> <EM>et al.</EM>, 1992</A>,<A
HREF="node1.html#Silipo-93">S<SMALL>ILIPO</SMALL> <EM>et al.</EM>, 1993</A>,<A
HREF="node1.html#Silipo-951">S<SMALL>ILIPO</SMALL> <EM>et al.</EM>, 1995a</A>],
and a number of recognition techniques to detect transient ischaemic events automatically
were introduced, including: time-domain analysis
[<A
HREF="node1.html#Jager-91">J<SMALL>AGER</SMALL> <EM>et al.</EM>, 1991</A>,<A
HREF="node1.html#Taddei-95">T<SMALL>ADDEI</SMALL> <EM>et al.</EM>, 1995</A>,<A
HREF="node1.html#Laguna-00">G<SMALL>ARCIA</SMALL> <EM>et al.</EM>, 2000</A>],
the Karhunen-Loève Transform (KLT) approach
[<A
HREF="node1.html#Jager-92">J<SMALL>AGER</SMALL> <EM>et al.</EM>, 1992</A>,<A
HREF="node1.html#Laguna-94">L<SMALL>AGUNA</SMALL> <EM>et al.</EM>, 1995</A>,<A
HREF="node1.html#Laguna-962">G<SMALL>ARCIA</SMALL> <EM>et al.</EM>, 1996</A>,<A
HREF="node1.html#Jager-980">J<SMALL>AGER</SMALL> <EM>et al.</EM>, 1998a</A>,<A
HREF="node1.html#Smrdel-98">S<SMALL>MRDEL</SMALL> and J<SMALL>AGER</SMALL>, 1998</A>],
non-linear principal components [<A
HREF="node1.html#Diamantaras-96">D<SMALL>IAMANTARAS</SMALL> <EM>et al.</EM>, 1996</A>], a variety of neural network
techniques [<A
HREF="node1.html#Silipo-952">S<SMALL>ILIPO</SMALL> <EM>et al.</EM>, 1995b</A>,<A
HREF="node1.html#Silipo-961">S<SMALL>ILIPO</SMALL> and M<SMALL>ARCHESI</SMALL>, 1996</A>,<A
HREF="node1.html#Stamkopoulos-98">S<SMALL>TAMKOPOULOS</SMALL> <EM>et al.</EM>, 1998</A>,<A
HREF="node1.html#Maglaveras-98">M<SMALL>AGLAVERAS</SMALL> <EM>et al.</EM>, 1998</A>]
and a fuzzy-logic approach [<A
HREF="node1.html#Presedo-96">P<SMALL>RESEDO</SMALL> <EM>et al.</EM>, 1996b</A>]. A bilateral project supported by the
CNR, involving the Institute of Clinical Physiology in Pisa, and the Massachusetts
Institute of Technology, in Cambridge, was conducted between 1995 and 1996 to address
standardisation of the analysis of ST-T changes during myocardial ischaemia.
<P>
Although the ESC DB represented a major contribution to the research community, the
relatively short record lengths presented significant limitations. For example,
careful analysis of the ESC DB had revealed intriguing temporal dynamics of
transient ischaemic episodes [<A
HREF="node1.html#Jager-961">J<SMALL>AGER</SMALL> <EM>et al.</EM>, 1996a</A>], but their full exploration was
prevented by the short record lengths. The ESC DB was found to contain a number
of <EM>non-ischaemic</EM> ST segment changes due to postural changes or slow drift
of the ST deviation level [<A
HREF="node1.html#Jager-95">J<SMALL>AGER</SMALL> <EM>et al.</EM>, 1995</A>]. Such non-ischaemic ST segment episodes
are quite common in real-world ECG monitoring. They complicate automated analysis
of transient ST events and account for many false positive ischaemia detections.
The ESC DB does not include a sufficient number of non-ischaemic episodes adequately
to test the specificity of automated ischaemia detectors.
<P>
The objective of the present study was to create an annotated database of long-term ECG
records that would more completely represent the spectrum of real-world ST events.
Development of the <EM>long-term ST database</EM> (LTST DB) began in 1995 with the joint
research project `Detection of transient ST segment changes during ambulatory monitoring'
v[<A
HREF="node1.html#Jager-951">J<SMALL>AGER</SMALL> <EM>et al.</EM>, 1998b</A>], conducted between the Faculty of Computer & Information Science,
University of Ljubljana, Slovenia, and the Massachusetts Institute of Technology,
Cambridge, USA. The project was sponsored by the US-Slovenian Science & Technology
Joint Fund Secretariat. The project produced an initial LTST DB of 11 annotated two-lead
24 h AECG records. The aim of this database was to support the development and evaluation
of ST segment change detectors capable of differentiating between ST episodes compatible
with ischaemia and non-ischaemic ST events.
<P>
In 1997, Medtronic, Inc. (Minneapolis, USA), agreed to sponsor further development of
the database. At that time, research groups from the Institute of Clinical Physiology,
in Pisa, the Beth Israel Deaconess Medical Center, in Boston, and University Medical
Center, in Ljubljana, joined the project. In 1999, Zymed, Inc. (Camarrilo, USA), became
an additional sponsor of the project with a special interest in adding a set of three-lead
AECG records to the database. It is important to observe that the LTST DB was not intended
as a replacement of the ESC DB, but as a complement. The ESC DB was fully annotated on a
beat-by-beat basis, thus supporting evaluation of algorithms for QRS detection in the
presence of ST-T abnormalities, in addition to detectors of ST segment and T-wave episodes.
On the other hand, the LTST DB is of far greater size, and the annotation methodology was
different. Owing to the enormous number of data, it was not practical to annotate the ST
segment changes beat-by-beat. The ST segment annotations are based on average waveforms.
The goals of the LTST DB are
<DL COMPACT>
<DT>(a)</DT>
<DD>more adequately to represent the wide variety of real-world data that
typically challenge real-time automatic ischaemia detectors. The database should include
a meaningful number of
<DL COMPACT>
<DT><IMG
WIDTH="16" HEIGHT="21" ALIGN="BOTTOM" BORDER="0"
SRC="img15.png"
ALT="$\bullet$"></DT>
<DD>transient ST segment episodes compatible with ischaemia (ischaemic
ST episodes)
</DD>
<DT><IMG
WIDTH="16" HEIGHT="21" ALIGN="BOTTOM" BORDER="0"
SRC="img15.png"
ALT="$\bullet$"></DT>
<DD>non-ischaemic ST episodes due to changes in heart rate (heart-rate
related ST episodes)
</DD>
<DT><IMG
WIDTH="16" HEIGHT="21" ALIGN="BOTTOM" BORDER="0"
SRC="img15.png"
ALT="$\bullet$"></DT>
<DD>non-ischaemic slow ST segment drifts
</DD>
<DT><IMG
WIDTH="16" HEIGHT="21" ALIGN="BOTTOM" BORDER="0"
SRC="img15.png"
ALT="$\bullet$"></DT>
<DD>non-ischaemic ST shifts due to postural changes (axis shifts)
</DD>
<DT><IMG
WIDTH="16" HEIGHT="21" ALIGN="BOTTOM" BORDER="0"
SRC="img15.png"
ALT="$\bullet$"></DT>
<DD>non-ischaemic ST shifts due to changes in ventricular conduction
(conduction changes)
</DD>
<DT><IMG
WIDTH="16" HEIGHT="21" ALIGN="BOTTOM" BORDER="0"
SRC="img15.png"
ALT="$\bullet$"></DT>
<DD>data corrupted by noise and artifacts
</DD>
</DL>
</DD>
<DT>(b)</DT>
<DD>to provide sufficient data in each record adequately to represent a variety
of characteristic temporal patterns and dynamics of episodic ischaemia
</DD>
<DT>(c)</DT>
<DD>to include a variety of arrhythmias to support studies on their possible
correlations with transient ischaemia.
</DD>
</DL>
<P>
In previous papers on the LTST DB, we reported our initial approach to the development of
the database [<A
HREF="node1.html#Jager-96">J<SMALL>AGER</SMALL> <EM>et al.</EM>, 1996b</A>], the newly established and continuously updated annotation
protocols, the newly developed annotating tool S<SMALL>EMIA</SMALL> and the status of the database
at that time [<A
HREF="node1.html#Jager-98">J<SMALL>AGER</SMALL> <EM>et al.</EM>, 1998c</A>,<A
HREF="node1.html#Jager-00">J<SMALL>AGER</SMALL> <EM>et al.</EM>, 2000</A>]. In this paper, we present the final design and
construction of the LTST DB. We present sources of AECG records, the selection procedure
and selection criteria for records, the automated preprocessing procedure, the methodology
to determine heart-beat fiducial points, the annotation protocols with definitions of
significant transient ST events, the annotating tools, the annotating procedure using
human expert annotators, the database annotations and the content of the records of the
database.
<BR>
<P>
<DIV ALIGN="LEFT">
<FONT SIZE="+2"><B>2 Methods</B></FONT>
<BR>
<BR><FONT SIZE="+2">2.1 <EM>Sources of AECG records</EM></FONT>
</DIV>
<P>
The records of the LTST DB were selected from Holter recordings obtained in
routine clinical practice settings, in the United States and Europe, between 1994
and 2000. The candidate AECG records were chosen from collections of two- and three-lead
AECG records at four different sites
<DL COMPACT>
<DT>(i)</DT>
<DD>the Holter library of the Beth Israel Deaconess Medical Center, in Boston.
This library represented the records of a general hospital-based cardiology department.
The recordings were performed for a variety of reasons during the period of development
of the database.
</DD>
<DT>(ii)</DT>
<DD>the Holter library from the collection of the Physiolab (Laboratory of
Biosignal Processing) of the Institute of Clinical Physiology, in Pisa. This laboratory
is particularly rich in examples of transient ischaemia. The laboratory provided recordings
with true ischaemic and/or non-ischaemic ST segment changes from patients with ascertained
coronary artery disease, other cardiac dysfunctions or conditions and non-ischaemic
heart-rate related ST segment changes. This laboratory has previously contributed records
to the ESC DB. In fact, 2 h excerpts of some LTST DB records from Pisa had previously
been included in the ESC DB. These records had been collected since 1980.
</DD>
<DT>(iii)</DT>
<DD>the Holter core laboratory that processed data for the asymptomatic
cardiac ischaemia pilot (ACIP) study [<A
HREF="node1.html#Davies-97">D<SMALL>AVIES</SMALL> <EM>et al.</EM>, 1997</A>], archived at the Brigham and
Womens Hospital in Boston. Patients in this study had known coronary artery disease
(CAD), and the study documented a significant incidence of silent ischaemia based on
Holter evidence.
</DD>
<DT>(iv)</DT>
<DD>three-channel Holters using the EASI lead system [<A
HREF="node1.html#Dower-88">D<SMALL>OWER</SMALL> <EM>et al.</EM>, 1988</A>] that
were provided by the Zymed company. The recordings were from individuals with known
CAD.
</DD>
</DL>
<P>
<DIV ALIGN="LEFT">
<FONT SIZE="+2">2.2 <EM>Selection procedure and selection criteria for records</EM></FONT>
</DIV>
<P>
The records of the database were selected to model real-world clinical conditions as
far as possible and to document significant numbers of ischaemic and non-ischaemic ST
events. The selection procedure for the records consisted of the following steps:
<DL COMPACT>
<DT>(a)</DT>
<DD>the original Holter reports and sample rhythm strips were reviewed so
that records with possible transient ST changes could be identified
</DD>
<DT>(b)</DT>
<DD>these tapes were then rescanned (see Fig. <A HREF="node1.html#fi:figure1"><IMG ALIGN="BOTTOM" BORDER="1" ALT="[*]" SRC="cross_ref.png"></A>) by expert Holter
technicians and cardiologists using standard Holter scanners; the digitised data from the
scanner were saved; trend plots of heart rate and ST segment level, together with detailed
hard-copy rhythm strips, were used to select records with ST episodes meeting one or
more of the goals of the project; those records showing episodes of significant ST
deviations were selected for further processing
</DD>
<DT>(c)</DT>
<DD>candidate records were further preprocessed (see section 2.5) to produce
trend plots of heart rate, ST segment deviation and KLT-based representations of the
ST segment and QRS complex; expert cardiologists using the trend plots, Holter reports,
original data and available clinical information selected final records for the database.
</DD>
</DL>
<P>
Each selected record contained one or more of the following features: transient ischaemic
ST episodes, transient non-ischaemic ST episodes due to heart rate changes, slow ST level
drifts and non-ischaemic ST shifts due to axis shifts or changes in ventricular excitation.
Records containing combinations of these features were preferred. Some of the selected
records contain atrio-ventricular and intraventricular conduction defects and/or arrhythmias
such as atrial and ventricular ectopy, and atrial fibrillation. Other records were selected
to include examples of baseline ST displacement resulting from conditions such as hypertension,
ventricular dyskinesia and the effects of medications. The cardiologists also selected a
number of records from patients with proven transient myocardial ischaemia, such as effort,
resting, unstable, mixed and Prinzmetal's angina.
<P>
<DIV ALIGN="LEFT">
<FONT SIZE="+2">2.3 <EM>ECG leads</EM></FONT>
</DIV>
<P>
Leads that were felt to be most likely to reveal ST segment changes were generally chosen
at the time of the original Holter recording. Not surprisingly therefore a variety of lead
combinations were used. The leads used in the two-channel records included: precordial leads
V<IMG
WIDTH="15" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img16.png"
ALT="$_{2}$">, V<IMG
WIDTH="15" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img17.png"
ALT="$_{3}$">, V<IMG
WIDTH="15" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img18.png"
ALT="$_{4}$"> or V<IMG
WIDTH="15" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img19.png"
ALT="$_{5}$">, together with modified limb lead III (MLIII); or
lead V<IMG
WIDTH="15" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img19.png"
ALT="$_{5}$"> and lead V<IMG
WIDTH="15" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img16.png"
ALT="$_{2}$">; or modified limb lead L2 (ML2) and modified lead V<IMG
WIDTH="15" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img16.png"
ALT="$_{2}$">
(MV2). The leads used in the three-channel records included: a combination from leads V<IMG
WIDTH="15" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img17.png"
ALT="$_{3}$">,
V<IMG
WIDTH="15" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img18.png"
ALT="$_{4}$">, V<IMG
WIDTH="15" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img19.png"
ALT="$_{5}$">, V<IMG
WIDTH="15" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img20.png"
ALT="$_{6}$">, II and aVF, or Zymed's EASI lead system with the leads E-S,
A-S and A-I.
<P>
<DIV ALIGN="LEFT">
<FONT SIZE="+2">2.4 <EM>Recorders and sampling</EM></FONT>
</DIV>
<P>
Analogue records were made using standard AECG recorders. The analogue output of the playback
units was passed through anti-aliasing filters and digitised. The records were digitised
at the same site as where they were obtained. As analogue AECG recorders typically preserve
frequency content in the signals, typically from close to 0.05 Hz up to 30 Hz (or to 45
Hz in best cases) [<A
HREF="node1.html#Brueggemann-91">B<SMALL>RUEGGEMANN</SMALL> <EM>et al.</EM>, 1991</A>], the records were digitised at 128 or 250 samples
per second per channel, depending on the scanning system, and the resolution was 12 bits.
There is no significant information to be gained from using a higher sampling frequency
for these records. The low frequency cutoff met the AHA [<A
HREF="node1.html#AHA-89">K<SMALL>NOEBEL</SMALL> <EM>et al.</EM>, 1989</A>] and AAMI [<A
HREF="node1.html#AAMI-94">AAMI, 1994</A>]
recommendations. The scanning systems available and used at the sites were Marquette, ICR,
Del Mar Avionics, Oxford Medilog, Remco Italia Cardioline and Zymed.
<P>
<DIV ALIGN="LEFT">
<FONT SIZE="+2">2.5 <EM>Automated preprocessing phase</EM></FONT>
</DIV>
<P>
During the preprocessing phase, which was performed at the central computer facility
site at the Faculty of Computer & Information Science, in Ljubljana, time series of
diagnostic and morphologic features were derived from ECG samples. The signal processing
methodology is summarised in Fig. <A HREF="node1.html#fi:figure1"><IMG ALIGN="BOTTOM" BORDER="1" ALT="[*]" SRC="cross_ref.png"></A>. The time series were needed later during
the annotation phases and to derive trend plots for selecting the final records of the
database. Initially, the selected records were resampled to a uniform sampling frequency of
250 samples per second per channel, and the amplitude scale was adjusted to 200 ADC units
mV<IMG
WIDTH="28" HEIGHT="25" ALIGN="BOTTOM" BORDER="0"
SRC="img21.png"
ALT="$^{-1}$">. To derive morphologic features, we used the KLT, which has been proven to be
useful for shape representation of the ECG morphology [<A
HREF="node1.html#Moody-89">M<SMALL>OODY</SMALL> and M<SMALL>ARK</SMALL>, 1990</A>,<A
HREF="node1.html#Jager-92">J<SMALL>AGER</SMALL> <EM>et al.</EM>, 1992</A>,<A
HREF="node1.html#Taddei-922">T<SMALL>ADDEI</SMALL> <EM>et al.</EM>, 1992a</A>].
<P>
Stable fiducial points for heart-beats were generated using the A<SMALL>RISTOTLE</SMALL>
arrhythmia detector [<A
HREF="node1.html#Moody-82">M<SMALL>OODY</SMALL> and M<SMALL>ARK</SMALL>, 1982</A>] for QRS complex detection and classification.
A<SMALL>RISTOTLE</SMALL> places its fiducial point (FP) within the QRS complex region in the
`centre of mass' of deflections. In the case of biphasic QRS complex, it is placed
close to more significant deflection, whereas, in the case of monophasic QRS complex,
it is placed close to a peak of the QRS complex. A stable fiducial point in each
heart-beat was a prerequisite for automatic identification of the iso-electric level,
calculation of KLT-based ST segment and QRS complex feature vectors, and time-averaging
of heart-beats. A<SMALL>RISTOTLE</SMALL>'s fiducial point is stable and suitable for our further
analysis.
<P>
Removal of baseline wander using a cubic spline approximation and subtraction technique
and low-pass filtering by a six-pole Butterworth filter (with a cutoff frequency of
55 Hz) followed. After that, instantaneous heart rate was calculated. Next, the position
of the iso-electric level in each heart-beat and in each ECG lead was defined as the
centre of the `most flat' region in the PQ interval prior to the A<SMALL>RISTOTLE</SMALL>'s
fiducial point [<A
HREF="node1.html#Jager-91">J<SMALL>AGER</SMALL> <EM>et al.</EM>, 1991</A>,<A
HREF="node1.html#Jager-94">J<SMALL>AGER</SMALL>, 1994</A>]. After that, the ST level was measured with
respect to the defined iso-electric level at the point FP + 120 ms, if the heart rate
(HR) was less than 100 beats min<IMG
WIDTH="28" HEIGHT="25" ALIGN="BOTTOM" BORDER="0"
SRC="img21.png"
ALT="$^{-1}$"> (or FP + 112 ms if 100 <IMG
WIDTH="22" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img22.png"
ALT="$\leq$"> HR <IMG
WIDTH="22" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img23.png"
ALT="$<$"> 110, or
FP + 104 ms if 110 <IMG
WIDTH="22" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img22.png"
ALT="$\leq$"> HR <IMG
WIDTH="22" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img23.png"
ALT="$<$"> 120, or FP + 100 ms if HR <IMG
WIDTH="22" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img24.png"
ALT="$\geq$">120) [<A
HREF="node1.html#Jager-94">J<SMALL>AGER</SMALL>, 1994</A>].
<P>
Next, abnormal beats and their neighbours were rejected, the KLT-based ST segment and
QRS complex morphology feature-vector time series were derived, and noisy beats were
rejected. Heart-beats were judged `noisy' if the ST segment or QRS complex KLT feature
vector differed sufficiently (mean + 1 SD) from those of the past few (15) normal
heart-beats, or if the normalised residual error for the ST segment or for the QRS
complex exceeded a certain percentage (25%) when the ST segment or QRS complex was
approximated using the first five KLT eigenvectors [<A
HREF="node1.html#Jager-92">J<SMALL>AGER</SMALL> <EM>et al.</EM>, 1992</A>,<A
HREF="node1.html#Jager-94">J<SMALL>AGER</SMALL>, 1994</A>]. The noisy
beat detection procedure in the KLT space appeared to be robust and accurate. The
percentage of rejected heart-beats was less than approximately 10% in almost all
records.
<P>
The resulting time series were finally smoothed, resampled and further smoothed.
Finally, trend plots of the time series were derived to aid in selecting the final
records of the database. Morphologic KLT feature-vector time series for QRS complexes
and ST segments allowed accurate visual detection of important, as well as subtle,
events in the time series.
<P>
<DIV ALIGN="LEFT">
<FONT SIZE="+2">2.6 <EM>Determining the iso-electric level and the J point</EM></FONT>
</DIV>
<P>
The automatically generated iso-electric points and J points during the preprocessing
phase required human editing to improve their accuracy. This was particularly true of
the J points that were estimated using the A<SMALL>RISTOTLE</SMALL>'s QRS fiducial points, i.e.
simply 120 ms (or less, depending on heart rate) after the fiducial point. The physician
annotators used S<SMALL>EMIA</SMALL> editing tools (see section 2.8) to interact with the data
at a number of points in the 24 h records and manually to adjust the positions of the
iso-electric level and the J point at the selected times. The flow of data through the
annotation phases is shown in Fig. <A HREF="node1.html#fi:figure1"><IMG ALIGN="BOTTOM" BORDER="1" ALT="[*]" SRC="cross_ref.png"></A>. The editing points were chosen by
the annotators and were set roughly prior to, at the extrema and at the end of ST episodes;
or, otherwise, approximately every 20 min. Manual adjustment of the positions of the
iso-electric level and the J point was done simultaneously for all ECG leads, using
average heart-beats computed over a 16 s window surrounding the points chosen for
editing.
<P>
An automatic post-processing procedure estimated the positions of the iso-electric
level and the J point for the remainder of the clean heart-beats by linearly interpolating
between points of editing. Next, time-averaged heart-beats over 16 s intervals surrounding
each clean heart-beat were computed. The <EM>ST level function</EM> was then constructed
in each lead using the adjusted iso-electric and J points. ST amplitudes were measured at
J + 80 ms, if HR was less than 100 beats min<IMG
WIDTH="28" HEIGHT="25" ALIGN="BOTTOM" BORDER="0"
SRC="img21.png"
ALT="$^{-1}$"> (or J + 72 ms if 100 <IMG
WIDTH="22" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img22.png"
ALT="$\leq$"> HR <IMG
WIDTH="22" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img23.png"
ALT="$<$"> 110,
or J + 64 ms if 110 <IMG
WIDTH="22" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img22.png"
ALT="$\leq$"> HR <IMG
WIDTH="22" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img23.png"
ALT="$<$"> 120, or J + 60 ms if HR <IMG
WIDTH="22" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img24.png"
ALT="$\geq$"> 120). The ST level
functions were then resampled (0.5 samples s<IMG
WIDTH="28" HEIGHT="25" ALIGN="BOTTOM" BORDER="0"
SRC="img21.png"
ALT="$^{-1}$">), and smoothed (7-point moving
average). Finally, these new ST level functions replaced those derived during the
preprocessing phase and formed the basis for annotating ST events.
<P>
<DIV ALIGN="LEFT">
<FONT SIZE="+2">2.7 <EM>Annotation protocol</EM></FONT>
</DIV>
<P>
The annotation protocol is compatible with that developed for the AHA, MIT-BIH arrhythmia
and ESC databases, but we have extended it to permit more detailed descriptions of
non-ischaemic ST events. The ST events were defined and annotated independently in each
ECG lead to support analysis of each ECG lead independently and also to enable evaluation
of single-lead ischaemia detection algorithms. Electrocardiogram waveform analysis alone
is often inadequate to make an unambiguous diagnosis of myocardial ischaemia and should
not exclusively be relied upon for annotating transient ischaemic ST change episodes.
Therefore our gold standard for annotating transient ischaemic and heart-rate related
ST segment episodes was the expert cardiologists' opinion, based on: their knowledge and
experience, type of change of ST segment waveforms, 24 h context of diagnostic and
morphology parameters, and detailed clinical information from the subjects, including
other clinical investigations and clinical history. The basis for annotating ST events
in each ECG lead was the ST level function (see Fig. <A HREF="node1.html#fi:figure2"><IMG ALIGN="BOTTOM" BORDER="1" ALT="[*]" SRC="cross_ref.png"></A>). The ST level
function typically varies widely and significantly in amplitude, owing to drifts, position
changes, changes in conduction, heart-rate related changes and ischaemia.
<P>
The annotators defined several <EM>classes</EM> of ST segment changes
<DL COMPACT>
<DT>(i)</DT>
<DD><EM>non-ischaemic changes in ST segment morphology</EM>
<DL COMPACT>
<DT><IMG
WIDTH="16" HEIGHT="21" ALIGN="BOTTOM" BORDER="0"
SRC="img15.png"
ALT="$\bullet$"></DT>
<DD>slow or sudden changes due to simultaneous slow or sudden (postural
- axis shifts) changes in the cardiac QRS electrical axis; these are characterised by
a change in the Q-, R- or S-wave amplitude
</DD>
<DT><IMG
WIDTH="16" HEIGHT="21" ALIGN="BOTTOM" BORDER="0"
SRC="img15.png"
ALT="$\bullet$"></DT>
<DD>slow or sudden changes due to paroxysmal or intermittent right or
left bundle branch block, or other slow or sudden intraventricular or intermittent QRS
conduction changes; these are characterised by bizarre and wider QRS complexes
</DD>
<DT><IMG
WIDTH="16" HEIGHT="21" ALIGN="BOTTOM" BORDER="0"
SRC="img15.png"
ALT="$\bullet$"></DT>
<DD>slow drifts due to heart-rate related diurnal changes or effects
of medication on repolarisation; drifts are characterised by slow and persistent typical
non-ischaemic changes in ST segment slope and shape within a longer period, and may or
may not be accompanied by a change in heart rate
</DD>
</DL>
</DD>
<DT>(ii)</DT>
<DD><EM>non-ischaemic heart-rate related change in ST segment morphology:</EM>
<BR>
this is characterised by changes in ST segment morphology and by a change in heart rate,
when clinical information from the subject does not suggest ischaemia. Typically, and
most often, changes in ST segment morphology of this class include: J point depression
with positive slope; moving of T-wave into ST segment; T-wave peaking; or parallel shift
of ST segment compared to the reference or basal ST segment
</DD>
<DT>(iii)</DT>
<DD><EM>ischaemic change in ST segment morphology:</EM>
<BR>
this is characterised by changes in ST segment morphology and may or may not be
accompanied by a change in heart rate, when clinical information from the subject
suggests ischaemia. Typically, and most often, changes in ST segment morphology of this
ischaemic class include: horizontal flattening; down sloping; scooping; or elevation
</DD>
<DT>(iv)</DT>
<DD><EM>noisy ST event:</EM>
<BR>
this is characterised by consecutive ST segments that cannot be evaluated by annotators
because of noise.
</DD>
</DL>
<P>
Record annotation began with the establishment of the <EM>global-reference</EM> annotation in
each ECG lead (refer to Fig. <A HREF="node1.html#fi:figure2"><IMG ALIGN="BOTTOM" BORDER="1" ALT="[*]" SRC="cross_ref.png"></A>). It was chosen to be near the beginning of
the record, at a time when the ST level was stable for at least 5 min. All subsequent ST
annotations were referenced to the global reference level. The next step in the annotation
process was manually to track the time-varying ST level, except for deviations due to ischaemia,
non-ischaemic heart-rate related changes in ST morphology and noisy ST events. The tracking
process permitted the human experts to remove from consideration variations in ST level
that could also be significant (<IMG
WIDTH="22" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img13.png"
ALT="$>$">50<IMG
WIDTH="18" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img14.png"
ALT="$\mu$">V) but were clinically not important. Annotations
(known as <EM>local references</EM>) were placed at intervals in the non-ischaemic data and
were connected with straight-line segments to produce the <EM>ST reference function</EM>.
The algebraic difference between the ST level function and the ST reference function
was the <EM>ST deviation function</EM>, which clearly identified transient ST deviations from
the local ST reference level, as defined by the annotators. Ischaemic and non-ischaemic
heart-rate related ST episodes were then identified and annotated in the ST deviation
function. To be annotated, a transient ST episode had to be significant,
satisfying the following criteria:
<UL>
<LI>an episode begins when the magnitude of the ST deviation function first exceeds
50<IMG
WIDTH="18" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img14.png"
ALT="$\mu$">V
</LI>
<LI>the deviation must reach a magnitude of <IMG
WIDTH="50" HEIGHT="41" ALIGN="MIDDLE" BORDER="0"
SRC="img25.png"
ALT="$V_{min}$"> or more throughout a continuous
interval of at least <IMG
WIDTH="50" HEIGHT="41" ALIGN="MIDDLE" BORDER="0"
SRC="img26.png"
ALT="$T_{min}$"> s
</LI>
<LI>the episode ends when the deviation becomes smaller than 50<IMG
WIDTH="18" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img14.png"
ALT="$\mu$">V, provided that
it does not exceed 50<IMG
WIDTH="18" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img14.png"
ALT="$\mu$">V in the following 30 s.
</LI>
</UL>
Different values for <IMG
WIDTH="50" HEIGHT="41" ALIGN="MIDDLE" BORDER="0"
SRC="img25.png"
ALT="$V_{min}$"> and <IMG
WIDTH="50" HEIGHT="41" ALIGN="MIDDLE" BORDER="0"
SRC="img26.png"
ALT="$T_{min}$"> were used, yielding three different ST
annotation protocols. Protocol <EM>A</EM> included: <IMG
WIDTH="50" HEIGHT="41" ALIGN="MIDDLE" BORDER="0"
SRC="img25.png"
ALT="$V_{min}$"> = 75 <IMG
WIDTH="18" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img14.png"
ALT="$\mu$">V, and <IMG
WIDTH="50" HEIGHT="41" ALIGN="MIDDLE" BORDER="0"
SRC="img26.png"
ALT="$T_{min}$"> = 30 s;
protocol <EM>B</EM>: <IMG
WIDTH="50" HEIGHT="41" ALIGN="MIDDLE" BORDER="0"
SRC="img25.png"
ALT="$V_{min}$"> = 100 <IMG
WIDTH="18" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img14.png"
ALT="$\mu$">V, and <IMG
WIDTH="50" HEIGHT="41" ALIGN="MIDDLE" BORDER="0"
SRC="img26.png"
ALT="$T_{min}$"> = 30 s; and protocol <EM>C</EM>:
<IMG
WIDTH="50" HEIGHT="41" ALIGN="MIDDLE" BORDER="0"
SRC="img25.png"
ALT="$V_{min}$"> = 100 <IMG
WIDTH="18" HEIGHT="39" ALIGN="MIDDLE" BORDER="0"
SRC="img14.png"
ALT="$\mu$">V, and <IMG
WIDTH="50" HEIGHT="41" ALIGN="MIDDLE" BORDER="0"
SRC="img26.png"
ALT="$T_{min}$"> = 60 s. Thus three sets of ST episode annotations
were provided, as differing criteria may be appropriate, depending on the application.
<P>
To annotate ST events successfully, the annotators considered ST level and ST deviation
functions, the original ECG signals, the time series of QRS complex and ST segment KLT
coefficients and clinical information about the patients (final diagnosis, other investigations,
patient history). The annotators used S<SMALL>EMIA</SMALL> editing tools to support their analysis.
An example of annotating is shown in Fig. <A HREF="node1.html#fi:figure3"><IMG ALIGN="BOTTOM" BORDER="1" ALT="[*]" SRC="cross_ref.png"></A>. For the annotation phases, refer
also to Fig. <A HREF="node1.html#fi:figure1"><IMG ALIGN="BOTTOM" BORDER="1" ALT="[*]" SRC="cross_ref.png"></A>. The ST segment level was tracked in the cases of slow drift
or in the cases of other non-ischaemic changes in ST segment morphology, which had to be
evident by simultaneous change in QRS complex morphology and also evident in the time shape
within a longer period, and may or may not be accompanied by a change in the course of the
QRS complex KLT coefficients. Any significant, sudden step-change of the ST level function
that was accompanied by a simultaneous sudden step-change in QRS complex morphology was
bounded by a local reference before and after the step change and was annotated as
<EM>significant axis shift</EM> or <EM>significant conduction change</EM>, according to its
nature.
<P>
Significant ST episodes associated with non-ischaemic heart-rate related changes in ST segment
morphology (defined above) were annotated as <EM>significant heart-rate related ST episodes</EM>.
Episodes associated with ischaemic changes in ST segment morphology (defined above) were
labelled as <EM>significant ischaemic ST episodes</EM>. Sometimes, significant axis shifts or
conduction changes appeared within significant ST episodes. In these cases, they were not
tracked out, but were annotated within the episodes. Sometimes, significant ST episodes were
caused by noisy ST intervals. Short, noisy episodes were annotated as <EM>noisy events</EM> at
their extrema, and longer noisy periods were annotated as <EM>unreadable intervals</EM>. Longer
intervals with all heart-beats rejected during preprocessing because of noise were also
annotated as unreadable intervals.
<P>
<DIV ALIGN="LEFT">
<FONT SIZE="+2">2.8 <EM>Annotating tools</EM></FONT>
</DIV>
<P>
S<SMALL>EMIA</SMALL> (semi-automatic) is a special-purpose graphic event-driven user interface
and signal-processing tool designed especially for this project [<A
HREF="node1.html#Jager-98">J<SMALL>AGER</SMALL> <EM>et al.</EM>, 1998c</A>,<A
HREF="node1.html#Jager-00">J<SMALL>AGER</SMALL> <EM>et al.</EM>, 2000</A>].
The system is a powerful graphical editing system and was critical to the success of the
annotation process. An abbreviated display of S<SMALL>EMIA</SMALL>'s windows is shown in
Fig. <A HREF="node1.html#fi:figure3"><IMG ALIGN="BOTTOM" BORDER="1" ALT="[*]" SRC="cross_ref.png"></A>. S<SMALL>EMIA</SMALL>'s display provides the annotator with a global view
(at different resolutions) of the ST deviation function and heart rate, a close-up view
of individual heart-beat waveforms and a view of the temporal course of KLT coefficient
representations of the QRS complexes and ST segments. S<SMALL>EMIA</SMALL> supports: manual
adjustment of heart-beat fiducial points, manual tracking of the ST reference level,
annotation of significant ST shifts, and manual or automatic annotation of ST episodes
according to selected criteria. S<SMALL>EMIA</SMALL> supported database annotation at different
geographical sites interacting via the Internet and without paper tracings.
<P>
<DIV ALIGN="LEFT">
<FONT SIZE="+2">2.9 <EM>Annotating procedure and expert annotators</EM></FONT>
</DIV>
<P>
After setting local references and annotations indicating significant ST shifts (see
Fig. <A HREF="node1.html#fi:figure1"><IMG ALIGN="BOTTOM" BORDER="1" ALT="[*]" SRC="cross_ref.png"></A>), the expert cardiologists of the team R.G. M<SMALL>ARK</SMALL>, M. E<SMALL>MDIN</SMALL>,
and G. A<SMALL>NTOLI</SMALL>Š<MALL>C</SMALL> reviewed and corrected the ST reference functions, automatically
annotated significant ST episodes in the ST deviation function using S<SMALL>EMIA</SMALL> and
then manually verified and corrected ST episode annotations. The three expert annotators
worked independently at three different sites: Boston, Pisa and Ljubljana. They reached
consensus on the annotations at seven joint meetings held during the project.
<P>
<DIV ALIGN="LEFT">
<FONT SIZE="+2">2.10 <EM>True QRS annotations</EM></FONT>
</DIV>
<P>
True QRS annotations for the selected records of the database were obtained as follows:
Records were rescanned once again (see Fig. <A HREF="node1.html#fi:figure1"><IMG ALIGN="BOTTOM" BORDER="1" ALT="[*]" SRC="cross_ref.png"></A>) by two independent Holter
technicians, one using a Marquette Holter scanner and the other using a Zymed Holter scanner.
Each of the Holter technicians identified all QRS complexes in each record during scanning
and manually corrected the type of those QRS complexes that were falsely classified by the
scanner. The output of the scanners was QRS annotation streams containing fiducial points
of QRS complexes and QRS annotations according to their beat types. The two QRS annotation
streams for each selected record were then merged together beat-by-beat into one annotation
stream using the B<SMALL>XB</SMALL> program of the WFDB utility software [<A
HREF="node1.html#Moody-91">M<SMALL>OODY</SMALL> and M<SMALL>ARK</SMALL>, 1991</A>]. The program
keeps both QRS annotations for an individual QRS complex, if the QRS annotations from the
two annotation streams for this QRS complex differ. Discrepancies in the individual QRS
annotations were then adjudicated manually by an expert cardiologist using the W<SMALL>AVE</SMALL>
tool of the WFDB.
<BR>
<P>
<DIV ALIGN="LEFT">
<FONT SIZE="+2"><B>3 Results</B></FONT>
<BR>
<BR><FONT SIZE="+2">3.1 <EM>Database annotations</EM></FONT>
</DIV>
<P>
The LTST DB record files are in the WFDB format [<A
HREF="node1.html#Moody-91">M<SMALL>OODY</SMALL> and M<SMALL>ARK</SMALL>, 1991</A>]. They contain
detailed clinical information for the patients, waveform data, true QRS annotations
and ST annotations that are easily accessible by the WFDB software. Record files are
summarised in Table <A HREF="node1.html#ta:table1"><IMG ALIGN="BOTTOM" BORDER="1" ALT="[*]" SRC="cross_ref.png"></A>.
<P>
The header file (.hea) describes the format of the signal files (.dat) and contains
technical information about the record (recorder, date and starting time of recording,
leads), comments of expert annotators and a detailed and compact clinical summary for
the patient. The clinical summary includes age, sex, the Holter report on symptoms
during recording, final diagnosis, previous coronary angioplasty or by-pass, and current
medications. Factors that could affect ST-T morphology were also documented, including
known heart disease (coronary heart disease, angina, previous myocardial infarction,
valvular heart disease, left ventricular hypertrophy, cardiomyopathy, AV nodal or
intraventricular conduction delay or block etc.), hypertension, electrolyte abnormalities,
hypercapnoea, hyperventilation, hypotension or anemia. The clinical summary also includes
reports of previous clinical investigations that have been performed (baseline ECG,
stress ECG, thallium positron emission tomography or scintigraphy, stress echo, left
ventricular function echocardiography and coronary arteriography).
<P>
A<SMALL>RISTOTLE</SMALL>'s QRS annotation file (.ari) contains automatically derived QRS
annotations and QRS complex fiducial points. The true QRS annotation file (.atr) contains
human QRS annotations. The annotation codes used for these two QRS annotation files are
the same as those in the MIT-BIH database [<A
HREF="node1.html#Moody-91">M<SMALL>OODY</SMALL> and M<SMALL>ARK</SMALL>, 1991</A>]. The ST segment annotation
files (.sta, .stb, .stc) contain ST segment annotations (see Table <A HREF="node1.html#ta:table2"><IMG ALIGN="BOTTOM" BORDER="1" ALT="[*]" SRC="cross_ref.png"></A>)
according to annotation protocols A, B and C. The numbers of ST episodes, as determined
by each of the three sets of criteria, and the number of significant ST shifts are summarised
in the (.cnt) text file. The ST segment measurements file (.16a) contains measurements
obtained on average heart-beats comprising clean heart-beats (those that passed the
preprocessing phase) in 16 s averaging windows. An annotation contains: the value of the
ST level function for that average heart-beat; ST segment amplitude measurements at the
points: J + 0 ms, J + 20 ms, J + 40 ms, J + 60 ms, J + 80 ms, J + 100 ms and J + 120 ms;
positions of the iso-electric level and J point relative to the QRS fiducial point for this
average beat; and the number of heart-beats left and right of the centre heart-beat included
in the corresponding average beat.
<P>
<DIV ALIGN="LEFT">
<FONT SIZE="+2">3.2 <EM>Database records</EM></FONT>
</DIV>
<P>
The LTST DB contains 86 AECG records from 80 patients with significant transient ST
events annotated by human experts. There are 68 two-channel recordings and 18 three-channel
recordings. The records vary in duration from approximately 19 h to 26 h. Table <A HREF="node1.html#ta:table3"><IMG ALIGN="BOTTOM" BORDER="1" ALT="[*]" SRC="cross_ref.png"></A>
summarises the content of the records with diagnoses and numbers of annotated ST events
according to protocol A. The subjects were 46 men, aged from 44 to 85 years, and 29 women,
aged from 23 to 87 years, for five subjects, sex and age data are not available. Each record
contains significant ST events of some type. Transient ST segment episodes were counted in
each ECG lead separately, as annotated, and in the sense of combined ST annotation streams.
Column ST/I in Table <A HREF="node1.html#ta:table3"><IMG ALIGN="BOTTOM" BORDER="1" ALT="[*]" SRC="cross_ref.png"></A> summarises the numbers of <EM>combined ST change episodes</EM>
and <EM>combined ischaemic ST episodes</EM>. Combined ST change episodes are those obtained by
merging the ST episode annotations of ischaemic ST episodes and of heart-rate related ST
episodes from the simultaneous leads into one single ST annotation stream, regardless of the
type of ST episode, i.e. a combined ST change episode occurs if an episode of any type occurs
in any lead. Combined ischaemic ST episodes are those obtained by merging the ST episode
annotations of ischaemic ST episodes only into one single ST annotation stream, i.e. a
combined ischaemic ST episode occurs if an ischaemic ST episode occurs in any lead.
<P>
Table <A HREF="node1.html#ta:table4"><IMG ALIGN="BOTTOM" BORDER="1" ALT="[*]" SRC="cross_ref.png"></A> summarises the overall numbers of annotated ST segment episodes and
their durations for the annotation protocols A, B and C. The total gross database duration
is 1991:50:49 (1991 h, 50 min and 49 s), and the average duration of records is 23:09:40.
According to protocol A, the LTST DB contains 856 true ischaemic ST episodes in lead 0,
786 episodes in lead 1 and 153 episodes in lead 2. Combining the ischaemic and heart-rate
related ST episode annotation streams from the simultaneous leads yields 1490 combined ST
change episodes of total duration of 200:22:42 (average episode duration 0:08:04), whereas
combining ischaemic ST episode annotation streams yields 1155 combined ischaemic ST
episodes of total duration of 151:40:12 (average episode duration 0:07:53).
<P>
Samples of the LTST DB are available
<A NAME="tex2html1"
HREF="footnode.html#foot234"><SUP>1</SUP></A>,
and the entire database has been published on DVD-ROMs and CD-ROMs
<A NAME="tex2html2"
HREF="footnode.html#foot551"><SUP>2</SUP></A>.
The database also includes a subset of utility files containing diagnostic and morphology
feature-vector time series used during annotating. These files are in text format and
include ST level, ST reference and ST deviation functions of the records, and time series
of ST segment and QRS complex KLT feature vectors. The S<SMALL>EMIA</SMALL> annotation tool,
version 3.0.1, that permits the viewing and examination of feature-vector time series
and database annotations is a part of the database and is available
<A NAME="tex2html3"
HREF="footnode.html#foot237"><SUP>3</SUP></A>.
<BR>
<P>
<DIV ALIGN="LEFT">
<FONT SIZE="+2"><B>4 Discussion</B></FONT>
</DIV>
<P>
Transient myocardial ischaemia is an important clinical problem, and it has been
demonstrated that much of it may be asymptomatic, but detectable using the ECG.
AECG recording therefore has a role in the diagnosis and follow-up of at-risk
patients. Automated systems are needed accurately to quantitate ischaemia in AECG
recordings. However, such systems are difficult to design, because of the many
non-ischaemic ST events and artifacts that are present in real-world ECG data.
There is also a need for tools to evaluate the performance of devices that claim
to detect transient ischaemia. The long-term ST database described in this paper
will provide a critically important research resource for algorithm developers
and will also make it possible to evaluate detector performance in a reproducible
manner.
<P>
The development of this database was complex, resource intensive, time consuming
and painstaking. The project benefited from the expertise, resources and experience
of the research groups and drew upon experiences obtained during the development of
the previous MIT-BIH, AHA and ESC databases. The semi-automatic interactive graphic
tools were critical to the success of the project. They supported paperless work and
facilitated international co-operation via the Internet. Reviewing and correcting the
annotations after their automatic derivation, instead of fully manually annotating,
proved to be much faster and more convenient for human experts.
<P>
It is important to emphasize that the LTST DB is not intended as a replacement for
the ESC database
<A NAME="tex2html4"
HREF="footnode.html#foot552"><SUP>4</SUP></A>,
or MIT-BIH
<A NAME="tex2html5"
HREF="footnode.html#foot553"><SUP>5</SUP></A>or AHA databases
<A NAME="tex2html6"
HREF="footnode.html#foot554"><SUP>6</SUP></A>.
Its goals are different.
The LTST DB fills a gap in the scope of previously published databases. The MIT-BIH
<A NAME="tex2html7"
HREF="footnode.html#foot555"><SUP>7</SUP></A>and AHA
<A NAME="tex2html8"
HREF="footnode.html#foot245"><SUP>8</SUP></A>databases are intended for evaluating arrhythmia and ventricular arrhythmia detectors.
The ESC DB
<A NAME="tex2html9"
HREF="footnode.html#foot556"><SUP>9</SUP></A>contains 2 h ambulatory records and is annotated beat-by-beat in terms of QRS onset,
beat type, arrhythmias and ST segment and T-wave changes. It is intended for evaluating
detectors of transient ST segment and T-wave changes, as well as for testing QRS detectors
in the presence of ST-T abnormalities.
<P>
The LTST DB contains long-term ambulatory records and ST segment measurements obtained
on average waveforms. What we hoped to accomplish was to represent better the wide variety
of real-world data, including many examples of ischaemic and mixtures of non-ischaemic ST
events. The LTST DB will support the development and evaluation of the performance of
algorithms to detect transient ischaemic and non-ischaemic ST segment changes. It will
also support researchers studying lengthy examples of quasi-periodic and other temporal
patterns of ST change and enable basic studies in the dynamics of mechanisms responsible
for ischaemia.
<BR>
<P>
<FONT SIZE="+1"><EM>Acknowledgements -</EM></FONT> The authors wish to thank Robert Stadler, PhD, Shannon
Nelson, BSc, and Lee Stylos, PhD, from Medtronic, Inc., in Mineapolis, and Dirk Feild,
PhD, from Zymed, Inc., in Camarrilo (now at the Philips Medical Systems in Oxnard), for
their sincere interest in this project and financial support. They wish to thank Dirk Feild,
PhD, also for contributing the three-channel records. They are particularly indebted to
Peter Stone, MD, and Gail McCallum for their assistance in accessing a number of Holter
recordings from the ACIP Core Laboratory at the Brigham and Womens Hospital in Boston.
The authors thank Diane Perry at the Beth Israel Deaconess Medical Center in Boston for
digitising the records and editing individual QRS annotations, and Sharon Stevens at the
Philips Medical Systems in Oxnard for editing individual QRS annotations as well. They
thank Isaac Henry, MSc, from the Beth Israel Deaconess Medical Center in Boston, for
managing QRS annotation files, and further thank many of those who contributed to the
project: Wei Zong, PhD, and Ramakrishna Mukamala, PhD, from the Massachusetts Institute
of Technology, in Cambridge; Maurizio Varanini, BSc, and Simone Bordigiago, BSc, from the
Institute of Clinical Physiology, in Pisa; and Boris Glavic, BSc, Mitja Zabukovec, BSc,
and Maja Škrjanc, BSc, from the Faculty of Computer and Information Science in Ljubljana.
<BR>
<P>
<DIV ALIGN="LEFT">
<FONT SIZE="+2"><B>References</B></FONT>
</DIV>
<BR>
<BR> <HR>
<!--Table of Child-Links-->
<A NAME="CHILD_LINKS"> </A>
<UL>
<LI><A NAME="tex2html19"
HREF="node1.html">Bibliography</A>
</UL>
<!--End of Table of Child-Links-->
<HR>
<A NAME="tex2html17"
HREF="node1.html">
<IMG WIDTH="37" HEIGHT="24" ALIGN="BOTTOM" BORDER="0" ALT="next" SRC="next.png"></A>
<IMG WIDTH="26" HEIGHT="24" ALIGN="BOTTOM" BORDER="0" ALT="up" SRC="up_gr.png">
<IMG WIDTH="63" HEIGHT="24" ALIGN="BOTTOM" BORDER="0" ALT="previous" SRC="prev_gr.png"> <BR>
<B> Next:</B> <A NAME="tex2html18"
HREF="node1.html">Bibliography</A>
<!--End of Navigation Panel-->
<hr>
<!--#include virtual="/footer.shtml" -->
</BODY>
</HTML>