Building the IMPROVE data library

Ilkka Korhonen; Jyrki Ojaniemi; Kari Nieminen; Mark van Gils; Arno Heikelä; Aarno Kari

doi:10.1109/51.637114

Building the IMPROVE data library

Ilkka Korhonen, Jyrki Ojaniemi, Kari Nieminen, Mark van Gils, Arno Heikelä, Aarno Kari

VTT Technical Research Centre of Finland

Research output: Contribution to journal › Article › Scientific › peer-review

31 Citations (Scopus)

Abstract

Well-characterized and comprehensive test data sets are essential in the development and evaluation of biosignal interpretation methods for intensive-care patient monitoring. The IMPROVE (IMPROVing control of patient status in critical carE) data library is an annotated data library that contains practically all the monitored and other clinical data from critically ill patients at high risk of oxygen-transport-related problems. The data, collected at the Intensive Care Unit of the Kuopio University Hospital, is supported by continuous patient-state assessments carried out by a bedside physician and includes 59 patient records, each having a typical duration of 24 hours. In this article, we describe the technical setup of the system, including what signals and parameters were collected and how the annotations were done. We also discuss the lessons learned from the data collection process.

Original language	English
Pages (from-to)	25-32
Journal	IEEE Engineering in Medicine and Biology Magazine
Volume	16
Issue number	6
DOIs	https://doi.org/10.1109/51.637114
Publication status	Published - 1997
MoE publication type	A1 Journal article-refereed

Access to Document

10.1109/51.637114

Cite this

@article{6dde6bc3debf4a7a84f35cba994d101b,

title = "Building the IMPROVE data library",

abstract = "Well-characterized and comprehensive test data sets are essential in the development and evaluation of biosignal interpretation methods for intensive-care patient monitoring. The IMPROVE (IMPROVing control of patient status in critical carE) data library is an annotated data library that contains practically all the monitored and other clinical data from critically ill patients at high risk of oxygen-transport-related problems. The data, collected at the Intensive Care Unit of the Kuopio University Hospital, is supported by continuous patient-state assessments carried out by a bedside physician and includes 59 patient records, each having a typical duration of 24 hours. In this article, we describe the technical setup of the system, including what signals and parameters were collected and how the annotations were done. We also discuss the lessons learned from the data collection process.",

author = "Ilkka Korhonen and Jyrki Ojaniemi and Kari Nieminen and {van Gils}, Mark and Arno Heikel{\"a} and Aarno Kari",

note = "Project code: T5SU00254",

year = "1997",

doi = "10.1109/51.637114",

language = "English",

volume = "16",

pages = "25--32",

journal = "IEEE Pulse",

issn = "2154-2287",

publisher = "IEEE Institute of Electrical and Electronic Engineers",

number = "6",

}

TY - JOUR

T1 - Building the IMPROVE data library

AU - Korhonen, Ilkka

AU - Ojaniemi, Jyrki

AU - Nieminen, Kari

AU - van Gils, Mark

AU - Heikelä, Arno

AU - Kari, Aarno

N1 - Project code: T5SU00254

PY - 1997

Y1 - 1997

N2 - Well-characterized and comprehensive test data sets are essential in the development and evaluation of biosignal interpretation methods for intensive-care patient monitoring. The IMPROVE (IMPROVing control of patient status in critical carE) data library is an annotated data library that contains practically all the monitored and other clinical data from critically ill patients at high risk of oxygen-transport-related problems. The data, collected at the Intensive Care Unit of the Kuopio University Hospital, is supported by continuous patient-state assessments carried out by a bedside physician and includes 59 patient records, each having a typical duration of 24 hours. In this article, we describe the technical setup of the system, including what signals and parameters were collected and how the annotations were done. We also discuss the lessons learned from the data collection process.

AB - Well-characterized and comprehensive test data sets are essential in the development and evaluation of biosignal interpretation methods for intensive-care patient monitoring. The IMPROVE (IMPROVing control of patient status in critical carE) data library is an annotated data library that contains practically all the monitored and other clinical data from critically ill patients at high risk of oxygen-transport-related problems. The data, collected at the Intensive Care Unit of the Kuopio University Hospital, is supported by continuous patient-state assessments carried out by a bedside physician and includes 59 patient records, each having a typical duration of 24 hours. In this article, we describe the technical setup of the system, including what signals and parameters were collected and how the annotations were done. We also discuss the lessons learned from the data collection process.

U2 - 10.1109/51.637114

DO - 10.1109/51.637114

M3 - Article

SN - 2154-2287

VL - 16

SP - 25

EP - 32

JO - IEEE Pulse

JF - IEEE Pulse

IS - 6

ER -

Building the IMPROVE data library

Abstract

Access to Document

Fingerprint

Cite this