GEMS: A system for automated cancer diagnosis and biomarker discovery from microarray gene expression data

Alexander Statnikov; Ioannis Tsamardinos; Yerbolat Dosbayev; Constantin F. Aliferis

doi:10.1016/j.ijmedinf.2005.05.002

GEMS: A system for automated cancer diagnosis and biomarker discovery from microarray gene expression data

Alexander Statnikov, Ioannis Tsamardinos, Yerbolat Dosbayev, Constantin F. Aliferis

Institute for Health Informatics

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

149 Scopus citations

Abstract

The success of treatment of patients with cancer depends on establishing an accurate diagnosis. To this end, we have built a system called GEMS (gene expression model selector) for the automated development and evaluation of high-quality cancer diagnostic models and biomarker discovery from microarray gene expression data. In order to determine and equip the system with the best performing diagnostic methodologies in this domain, we first conducted a comprehensive evaluation of classification algorithms using 11 cancer microarray datasets. In this paper we present a preliminary evaluation of the system with five new datasets. The performance of the models produced automatically by GEMS is comparable or better than the results obtained by human analysts. Additionally, we performed a cross-dataset evaluation of the system. This involved using a dataset to build a diagnostic model and to estimate its future performance, then applying this model and evaluating its performance on a different dataset. We found that models produced by GEMS indeed perform well in independent samples and, furthermore, the cross-validation performance estimates output by the system approximate well the error obtained by the independent validation. GEMS is freely available for download for non-commercial use from http://www.gems-system.org.

Original language	English (US)
Pages (from-to)	491-503
Number of pages	13
Journal	International Journal of Medical Informatics
Volume	74
Issue number	7-8
DOIs	https://doi.org/10.1016/j.ijmedinf.2005.05.002
State	Published - Aug 2005

Bibliographical note

Funding Information:
This research was supported by NIH grants RO1 LM007948-01 and P20 LM 007613-01. We also acknowledge all developers of the systems listed in Table 1 for access to their software. In particular, we would like to acknowledge Partek Inc. for arranging a web-conference with demonstration of their software.

Keywords

Artificial intelligence
Computer-assisted
Decision support systems
Diagnosis
Gene expression microarray analysis
Neoplasms

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Publisher link

10.1016/j.ijmedinf.2005.05.002

Find It

Find It at U of M Libraries

Cite this

@article{00e68470566445b781f0eb200eeac9c9,

title = "GEMS: A system for automated cancer diagnosis and biomarker discovery from microarray gene expression data",

abstract = "The success of treatment of patients with cancer depends on establishing an accurate diagnosis. To this end, we have built a system called GEMS (gene expression model selector) for the automated development and evaluation of high-quality cancer diagnostic models and biomarker discovery from microarray gene expression data. In order to determine and equip the system with the best performing diagnostic methodologies in this domain, we first conducted a comprehensive evaluation of classification algorithms using 11 cancer microarray datasets. In this paper we present a preliminary evaluation of the system with five new datasets. The performance of the models produced automatically by GEMS is comparable or better than the results obtained by human analysts. Additionally, we performed a cross-dataset evaluation of the system. This involved using a dataset to build a diagnostic model and to estimate its future performance, then applying this model and evaluating its performance on a different dataset. We found that models produced by GEMS indeed perform well in independent samples and, furthermore, the cross-validation performance estimates output by the system approximate well the error obtained by the independent validation. GEMS is freely available for download for non-commercial use from http://www.gems-system.org.",

keywords = "Artificial intelligence, Computer-assisted, Decision support systems, Diagnosis, Gene expression microarray analysis, Neoplasms",

author = "Alexander Statnikov and Ioannis Tsamardinos and Yerbolat Dosbayev and Aliferis, {Constantin F.}",

note = "Funding Information: This research was supported by NIH grants RO1 LM007948-01 and P20 LM 007613-01. We also acknowledge all developers of the systems listed in Table 1 for access to their software. In particular, we would like to acknowledge Partek Inc. for arranging a web-conference with demonstration of their software.",

year = "2005",

month = aug,

doi = "10.1016/j.ijmedinf.2005.05.002",

language = "English (US)",

volume = "74",

pages = "491--503",

journal = "International Journal of Medical Informatics",

issn = "1386-5056",

publisher = "Elsevier Ireland Ltd",

number = "7-8",

}

TY - JOUR

T1 - GEMS

T2 - A system for automated cancer diagnosis and biomarker discovery from microarray gene expression data

AU - Statnikov, Alexander

AU - Tsamardinos, Ioannis

AU - Dosbayev, Yerbolat

AU - Aliferis, Constantin F.

N1 - Funding Information: This research was supported by NIH grants RO1 LM007948-01 and P20 LM 007613-01. We also acknowledge all developers of the systems listed in Table 1 for access to their software. In particular, we would like to acknowledge Partek Inc. for arranging a web-conference with demonstration of their software.

PY - 2005/8

Y1 - 2005/8

N2 - The success of treatment of patients with cancer depends on establishing an accurate diagnosis. To this end, we have built a system called GEMS (gene expression model selector) for the automated development and evaluation of high-quality cancer diagnostic models and biomarker discovery from microarray gene expression data. In order to determine and equip the system with the best performing diagnostic methodologies in this domain, we first conducted a comprehensive evaluation of classification algorithms using 11 cancer microarray datasets. In this paper we present a preliminary evaluation of the system with five new datasets. The performance of the models produced automatically by GEMS is comparable or better than the results obtained by human analysts. Additionally, we performed a cross-dataset evaluation of the system. This involved using a dataset to build a diagnostic model and to estimate its future performance, then applying this model and evaluating its performance on a different dataset. We found that models produced by GEMS indeed perform well in independent samples and, furthermore, the cross-validation performance estimates output by the system approximate well the error obtained by the independent validation. GEMS is freely available for download for non-commercial use from http://www.gems-system.org.

AB - The success of treatment of patients with cancer depends on establishing an accurate diagnosis. To this end, we have built a system called GEMS (gene expression model selector) for the automated development and evaluation of high-quality cancer diagnostic models and biomarker discovery from microarray gene expression data. In order to determine and equip the system with the best performing diagnostic methodologies in this domain, we first conducted a comprehensive evaluation of classification algorithms using 11 cancer microarray datasets. In this paper we present a preliminary evaluation of the system with five new datasets. The performance of the models produced automatically by GEMS is comparable or better than the results obtained by human analysts. Additionally, we performed a cross-dataset evaluation of the system. This involved using a dataset to build a diagnostic model and to estimate its future performance, then applying this model and evaluating its performance on a different dataset. We found that models produced by GEMS indeed perform well in independent samples and, furthermore, the cross-validation performance estimates output by the system approximate well the error obtained by the independent validation. GEMS is freely available for download for non-commercial use from http://www.gems-system.org.

KW - Artificial intelligence

KW - Computer-assisted

KW - Decision support systems

KW - Diagnosis

KW - Gene expression microarray analysis

KW - Neoplasms

UR - http://www.scopus.com/inward/record.url?scp=22544475586&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=22544475586&partnerID=8YFLogxK

U2 - 10.1016/j.ijmedinf.2005.05.002

DO - 10.1016/j.ijmedinf.2005.05.002

M3 - Article

C2 - 15967710

AN - SCOPUS:22544475586

SN - 1386-5056

VL - 74

SP - 491

EP - 503

JO - International Journal of Medical Informatics

JF - International Journal of Medical Informatics

IS - 7-8

ER -

GEMS: A system for automated cancer diagnosis and biomarker discovery from microarray gene expression data

Abstract

Bibliographical note

Keywords

UN SDGs

Publisher link

Find It

Other files and links

Fingerprint

Cite this