Use of statistical classifiers as support tools for the diagnosis of iron-deficiency anemia in patients on chronic hemodialysis

P. Baiardi, V. Piazza, G. Montagna, M. C. Mazzoleni

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Discriminant analysis, logistic regression and neural network models were applied to the diagnosis of iron-deficiency anemia in hemodialyzed patients. The ability of the three quantitative approaches to distinguish between subjects suffering or not from iron-deficiency anemia was compared by re-substitution and cross-validation testing. Methods performance was evaluated by means of sensitivity, specificity and accuracy. All the methods performed globally well (sensitivity and specificity>0.85), revealing that the problem is classifiable. Neural networks showed the highest accuracy, both in the re-substitution (models developed and tested on the complete data set) and 3-way cross-validation (data set randomly splitted into 3 developmental and validation data sets) testing. These preliminary results suggest that the correct classification of iron status in the hemodialytic population can be treated as a pattern classification problem, for which neural networks and traditional statistical modelling can be a valuable aid to the clinical diagnosis of iron-deficiency anemia. A better performance of the neural network model must be confirmed through prospective testing on a larger data set.

Original languageEnglish
Title of host publicationStudies in Health Technology and Informatics
Pages666-670
Number of pages5
Volume43
DOIs
Publication statusPublished - 1997
Event14th Conference on Medical Informatics Europe 1997, MIE 1997 - Thessaloniki, Greece
Duration: May 25 1997May 29 1997

Other

Other14th Conference on Medical Informatics Europe 1997, MIE 1997
CountryGreece
CityThessaloniki
Period5/25/975/29/97

Fingerprint

Iron-Deficiency Anemias
Renal Dialysis
Classifiers
Iron
Neural networks
Neural Networks (Computer)
Testing
Substitution reactions
Sensitivity and Specificity
Discriminant Analysis
Discriminant analysis
Pattern recognition
Logistics
Logistic Models
Datasets
Population

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics
  • Health Information Management

Cite this

Baiardi, P., Piazza, V., Montagna, G., & Mazzoleni, M. C. (1997). Use of statistical classifiers as support tools for the diagnosis of iron-deficiency anemia in patients on chronic hemodialysis. In Studies in Health Technology and Informatics (Vol. 43, pp. 666-670) https://doi.org/10.3233/978-1-60750-887-8-666

Use of statistical classifiers as support tools for the diagnosis of iron-deficiency anemia in patients on chronic hemodialysis. / Baiardi, P.; Piazza, V.; Montagna, G.; Mazzoleni, M. C.

Studies in Health Technology and Informatics. Vol. 43 1997. p. 666-670.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Baiardi, P, Piazza, V, Montagna, G & Mazzoleni, MC 1997, Use of statistical classifiers as support tools for the diagnosis of iron-deficiency anemia in patients on chronic hemodialysis. in Studies in Health Technology and Informatics. vol. 43, pp. 666-670, 14th Conference on Medical Informatics Europe 1997, MIE 1997, Thessaloniki, Greece, 5/25/97. https://doi.org/10.3233/978-1-60750-887-8-666
Baiardi, P. ; Piazza, V. ; Montagna, G. ; Mazzoleni, M. C. / Use of statistical classifiers as support tools for the diagnosis of iron-deficiency anemia in patients on chronic hemodialysis. Studies in Health Technology and Informatics. Vol. 43 1997. pp. 666-670
@inproceedings{f1c7c9ed858f4eb590a945c4dc5cf8be,
title = "Use of statistical classifiers as support tools for the diagnosis of iron-deficiency anemia in patients on chronic hemodialysis",
abstract = "Discriminant analysis, logistic regression and neural network models were applied to the diagnosis of iron-deficiency anemia in hemodialyzed patients. The ability of the three quantitative approaches to distinguish between subjects suffering or not from iron-deficiency anemia was compared by re-substitution and cross-validation testing. Methods performance was evaluated by means of sensitivity, specificity and accuracy. All the methods performed globally well (sensitivity and specificity>0.85), revealing that the problem is classifiable. Neural networks showed the highest accuracy, both in the re-substitution (models developed and tested on the complete data set) and 3-way cross-validation (data set randomly splitted into 3 developmental and validation data sets) testing. These preliminary results suggest that the correct classification of iron status in the hemodialytic population can be treated as a pattern classification problem, for which neural networks and traditional statistical modelling can be a valuable aid to the clinical diagnosis of iron-deficiency anemia. A better performance of the neural network model must be confirmed through prospective testing on a larger data set.",
author = "P. Baiardi and V. Piazza and G. Montagna and Mazzoleni, {M. C.}",
year = "1997",
doi = "10.3233/978-1-60750-887-8-666",
language = "English",
isbn = "9051993439",
volume = "43",
pages = "666--670",
booktitle = "Studies in Health Technology and Informatics",

}

TY - GEN

T1 - Use of statistical classifiers as support tools for the diagnosis of iron-deficiency anemia in patients on chronic hemodialysis

AU - Baiardi, P.

AU - Piazza, V.

AU - Montagna, G.

AU - Mazzoleni, M. C.

PY - 1997

Y1 - 1997

N2 - Discriminant analysis, logistic regression and neural network models were applied to the diagnosis of iron-deficiency anemia in hemodialyzed patients. The ability of the three quantitative approaches to distinguish between subjects suffering or not from iron-deficiency anemia was compared by re-substitution and cross-validation testing. Methods performance was evaluated by means of sensitivity, specificity and accuracy. All the methods performed globally well (sensitivity and specificity>0.85), revealing that the problem is classifiable. Neural networks showed the highest accuracy, both in the re-substitution (models developed and tested on the complete data set) and 3-way cross-validation (data set randomly splitted into 3 developmental and validation data sets) testing. These preliminary results suggest that the correct classification of iron status in the hemodialytic population can be treated as a pattern classification problem, for which neural networks and traditional statistical modelling can be a valuable aid to the clinical diagnosis of iron-deficiency anemia. A better performance of the neural network model must be confirmed through prospective testing on a larger data set.

AB - Discriminant analysis, logistic regression and neural network models were applied to the diagnosis of iron-deficiency anemia in hemodialyzed patients. The ability of the three quantitative approaches to distinguish between subjects suffering or not from iron-deficiency anemia was compared by re-substitution and cross-validation testing. Methods performance was evaluated by means of sensitivity, specificity and accuracy. All the methods performed globally well (sensitivity and specificity>0.85), revealing that the problem is classifiable. Neural networks showed the highest accuracy, both in the re-substitution (models developed and tested on the complete data set) and 3-way cross-validation (data set randomly splitted into 3 developmental and validation data sets) testing. These preliminary results suggest that the correct classification of iron status in the hemodialytic population can be treated as a pattern classification problem, for which neural networks and traditional statistical modelling can be a valuable aid to the clinical diagnosis of iron-deficiency anemia. A better performance of the neural network model must be confirmed through prospective testing on a larger data set.

UR - http://www.scopus.com/inward/record.url?scp=0031319264&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031319264&partnerID=8YFLogxK

U2 - 10.3233/978-1-60750-887-8-666

DO - 10.3233/978-1-60750-887-8-666

M3 - Conference contribution

C2 - 1998125844

AN - SCOPUS:0031319264

SN - 9051993439

SN - 9789051993431

VL - 43

SP - 666

EP - 670

BT - Studies in Health Technology and Informatics

ER -