TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Automatic classification of IgA endomysial antibody test for celiac disease: a new method deploying machine learning

Tutkimustuotosvertaisarvioitu

Standard

Automatic classification of IgA endomysial antibody test for celiac disease : a new method deploying machine learning. / Caetano dos Santos, Florentino Luciano; Michalek, Irmina Maria; Laurila, Kaija; Kaukinen, Katri; Hyttinen, Jari; Lindfors, Katri.

julkaisussa: Scientific Reports, Vuosikerta 9, Nro 1, 9217, 01.12.2019.

Tutkimustuotosvertaisarvioitu

Harvard

Caetano dos Santos, FL, Michalek, IM, Laurila, K, Kaukinen, K, Hyttinen, J & Lindfors, K 2019, 'Automatic classification of IgA endomysial antibody test for celiac disease: a new method deploying machine learning' Scientific Reports, Vuosikerta. 9, Nro 1, 9217. https://doi.org/10.1038/s41598-019-45679-x

APA

Caetano dos Santos, F. L., Michalek, I. M., Laurila, K., Kaukinen, K., Hyttinen, J., & Lindfors, K. (2019). Automatic classification of IgA endomysial antibody test for celiac disease: a new method deploying machine learning. Scientific Reports, 9(1), [9217]. https://doi.org/10.1038/s41598-019-45679-x

Vancouver

Caetano dos Santos FL, Michalek IM, Laurila K, Kaukinen K, Hyttinen J, Lindfors K. Automatic classification of IgA endomysial antibody test for celiac disease: a new method deploying machine learning. Scientific Reports. 2019 joulu 1;9(1). 9217. https://doi.org/10.1038/s41598-019-45679-x

Author

Caetano dos Santos, Florentino Luciano ; Michalek, Irmina Maria ; Laurila, Kaija ; Kaukinen, Katri ; Hyttinen, Jari ; Lindfors, Katri. / Automatic classification of IgA endomysial antibody test for celiac disease : a new method deploying machine learning. Julkaisussa: Scientific Reports. 2019 ; Vuosikerta 9, Nro 1.

Bibtex - Lataa

@article{9fec09af89b64c35812c44cebf630443,
title = "Automatic classification of IgA endomysial antibody test for celiac disease: a new method deploying machine learning",
abstract = "Widespread use of endomysial autoantibody (EmA) test in diagnostics of celiac disease is limited due to its subjectivity and its requirement of an expert evaluator. The study aimed to determine whether machine learning can be applied to create a new observer-independent method of automatic assessment and classification of the EmA test for celiac disease. The study material comprised of 2597 high-quality IgA-class EmA images collected in 2017–2018. According to standard procedure, highly-experienced professional classified samples into the following four classes: I - positive, II - negative, III - IgA deficient, and IV - equivocal. Machine learning was deployed to create a classification model. The sensitivity and specificity of the model were 82.84{\%} and 99.40{\%}, respectively. The accuracy was 96.80{\%}. The classification error was 3.20{\%}. The area under the curve was 99.67{\%}, 99.61{\%}, 100{\%}, and 99.89{\%}, for I, II, III, and IV class, respectively. The mean assessment time per image was 16.11 seconds. This is the first study deploying machine learning for the automatic classification of IgA-class EmA test for celiac disease. The results indicate that using machine learning enables quick and precise EmA test analysis that can be further developed to simplify EmA analysis.",
author = "{Caetano dos Santos}, {Florentino Luciano} and Michalek, {Irmina Maria} and Kaija Laurila and Katri Kaukinen and Jari Hyttinen and Katri Lindfors",
year = "2019",
month = "12",
day = "1",
doi = "10.1038/s41598-019-45679-x",
language = "English",
volume = "9",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",
number = "1",

}

RIS (suitable for import to EndNote) - Lataa

TY - JOUR

T1 - Automatic classification of IgA endomysial antibody test for celiac disease

T2 - a new method deploying machine learning

AU - Caetano dos Santos, Florentino Luciano

AU - Michalek, Irmina Maria

AU - Laurila, Kaija

AU - Kaukinen, Katri

AU - Hyttinen, Jari

AU - Lindfors, Katri

PY - 2019/12/1

Y1 - 2019/12/1

N2 - Widespread use of endomysial autoantibody (EmA) test in diagnostics of celiac disease is limited due to its subjectivity and its requirement of an expert evaluator. The study aimed to determine whether machine learning can be applied to create a new observer-independent method of automatic assessment and classification of the EmA test for celiac disease. The study material comprised of 2597 high-quality IgA-class EmA images collected in 2017–2018. According to standard procedure, highly-experienced professional classified samples into the following four classes: I - positive, II - negative, III - IgA deficient, and IV - equivocal. Machine learning was deployed to create a classification model. The sensitivity and specificity of the model were 82.84% and 99.40%, respectively. The accuracy was 96.80%. The classification error was 3.20%. The area under the curve was 99.67%, 99.61%, 100%, and 99.89%, for I, II, III, and IV class, respectively. The mean assessment time per image was 16.11 seconds. This is the first study deploying machine learning for the automatic classification of IgA-class EmA test for celiac disease. The results indicate that using machine learning enables quick and precise EmA test analysis that can be further developed to simplify EmA analysis.

AB - Widespread use of endomysial autoantibody (EmA) test in diagnostics of celiac disease is limited due to its subjectivity and its requirement of an expert evaluator. The study aimed to determine whether machine learning can be applied to create a new observer-independent method of automatic assessment and classification of the EmA test for celiac disease. The study material comprised of 2597 high-quality IgA-class EmA images collected in 2017–2018. According to standard procedure, highly-experienced professional classified samples into the following four classes: I - positive, II - negative, III - IgA deficient, and IV - equivocal. Machine learning was deployed to create a classification model. The sensitivity and specificity of the model were 82.84% and 99.40%, respectively. The accuracy was 96.80%. The classification error was 3.20%. The area under the curve was 99.67%, 99.61%, 100%, and 99.89%, for I, II, III, and IV class, respectively. The mean assessment time per image was 16.11 seconds. This is the first study deploying machine learning for the automatic classification of IgA-class EmA test for celiac disease. The results indicate that using machine learning enables quick and precise EmA test analysis that can be further developed to simplify EmA analysis.

U2 - 10.1038/s41598-019-45679-x

DO - 10.1038/s41598-019-45679-x

M3 - Article

VL - 9

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

IS - 1

M1 - 9217

ER -