An application of machine learning to haematological diagnosis

Abstract Quick and accurate medical diagnoses are crucial for the successful treatment of diseases. Using machine learning algorithms and based on laboratory blood test results, we have built two models to predict a haematologic disease. One predictive model used all the available blood test paramet...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Gregor Gunčar, Matjaž Kukar, Mateja Notar, Miran Brvar, Peter Černelč, Manca Notar, Marko Notar
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2018
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/6ce1c80be791462db5395b7bfc94e092
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:6ce1c80be791462db5395b7bfc94e092
record_format	dspace
spelling	oai:doaj.org-article:6ce1c80be791462db5395b7bfc94e0922021-12-02T15:09:11ZAn application of machine learning to haematological diagnosis10.1038/s41598-017-18564-82045-2322https://doaj.org/article/6ce1c80be791462db5395b7bfc94e0922018-01-01T00:00:00Zhttps://doi.org/10.1038/s41598-017-18564-8https://doaj.org/toc/2045-2322Abstract Quick and accurate medical diagnoses are crucial for the successful treatment of diseases. Using machine learning algorithms and based on laboratory blood test results, we have built two models to predict a haematologic disease. One predictive model used all the available blood test parameters and the other used only a reduced set that is usually measured upon patient admittance. Both models produced good results, obtaining prediction accuracies of 0.88 and 0.86 when considering the list of five most likely diseases and 0.59 and 0.57 when considering only the most likely disease. The models did not differ significantly, which indicates that a reduced set of parameters can represent a relevant “fingerprint” of a disease. This knowledge expands the model’s utility for use by general practitioners and indicates that blood test results contain more information than physicians generally recognize. A clinical test showed that the accuracy of our predictive models was on par with that of haematology specialists. Our study is the first to show that a machine learning predictive model based on blood tests alone can be successfully applied to predict haematologic diseases. This result and could open up unprecedented possibilities for medical diagnosis.Gregor GunčarMatjaž KukarMateja NotarMiran BrvarPeter ČernelčManca NotarMarko NotarNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 8, Iss 1, Pp 1-12 (2018)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Gregor Gunčar Matjaž Kukar Mateja Notar Miran Brvar Peter Černelč Manca Notar Marko Notar An application of machine learning to haematological diagnosis
description	Abstract Quick and accurate medical diagnoses are crucial for the successful treatment of diseases. Using machine learning algorithms and based on laboratory blood test results, we have built two models to predict a haematologic disease. One predictive model used all the available blood test parameters and the other used only a reduced set that is usually measured upon patient admittance. Both models produced good results, obtaining prediction accuracies of 0.88 and 0.86 when considering the list of five most likely diseases and 0.59 and 0.57 when considering only the most likely disease. The models did not differ significantly, which indicates that a reduced set of parameters can represent a relevant “fingerprint” of a disease. This knowledge expands the model’s utility for use by general practitioners and indicates that blood test results contain more information than physicians generally recognize. A clinical test showed that the accuracy of our predictive models was on par with that of haematology specialists. Our study is the first to show that a machine learning predictive model based on blood tests alone can be successfully applied to predict haematologic diseases. This result and could open up unprecedented possibilities for medical diagnosis.
format	article
author	Gregor Gunčar Matjaž Kukar Mateja Notar Miran Brvar Peter Černelč Manca Notar Marko Notar
author_facet	Gregor Gunčar Matjaž Kukar Mateja Notar Miran Brvar Peter Černelč Manca Notar Marko Notar
author_sort	Gregor Gunčar
title	An application of machine learning to haematological diagnosis
title_short	An application of machine learning to haematological diagnosis
title_full	An application of machine learning to haematological diagnosis
title_fullStr	An application of machine learning to haematological diagnosis
title_full_unstemmed	An application of machine learning to haematological diagnosis
title_sort	application of machine learning to haematological diagnosis
publisher	Nature Portfolio
publishDate	2018
url	https://doaj.org/article/6ce1c80be791462db5395b7bfc94e092
work_keys_str_mv	AT gregorguncar anapplicationofmachinelearningtohaematologicaldiagnosis AT matjazkukar anapplicationofmachinelearningtohaematologicaldiagnosis AT matejanotar anapplicationofmachinelearningtohaematologicaldiagnosis AT miranbrvar anapplicationofmachinelearningtohaematologicaldiagnosis AT petercernelc anapplicationofmachinelearningtohaematologicaldiagnosis AT mancanotar anapplicationofmachinelearningtohaematologicaldiagnosis AT markonotar anapplicationofmachinelearningtohaematologicaldiagnosis AT gregorguncar applicationofmachinelearningtohaematologicaldiagnosis AT matjazkukar applicationofmachinelearningtohaematologicaldiagnosis AT matejanotar applicationofmachinelearningtohaematologicaldiagnosis AT miranbrvar applicationofmachinelearningtohaematologicaldiagnosis AT petercernelc applicationofmachinelearningtohaematologicaldiagnosis AT mancanotar applicationofmachinelearningtohaematologicaldiagnosis AT markonotar applicationofmachinelearningtohaematologicaldiagnosis
_version_	1718387879572406272

An application of machine learning to haematological diagnosis

Ejemplares similares