Machine Learning Refutes Loss of Smell as a Risk Indicator of Diabetes Mellitus

Because it is associated with central nervous changes, and olfactory dysfunction has been reported with increased prevalence among persons with diabetes, this study addressed the question of whether the risk of developing diabetes in the next 10 years is reflected in olfactory symptoms. In a cross-s...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jörn Lötsch, Antje Hähner, Peter E. H. Schwarz, Sergey Tselmin, Thomas Hummel
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	human olfaction diabetes mellitus machine-learning data science patients Medicine R
Acceso en línea:	https://doaj.org/article/29e8f104f6c3496fbaef6b83aca8e50d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:29e8f104f6c3496fbaef6b83aca8e50d
record_format	dspace
spelling	oai:doaj.org-article:29e8f104f6c3496fbaef6b83aca8e50d2021-11-11T17:36:19ZMachine Learning Refutes Loss of Smell as a Risk Indicator of Diabetes Mellitus10.3390/jcm102149712077-0383https://doaj.org/article/29e8f104f6c3496fbaef6b83aca8e50d2021-10-01T00:00:00Zhttps://www.mdpi.com/2077-0383/10/21/4971https://doaj.org/toc/2077-0383Because it is associated with central nervous changes, and olfactory dysfunction has been reported with increased prevalence among persons with diabetes, this study addressed the question of whether the risk of developing diabetes in the next 10 years is reflected in olfactory symptoms. In a cross-sectional study, in 164 individuals seeking medical consulting for possible diabetes, olfactory function was evaluated using a standardized clinical test assessing olfactory threshold, odor discrimination, and odor identification. Metabolomics parameters were assessed via blood concentrations. The individual diabetes risk was quantified according to the validated German version of the “FINDRISK” diabetes risk score. Machine learning algorithms trained with metabolomics patterns predicted low or high diabetes risk with a balanced accuracy of 63–75%. Similarly, olfactory subtest results predicted the olfactory dysfunction category with a balanced accuracy of 85–94%, occasionally reaching 100%. However, olfactory subtest results failed to improve the prediction of diabetes risk based on metabolomics data, and metabolomics data did not improve the prediction of the olfactory dysfunction category based on olfactory subtest results. Results of the present study suggest that olfactory function is not a useful predictor of diabetes.Jörn LötschAntje HähnerPeter E. H. SchwarzSergey TselminThomas HummelMDPI AGarticlehuman olfactiondiabetes mellitusmachine-learningdata sciencepatientsMedicineRENJournal of Clinical Medicine, Vol 10, Iss 4971, p 4971 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	human olfaction diabetes mellitus machine-learning data science patients Medicine R
spellingShingle	human olfaction diabetes mellitus machine-learning data science patients Medicine R Jörn Lötsch Antje Hähner Peter E. H. Schwarz Sergey Tselmin Thomas Hummel Machine Learning Refutes Loss of Smell as a Risk Indicator of Diabetes Mellitus
description	Because it is associated with central nervous changes, and olfactory dysfunction has been reported with increased prevalence among persons with diabetes, this study addressed the question of whether the risk of developing diabetes in the next 10 years is reflected in olfactory symptoms. In a cross-sectional study, in 164 individuals seeking medical consulting for possible diabetes, olfactory function was evaluated using a standardized clinical test assessing olfactory threshold, odor discrimination, and odor identification. Metabolomics parameters were assessed via blood concentrations. The individual diabetes risk was quantified according to the validated German version of the “FINDRISK” diabetes risk score. Machine learning algorithms trained with metabolomics patterns predicted low or high diabetes risk with a balanced accuracy of 63–75%. Similarly, olfactory subtest results predicted the olfactory dysfunction category with a balanced accuracy of 85–94%, occasionally reaching 100%. However, olfactory subtest results failed to improve the prediction of diabetes risk based on metabolomics data, and metabolomics data did not improve the prediction of the olfactory dysfunction category based on olfactory subtest results. Results of the present study suggest that olfactory function is not a useful predictor of diabetes.
format	article
author	Jörn Lötsch Antje Hähner Peter E. H. Schwarz Sergey Tselmin Thomas Hummel
author_facet	Jörn Lötsch Antje Hähner Peter E. H. Schwarz Sergey Tselmin Thomas Hummel
author_sort	Jörn Lötsch
title	Machine Learning Refutes Loss of Smell as a Risk Indicator of Diabetes Mellitus
title_short	Machine Learning Refutes Loss of Smell as a Risk Indicator of Diabetes Mellitus
title_full	Machine Learning Refutes Loss of Smell as a Risk Indicator of Diabetes Mellitus
title_fullStr	Machine Learning Refutes Loss of Smell as a Risk Indicator of Diabetes Mellitus
title_full_unstemmed	Machine Learning Refutes Loss of Smell as a Risk Indicator of Diabetes Mellitus
title_sort	machine learning refutes loss of smell as a risk indicator of diabetes mellitus
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/29e8f104f6c3496fbaef6b83aca8e50d
work_keys_str_mv	AT jornlotsch machinelearningrefuteslossofsmellasariskindicatorofdiabetesmellitus AT antjehahner machinelearningrefuteslossofsmellasariskindicatorofdiabetesmellitus AT peterehschwarz machinelearningrefuteslossofsmellasariskindicatorofdiabetesmellitus AT sergeytselmin machinelearningrefuteslossofsmellasariskindicatorofdiabetesmellitus AT thomashummel machinelearningrefuteslossofsmellasariskindicatorofdiabetesmellitus
_version_	1718432052216332288

Machine Learning Refutes Loss of Smell as a Risk Indicator of Diabetes Mellitus

Ejemplares similares