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...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | Journal of Clinical Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-0383/10/21/4971 |
| _version_ | 1797512271000240128 |
|---|---|
| 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 |
| collection | DOAJ |
| 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. |
| first_indexed | 2024-03-10T05:59:30Z |
| format | Article |
| id | doaj.art-29e8f104f6c3496fbaef6b83aca8e50d |
| institution | Directory Open Access Journal |
| issn | 2077-0383 |
| language | English |
| last_indexed | 2024-03-10T05:59:30Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Clinical Medicine |
| spelling | doaj.art-29e8f104f6c3496fbaef6b83aca8e50d2023-11-22T21:05:26ZengMDPI AGJournal of Clinical Medicine2077-03832021-10-011021497110.3390/jcm10214971Machine Learning Refutes Loss of Smell as a Risk Indicator of Diabetes MellitusJörn Lötsch0Antje Hähner1Peter E. H. Schwarz2Sergey Tselmin3Thomas Hummel4Institute of Clinical Pharmacology, Goethe University, Theodor Stern Kai 7, 60590 Frankfurt am Main, GermanySmell & Taste Clinic, Department of Otorhinolaryngology, Technische Universität Dresden, Fetscherstrasse 74, 01307 Dresden, GermanyDepartment of Internal Medicine III, Technische Universität Dresden, Fetscherstrasse 74, 01307 Dresden, GermanyDepartment of Internal Medicine III, Technische Universität Dresden, Fetscherstrasse 74, 01307 Dresden, GermanySmell & Taste Clinic, Department of Otorhinolaryngology, Technische Universität Dresden, Fetscherstrasse 74, 01307 Dresden, GermanyBecause 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.https://www.mdpi.com/2077-0383/10/21/4971human olfactiondiabetes mellitusmachine-learningdata sciencepatients |
| spellingShingle | 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 Journal of Clinical Medicine human olfaction diabetes mellitus machine-learning data science patients |
| title | 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_short | 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 |
| topic | human olfaction diabetes mellitus machine-learning data science patients |
| url | https://www.mdpi.com/2077-0383/10/21/4971 |
| work_keys_str_mv | AT jornlotsch machinelearningrefuteslossofsmellasariskindicatorofdiabetesmellitus AT antjehahner machinelearningrefuteslossofsmellasariskindicatorofdiabetesmellitus AT peterehschwarz machinelearningrefuteslossofsmellasariskindicatorofdiabetesmellitus AT sergeytselmin machinelearningrefuteslossofsmellasariskindicatorofdiabetesmellitus AT thomashummel machinelearningrefuteslossofsmellasariskindicatorofdiabetesmellitus |