Supervised Machine Learning for Predicting Carbohydrate Malabsorptions Using Hydrogen Breath Tests
Introduction: Carbohydrate malabsorptions symptoms include intestinal fluid retention, causing diarrhea and abdominal distention. The aim of this work is to create a machine learning model that predicts carbohydrate malabsorption using H2 measurements from lactose and fructose tolerance tests. Metho...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
De Gruyter
2022-09-01
|
| Series: | Current Directions in Biomedical Engineering |
| Subjects: | |
| Online Access: | https://doi.org/10.1515/cdbme-2022-1073 |
| _version_ | 1797947906800484352 |
|---|---|
| author | Netzer Michael Hanser Friedrich Ledochowski Maximilian Baumgarten Daniel |
| author_facet | Netzer Michael Hanser Friedrich Ledochowski Maximilian Baumgarten Daniel |
| author_sort | Netzer Michael |
| collection | DOAJ |
| description | Introduction: Carbohydrate malabsorptions symptoms include intestinal fluid retention, causing diarrhea and abdominal distention. The aim of this work is to create a machine learning model that predicts carbohydrate malabsorption using H2 measurements from lactose and fructose tolerance tests. Methods: We compare the predictive ability of popular classifiers with classifiers that are specifically designed for time series data. Our approach was implemented using sklearn and sktime Python machine learning libraries. Results: The highest predictive ability for the fructose dataset was achieved using a Random Forest Classifier (balanced accuracy = 0.91). In contrast, the highest predictive ability (balanced accuracy = 0.81) for the lactose dataset was obtained using an IndividualTDE time classifier. Conclusion: Our results indicate a high predictive ability for distinguishing between carbohydrate malabsorptions. However, the detection of SIBO is challenging but adapted time classifier models could reach higher performances compared to standard methods. Our results could establish the basis of an expert system for diagnosing carbohydrate malabsorptions and SIBO, respectively. |
| first_indexed | 2024-04-10T21:33:56Z |
| format | Article |
| id | doaj.art-9cc090319b7845c98a3b860f2d7eefb6 |
| institution | Directory Open Access Journal |
| issn | 2364-5504 |
| language | English |
| last_indexed | 2024-04-10T21:33:56Z |
| publishDate | 2022-09-01 |
| publisher | De Gruyter |
| record_format | Article |
| series | Current Directions in Biomedical Engineering |
| spelling | doaj.art-9cc090319b7845c98a3b860f2d7eefb62023-01-19T12:47:02ZengDe GruyterCurrent Directions in Biomedical Engineering2364-55042022-09-018228528810.1515/cdbme-2022-1073Supervised Machine Learning for Predicting Carbohydrate Malabsorptions Using Hydrogen Breath TestsNetzer Michael0Hanser Friedrich1Ledochowski Maximilian2Baumgarten Daniel3Institute of Electrical and Biomedical Engineering, UMIT – Private University for Health Sciences, Medical Informatics and Technology,Hall in Tirol, AustriaInstitute of Electrical and Biomedical Engineering, UMIT - Private University for Health Sciences, Medical Informatics and Technology,Hall in Tirol, AustriaAkademie fur Ernahrungsmedizin,Innsbruck, AustriaInstitute of Electrical and Biomedical Engineering, UMIT - Private University for Health Sciences, Medical Informatics and Technology,Hall in Tirol, AustriaIntroduction: Carbohydrate malabsorptions symptoms include intestinal fluid retention, causing diarrhea and abdominal distention. The aim of this work is to create a machine learning model that predicts carbohydrate malabsorption using H2 measurements from lactose and fructose tolerance tests. Methods: We compare the predictive ability of popular classifiers with classifiers that are specifically designed for time series data. Our approach was implemented using sklearn and sktime Python machine learning libraries. Results: The highest predictive ability for the fructose dataset was achieved using a Random Forest Classifier (balanced accuracy = 0.91). In contrast, the highest predictive ability (balanced accuracy = 0.81) for the lactose dataset was obtained using an IndividualTDE time classifier. Conclusion: Our results indicate a high predictive ability for distinguishing between carbohydrate malabsorptions. However, the detection of SIBO is challenging but adapted time classifier models could reach higher performances compared to standard methods. Our results could establish the basis of an expert system for diagnosing carbohydrate malabsorptions and SIBO, respectively.https://doi.org/10.1515/cdbme-2022-1073carbohydrate malabsorptionshydrogen breath testssupervised machine learningtime classifier |
| spellingShingle | Netzer Michael Hanser Friedrich Ledochowski Maximilian Baumgarten Daniel Supervised Machine Learning for Predicting Carbohydrate Malabsorptions Using Hydrogen Breath Tests Current Directions in Biomedical Engineering carbohydrate malabsorptions hydrogen breath tests supervised machine learning time classifier |
| title | Supervised Machine Learning for Predicting Carbohydrate Malabsorptions Using Hydrogen Breath Tests |
| title_full | Supervised Machine Learning for Predicting Carbohydrate Malabsorptions Using Hydrogen Breath Tests |
| title_fullStr | Supervised Machine Learning for Predicting Carbohydrate Malabsorptions Using Hydrogen Breath Tests |
| title_full_unstemmed | Supervised Machine Learning for Predicting Carbohydrate Malabsorptions Using Hydrogen Breath Tests |
| title_short | Supervised Machine Learning for Predicting Carbohydrate Malabsorptions Using Hydrogen Breath Tests |
| title_sort | supervised machine learning for predicting carbohydrate malabsorptions using hydrogen breath tests |
| topic | carbohydrate malabsorptions hydrogen breath tests supervised machine learning time classifier |
| url | https://doi.org/10.1515/cdbme-2022-1073 |
| work_keys_str_mv | AT netzermichael supervisedmachinelearningforpredictingcarbohydratemalabsorptionsusinghydrogenbreathtests AT hanserfriedrich supervisedmachinelearningforpredictingcarbohydratemalabsorptionsusinghydrogenbreathtests AT ledochowskimaximilian supervisedmachinelearningforpredictingcarbohydratemalabsorptionsusinghydrogenbreathtests AT baumgartendaniel supervisedmachinelearningforpredictingcarbohydratemalabsorptionsusinghydrogenbreathtests |