Unraveling Functional Dysphagia: A Game-Changing Automated Machine-Learning Diagnostic Approach
(1) Background: Dysphagia affects around 16% of the US population. Diagnostic tests like X-ray barium swallow and endoscopy are used initially to diagnose the cause of dysphagia, followed by high-resolution esophageal manometry (HRM). If the above tests are normal, the patient is classified as funct...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/18/10116 |
| _version_ | 1827727344422354944 |
|---|---|
| author | Ali Zifan Junyue Lin Zihan Peng Yiqing Bo Ravinder K. Mittal |
| author_facet | Ali Zifan Junyue Lin Zihan Peng Yiqing Bo Ravinder K. Mittal |
| author_sort | Ali Zifan |
| collection | DOAJ |
| description | (1) Background: Dysphagia affects around 16% of the US population. Diagnostic tests like X-ray barium swallow and endoscopy are used initially to diagnose the cause of dysphagia, followed by high-resolution esophageal manometry (HRM). If the above tests are normal, the patient is classified as functional dysphagia (FD), suggesting esophageal sensory dysfunction. HRM records only the contraction phase of peristalsis, not the distension phase. We investigated the utilization of esophageal distension–contraction patterns for the automatic classification of FD, using artificial intelligent shallow learners. (2) Methods: Studies were performed in 30 healthy subjects and 30 patients with FD. Custom-built software (Dplots 1.0) was used to extract relevant esophageal distension–contraction features. Next, we used multiple shallow learners, namely support vector machines, random forest, K-nearest neighbors, and logistic regression, to determine which had the best performance in terms of accuracy, precision, and recall. (3) Results: In the proximal segment, LR produced the best results, with accuracy of 91.7% and precision of 92.86%, using only distension features. In the distal segment, random forest produced accuracy of 90.5% and precision of 91.1% using both pressure and distension features. (4) Conclusions: Findings emphasize the crucial role of abnormality in the distension phase of peristalsis in FD patients. |
| first_indexed | 2024-03-10T23:05:08Z |
| format | Article |
| id | doaj.art-145415cae13b478e93ab600b93526af6 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T23:05:08Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-145415cae13b478e93ab600b93526af62023-11-19T09:23:14ZengMDPI AGApplied Sciences2076-34172023-09-0113181011610.3390/app131810116Unraveling Functional Dysphagia: A Game-Changing Automated Machine-Learning Diagnostic ApproachAli Zifan0Junyue Lin1Zihan Peng2Yiqing Bo3Ravinder K. Mittal4Division of Gastroenterology, Department of Medicine, University of California, San Diego, CA 92093, USADivision of Gastroenterology, Department of Medicine, University of California, San Diego, CA 92093, USADivision of Gastroenterology, Department of Medicine, University of California, San Diego, CA 92093, USADivision of Gastroenterology, Department of Medicine, University of California, San Diego, CA 92093, USADivision of Gastroenterology, Department of Medicine, University of California, San Diego, CA 92093, USA(1) Background: Dysphagia affects around 16% of the US population. Diagnostic tests like X-ray barium swallow and endoscopy are used initially to diagnose the cause of dysphagia, followed by high-resolution esophageal manometry (HRM). If the above tests are normal, the patient is classified as functional dysphagia (FD), suggesting esophageal sensory dysfunction. HRM records only the contraction phase of peristalsis, not the distension phase. We investigated the utilization of esophageal distension–contraction patterns for the automatic classification of FD, using artificial intelligent shallow learners. (2) Methods: Studies were performed in 30 healthy subjects and 30 patients with FD. Custom-built software (Dplots 1.0) was used to extract relevant esophageal distension–contraction features. Next, we used multiple shallow learners, namely support vector machines, random forest, K-nearest neighbors, and logistic regression, to determine which had the best performance in terms of accuracy, precision, and recall. (3) Results: In the proximal segment, LR produced the best results, with accuracy of 91.7% and precision of 92.86%, using only distension features. In the distal segment, random forest produced accuracy of 90.5% and precision of 91.1% using both pressure and distension features. (4) Conclusions: Findings emphasize the crucial role of abnormality in the distension phase of peristalsis in FD patients.https://www.mdpi.com/2076-3417/13/18/10116functional dysphagiashallow learnersdistension–contraction features |
| spellingShingle | Ali Zifan Junyue Lin Zihan Peng Yiqing Bo Ravinder K. Mittal Unraveling Functional Dysphagia: A Game-Changing Automated Machine-Learning Diagnostic Approach Applied Sciences functional dysphagia shallow learners distension–contraction features |
| title | Unraveling Functional Dysphagia: A Game-Changing Automated Machine-Learning Diagnostic Approach |
| title_full | Unraveling Functional Dysphagia: A Game-Changing Automated Machine-Learning Diagnostic Approach |
| title_fullStr | Unraveling Functional Dysphagia: A Game-Changing Automated Machine-Learning Diagnostic Approach |
| title_full_unstemmed | Unraveling Functional Dysphagia: A Game-Changing Automated Machine-Learning Diagnostic Approach |
| title_short | Unraveling Functional Dysphagia: A Game-Changing Automated Machine-Learning Diagnostic Approach |
| title_sort | unraveling functional dysphagia a game changing automated machine learning diagnostic approach |
| topic | functional dysphagia shallow learners distension–contraction features |
| url | https://www.mdpi.com/2076-3417/13/18/10116 |
| work_keys_str_mv | AT alizifan unravelingfunctionaldysphagiaagamechangingautomatedmachinelearningdiagnosticapproach AT junyuelin unravelingfunctionaldysphagiaagamechangingautomatedmachinelearningdiagnosticapproach AT zihanpeng unravelingfunctionaldysphagiaagamechangingautomatedmachinelearningdiagnosticapproach AT yiqingbo unravelingfunctionaldysphagiaagamechangingautomatedmachinelearningdiagnosticapproach AT ravinderkmittal unravelingfunctionaldysphagiaagamechangingautomatedmachinelearningdiagnosticapproach |