|
1
|
Hao R, Zhang L, Liu J, Liu Y, Yi J, Liu X. A Promising Approach: Artificial Intelligence Applied to Small Intestinal Bacterial Overgrowth (SIBO) Diagnosis Using Cluster Analysis. Diagnostics (Basel) 2021; 11:1445. [PMID: 34441379 PMCID: PMC8392862 DOI: 10.3390/diagnostics11081445] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/26/2021] [Revised: 07/16/2021] [Accepted: 08/07/2021] [Indexed: 11/16/2022] Open
Abstract
Small intestinal bacterial overgrowth (SIBO) is characterized by abnormal and excessive amounts of bacteria in the small intestine. Since symptoms and lab tests are non-specific, the diagnosis of SIBO is highly dependent on breath testing. There is a lack of a universally accepted cut-off point for breath testing to diagnose SIBO, and the dilemma of defining "SIBO patients" has made it more difficult to explore the gold standard for SIBO diagnosis. How to validate the gold standard for breath testing without defining "SIBO patients" has become an imperious demand in clinic. Breath-testing datasets from 1071 patients were collected from Xiangya Hospital in the past 3 years and analyzed with an artificial intelligence method using cluster analysis. K-means and DBSCAN algorithms were applied to the dataset after the clustering tendency was confirmed with Hopkins Statistic. Satisfying the clustering effect was evaluated with a Silhouette score, and patterns of each group were described. Advantages of artificial intelligence application in adaptive breath-testing diagnosis criteria with SIBO were discussed from the aspects of high dimensional analysis, and data-driven and regional specific dietary influence. This research work implied a promising application of artificial intelligence for SIBO diagnosis, which would benefit clinical practice and scientific research.
Collapse
Affiliation(s)
- Rong Hao
- Department of Gastroenterology, Xiangya Hospital, Central South University, Changsha 410008, China; (R.H.); (J.L.); (Y.L.)
- Hunan International Scientific and Technological Cooperation Base of Artificial Intelligence Computer Aided Diagnosis and Treatment for Digestive Disease, Changsha 410008, China
| | - Lun Zhang
- Laboratory of Science and Technology on Integrated Logistics Support, National University of Defense Technology, Changsha 410072, China;
- College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410072, China
| | - Jiashuang Liu
- Department of Gastroenterology, Xiangya Hospital, Central South University, Changsha 410008, China; (R.H.); (J.L.); (Y.L.)
- Hunan International Scientific and Technological Cooperation Base of Artificial Intelligence Computer Aided Diagnosis and Treatment for Digestive Disease, Changsha 410008, China
| | - Yajun Liu
- Department of Gastroenterology, Xiangya Hospital, Central South University, Changsha 410008, China; (R.H.); (J.L.); (Y.L.)
- Hunan International Scientific and Technological Cooperation Base of Artificial Intelligence Computer Aided Diagnosis and Treatment for Digestive Disease, Changsha 410008, China
| | - Jun Yi
- Department of Gastroenterology, Xiangya Hospital, Central South University, Changsha 410008, China; (R.H.); (J.L.); (Y.L.)
- Hunan International Scientific and Technological Cooperation Base of Artificial Intelligence Computer Aided Diagnosis and Treatment for Digestive Disease, Changsha 410008, China
| | - Xiaowei Liu
- Department of Gastroenterology, Xiangya Hospital, Central South University, Changsha 410008, China; (R.H.); (J.L.); (Y.L.)
- Hunan International Scientific and Technological Cooperation Base of Artificial Intelligence Computer Aided Diagnosis and Treatment for Digestive Disease, Changsha 410008, China
| |
Collapse
|