Fuzzy ontology-based approach for liver fibrosis diagnosis
The domain of the digestive system is prone to severe chronic disease in the form of liver cirrhosis, which is currently a leading cause of mortality. This article presents a new intelligent system for predicting the severity of liver fibrosis in patients with chronic viral hepatitis C. The proposed...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-09-01
|
| Series: | Journal of King Saud University: Computer and Information Sciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1319157823002744 |
| _version_ | 1797663860744781824 |
|---|---|
| author | Sara Sweidan Nuha Zamzami Sahar F. Sabbeh |
| author_facet | Sara Sweidan Nuha Zamzami Sahar F. Sabbeh |
| author_sort | Sara Sweidan |
| collection | DOAJ |
| description | The domain of the digestive system is prone to severe chronic disease in the form of liver cirrhosis, which is currently a leading cause of mortality. This article presents a new intelligent system for predicting the severity of liver fibrosis in patients with chronic viral hepatitis C. The proposed system is based on the inference capabilities of fuzzy ontology and operates on semantic rule-based techniques. A fuzzy decision tree technique was employed to generate the ontology rule base using a dataset of real fibrosis cases from the Mansoura University Hospital, Egypt. These rules were then encoded into a set of fuzzy semantic rules using the fuzzy description logic format. To evaluate the system’s effectiveness, the proposed ontology was then tested on 47 chronic HCV cases, with an attempt made to see if this correctly diagnosed the patients’ conditions. The performance of the proposed system was compared with that of the now-standard Mamdani fuzzy inference system; while the latter achieved an accuracy of 95.7/%, the proposed fuzzy ontology-based system demonstrated higher performance, with 97.8% accuracy. Furthermore, the proposed system also supports semantic interoperability between clinical decision support systems and electronic health record ecosystems. The positive impacts of this system on the correct prediction of liver fibrosis severity thus suggest that it has the potential to assist medical professionals in diagnosing and treating this dangerous disease. |
| first_indexed | 2024-03-11T19:20:53Z |
| format | Article |
| id | doaj.art-43f4bdd02471480eae938843d139f803 |
| institution | Directory Open Access Journal |
| issn | 1319-1578 |
| language | English |
| last_indexed | 2024-03-11T19:20:53Z |
| publishDate | 2023-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of King Saud University: Computer and Information Sciences |
| spelling | doaj.art-43f4bdd02471480eae938843d139f8032023-10-07T04:34:10ZengElsevierJournal of King Saud University: Computer and Information Sciences1319-15782023-09-01358101720Fuzzy ontology-based approach for liver fibrosis diagnosisSara Sweidan0Nuha Zamzami1Sahar F. Sabbeh2Faculty of Computers and Artificial Intelligence, Artificial Intelligence Department, Benha University, Benha 13518, Egypt; University of new Mansoura university, Faculty of Computer Science and Engineering, Gamasa 35712, EgyptUniversity of Jeddah, College of Computer Science and Engineering, Department of Computer Science and Artificial Intelligence, Jeddah, Saudi Arabia; Corresponding author.University of Jeddah, College of Computer Science and Engineering, Department of Information Systems and Technology, Jeddah, Saudi Arabia; Faculty of Computers and Artificial Intelligence, Information Systems Department, Benha University, Benha 13518, EgyptThe domain of the digestive system is prone to severe chronic disease in the form of liver cirrhosis, which is currently a leading cause of mortality. This article presents a new intelligent system for predicting the severity of liver fibrosis in patients with chronic viral hepatitis C. The proposed system is based on the inference capabilities of fuzzy ontology and operates on semantic rule-based techniques. A fuzzy decision tree technique was employed to generate the ontology rule base using a dataset of real fibrosis cases from the Mansoura University Hospital, Egypt. These rules were then encoded into a set of fuzzy semantic rules using the fuzzy description logic format. To evaluate the system’s effectiveness, the proposed ontology was then tested on 47 chronic HCV cases, with an attempt made to see if this correctly diagnosed the patients’ conditions. The performance of the proposed system was compared with that of the now-standard Mamdani fuzzy inference system; while the latter achieved an accuracy of 95.7/%, the proposed fuzzy ontology-based system demonstrated higher performance, with 97.8% accuracy. Furthermore, the proposed system also supports semantic interoperability between clinical decision support systems and electronic health record ecosystems. The positive impacts of this system on the correct prediction of liver fibrosis severity thus suggest that it has the potential to assist medical professionals in diagnosing and treating this dangerous disease.http://www.sciencedirect.com/science/article/pii/S1319157823002744Liver fibrosisFuzzy ontologyRule-based systemSemantics reasoningFuzzy reasoning |
| spellingShingle | Sara Sweidan Nuha Zamzami Sahar F. Sabbeh Fuzzy ontology-based approach for liver fibrosis diagnosis Journal of King Saud University: Computer and Information Sciences Liver fibrosis Fuzzy ontology Rule-based system Semantics reasoning Fuzzy reasoning |
| title | Fuzzy ontology-based approach for liver fibrosis diagnosis |
| title_full | Fuzzy ontology-based approach for liver fibrosis diagnosis |
| title_fullStr | Fuzzy ontology-based approach for liver fibrosis diagnosis |
| title_full_unstemmed | Fuzzy ontology-based approach for liver fibrosis diagnosis |
| title_short | Fuzzy ontology-based approach for liver fibrosis diagnosis |
| title_sort | fuzzy ontology based approach for liver fibrosis diagnosis |
| topic | Liver fibrosis Fuzzy ontology Rule-based system Semantics reasoning Fuzzy reasoning |
| url | http://www.sciencedirect.com/science/article/pii/S1319157823002744 |
| work_keys_str_mv | AT sarasweidan fuzzyontologybasedapproachforliverfibrosisdiagnosis AT nuhazamzami fuzzyontologybasedapproachforliverfibrosisdiagnosis AT saharfsabbeh fuzzyontologybasedapproachforliverfibrosisdiagnosis |