File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Improvement of liver fibrosis diagnostic models based on Youden index

TitleImprovement of liver fibrosis diagnostic models based on Youden index
Authors
KeywordsDisease diagnosis
Liver fibrosis
Machine learning
Youden index
Issue Date2019
Citation
Journal of Shanghai Jiaotong University (Medical Science), 2019, v. 39, n. 10, p. 1156-1161 How to Cite?
AbstractObjective: By using Youden index, to improve the performance of the hepatic fibrosis diagnostic models, and to solve the problem of unbalanced diagnostic sensitivity when there is a big difference in the sample size of two groups. Methods: Two hepatitis B virus (HBV) datasets available on GitHub were selected, including 482 HBV infected subjects recruited from Shuguang Hospital in affiliation with Shanghai University of Traditional Chinese Medicine (train set) and 86 HBV infected subjects from Xiamen Hospital of Traditional Chinese Medicine (validation set). By using the two datasets, linear discriminant analysis model, random forest model, gradient boosting model and decision tree model were established, based on four clinical parameters (age, glutamic-oxaloacetic transaminase, glutamic-pyruvic transaminase, and platelet count) of patients, for the diagnosis of early and advanced hepatic fibrosis as well as the diagnosis of hepatic fibrosis and cirrhosis. Youden index was used to adjust the threshold value and the classification result of each diagnostic model. The diagnostic performances of each machine learning model and fibrosis index based on the 4 factor (FIB-4) were evaluated by accuracy, the area under the receiver operating characteristic curve (AUC) and sensitivity. Results: The intergroup sensitivity imbalance occurred in all machine learning models. After using Youden index, the difference of intergroup sensitivity was greatly reduced, and the total accuracy and AUC values of machine learning models were generally higher than those of FIB-4 index. Conclusion:The improved diagnostic models based on Youden index can reduce the difference of intergroup sensitivity and improve the comprehensive performance of the diagnostic models of hepatic fibrosis.
Persistent Identifierhttp://hdl.handle.net/10722/342739
ISSN
2023 SCImago Journal Rankings: 0.110

 

DC FieldValueLanguage
dc.contributor.authorSang, Chao-
dc.contributor.authorXie, Guo Xiang-
dc.contributor.authorLiang, Dan Dan-
dc.contributor.authorZhao, Ai Hua-
dc.contributor.authorJia, Wei-
dc.contributor.authorChen, Tian Lu-
dc.date.accessioned2024-04-17T07:05:55Z-
dc.date.available2024-04-17T07:05:55Z-
dc.date.issued2019-
dc.identifier.citationJournal of Shanghai Jiaotong University (Medical Science), 2019, v. 39, n. 10, p. 1156-1161-
dc.identifier.issn1674-8115-
dc.identifier.urihttp://hdl.handle.net/10722/342739-
dc.description.abstractObjective: By using Youden index, to improve the performance of the hepatic fibrosis diagnostic models, and to solve the problem of unbalanced diagnostic sensitivity when there is a big difference in the sample size of two groups. Methods: Two hepatitis B virus (HBV) datasets available on GitHub were selected, including 482 HBV infected subjects recruited from Shuguang Hospital in affiliation with Shanghai University of Traditional Chinese Medicine (train set) and 86 HBV infected subjects from Xiamen Hospital of Traditional Chinese Medicine (validation set). By using the two datasets, linear discriminant analysis model, random forest model, gradient boosting model and decision tree model were established, based on four clinical parameters (age, glutamic-oxaloacetic transaminase, glutamic-pyruvic transaminase, and platelet count) of patients, for the diagnosis of early and advanced hepatic fibrosis as well as the diagnosis of hepatic fibrosis and cirrhosis. Youden index was used to adjust the threshold value and the classification result of each diagnostic model. The diagnostic performances of each machine learning model and fibrosis index based on the 4 factor (FIB-4) were evaluated by accuracy, the area under the receiver operating characteristic curve (AUC) and sensitivity. Results: The intergroup sensitivity imbalance occurred in all machine learning models. After using Youden index, the difference of intergroup sensitivity was greatly reduced, and the total accuracy and AUC values of machine learning models were generally higher than those of FIB-4 index. Conclusion:The improved diagnostic models based on Youden index can reduce the difference of intergroup sensitivity and improve the comprehensive performance of the diagnostic models of hepatic fibrosis.-
dc.languageeng-
dc.relation.ispartofJournal of Shanghai Jiaotong University (Medical Science)-
dc.subjectDisease diagnosis-
dc.subjectLiver fibrosis-
dc.subjectMachine learning-
dc.subjectYouden index-
dc.titleImprovement of liver fibrosis diagnostic models based on Youden index-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.3969/j.issn.1674-8115.2019.10.009-
dc.identifier.scopuseid_2-s2.0-85075552434-
dc.identifier.volume39-
dc.identifier.issue10-
dc.identifier.spage1156-
dc.identifier.epage1161-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats