Diagnostic Value and Effectiveness of an Artificial Neural Network in Biliary Atresia
Objectives: Biliary atresia (BA) is a devastating pediatric liver disease. Early diagnosis is important for timely intervention and better prognosis. Using clinical parameters for non-invasive and efficient BA diagnosis, we aimed to establish an artificial neural network (ANN).Methods: A total of 2,...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2020-08-01
|
| Series: | Frontiers in Pediatrics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/fped.2020.00409/full |
| _version_ | 1818282728870641664 |
|---|---|
| author | Jia Liu ShuYang Dai Gong Chen Song Sun JingYing Jiang Shan Zheng YiJie Zheng Rui Dong |
| author_facet | Jia Liu ShuYang Dai Gong Chen Song Sun JingYing Jiang Shan Zheng YiJie Zheng Rui Dong |
| author_sort | Jia Liu |
| collection | DOAJ |
| description | Objectives: Biliary atresia (BA) is a devastating pediatric liver disease. Early diagnosis is important for timely intervention and better prognosis. Using clinical parameters for non-invasive and efficient BA diagnosis, we aimed to establish an artificial neural network (ANN).Methods: A total of 2,384 obstructive jaundice patients from 2012 to 2017 and their 137 clinical parameters were screened for eligibility. A standard binary classification feed-forward ANN was employed. The network was trained and validated for accuracy. Gamma-glutamyl transpeptidase (GGT) level was used as an independent predictor and a comparison to assess the network effectiveness.Results: We included 46 parameters and 1,452 patients for ANN modeling. Total bilirubin, direct bilirubin, and GGT were the most significant indicators. The network consisted of an input layer, 3 hidden layers with 12 neurons each, and an output layer. The network showed good predictive property with a high area under curve (AUC) (0.967, sensitivity 97.2% and specificity 91.0%). Five-fold cross validation showed the mean accuracy for training data of 93.2% and for validation data of 88.6%.Conclusions: The high accuracy and efficiency demonstrated by the ANN model is promising in the noninvasive diagnosis of BA and could be considered as in a low-cost and independent expert diagnosis system. |
| first_indexed | 2024-12-13T00:25:38Z |
| format | Article |
| id | doaj.art-4a7d55f90a4248e58c2909e7348d8a3f |
| institution | Directory Open Access Journal |
| issn | 2296-2360 |
| language | English |
| last_indexed | 2024-12-13T00:25:38Z |
| publishDate | 2020-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Pediatrics |
| spelling | doaj.art-4a7d55f90a4248e58c2909e7348d8a3f2022-12-22T00:05:26ZengFrontiers Media S.A.Frontiers in Pediatrics2296-23602020-08-01810.3389/fped.2020.00409556023Diagnostic Value and Effectiveness of an Artificial Neural Network in Biliary AtresiaJia Liu0ShuYang Dai1Gong Chen2Song Sun3JingYing Jiang4Shan Zheng5YiJie Zheng6Rui Dong7Department of Pediatric Surgery, Children's Hospital of Fudan University, Shanghai Key Laboratory of Birth Defect, Shanghai, ChinaDepartment of Pediatric Surgery, Children's Hospital of Fudan University, Shanghai Key Laboratory of Birth Defect, Shanghai, ChinaDepartment of Pediatric Surgery, Children's Hospital of Fudan University, Shanghai Key Laboratory of Birth Defect, Shanghai, ChinaDepartment of Pediatric Surgery, Children's Hospital of Fudan University, Shanghai Key Laboratory of Birth Defect, Shanghai, ChinaDepartment of Pediatric Surgery, Children's Hospital of Fudan University, Shanghai Key Laboratory of Birth Defect, Shanghai, ChinaDepartment of Pediatric Surgery, Children's Hospital of Fudan University, Shanghai Key Laboratory of Birth Defect, Shanghai, ChinaDepartment of Medicine, Pulmonary Hospital Affiliated to Tongji University, Shanghai, ChinaDepartment of Pediatric Surgery, Children's Hospital of Fudan University, Shanghai Key Laboratory of Birth Defect, Shanghai, ChinaObjectives: Biliary atresia (BA) is a devastating pediatric liver disease. Early diagnosis is important for timely intervention and better prognosis. Using clinical parameters for non-invasive and efficient BA diagnosis, we aimed to establish an artificial neural network (ANN).Methods: A total of 2,384 obstructive jaundice patients from 2012 to 2017 and their 137 clinical parameters were screened for eligibility. A standard binary classification feed-forward ANN was employed. The network was trained and validated for accuracy. Gamma-glutamyl transpeptidase (GGT) level was used as an independent predictor and a comparison to assess the network effectiveness.Results: We included 46 parameters and 1,452 patients for ANN modeling. Total bilirubin, direct bilirubin, and GGT were the most significant indicators. The network consisted of an input layer, 3 hidden layers with 12 neurons each, and an output layer. The network showed good predictive property with a high area under curve (AUC) (0.967, sensitivity 97.2% and specificity 91.0%). Five-fold cross validation showed the mean accuracy for training data of 93.2% and for validation data of 88.6%.Conclusions: The high accuracy and efficiency demonstrated by the ANN model is promising in the noninvasive diagnosis of BA and could be considered as in a low-cost and independent expert diagnosis system.https://www.frontiersin.org/article/10.3389/fped.2020.00409/fullbiliary atresiaobstructive jaundicediagnosisgamma-glutamyl transpeptidasenon-invasive |
| spellingShingle | Jia Liu ShuYang Dai Gong Chen Song Sun JingYing Jiang Shan Zheng YiJie Zheng Rui Dong Diagnostic Value and Effectiveness of an Artificial Neural Network in Biliary Atresia Frontiers in Pediatrics biliary atresia obstructive jaundice diagnosis gamma-glutamyl transpeptidase non-invasive |
| title | Diagnostic Value and Effectiveness of an Artificial Neural Network in Biliary Atresia |
| title_full | Diagnostic Value and Effectiveness of an Artificial Neural Network in Biliary Atresia |
| title_fullStr | Diagnostic Value and Effectiveness of an Artificial Neural Network in Biliary Atresia |
| title_full_unstemmed | Diagnostic Value and Effectiveness of an Artificial Neural Network in Biliary Atresia |
| title_short | Diagnostic Value and Effectiveness of an Artificial Neural Network in Biliary Atresia |
| title_sort | diagnostic value and effectiveness of an artificial neural network in biliary atresia |
| topic | biliary atresia obstructive jaundice diagnosis gamma-glutamyl transpeptidase non-invasive |
| url | https://www.frontiersin.org/article/10.3389/fped.2020.00409/full |
| work_keys_str_mv | AT jialiu diagnosticvalueandeffectivenessofanartificialneuralnetworkinbiliaryatresia AT shuyangdai diagnosticvalueandeffectivenessofanartificialneuralnetworkinbiliaryatresia AT gongchen diagnosticvalueandeffectivenessofanartificialneuralnetworkinbiliaryatresia AT songsun diagnosticvalueandeffectivenessofanartificialneuralnetworkinbiliaryatresia AT jingyingjiang diagnosticvalueandeffectivenessofanartificialneuralnetworkinbiliaryatresia AT shanzheng diagnosticvalueandeffectivenessofanartificialneuralnetworkinbiliaryatresia AT yijiezheng diagnosticvalueandeffectivenessofanartificialneuralnetworkinbiliaryatresia AT ruidong diagnosticvalueandeffectivenessofanartificialneuralnetworkinbiliaryatresia |