Using Akaike information criterion and minimum mean square error mode in compensating for ultrasonographic errors for estimation of fetal weight by new operators
Objectives: The accuracy of ultrasound (US) measurements is operator dependent. In order to decrease the operator-dependent errors in estimated fetal weight (EFW), a model selection analysis was undertaken to select significant compensation weighting factors on ultrasonographic parameters to support...
| 主要な著者: | , , , , , , |
|---|---|
| フォーマット: | 論文 |
| 言語: | English |
| 出版事項: |
Elsevier
2013-03-01
|
| シリーズ: | Taiwanese Journal of Obstetrics & Gynecology |
| 主題: | |
| オンライン･アクセス: | http://www.sciencedirect.com/science/article/pii/S1028455913000090 |
| _version_ | 1828453979907948544 |
|---|---|
| author | Yueh-Chin Cheng Yu Hsien Chiu Hsien-Chang Wang Fong-Ming Chang Kao-Chi Chung Chiung-Hsin Chang Kuo-Sheng Cheng |
| author_facet | Yueh-Chin Cheng Yu Hsien Chiu Hsien-Chang Wang Fong-Ming Chang Kao-Chi Chung Chiung-Hsin Chang Kuo-Sheng Cheng |
| author_sort | Yueh-Chin Cheng |
| collection | DOAJ |
| description | Objectives: The accuracy of ultrasound (US) measurements is operator dependent. In order to decrease the operator-dependent errors in estimated fetal weight (EFW), a model selection analysis was undertaken to select significant compensation weighting factors on ultrasonographic parameters to support artificial neural network (ANN), and thus to enhance the accuracy of fetal weight estimation.
Materials and Methods: In total, 2127 singletons were examined by prenatal US within 3 days before delivery for ANN development, and another 100 cases were selected from new operators for evaluation. First, correlation analysis was used to analyze the differences between the prenatal and postnatal parameters. Second, Akaike information criterion (AIC) was used to determine the number of database partition and optimal weightings for compensating the input parameters of the ANN model. Finally, minimum mean squared error (MMSE) mode was utilized to determine the optimal EFW.
Results: EFW of the proposed compensation model using AIC and MMSE showed mean absolute percent error of 5.1 ± 3.1% and mean absolute error of 158.9 ± 96.2 g. When comparing the accuracy of EFW, our model using AIC and MMSE was superior to those conventional EFW formulas (all p < 0.05).
Conclusion: We proved that performing the parameter compensation (by AIC) and model compensations (by MMSE) for the ANN model can improve EFW accuracy. Our AIC–MMSE model of EFW will contribute to the improvement of accuracy when adding new US datasets measured by new operators. |
| first_indexed | 2024-12-11T00:15:41Z |
| format | Article |
| id | doaj.art-db0ae7d25b5847a4b7f5ea414014f84d |
| institution | Directory Open Access Journal |
| issn | 1028-4559 |
| language | English |
| last_indexed | 2024-12-11T00:15:41Z |
| publishDate | 2013-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Taiwanese Journal of Obstetrics & Gynecology |
| spelling | doaj.art-db0ae7d25b5847a4b7f5ea414014f84d2022-12-22T01:27:59ZengElsevierTaiwanese Journal of Obstetrics & Gynecology1028-45592013-03-01521465210.1016/j.tjog.2013.01.008Using Akaike information criterion and minimum mean square error mode in compensating for ultrasonographic errors for estimation of fetal weight by new operatorsYueh-Chin Cheng0Yu Hsien Chiu1Hsien-Chang Wang2Fong-Ming Chang3Kao-Chi Chung4Chiung-Hsin Chang5Kuo-Sheng Cheng6Department of Biomedical Engineering, National Cheng Kung University, Tainan, TaiwanDepartment of Healthcare Administration and Medical Informatics, Kaohsiung Medical University, Kaohsiung, TaiwanDepartment of Information Management, Chang-Jung Christian University, Tainan, TaiwanDepartment of Obstetrics and Gynecology, National Cheng Kung University Medical College and Hospital, Tainan, TaiwanDepartment of Biomedical Engineering, National Cheng Kung University, Tainan, TaiwanDepartment of Obstetrics and Gynecology, National Cheng Kung University Medical College and Hospital, Tainan, TaiwanDepartment of Biomedical Engineering, National Cheng Kung University, Tainan, TaiwanObjectives: The accuracy of ultrasound (US) measurements is operator dependent. In order to decrease the operator-dependent errors in estimated fetal weight (EFW), a model selection analysis was undertaken to select significant compensation weighting factors on ultrasonographic parameters to support artificial neural network (ANN), and thus to enhance the accuracy of fetal weight estimation. Materials and Methods: In total, 2127 singletons were examined by prenatal US within 3 days before delivery for ANN development, and another 100 cases were selected from new operators for evaluation. First, correlation analysis was used to analyze the differences between the prenatal and postnatal parameters. Second, Akaike information criterion (AIC) was used to determine the number of database partition and optimal weightings for compensating the input parameters of the ANN model. Finally, minimum mean squared error (MMSE) mode was utilized to determine the optimal EFW. Results: EFW of the proposed compensation model using AIC and MMSE showed mean absolute percent error of 5.1 ± 3.1% and mean absolute error of 158.9 ± 96.2 g. When comparing the accuracy of EFW, our model using AIC and MMSE was superior to those conventional EFW formulas (all p < 0.05). Conclusion: We proved that performing the parameter compensation (by AIC) and model compensations (by MMSE) for the ANN model can improve EFW accuracy. Our AIC–MMSE model of EFW will contribute to the improvement of accuracy when adding new US datasets measured by new operators.http://www.sciencedirect.com/science/article/pii/S1028455913000090Akaike information criterionartificial neural networkestimated fetal weightminimum mean squared errorultrasonography |
| spellingShingle | Yueh-Chin Cheng Yu Hsien Chiu Hsien-Chang Wang Fong-Ming Chang Kao-Chi Chung Chiung-Hsin Chang Kuo-Sheng Cheng Using Akaike information criterion and minimum mean square error mode in compensating for ultrasonographic errors for estimation of fetal weight by new operators Taiwanese Journal of Obstetrics & Gynecology Akaike information criterion artificial neural network estimated fetal weight minimum mean squared error ultrasonography |
| title | Using Akaike information criterion and minimum mean square error mode in compensating for ultrasonographic errors for estimation of fetal weight by new operators |
| title_full | Using Akaike information criterion and minimum mean square error mode in compensating for ultrasonographic errors for estimation of fetal weight by new operators |
| title_fullStr | Using Akaike information criterion and minimum mean square error mode in compensating for ultrasonographic errors for estimation of fetal weight by new operators |
| title_full_unstemmed | Using Akaike information criterion and minimum mean square error mode in compensating for ultrasonographic errors for estimation of fetal weight by new operators |
| title_short | Using Akaike information criterion and minimum mean square error mode in compensating for ultrasonographic errors for estimation of fetal weight by new operators |
| title_sort | using akaike information criterion and minimum mean square error mode in compensating for ultrasonographic errors for estimation of fetal weight by new operators |
| topic | Akaike information criterion artificial neural network estimated fetal weight minimum mean squared error ultrasonography |
| url | http://www.sciencedirect.com/science/article/pii/S1028455913000090 |
| work_keys_str_mv | AT yuehchincheng usingakaikeinformationcriterionandminimummeansquareerrormodeincompensatingforultrasonographicerrorsforestimationoffetalweightbynewoperators AT yuhsienchiu usingakaikeinformationcriterionandminimummeansquareerrormodeincompensatingforultrasonographicerrorsforestimationoffetalweightbynewoperators AT hsienchangwang usingakaikeinformationcriterionandminimummeansquareerrormodeincompensatingforultrasonographicerrorsforestimationoffetalweightbynewoperators AT fongmingchang usingakaikeinformationcriterionandminimummeansquareerrormodeincompensatingforultrasonographicerrorsforestimationoffetalweightbynewoperators AT kaochichung usingakaikeinformationcriterionandminimummeansquareerrormodeincompensatingforultrasonographicerrorsforestimationoffetalweightbynewoperators AT chiunghsinchang usingakaikeinformationcriterionandminimummeansquareerrormodeincompensatingforultrasonographicerrorsforestimationoffetalweightbynewoperators AT kuoshengcheng usingakaikeinformationcriterionandminimummeansquareerrormodeincompensatingforultrasonographicerrorsforestimationoffetalweightbynewoperators |