Accuracy Improvement of IOL Power Prediction for Highly Myopic Eyes With an XGBoost Machine Learning-Based Calculator
Purpose: To develop a machine learning-based calculator to improve the accuracy of IOL power predictions for highly myopic eyes.Methods: Data of 1,450 highly myopic eyes from 1,450 patients who had cataract surgeries at our hospital were used as internal dataset (train and validate). Another 114 hig...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2020-12-01
|
| Series: | Frontiers in Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmed.2020.592663/full |
| _version_ | 1818596040580792320 |
|---|---|
| author | Ling Wei Ling Wei Ling Wei Ling Wei Yunxiao Song Wenwen He Wenwen He Wenwen He Wenwen He Xu Chen Bo Ma Yi Lu Yi Lu Yi Lu Yi Lu Xiangjia Zhu Xiangjia Zhu Xiangjia Zhu Xiangjia Zhu |
| author_facet | Ling Wei Ling Wei Ling Wei Ling Wei Yunxiao Song Wenwen He Wenwen He Wenwen He Wenwen He Xu Chen Bo Ma Yi Lu Yi Lu Yi Lu Yi Lu Xiangjia Zhu Xiangjia Zhu Xiangjia Zhu Xiangjia Zhu |
| author_sort | Ling Wei |
| collection | DOAJ |
| description | Purpose: To develop a machine learning-based calculator to improve the accuracy of IOL power predictions for highly myopic eyes.Methods: Data of 1,450 highly myopic eyes from 1,450 patients who had cataract surgeries at our hospital were used as internal dataset (train and validate). Another 114 highly myopic eyes from other hospitals were used as external test dataset. A new calculator was developed using XGBoost regression model based on features including demographics, biometrics, IOL powers, A constants, and the predicted refractions by Barrett Universal II (BUII) formula. The accuracies were compared between our calculator and BUII formula, and axial length (AL) subgroup analysis (26.0–28.0, 28.0–30.0, or ≥30.0 mm) was further conducted.Results: The median absolute errors (MedAEs) and median squared errors (MedSEs) were lower with the XGBoost calculator (internal: 0.25 D and 0.06 D2; external: 0.29 D and 0.09 D2) vs. the BUII formula (all P ≤ 0.001). The mean absolute errors and were 0.33 ± 0.28 vs. 0.45 ± 0.31 (internal), and 0.35 ± 0.24 vs. 0.43 ± 0.29 D (external). The mean squared errors were 0.19 ± 0.32 vs. 0.30 ± 0.36 (internal), and 0.18 ± 0.21 vs. 0.27 ± 0.29 D2 (external). The percentages of eyes within ±0.25 D of the prediction errors were significantly greater with the XGBoost calculator (internal: 49.66 vs. 29.66%; external: 78.28 vs. 60.34%; both P < 0.05). The same trend was in MedAEs and MedSEs in all subgroups (internal) and in AL ≥30.0 mm subgroup (external) (all P < 0.001).Conclusions: The new XGBoost calculator showed promising accuracy for highly or extremely myopic eyes. |
| first_indexed | 2024-12-16T11:25:35Z |
| format | Article |
| id | doaj.art-1d6c7b633ebc46feb2e8265f7b934a5d |
| institution | Directory Open Access Journal |
| issn | 2296-858X |
| language | English |
| last_indexed | 2024-12-16T11:25:35Z |
| publishDate | 2020-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Medicine |
| spelling | doaj.art-1d6c7b633ebc46feb2e8265f7b934a5d2022-12-21T22:33:22ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2020-12-01710.3389/fmed.2020.592663592663Accuracy Improvement of IOL Power Prediction for Highly Myopic Eyes With an XGBoost Machine Learning-Based CalculatorLing Wei0Ling Wei1Ling Wei2Ling Wei3Yunxiao Song4Wenwen He5Wenwen He6Wenwen He7Wenwen He8Xu Chen9Bo Ma10Yi Lu11Yi Lu12Yi Lu13Yi Lu14Xiangjia Zhu15Xiangjia Zhu16Xiangjia Zhu17Xiangjia Zhu18Department of Ophthalmology and Eye Institute, Eye & ENT Hospital, Fudan University, Shanghai, ChinaNational Health Commission Key Laboratory of Myopia, Fudan University, Shanghai, ChinaKey Laboratory of Myopia, Chinese Academy of Medical Science, Shanghai, ChinaShanghai Key Laboratory of Visual Impairment and Restoration, Shanghai, ChinaNew York University Shanghai, Shanghai, ChinaDepartment of Ophthalmology and Eye Institute, Eye & ENT Hospital, Fudan University, Shanghai, ChinaNational Health Commission Key Laboratory of Myopia, Fudan University, Shanghai, ChinaKey Laboratory of Myopia, Chinese Academy of Medical Science, Shanghai, ChinaShanghai Key Laboratory of Visual Impairment and Restoration, Shanghai, ChinaShanghai Aier Eye Hospital, Shanghai, ChinaDepartment of Ophthalmology, Ninth People's Hospital of Shanghai Jiaotong University, Shanghai, ChinaDepartment of Ophthalmology and Eye Institute, Eye & ENT Hospital, Fudan University, Shanghai, ChinaNational Health Commission Key Laboratory of Myopia, Fudan University, Shanghai, ChinaKey Laboratory of Myopia, Chinese Academy of Medical Science, Shanghai, ChinaShanghai Key Laboratory of Visual Impairment and Restoration, Shanghai, ChinaDepartment of Ophthalmology and Eye Institute, Eye & ENT Hospital, Fudan University, Shanghai, ChinaNational Health Commission Key Laboratory of Myopia, Fudan University, Shanghai, ChinaKey Laboratory of Myopia, Chinese Academy of Medical Science, Shanghai, ChinaShanghai Key Laboratory of Visual Impairment and Restoration, Shanghai, ChinaPurpose: To develop a machine learning-based calculator to improve the accuracy of IOL power predictions for highly myopic eyes.Methods: Data of 1,450 highly myopic eyes from 1,450 patients who had cataract surgeries at our hospital were used as internal dataset (train and validate). Another 114 highly myopic eyes from other hospitals were used as external test dataset. A new calculator was developed using XGBoost regression model based on features including demographics, biometrics, IOL powers, A constants, and the predicted refractions by Barrett Universal II (BUII) formula. The accuracies were compared between our calculator and BUII formula, and axial length (AL) subgroup analysis (26.0–28.0, 28.0–30.0, or ≥30.0 mm) was further conducted.Results: The median absolute errors (MedAEs) and median squared errors (MedSEs) were lower with the XGBoost calculator (internal: 0.25 D and 0.06 D2; external: 0.29 D and 0.09 D2) vs. the BUII formula (all P ≤ 0.001). The mean absolute errors and were 0.33 ± 0.28 vs. 0.45 ± 0.31 (internal), and 0.35 ± 0.24 vs. 0.43 ± 0.29 D (external). The mean squared errors were 0.19 ± 0.32 vs. 0.30 ± 0.36 (internal), and 0.18 ± 0.21 vs. 0.27 ± 0.29 D2 (external). The percentages of eyes within ±0.25 D of the prediction errors were significantly greater with the XGBoost calculator (internal: 49.66 vs. 29.66%; external: 78.28 vs. 60.34%; both P < 0.05). The same trend was in MedAEs and MedSEs in all subgroups (internal) and in AL ≥30.0 mm subgroup (external) (all P < 0.001).Conclusions: The new XGBoost calculator showed promising accuracy for highly or extremely myopic eyes.https://www.frontiersin.org/articles/10.3389/fmed.2020.592663/fullmachine learningrefractive errormyopiaintraocular lensIOL power calculation |
| spellingShingle | Ling Wei Ling Wei Ling Wei Ling Wei Yunxiao Song Wenwen He Wenwen He Wenwen He Wenwen He Xu Chen Bo Ma Yi Lu Yi Lu Yi Lu Yi Lu Xiangjia Zhu Xiangjia Zhu Xiangjia Zhu Xiangjia Zhu Accuracy Improvement of IOL Power Prediction for Highly Myopic Eyes With an XGBoost Machine Learning-Based Calculator Frontiers in Medicine machine learning refractive error myopia intraocular lens IOL power calculation |
| title | Accuracy Improvement of IOL Power Prediction for Highly Myopic Eyes With an XGBoost Machine Learning-Based Calculator |
| title_full | Accuracy Improvement of IOL Power Prediction for Highly Myopic Eyes With an XGBoost Machine Learning-Based Calculator |
| title_fullStr | Accuracy Improvement of IOL Power Prediction for Highly Myopic Eyes With an XGBoost Machine Learning-Based Calculator |
| title_full_unstemmed | Accuracy Improvement of IOL Power Prediction for Highly Myopic Eyes With an XGBoost Machine Learning-Based Calculator |
| title_short | Accuracy Improvement of IOL Power Prediction for Highly Myopic Eyes With an XGBoost Machine Learning-Based Calculator |
| title_sort | accuracy improvement of iol power prediction for highly myopic eyes with an xgboost machine learning based calculator |
| topic | machine learning refractive error myopia intraocular lens IOL power calculation |
| url | https://www.frontiersin.org/articles/10.3389/fmed.2020.592663/full |
| work_keys_str_mv | AT lingwei accuracyimprovementofiolpowerpredictionforhighlymyopiceyeswithanxgboostmachinelearningbasedcalculator AT lingwei accuracyimprovementofiolpowerpredictionforhighlymyopiceyeswithanxgboostmachinelearningbasedcalculator AT lingwei accuracyimprovementofiolpowerpredictionforhighlymyopiceyeswithanxgboostmachinelearningbasedcalculator AT lingwei accuracyimprovementofiolpowerpredictionforhighlymyopiceyeswithanxgboostmachinelearningbasedcalculator AT yunxiaosong accuracyimprovementofiolpowerpredictionforhighlymyopiceyeswithanxgboostmachinelearningbasedcalculator AT wenwenhe accuracyimprovementofiolpowerpredictionforhighlymyopiceyeswithanxgboostmachinelearningbasedcalculator AT wenwenhe accuracyimprovementofiolpowerpredictionforhighlymyopiceyeswithanxgboostmachinelearningbasedcalculator AT wenwenhe accuracyimprovementofiolpowerpredictionforhighlymyopiceyeswithanxgboostmachinelearningbasedcalculator AT wenwenhe accuracyimprovementofiolpowerpredictionforhighlymyopiceyeswithanxgboostmachinelearningbasedcalculator AT xuchen accuracyimprovementofiolpowerpredictionforhighlymyopiceyeswithanxgboostmachinelearningbasedcalculator AT boma accuracyimprovementofiolpowerpredictionforhighlymyopiceyeswithanxgboostmachinelearningbasedcalculator AT yilu accuracyimprovementofiolpowerpredictionforhighlymyopiceyeswithanxgboostmachinelearningbasedcalculator AT yilu accuracyimprovementofiolpowerpredictionforhighlymyopiceyeswithanxgboostmachinelearningbasedcalculator AT yilu accuracyimprovementofiolpowerpredictionforhighlymyopiceyeswithanxgboostmachinelearningbasedcalculator AT yilu accuracyimprovementofiolpowerpredictionforhighlymyopiceyeswithanxgboostmachinelearningbasedcalculator AT xiangjiazhu accuracyimprovementofiolpowerpredictionforhighlymyopiceyeswithanxgboostmachinelearningbasedcalculator AT xiangjiazhu accuracyimprovementofiolpowerpredictionforhighlymyopiceyeswithanxgboostmachinelearningbasedcalculator AT xiangjiazhu accuracyimprovementofiolpowerpredictionforhighlymyopiceyeswithanxgboostmachinelearningbasedcalculator AT xiangjiazhu accuracyimprovementofiolpowerpredictionforhighlymyopiceyeswithanxgboostmachinelearningbasedcalculator |