Development and validation of predictive models for myopia onset and progression using extensive 15-year refractive data in children and adolescents
Abstract Background Global myopia prevalence poses a substantial public health burden with vision-threatening complications, necessitating effective prevention and control strategies. Precise prediction of spherical equivalent (SE), myopia, and high myopia onset is vital for proactive clinical inter...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-03-01
|
| Series: | Journal of Translational Medicine |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12967-024-05075-0 |
| _version_ | 1797247061708505088 |
|---|---|
| author | Jing Zhao Yanze Yu Yiming Li Feng Li Zhe Zhang Weijun Jian Zhi Chen Yang Shen Xiaoying Wang Zhengqiang Ye Chencui Huang Xingtao Zhou |
| author_facet | Jing Zhao Yanze Yu Yiming Li Feng Li Zhe Zhang Weijun Jian Zhi Chen Yang Shen Xiaoying Wang Zhengqiang Ye Chencui Huang Xingtao Zhou |
| author_sort | Jing Zhao |
| collection | DOAJ |
| description | Abstract Background Global myopia prevalence poses a substantial public health burden with vision-threatening complications, necessitating effective prevention and control strategies. Precise prediction of spherical equivalent (SE), myopia, and high myopia onset is vital for proactive clinical interventions. Methods We reviewed electronic medical records of pediatric and adolescent patients who underwent cycloplegic refraction measurements at the Eye & Ear, Nose, and Throat Hospital of Fudan University between January 2005 and December 2019. Patients aged 3–18 years who met the inclusion criteria were enrolled in this study. To predict the SE and onset of myopia and high myopia in a specific year, two distinct models, random forest (RF) and the gradient boosted tree algorithm (XGBoost), were trained and validated based on variables such as age at baseline, and SE at various intervals. Outputs included SE, the onset of myopia, and high myopia up to 15 years post-initial examination. Age-stratified analyses and feature importance assessments were conducted to augment the clinical significance of the models. Results The study enrolled 88,250 individuals with 408,255 refraction records. The XGBoost-based SE prediction model consistently demonstrated robust and better performance than RF over 15 years, maintaining an R 2 exceeding 0.729, and a Mean Absolute Error ranging from 0.078 to 1.802 in the test set. Myopia onset prediction exhibited strong area under the curve (AUC) values between 0.845 and 0.953 over 15 years, and high myopia onset prediction showed robust AUC values (0.807–0.997 over 13 years, with the 14th year at 0.765), emphasizing the models' effectiveness across age groups and temporal dimensions on the test set. Additionally, our classification models exhibited excellent calibration, as evidenced by consistently low brier score values, all falling below 0.25. Moreover, our findings underscore the importance of commencing regular examinations at an early age to predict high myopia. Conclusions The XGBoost predictive models exhibited high accuracy in predicting SE, onset of myopia, and high myopia among children and adolescents aged 3–18 years. Our findings emphasize the importance of early and regular examinations at a young age for predicting high myopia, thereby providing valuable insights for clinical practice. |
| first_indexed | 2024-04-24T19:52:42Z |
| format | Article |
| id | doaj.art-506576f9145444d4990e2d73574c9113 |
| institution | Directory Open Access Journal |
| issn | 1479-5876 |
| language | English |
| last_indexed | 2024-04-24T19:52:42Z |
| publishDate | 2024-03-01 |
| publisher | BMC |
| record_format | Article |
| series | Journal of Translational Medicine |
| spelling | doaj.art-506576f9145444d4990e2d73574c91132024-03-24T12:32:06ZengBMCJournal of Translational Medicine1479-58762024-03-0122111210.1186/s12967-024-05075-0Development and validation of predictive models for myopia onset and progression using extensive 15-year refractive data in children and adolescentsJing Zhao0Yanze Yu1Yiming Li2Feng Li3Zhe Zhang4Weijun Jian5Zhi Chen6Yang Shen7Xiaoying Wang8Zhengqiang Ye9Chencui Huang10Xingtao Zhou11Department of Ophthalmology and Vision Science, Eye and ENT Hospital, Fudan UniversityDepartment of Ophthalmology and Vision Science, Eye and ENT Hospital, Fudan UniversityDepartment of Research Collaboration, R&D Center. Beijing Deepwise & League of PHD Technology Co, Ltd.Department of Research Collaboration, R&D Center. Beijing Deepwise & League of PHD Technology Co, Ltd.Department of Ophthalmology and Vision Science, Eye and ENT Hospital, Fudan UniversityDepartment of Ophthalmology and Vision Science, Eye and ENT Hospital, Fudan UniversityDepartment of Ophthalmology and Vision Science, Eye and ENT Hospital, Fudan UniversityDepartment of Ophthalmology and Vision Science, Eye and ENT Hospital, Fudan UniversityDepartment of Ophthalmology and Vision Science, Eye and ENT Hospital, Fudan UniversityInformation Center, Eye & ENT Hospital, Fudan UniversityDepartment of Research Collaboration, R&D Center. Beijing Deepwise & League of PHD Technology Co, Ltd.Department of Ophthalmology and Vision Science, Eye and ENT Hospital, Fudan UniversityAbstract Background Global myopia prevalence poses a substantial public health burden with vision-threatening complications, necessitating effective prevention and control strategies. Precise prediction of spherical equivalent (SE), myopia, and high myopia onset is vital for proactive clinical interventions. Methods We reviewed electronic medical records of pediatric and adolescent patients who underwent cycloplegic refraction measurements at the Eye & Ear, Nose, and Throat Hospital of Fudan University between January 2005 and December 2019. Patients aged 3–18 years who met the inclusion criteria were enrolled in this study. To predict the SE and onset of myopia and high myopia in a specific year, two distinct models, random forest (RF) and the gradient boosted tree algorithm (XGBoost), were trained and validated based on variables such as age at baseline, and SE at various intervals. Outputs included SE, the onset of myopia, and high myopia up to 15 years post-initial examination. Age-stratified analyses and feature importance assessments were conducted to augment the clinical significance of the models. Results The study enrolled 88,250 individuals with 408,255 refraction records. The XGBoost-based SE prediction model consistently demonstrated robust and better performance than RF over 15 years, maintaining an R 2 exceeding 0.729, and a Mean Absolute Error ranging from 0.078 to 1.802 in the test set. Myopia onset prediction exhibited strong area under the curve (AUC) values between 0.845 and 0.953 over 15 years, and high myopia onset prediction showed robust AUC values (0.807–0.997 over 13 years, with the 14th year at 0.765), emphasizing the models' effectiveness across age groups and temporal dimensions on the test set. Additionally, our classification models exhibited excellent calibration, as evidenced by consistently low brier score values, all falling below 0.25. Moreover, our findings underscore the importance of commencing regular examinations at an early age to predict high myopia. Conclusions The XGBoost predictive models exhibited high accuracy in predicting SE, onset of myopia, and high myopia among children and adolescents aged 3–18 years. Our findings emphasize the importance of early and regular examinations at a young age for predicting high myopia, thereby providing valuable insights for clinical practice.https://doi.org/10.1186/s12967-024-05075-0MyopiaHigh myopiaCycloplegic refractionMachine learningPredictive model |
| spellingShingle | Jing Zhao Yanze Yu Yiming Li Feng Li Zhe Zhang Weijun Jian Zhi Chen Yang Shen Xiaoying Wang Zhengqiang Ye Chencui Huang Xingtao Zhou Development and validation of predictive models for myopia onset and progression using extensive 15-year refractive data in children and adolescents Journal of Translational Medicine Myopia High myopia Cycloplegic refraction Machine learning Predictive model |
| title | Development and validation of predictive models for myopia onset and progression using extensive 15-year refractive data in children and adolescents |
| title_full | Development and validation of predictive models for myopia onset and progression using extensive 15-year refractive data in children and adolescents |
| title_fullStr | Development and validation of predictive models for myopia onset and progression using extensive 15-year refractive data in children and adolescents |
| title_full_unstemmed | Development and validation of predictive models for myopia onset and progression using extensive 15-year refractive data in children and adolescents |
| title_short | Development and validation of predictive models for myopia onset and progression using extensive 15-year refractive data in children and adolescents |
| title_sort | development and validation of predictive models for myopia onset and progression using extensive 15 year refractive data in children and adolescents |
| topic | Myopia High myopia Cycloplegic refraction Machine learning Predictive model |
| url | https://doi.org/10.1186/s12967-024-05075-0 |
| work_keys_str_mv | AT jingzhao developmentandvalidationofpredictivemodelsformyopiaonsetandprogressionusingextensive15yearrefractivedatainchildrenandadolescents AT yanzeyu developmentandvalidationofpredictivemodelsformyopiaonsetandprogressionusingextensive15yearrefractivedatainchildrenandadolescents AT yimingli developmentandvalidationofpredictivemodelsformyopiaonsetandprogressionusingextensive15yearrefractivedatainchildrenandadolescents AT fengli developmentandvalidationofpredictivemodelsformyopiaonsetandprogressionusingextensive15yearrefractivedatainchildrenandadolescents AT zhezhang developmentandvalidationofpredictivemodelsformyopiaonsetandprogressionusingextensive15yearrefractivedatainchildrenandadolescents AT weijunjian developmentandvalidationofpredictivemodelsformyopiaonsetandprogressionusingextensive15yearrefractivedatainchildrenandadolescents AT zhichen developmentandvalidationofpredictivemodelsformyopiaonsetandprogressionusingextensive15yearrefractivedatainchildrenandadolescents AT yangshen developmentandvalidationofpredictivemodelsformyopiaonsetandprogressionusingextensive15yearrefractivedatainchildrenandadolescents AT xiaoyingwang developmentandvalidationofpredictivemodelsformyopiaonsetandprogressionusingextensive15yearrefractivedatainchildrenandadolescents AT zhengqiangye developmentandvalidationofpredictivemodelsformyopiaonsetandprogressionusingextensive15yearrefractivedatainchildrenandadolescents AT chencuihuang developmentandvalidationofpredictivemodelsformyopiaonsetandprogressionusingextensive15yearrefractivedatainchildrenandadolescents AT xingtaozhou developmentandvalidationofpredictivemodelsformyopiaonsetandprogressionusingextensive15yearrefractivedatainchildrenandadolescents |