Prediction of Reactivation After Antivascular Endothelial Growth Factor Monotherapy for Retinopathy of Prematurity: Multimodal Machine Learning Model Study

BackgroundRetinopathy of prematurity (ROP) is the leading preventable cause of childhood blindness. A timely intravitreal injection of antivascular endothelial growth factor (anti-VEGF) is required to prevent retinal detachment with consequent vision impairment and loss. Howe...

Full description

Saved in:
Bibliographic Details
Main Authors: Rong Wu, Yu Zhang, Peijie Huang, Yiying Xie, Jianxun Wang, Shuangyong Wang, Qiuxia Lin, Yichen Bai, Songfu Feng, Nian Cai, Xiaohe Lu
Format: Article
Language:English
Published: JMIR Publications 2025-04-01
Series:Journal of Medical Internet Research
Online Access:https://www.jmir.org/2025/1/e60367
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850155265168506880
author Rong Wu
Yu Zhang
Peijie Huang
Yiying Xie
Jianxun Wang
Shuangyong Wang
Qiuxia Lin
Yichen Bai
Songfu Feng
Nian Cai
Xiaohe Lu
author_facet Rong Wu
Yu Zhang
Peijie Huang
Yiying Xie
Jianxun Wang
Shuangyong Wang
Qiuxia Lin
Yichen Bai
Songfu Feng
Nian Cai
Xiaohe Lu
author_sort Rong Wu
collection DOAJ
description BackgroundRetinopathy of prematurity (ROP) is the leading preventable cause of childhood blindness. A timely intravitreal injection of antivascular endothelial growth factor (anti-VEGF) is required to prevent retinal detachment with consequent vision impairment and loss. However, anti-VEGF has been reported to be associated with ROP reactivation. Therefore, an accurate prediction of reactivation after treatment is urgently needed. ObjectiveTo develop and validate prediction models for reactivation after anti-VEGF intravitreal injection in infants with ROP using multimodal machine learning algorithms. MethodsInfants with ROP undergoing anti-VEGF treatment were recruited from 3 hospitals, and conventional machine learning, deep learning, and fusion models were constructed. The areas under the curve (AUCs), accuracy, sensitivity, and specificity were used to show the performances of the prediction models. ResultsA total of 239 cases with anti-VEGF treatment were recruited, including 90 (37.66%) with reactivation and 149 (62.34%) nonreactivation cases. The AUCs for the conventional machine learning model were 0.806 and 0.805 in the internal validation and test groups, respectively. The average AUC, sensitivity, and specificity in the test for the deep learning model were 0.787, 0.800, and 0.570, respectively. The specificity, AUC, and sensitivity for the fusion model were 0.686, 0.822, and 0.800 in a test, separately. ConclusionsWe constructed 3 prediction models for ROP reactivation. The fusion model achieved the best performance. Using this prediction model, we could optimize strategies for treating ROP in infants and develop better screening plans after treatment.
format Article
id doaj-art-0a6f2583710f4ae7bed5df3dbc834a68
institution OA Journals
issn 1438-8871
language English
publishDate 2025-04-01
publisher JMIR Publications
record_format Article
series Journal of Medical Internet Research
spelling doaj-art-0a6f2583710f4ae7bed5df3dbc834a682025-08-20T02:24:59ZengJMIR PublicationsJournal of Medical Internet Research1438-88712025-04-0127e6036710.2196/60367Prediction of Reactivation After Antivascular Endothelial Growth Factor Monotherapy for Retinopathy of Prematurity: Multimodal Machine Learning Model StudyRong Wuhttps://orcid.org/0000-0001-8714-1508Yu Zhanghttps://orcid.org/0000-0003-2057-8814Peijie Huanghttps://orcid.org/0009-0004-3963-3742Yiying Xiehttps://orcid.org/0009-0008-9922-4851Jianxun Wanghttps://orcid.org/0000-0002-6386-1807Shuangyong Wanghttps://orcid.org/0000-0003-1465-4200Qiuxia Linhttps://orcid.org/0009-0004-3646-6221Yichen Baihttps://orcid.org/0009-0009-6358-2363Songfu Fenghttps://orcid.org/0000-0002-3494-4013Nian Caihttps://orcid.org/0000-0002-7826-5055Xiaohe Luhttps://orcid.org/0000-0003-2173-7290 BackgroundRetinopathy of prematurity (ROP) is the leading preventable cause of childhood blindness. A timely intravitreal injection of antivascular endothelial growth factor (anti-VEGF) is required to prevent retinal detachment with consequent vision impairment and loss. However, anti-VEGF has been reported to be associated with ROP reactivation. Therefore, an accurate prediction of reactivation after treatment is urgently needed. ObjectiveTo develop and validate prediction models for reactivation after anti-VEGF intravitreal injection in infants with ROP using multimodal machine learning algorithms. MethodsInfants with ROP undergoing anti-VEGF treatment were recruited from 3 hospitals, and conventional machine learning, deep learning, and fusion models were constructed. The areas under the curve (AUCs), accuracy, sensitivity, and specificity were used to show the performances of the prediction models. ResultsA total of 239 cases with anti-VEGF treatment were recruited, including 90 (37.66%) with reactivation and 149 (62.34%) nonreactivation cases. The AUCs for the conventional machine learning model were 0.806 and 0.805 in the internal validation and test groups, respectively. The average AUC, sensitivity, and specificity in the test for the deep learning model were 0.787, 0.800, and 0.570, respectively. The specificity, AUC, and sensitivity for the fusion model were 0.686, 0.822, and 0.800 in a test, separately. ConclusionsWe constructed 3 prediction models for ROP reactivation. The fusion model achieved the best performance. Using this prediction model, we could optimize strategies for treating ROP in infants and develop better screening plans after treatment.https://www.jmir.org/2025/1/e60367
spellingShingle Rong Wu
Yu Zhang
Peijie Huang
Yiying Xie
Jianxun Wang
Shuangyong Wang
Qiuxia Lin
Yichen Bai
Songfu Feng
Nian Cai
Xiaohe Lu
Prediction of Reactivation After Antivascular Endothelial Growth Factor Monotherapy for Retinopathy of Prematurity: Multimodal Machine Learning Model Study
Journal of Medical Internet Research
title Prediction of Reactivation After Antivascular Endothelial Growth Factor Monotherapy for Retinopathy of Prematurity: Multimodal Machine Learning Model Study
title_full Prediction of Reactivation After Antivascular Endothelial Growth Factor Monotherapy for Retinopathy of Prematurity: Multimodal Machine Learning Model Study
title_fullStr Prediction of Reactivation After Antivascular Endothelial Growth Factor Monotherapy for Retinopathy of Prematurity: Multimodal Machine Learning Model Study
title_full_unstemmed Prediction of Reactivation After Antivascular Endothelial Growth Factor Monotherapy for Retinopathy of Prematurity: Multimodal Machine Learning Model Study
title_short Prediction of Reactivation After Antivascular Endothelial Growth Factor Monotherapy for Retinopathy of Prematurity: Multimodal Machine Learning Model Study
title_sort prediction of reactivation after antivascular endothelial growth factor monotherapy for retinopathy of prematurity multimodal machine learning model study
url https://www.jmir.org/2025/1/e60367
work_keys_str_mv AT rongwu predictionofreactivationafterantivascularendothelialgrowthfactormonotherapyforretinopathyofprematuritymultimodalmachinelearningmodelstudy
AT yuzhang predictionofreactivationafterantivascularendothelialgrowthfactormonotherapyforretinopathyofprematuritymultimodalmachinelearningmodelstudy
AT peijiehuang predictionofreactivationafterantivascularendothelialgrowthfactormonotherapyforretinopathyofprematuritymultimodalmachinelearningmodelstudy
AT yiyingxie predictionofreactivationafterantivascularendothelialgrowthfactormonotherapyforretinopathyofprematuritymultimodalmachinelearningmodelstudy
AT jianxunwang predictionofreactivationafterantivascularendothelialgrowthfactormonotherapyforretinopathyofprematuritymultimodalmachinelearningmodelstudy
AT shuangyongwang predictionofreactivationafterantivascularendothelialgrowthfactormonotherapyforretinopathyofprematuritymultimodalmachinelearningmodelstudy
AT qiuxialin predictionofreactivationafterantivascularendothelialgrowthfactormonotherapyforretinopathyofprematuritymultimodalmachinelearningmodelstudy
AT yichenbai predictionofreactivationafterantivascularendothelialgrowthfactormonotherapyforretinopathyofprematuritymultimodalmachinelearningmodelstudy
AT songfufeng predictionofreactivationafterantivascularendothelialgrowthfactormonotherapyforretinopathyofprematuritymultimodalmachinelearningmodelstudy
AT niancai predictionofreactivationafterantivascularendothelialgrowthfactormonotherapyforretinopathyofprematuritymultimodalmachinelearningmodelstudy
AT xiaohelu predictionofreactivationafterantivascularendothelialgrowthfactormonotherapyforretinopathyofprematuritymultimodalmachinelearningmodelstudy