Zihan Huang, Di Gong, Cuicui Tang, Jinghui Wang, Chenchen Zhang, Kuanrong Dang, Xiaoyan Chai, Jiantao Wang, Zhichao Yan
{"title":"A risk prediction model for neovascular glaucoma secondary to proliferative diabetic retinopathy based on Boruta feature selection and random forest.","authors":"Zihan Huang, Di Gong, Cuicui Tang, Jinghui Wang, Chenchen Zhang, Kuanrong Dang, Xiaoyan Chai, Jiantao Wang, Zhichao Yan","doi":"10.3389/fcell.2025.1604832","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Neovascular glaucoma (NVG) is one of the most severe complications of proliferative diabetic retinopathy (PDR), carrying a high risk of blindness. Establishing an effective risk prediction model can assist clinicians in early identification of high-risk patients and implementing personalized interventions to reduce the incidence of vision impairment. This study aimed to develop and evaluate a risk prediction model for NVG in PDR patients based on the Boruta feature selection method and random forest algorithm to improve clinical predictive performance.</p><p><strong>Methods: </strong>This retrospective study included 365 PDR patients treated at Shenzhen Eye Hospital between January 2019 and December 2024, comprising 269 controls (non-NVG) and 96 cases (NVG). The Boruta feature selection method was employed to identify key features associated with NVG development in PDR. A risk prediction model was then constructed using the random forest algorithm. Model performance was evaluated based on accuracy, sensitivity, specificity, and area under the curve (AUC). Additionally, calibration curves and decision curve analysis (DCA) were used to assess clinical utility. All data analyses and modeling were performed in R (version 4.2.3).</p><p><strong>Results: </strong>The Boruta algorithm selected 12 significant predictive features. The random forest-based model achieved an accuracy of 90.74%, sensitivity of 82.14%, specificity of 93.75%, and an AUC of 0.87, demonstrating strong predictive performance. Calibration curves indicated reliable prediction probabilities within the 0.4-0.8 range. Decision curve analysis revealed substantial clinical net benefit across threshold probabilities of 0.2-0.8.</p><p><strong>Conclusion: </strong>The Boruta-guided random forest model developed in this study exhibits excellent predictive performance and clinical applicability for assessing NVG risk in PDR patients.</p>","PeriodicalId":12448,"journal":{"name":"Frontiers in Cell and Developmental Biology","volume":"13 ","pages":"1604832"},"PeriodicalIF":4.6000,"publicationDate":"2025-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12247303/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in Cell and Developmental Biology","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.3389/fcell.2025.1604832","RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"CELL BIOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Background: Neovascular glaucoma (NVG) is one of the most severe complications of proliferative diabetic retinopathy (PDR), carrying a high risk of blindness. Establishing an effective risk prediction model can assist clinicians in early identification of high-risk patients and implementing personalized interventions to reduce the incidence of vision impairment. This study aimed to develop and evaluate a risk prediction model for NVG in PDR patients based on the Boruta feature selection method and random forest algorithm to improve clinical predictive performance.
Methods: This retrospective study included 365 PDR patients treated at Shenzhen Eye Hospital between January 2019 and December 2024, comprising 269 controls (non-NVG) and 96 cases (NVG). The Boruta feature selection method was employed to identify key features associated with NVG development in PDR. A risk prediction model was then constructed using the random forest algorithm. Model performance was evaluated based on accuracy, sensitivity, specificity, and area under the curve (AUC). Additionally, calibration curves and decision curve analysis (DCA) were used to assess clinical utility. All data analyses and modeling were performed in R (version 4.2.3).
Results: The Boruta algorithm selected 12 significant predictive features. The random forest-based model achieved an accuracy of 90.74%, sensitivity of 82.14%, specificity of 93.75%, and an AUC of 0.87, demonstrating strong predictive performance. Calibration curves indicated reliable prediction probabilities within the 0.4-0.8 range. Decision curve analysis revealed substantial clinical net benefit across threshold probabilities of 0.2-0.8.
Conclusion: The Boruta-guided random forest model developed in this study exhibits excellent predictive performance and clinical applicability for assessing NVG risk in PDR patients.
期刊介绍:
Frontiers in Cell and Developmental Biology is a broad-scope, interdisciplinary open-access journal, focusing on the fundamental processes of life, led by Prof Amanda Fisher and supported by a geographically diverse, high-quality editorial board.
The journal welcomes submissions on a wide spectrum of cell and developmental biology, covering intracellular and extracellular dynamics, with sections focusing on signaling, adhesion, migration, cell death and survival and membrane trafficking. Additionally, the journal offers sections dedicated to the cutting edge of fundamental and translational research in molecular medicine and stem cell biology.
With a collaborative, rigorous and transparent peer-review, the journal produces the highest scientific quality in both fundamental and applied research, and advanced article level metrics measure the real-time impact and influence of each publication.