Aug 2026· Seminars in Ophthalmology· pp.
1-9
· 0 citations· 19 references
Medicine
TL;DR
A model integrating corneal biomechanical parameters, genetic risk scores, and tear molecular biomarkers was developed to predict the risk of NTG progression and demonstrated potential clinical utility.
Abstract
Objective
Normal-tension glaucoma (NTG) is characterized by progressive optic nerve damage despite intraocular pressure remaining consistently within the normal range. Predicting disease progression in patients with confirmed NTG remains challenging. This study aimed to develop and validate an interpretable machine learning model integrating genetic risk scores and corneal biomechanical parameters to predict progression risk in patients with NTG, identify independent predictors, and quantify the contribution of individual features to support precision clinical management.
Methods
A total of 342 patients with NTG were consecutively enrolled at a tertiary hospital and randomly allocated to training set (n = 238) and validation set (n = 104) at a ratio of 7:3. Baseline characteristics and six core indicators were collected. Candidate predictors were selected through univariate analysis and least absolute shrinkage and selection operator (LASSO) regression with 10-fold cross-validation and the λ-1se criterion. Independent predictors were subsequently identified using multivariable logistic regression. Three machine learning models-random forest (RF), support vector machine (SVM), and logistic regression (LR)-were developed. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis (DCA). SHapley Additive exPlanations (SHAP) analysis was performed to interpret feature contributions.
Results
Univariate analysis revealed significant differences in all six indicators between the progression and non-progression groups (p < .05). Multivariable logistic regression further confirmed that all six indicators were independently associated with NTG progression (p < .05). The RF model demonstrated the best predictive performance, with an AUC of 0.760 (95% confidence interval (CI) : 0.678-0.842) in the training set and 0.747 (95% CI: 0.623-0.871) in the validation set. It outperformed both the SVM model (training AUC = 0.704; validation AUC = 0.694) and the LR model (training AUC = 0.742; validation AUC = 0.729). SHAP analysis ranked the features, in descending order of contribution, as mean retinal nerve fibre layer (RNFL) thickness, first applanation velocity, visual field mean deviation, relative tear GNAI1 level, polygenic risk score for NTG, and relative tear PRDX4 level. The calibration curves showed good agreement between predicted and observed probabilities, while DCA demonstrated a high clinical net benefit across a broad range of threshold probabilities.
Conclusion
A model integrating corneal biomechanical parameters, genetic risk scores, and tear molecular biomarkers was developed to predict the risk of NTG progression and demonstrated potential clinical utility. This model may provide a quantitative reference for risk stratification and personalised management in patients with NTG.
INTRODUCTION
This study aims to develop a machine-learning-based risk prediction model for a long-term visual prognosis in patients with proliferative diabetic retinopathy (PDR) following pars plana vitrectomy (PPV).
METHODS
We analysed 609 PDR patients (609 eyes) who underwent PPV at Shanxi Eye Hospital from January 1, 2022, to January 1, 2025. The dataset was randomly split into training and validation sets at an 8:2 ratio. Candidate risk factors were identified using LASSO regression, followed by multivariate logistic regression to determine independent predictors. Machine learning algorithms were then trained to construct the prediction model, with performance evaluated by AUC-ROC, accuracy, precision, recall, and F1 score. Calibration was assessed via calibration curves, and clinical utility by decision curve analysis (DCA).
RESULTS
LASSO regression and multivariate logistic regression indicated that several factors influenced postoperative long-term visual prognosis. These included Renal Insufficiency (OR = 6.932, 95% CI: 3.394-14.158), Preoperative iris neovascularization (OR = 7.674, 95% CI: 3.699-15.920), Silicone oil tamponade (OR = 2.799, 95% CI: 1.641-4.707), Indirect bilirubin (IBIL) (OR = 0.902, 95% CI: 0.829-0.981) (p < 0.05). LightGBM was found to be the best for predicting postoperative long-term visual prognosis risk in PDR patients. The LightGBM model demonstrated good calibration in both training and validation sets. DCA of the validation set showed clinical net benefit at low-to-moderate risk thresholds, outperforming both 'treat-all' and 'treat-none' strategies.
CONCLUSIONS
In conclusion, this study developed a machine learning-based prognostic model for long-term visual prognosis in PDR patients after PPV, visualized as a proof-of-concept web calculator to assist clinical staff in early risk identification and support personalised treatment planning, pending external validation and prospective evaluation.
Machine learning–based prediction of Kmax progression may aid in scheduling risk-adapted follow-up appointments, potentially leading to more rapid identification of progression-suspect KC cases.
A. Schlatter, L. Pomberger, A. Honeder et al.· Translational Vision Science...· 0 citations
This study aimed to explore the risk factors associated with bilateral involvement and to develop a predictive model for visual prognosis in Chinese patients with non-arteritic anterior ischemic optic neuropathy (NAION). In this retrospective database-related meta-analysis, we retrospectively identified patients with NAION from the Chinese Neuro-Ophthalmic Diseases project database between September 2020 and December 2024. The clinical characteristics of the patients were summarized. Logistic and stepwise regression analyses were performed to identify the factors associated with bilateral involvement. Patients were randomly divided into training (75%) and validation (25%) cohorts. Least absolute shrinkage and selection operator (LASSO) and logistic regression analyses were used to develop a model for predicting factors associated with a best-corrected visual acuity (BCVA) ≤ 0.3 (decimal). The study included 895 patients (560 [62.57%] males, 1,128 eyes; mean age: 55.6 ± 10.4 years). Bilateral NAION was present in 226 (25.3%) patients. At the follow-up examination, 522 patients (730 eyes) had a BCVA ≤ 0.3 in 369 (50.6%) eyes. Bilateral NAION involvement was associated with hyperlipidemia (t = 2.02, P = 0.04), hematologic disorders (t = 2.31, P = 0.02), and smoking (t = 4.79, P < 0.01). Risk factors for a BCVA ≤ 0.3 at follow-up were a lower BCVA at onset (odds ratio [OR] = 0.72, 95% confidence interval [CI]: 0.64–0.82, P < 0.01), diabetes mellitus (OR = 2.97, 95% CI: 1.10–8.03, P = 0.03), hyperhomocysteinemia (OR = 11.59, 95% CI: 1.87–71.97, P = 0.01), and macular serous detachment (OR = 6.70, 95% CI: 1.34–33.40, P = 0.02). The area under the receiver operating characteristic curve was 0.87 (95% CI: 0.83–0.87) for the training cohort and 0.86 (95% CI: 0.80–0.86) for the validation cohort. Hyperlipidemia, hematologic disorders, and smoking were significant risk factors for bilateral NAION, whereas the severity of vision loss at onset, diabetes mellitus, hyperhomocysteinemia, and macular serous detachment were associated with poor visual prognosis in Chinese patients with NAION.
Xintong Xu, Mingming Sun, S. Cao et al.· Eye and Vision· 0 citations
ML models can distinguish high-risk KC groups based on clinical risk factors, facilitating risk stratification and early lifestyle interventions and confirmed by univariable logistic regression.
Kaiyue Du, R. Peng, Yueguo Chen et al.· PLoS ONE· 0 citations
Background/Aims: Neovascular glaucoma (NVG) is a severe, secondary glaucoma. This study aimed to identify factors associated with vision, intraocular pressure (IOP), and ocular pain outcomes. Methods: The cohort included all patients diagnosed with NVG during 2008-2024 at Helsinki University Hospital, Finland. Linear mixed-effects models used pre-specified covariates, whereas machine learning was given the full longitudinal data with biomicroscopic findings as an exploratory approach. Results: 626 patients were analysed. Worse baseline vision and a closed angle were associated with worse follow-up vision. Treatments were associated with lower IOP and less pain rather than better vision. Age, sex and comorbidity were largely not associated with the outcomes. Glaucoma drainage devices showed the greatest initial IOP reduction (-10.2 mmHg, 95% confidence interval, CI -11.9 to -8.6 mmHg), followed by transscleral cyclophotocoagulation (TSCPC, -4.7 mmHg, 95% CI -5.8 to -3.7 mmHg) and peripheral retinal cryotherapy (-2.2 mmHg, 95% CI -3.1 to -1.4 mmHg). TSCPC and cryotherapy were also associated with reduced pain (odds ratio 0.51 and 0.46). Pan-retinal photocoagulation and anti-VEGF showed smaller IOP reductions, with a pain reduction for pan-retinal photocoagulation only. Both methods agreed, and machine learning added no novel clinical findings. Conclusions: Vision in this cohort was largely set by the state of the eye at diagnosis. IOP control and pain relief therefore remain realistic goals even when sight cannot be saved. Peripheral retinal cryotherapy stood out, linked to both lower IOP and less pain, seldom reported in NVG. These associations from a large, unselected cohort identify treatments worth comparing prospectively.
G. Simons, M. von Fersen, A. Dahlberg et al.· medRxiv· 0 citations
PURPOSE
To propose a comprehensive, evidence-based classification system for open-angle glaucoma (OAG) that integrates risk profiling, modern optic nerve functional and structural diagnostic testing and analytics, and disease velocity.
METHODS
We synthesized data from landmark randomized clinical trials and utility analysis studies. Critical gaps in current systems were identified, specifically regarding the 'pre-perimetric' window and macular vulnerability. A new staging framework was developed to align disease definitions with biological severity, rates of progression, and therapeutic urgency.
RESULTS
The proposed system stratifies the glaucoma continuum into seven stages. Stages 0, 1, and 2 are assigned using a formalized risk-factor framework in eyes without glaucomatous optic neuropathy (GON). Stage 0 (healthy) denotes individuals with no identifiable risk factors for glaucoma. Stage 1 (At Risk) corresponds to a single minor risk factor with otherwise low calculated risk (e.g., OHTS 5-year risk less than 5% rather than arbitrary IOP cutoffs), whereas Stage 2 (Glaucoma Suspect) requires at least one major risk factor or at least two minor risk factors. Stage 3 (Mild Glaucoma) reflects the presence of GON detected by optical coherence tomography (OCT) prior to visual field loss. Stage 4 (Moderate Glaucoma) denotes the presence of peripheral visual field damage limited to one visual hemifield. Stage 5 (Severe Glaucoma) utilizes central 5-degree involvement and/or widespread disease to reflect Quality of Life impact. Stage 6 (End-stage Glaucoma) reflects significant glaucoma-related visual disability. A novel "(+) Disease" modifier, analogous to retinopathy of prematurity staging systems, is introduced to denote clinically-significant active progression, signaling the need for more intensive surveillance or treatment.
CONCLUSION
We propose a comprehensive staging framework for open-angle glaucoma that integrates structural imaging, functional testing, and progression risk into a unified classification system. By incorporating OCT-defined glaucomatous optic neuropathy and a modifier for active progression, this framework is intended to align disease classification with contemporary diagnostics and longitudinal risk assessment.
C. Gustavo De Moraes, Jeffrey M. Liebmann· American journal of ophthalm...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
