XEN Gel Stent Versus Nonpenetrating Deep Sclerectomy in Ocular Hypertension and Open Angle Glaucoma Patients.

PRCIS: XEN gel stent and nonpenetrating deep sclerectomy, both either alone or in combination with cataract surgery, significantly lowered the intraocular pressure (IOP) and reduced the number of antiglaucoma medications in patients with open angle glaucoma, with no significant differences between them. PURPOSE: To compare the surgical outcomes of XEN45 implant and nonpenetrating deep sclerectomy (NPDS), either alone or in combination with cataract surgery, in patients with ocular hypertension and open angle glaucoma (OAG). A retrospective and single-center cohort study was conducted on consecutive patients who underwent a XEN45 implant or an NPDS, either alone or in combination with phacoemulsification. The primary endpoint was the mean change in IOP from the baseline to the last follow-up visit. One hundred twenty-eight eyes, 65 (50.8%) eyes in the NPDS group and 63 (49.2%) eyes in the XEN group, were included in the study. The mean preoperative IOP was significantly lowered from 17.6±5.3 mm Hg and 17.8±6.2 mm Hg to 12.6±2.6 mm Hg and 13.8±2.8 mm Hg at month 12 in the XEN and NPDS groups, respectively; P <0.0001 each. At month 12, 70 (54.7%) eyes were classified as a success, with no significant differences between XEN (57.1%; 36/63 eyes) and NPDS (52.3%; 34/65 eyes) (mean difference: 4.8%; 95% CI: -30.5% to 20.8%; P =0.7115). The number of ocular hypotensive medications was significantly reduced in the XEN (from 2.1±0.7-0.2±0.5, P <0.0001) and in the NPDS (from 2.0±0.8 to 0.3±0.6, P <0.0001) groups, with no significant differences between them ( P =0.2629). The incidence of postoperative adverse events in the overall study population was 12.5%, with no significant differences between groups ( P =0.1275). Seven (11.1%) eyes underwent needling (XEN group) and 10 (15.4%) goniopuncture (NPDS group); P =0.4753. CONCLUSIONS: XEN45 implant and the NPDS, either alone or in combination with cataract surgery, significantly lowered IOP and reduced the number of ocular hypotensive medications in ocular hypertension and patients with open angle glaucoma.

High interpretable machine learning classifier for early glaucoma diagnosis.

AIM: To develop a classifier for differentiating between healthy and early stage glaucoma eyes based on peripapillary retinal nerve fiber layer (RNFL) thicknesses measured with optical coherence tomography (OCT), using machine learning algorithms with a high interpretability. METHODS: Ninety patients with early glaucoma and 85 healthy eyes were included. Early glaucoma eyes showed a visual field (VF) defect with mean deviation >-6.00 dB and characteristic glaucomatous morphology. RNFL thickness in every quadrant, clock-hour and average thickness were used to feed machine learning algorithms. Cluster analysis was conducted to detect and exclude outliers. Tree gradient boosting algorithms were used to calculate the importance of parameters on the classifier and to check the relation between their values and its impact on the classifier. Parameters with the lowest importance were excluded and a weighted decision tree analysis was applied to obtain an interpretable classifier. Area under the ROC curve (AUC), accuracy and generalization ability of the model were estimated using cross validation techniques. RESULTS: Average and 7 clock-hour RNFL thicknesses were the parameters with the highest importance. Correlation between parameter values and impact on classification displayed a stepped pattern for average thickness. Decision tree model revealed that average thickness lower than 82 µm was a high predictor for early glaucoma. Model scores had AUC of 0.953 (95%CI: 0.903-0998), with an accuracy of 89%. CONCLUSION: Gradient boosting methods provide accurate and highly interpretable classifiers to discriminate between early glaucoma and healthy eyes. Average and 7-hour RNFL thicknesses have the best discriminant power.