Machine learning-couched treatment algorithms tailored to individualized profile of patients with primary anterior chamber angle closure predisposed to the glaucomatous optic neuropathy.

Background: Primary angle closure glaucoma (PACG) is still one of the leading causes of irreversible blindness, with a trend towards an increase in the number of patients to 32.04 million by 2040, an increase of 58.4% compared with 2013. Health risk assessment based on multi-level diagnostics and machine learning-couched treatment algorithms tailored to individualized profile of patients with primary anterior chamber angle closure are considered essential tools to reverse the trend and protect vulnerable subpopulations against health-to-disease progression. Aim: To develop a methodology for personalized choice of an effective method of primary angle closure (PAC) treatment based on comparing the prognosis of intraocular pressure (IOP) changes due to laser peripheral iridotomy (LPI) or lens extraction (LE). Methods: The multi-parametric data analysis was used to develop models predicting individual outcomes of the primary angle closure (PAC) treatment with LPI and LE. For doing this, we suggested a positive dynamics in the intraocular pressure (IOP) after treatment, as the objective measure of a successful treatment. Thirty-seven anatomical parameters have been considered by applying artificial intelligence to the prospective study on 30 (LE) + 30 (LPI) patients with PAC. Results and data interpretation in the framework of 3P medicine: Based on the anatomical and topographic features of the patients with PAC, mathematical models have been developed that provide a personalized choice of LE or LPI in the treatment. Multi-level diagnostics is the key tool in the overall advanced approach. To this end, for the future application of AI in the area, it is strongly recommended to consider the following:Clinically relevant phenotyping applicable to advanced population screeningSystemic effects causing suboptimal health conditions considered in order to cost-effectively protect affected individuals against health-to-disease transitionClinically relevant health risk assessment utilizing health/disease-specific molecular patterns detectable in body fluids with high predictive power such as a comprehensive tear fluid analysis. Supplementary Information: The online version contains supplementary material available at 10.1007/s13167-023-00337-1.

Detection of Primary Angle Closure Glaucoma Progression by Optical Coherence Tomography.

PURPOSE: To compare the role of spectral-domain optical coherence tomography (SD-OCT) in regard to retinal nerve fiber layer (RNFL) and ganglion cell complex (GCC) assessment in the detection of primary angle-closure glaucoma (PACG) and primary open-angle glaucoma (POAG) progression. MATERIALS AND METHODS: In the prospective study, 131 subjects with PACG and POAG were examined during 72 months with follow-up visits every 6 months. Visual field (VF) progression was detected using the Guided Progression Analysis (GPA) of the Humphrey visual field analyzer and structural change using SD-OCT while a significant negative trend for the RNFL and GCC was gauged. The diagnostic accuracy of RNFL and GCC thinning in the detection of glaucoma progression was compared between PACG and POAG eyes using the Kaplan-Meier method with the calculation of the log-rank test. RESULTS: Progression was detected in 57% of eyes with POAG and 59% of eyes with PACG. The rate of thinning of RNFL (-2.95±1.85 µm/y) and GCC (-3.22±2.96 µm/y) was significantly higher in PACG progression eyes compared with POAG [-1.64±2.00 µm/y (P=0.018) and -1.74±2.05 µm/y (P=0.046), respectively]. The progression was associated with initial pattern standard deviation in both glaucoma subtypes, while only in PACG-with long-term intraocular pressure fluctuations (cutoff >5.2 mm Hg) and lens thickness (cutoff >4.92 mm), and only in POAG-with initial focal loss volume of GCC (cutoff >1.5%).In PACG, the rate of the visual function deterioration correlated with GCC thinning rate (r=0.330, P=0.027), but not with the RNFL thinning rate (r=-0.010, P=0.79), while in POAG, it was significant for both RNFL thinning (r=0.296, P=0.039) and GCC thinning (r=0.359, P=0.011). In PACG patients with progressive GCC thinning, functional progression was detected earlier (log-rank test P≤0.001) than in patients with progressive RNFL thinning (log-rank test P=0.457), while for POAG, these results were P=0.012 and ≤0.001 for GCC and RNFL thinning, respectively. CONCLUSIONS: SD-OCT plays an important role in detecting PACG progression. In contrast to POAG, GCC thinning predicted functional loss better than RNFL thinning in PACG.

Predictors of Outcome in Selective Laser Trabeculoplasty: A Long-term Observation Study in Primary Angle-closure Glaucoma After Laser Peripheral Iridotomy Compared With Primary Open-angle Glaucoma.

PURPOSE: To evaluate the efficacy of selective laser trabeculoplasty (SLT) for patients with primary angle-closure glaucoma (PACG) following a YAG laser peripheral iridotomy (PI) in comparison with primary open-angle glaucoma (POAG) and to assess the predictors of outcome of SLT. PATIENTS AND METHODS: In retrospective study 68 patients with PACG after PI (68 eyes) and 74 POAG patients (74 eyes) were observed for 6 years. The effectiveness of SLT (20% reduction of intraocular pressure) was assessed using Kaplan-Meier survival analysis. The parameters for distinguishing the eyes with success and failure of SLT were detected by means of area under receiver operating characteristic curve (AUC). The predictive factors affecting SLT outcome were determined using Cox-regression analysis. RESULTS: The success ratio was 87% in both groups in 1 year and dropped to 4% in PACG and to 6% in POAG in 6 years. Corneal hysteresis [odds ratio (ОR)=0.367, Р=0.005 for PACG, ОR=0.446, Р=0.008 for POAG] and age (OR=1.182, P=0.012 for PACG, OR=1.164, P=0.002 for POAG) were detected as the predictors of SLT outcome. In PACG pre-SLT anterior chamber depth was additional predictor (ОR=0.242, Р=0.001). The number of pre-SLT pressure-lowing medications was higher in the eyes with SLT failure (AUC, 0.794; P=0.0005 in PACG and AUC, 0.760; P=0.014 in POAG). CONCLUSIONS: One-year efficacy of SLT in POAG and PACG after PI was high, but it was reduced in long-term period. Corneal hysteresis, age, and number of pre-SLT hypotensive eye drops were significant prognostic factors for treatment success in both glaucoma forms. In PACG pre-SLT anterior chamber depth affected the SLT outcome.

Value of Structural and Hemodynamic Parameters for the Early Detection of Primary Open-Angle Glaucoma.

PURPOSE: To compare the diagnostic value of ocular blood flow parameters and choroidal thickness (CT) with standard structural parameters for early glaucoma detection. METHODS: A total of 32 patients with pre-perimetric glaucoma were compared with 30 age-matched normal subjects. The thickness of the ganglion cell complex (GCC), retinal nerve fiber layer (RNFL), and the choroid and foveal loss volume (FLV) were measured by means of optical coherence tomography (OCT). Retrobulbar blood velocities (Color Doppler Imaging), corneal compensated intraocular pressure (IOPcc), and corneal hysteresis (CH) were also evaluated. Mean ocular perfusion pressure (MOPP) was calculated by measuring IOP and mean arterial blood pressure as MOPP = ([2/3 diastolic BP + 1/3 systolic BP] × 2/3-IOP). The value of each diagnostic indicator (z-value) was calculated using the Wilcoxon-Mann-Whitney test and the area under the receiver operating characteristic curve (AUC). RESULTS: The following indicators had the largest AUC and diagnostic value (z-value): mean blood flow velocity in the vortex veins (AUC 1.0; z-value 5.35) and central retinal vein (0.85; 3.74), diastolic blood flow velocity in the central retinal artery (0.73; 2.74) and lateral short posterior ciliary arteries (0.71; 2.53), IOPcc (0.74; -2.9), CH (0.69; 2.24), CT (0.69; -2.28), GCC (0.67; 2.05), and FLV (0.66; -1.86) to discriminate pre-perimetric glaucoma from healthy subjects. CONCLUSIONS: Interestingly, ocular hemodynamic parameters performed better than structural parameters in detecting early glaucoma. This highlights the potential of techniques to measure ocular blood flow in glaucoma diagnostics independently of the question whether perfusion abnormalities are a cause or a consequence of the disease.