Deep learning model using retinal vascular images for classifying schizophrenia.

Contemporary psychiatric diagnosis still relies on the subjective symptom report of the patient during a clinical interview by a psychiatrist. Given the significant variability in personal reporting and differences in the skill set of psychiatrists, it is desirable to have objective diagnostic markers that could help clinicians differentiate patients from healthy individuals. A few recent studies have reported retinal vascular abnormalities in patients with schizophrenia (SCZ) using retinal fundus images. The goal of this study was to use a trained convolution neural network (CNN) deep learning algorithm to detect SCZ using retinal fundus images. A total of 327 subjects [139 patients with Schizophrenia (SCZ) and 188 Healthy volunteers (HV)] were recruited, and retinal images were acquired using a fundus camera. The images were preprocessed and fed to a convolution neural network for the classification. The model performance was evaluated using the area under the receiver operating characteristic curve (AUC). The CNN achieved an accuracy of 95% for classifying SCZ and HV with an AUC of 0.98. Findings from the current study suggest the potential utility of deep learning to classify patients with SCZ and assist clinicians in clinical settings. Future studies need to examine the utility of the deep learning model with retinal vascular images as biomarkers in schizophrenia with larger sample sizes.

Association between retinal vascular measures and brain white matter lesions in schizophrenia.

OBJECTIVE: Recent studies have examined retinal vascular abnormalities in schizophrenia as retinal vascular imaging is a non-invasive proxy to cerebral microvasculature. However, relation between retinal vascular abnormalities and brain structure is not well examined in schizophrenia. Hence in this study, for the first time, we examined the relationship between retinal vascular measures and brain white matter lesions in schizophrenia. We examined brain white matter lesions as they are considered a predictive marker for future adverse cerebrovascular event. METHODS: We acquired retinal vascular images of both eyes using a non-mydriatic camera and calculated retinal vascular diameter, tortuosity, trajectory and fractal dimension using validated methods. All patients underwent Magnetic Resonance Imaging of bran and we computed white matter hypo-intensities using Freesurfer software. We performed a linear regression analysis to examine the relationship between white matter hypo-intensities and retinal vascular measures controlling for age, sex, fasting blood sugar, creatinine, whole-brain volume, and antipsychotic dose. RESULTS: The regression model was significant in Schizophrenia patients (R=0.983;R2 =0.966;-F=10.849;p = 0.008) but not in healthy volunteers (R=0.828;R2 =0.686;F=0.182; p = 0.963). Among the retinal vascular measures, arterial tortuosity (ß = 0.963;p-0.002), tortuosity (ß = -1.002;p = 0.001) and fractal dimension (ß = -0.688;p = 0.014) were significant predictors of white matter lesions. DISCUSSION: The current study's findings support the conclusion that retinal vascular fractal dimension and tortuosity are associated with changes in cerebral white matter and may be considered proxy markers for cerebral microvasculature in schizophrenia. Considering the relationship between white matter lesions and stroke, these observations could have important clinical implications to screen schizophrenia patients for risk of adverse cerebrovascular event.

Factors affecting compliance to intravitreal anti-vascular endothelial growth factor therapy in Indian patients with retinal vein occlusion, age-related macular degeneration, and diabetic macular edema.

PURPOSE: To evaluate the rate of compliance and the reasons for loss to follow-up in Indian patients with diabetic macular edema (DME), age-related macular degeneration (AMD), and retinal vein occlusion (RVO) being treated with anti-vascular endothelial growth factor (VEGF) therapy. METHODS: This was a retrospective single-center study. Patients with DME, AMD, or RVO were eligible if they initiated anti-VEGF therapy between January 2013 and December 2017. Patients' data were obtained from hospital electronic records, including the number of injections received, visits, details of follow-up, missed appointments, and reasons for loss to follow-up (>365 days). RESULTS: A total of 648 patients were eligible for the study, of which 334 (51.54%) patients were lost to follow-up. Overall, 343 (64.96%) were males and the overall mean (SD) age was 66.40 (7.44) years. A total of 376 (58.0%) patients had a history of diabetes and 364 (56.2%) patients had a history of hypertension. Further, 127 (38.0), 112 (33.5), and 95 (28.4) had DME, AMD, and RVO, respectively and were lost to follow-up. The most commonly reported reason for loss to follow-up was "non-affordability" (n = 120; 41.1%) followed by "no improvement in vision" (n = 83; 28.4%). "No improvement in vision" (42.2%) and "non-affordability" (37.5%) were higher among patients with DME. No association was found in gender- and treatment-wise distribution of reasons for loss to follow-up. CONCLUSION: The results showed that around half of the patients with DME, AMD, and RVO were lost to follow-up to intravitreal anti-VEGF therapy, and the most common factors were "non-affordability" and "no improvement in vision."

Serum Phosphate and Microvascular Function in a Population-Based Cohort.

BACKGROUND AND OBJECTIVES: Higher serum phosphate is associated with cardiovascular events and all-cause mortality. Explanations of this association have focused on large vessel calcification and stiffness. Studies suggest that a higher serum phosphate induces microvascular dysfunction, but relationships in humans with direct measures of microvascular function are lacking. DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS: We performed a cross-sectional analysis of 3189 community-living participants that underwent skin capillaroscopy, laser-Doppler flowmetry, and flicker light-induced retinal vessel responses. We used linear regression to assess the association between serum phosphate and each microvascular outcome. The primary outcome was skin capillary recruitment during postocclusive peak reactive hyperemia by capillaroscopy. Secondary outcomes included capillary recruitment during venous congestion, heat-induced skin hyperemic response, flicker light-induced retinal arteriolar, and venular dilation. RESULTS: The mean age of the cohort was 59±8 years, 48% were women, 7% had an eGFR <60 ml/min per 1.73 m2, and the mean serum phosphate concentration was 3.2±0.5 mg/dl. A 1 mg/dl higher serum phosphate was independently associated with a 5.0% lower postocclusive capillary recruitment (95% CI, -10.0% to -0.1%). Results were similar for capillary recruitment with venous congestion (-4.5%; 95% CI, -9.8% to 0.7%). A 1 mg/dl higher serum phosphate was also independently associated with a 0.23% lower retinal venular dilation in response to flicker light (95% CI, -0.44% to -0.02%). A higher serum phosphate was not associated with change in flicker light-induced retinal arteriolar dilation or heat-induced skin hyperemic response, however a higher serum phosphate was associated with a lower heat-induced skin hyperemic response among men (-149% [95% CI, -260 to -38] per 1 mg/dl higher serum phosphate) but not women (P interaction, 0.01). CONCLUSIONS: Higher serum phosphate concentrations, even within the normal range, are associated with microvascular dysfunction in community-living individuals. PODCAST: This article contains a podcast at https://www.asn-online.org/media/podcast/CJASN/2019_09_20_CJN02610319.mp3.

Genetic analysis and clinical phenotype of two Indian families with X-linked choroideremia.

PURPOSE: This study aims to describe the phenotype and genotype of two Indian families affected with X-linked choroideremia (CHM). MATERIALS AND METHODS: In these two families, the affected individuals and unaffected family members underwent a comprehensive ophthalmic examination including an optical coherence tomography (OCT) and electroretinogram. Blood samples were collected from the families for genetic analysis. Next generation sequencing (NGS) was done using a panel of 184 genes, which covered previously associated genes with retinal dystrophies. Sequencing data were analyzed for the CHM, RPGR, and RP2 genes that have been implicated in CHM and X-linked retinitis pigmentosa (XLRP), respectively. The identified variants were confirmed by Sanger sequencing in available individuals and unrelated controls. RESULTS: In two unrelated male patients, NGS analysis revealed a previously reported 3'-splice site change c.820-1G>C in the CHM gene in the first family and hemizygous mutation c.653G>C (p.Ser218X) in the second family. The asymptomatic family members were carriers for these mutations. Spectral domain-OCT showed loss of outer retina, preservation of the inner retina, and choroidal thinning in the affected males and retinal pigment epithelial changes in the asymptomatic carriers. The identified mutations were not present in 100 controls of Indian origin. There were no potential mutations found in XLRP-associated (RPGR and RP2) genes. CONCLUSION: This report describes the genotype and phenotype findings in patients with CHM from India. The identified genetic mutation leads to lack of Rab escort protein-1 (REP-1) or affects the production of a REP-1 protein that is likely to cause retinal abnormalities in patients.