Machine Learning-Based Automated Detection of Hydroxychloroquine Toxicity and Prediction of Future Toxicity Using Higher-Order OCT Biomarkers

Automated Evaluation of Ellipsoid Zone At-Risk Burden for Detection of Hydroxychloroquine Retinopathy

BACKGROUND

Screening for hydroxychloroquine (HCQ) retinopathy is crucial to detecting early disease. A novel machine-learning-based optical coherence tomography (OCT) biomarker, Ellipsoid Zone (EZ) At-Risk, can quantitatively measure EZ alterations and at-risk areas for progressive EZ loss in a fully automated fashion. The purpose of this analysis was to compare the EZ At-Risk burden in eyes with HCQ toxicity to eyes without toxicity.

METHODS

IRB-approved image analysis study of 83 subjects on HCQ and 44 age-matched normal subjects. SD-OCT images were reviewed for evidence of HCQ retinopathy. A ML-based, fully automatic measurement of the percentage of the macular area with EZ At-Risk was performed.

RESULTS

The mean age for HCQ subjects was 67.1 ± 13.2 years and 64.2 ± 14.3 years for normal subjects. The mean EZ At-Risk macular burden in the "toxic" group (n = 38) was significantly higher (10.7%) compared to the "non-toxic" group (n = 45; 2.2%; p = 0.023) and the "normal" group (1.4%; p = 0.012). Additionally, the amount of EZ At-Risk burden was significantly correlated with the HCQ dose based on the actual (p = 0.016) and ideal body weight (p = 0.033).

CONCLUSIONS

The novel biomarker EZ-At Risk was significantly higher in subjects with evidence of HCQ retinopathy as well as significantly associated with HCQ dose. This novel biomarker should be further evaluated as a potential screening tool for subjects on HCQ.

Longitudinal Quantitative Ultrawidefield Angiographic Features in Diabetic Retinopathy Treated with Aflibercept from the Intravitreal Aflibercept as Indicated by Real-Time Objective Imaging to Achieve Diabetic Retinopathy Improvement Trial

OBJECTIVE

To report longitudinal trends of quantitative ultrawidefield fluorescein angiography (qUWFA) biomarkers in the Intravitreal Aflibercept as Indicated by Real-Time Objective Imaging to Achieve Diabetic Retinopathy Improvement (PRIME) diabetic retinopathy (DR) clinical trial.

DESIGN

Post hoc analysis of the PRIME prospective randomized DR clinical trial comparing intravitreal aflibercept treatment based on the DR severity score (DRSS) or quantitative leakage index for DR improvement (ClinicalTrials.gov identifier: NCT03531294).

PARTICIPANTS

Patients were enrolled with a DRSS level of 47A to 71A and best-corrected visual acuity of 20/800 or better. Key exclusion criteria were previous intravitreal injection, panretinal photocoagulation, vitrectomy, central-involving macular edema, or vitreous hemorrhage.

METHODS

A previously validated, machine learning-based qUWFA analysis platform was used for panretinal leakage index assessment and differentiation of generalized and perivascular leakage phenotypes. Additionally, microaneurysm count and ischemic index were quantified in panretinal and macular regions. The trends in these biomarkers and therapeutic response were studied over 1 year.

MAIN OUTCOME MEASURES

Longitudinal trends of qUWFA biomarkers. The impact of these qUWFA metrics on treatment response was assessed by studying their associations with time to 2-step DRSS improvement and number of treatment-free days.

RESULTS

Forty eyes from 40 subjects with DR were enrolled. Lower baseline generalized leakage was noted in eyes that attained the 2-step DRSS improvement in < 16 weeks (1.9% vs. 2.8%; P = 0.026). Baseline macular perivascular-generalized leakage ratio had a significant correlation with the number of treatment-free days (r = 0.4; P = 0.012). At the end of 1 year, therapy significantly reduced the mean panretinal (3.9% vs. 5.8%; P = 0.002) and macular (6.2% vs. 12.2%; P = 0.008) generalized leakage indices compared with baseline, as well as the mean panretinal perivascular leakage index (1.5% vs. 2.3%; P = 0.002). The mean panretinal ischemic index demonstrated a small but likely clinically insignificant decrease from 12.5% at baseline to 11.6% at year 1 (P = 0.016).

CONCLUSIONS

Down-trending leakage indices and microaneurysm counts were demonstrated over 1 year of anti-VEGF therapy. At baseline, DR eyes with lower generalized leakage responded to therapy more rapidly. Eyes with greater perivascular leakage relative to generalized leakage showed a longer-lasting anti-VEGF treatment response.

FINANCIAL DISCLOSURE(S)

Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Quantitative Fundus Autofluorescence in Systemic Chloroquine/Hydroxychloroquine Therapy: One Year Follow-Up

Purpose

Systemic chloroquine/hydroxychloroquine (CQ/HCQ) can cause severe ocular side effects including bull's eye maculopathy (BEM). Recently, we reported higher quantitative autofluorescence (QAF) levels in patients with CQ/HCQ intake. Here, QAF in patients taking CQ/HCQ in a 1-year follow-up is reported.

Methods

Fifty-eight patients currently or previously treated with CQ/HCQ (cumulative doses 94-2435 g) and 32 age- and sex-matched healthy subjects underwent multimodal retinal imaging (infrared, red free, fundus autofluorescence [FAF], QAF [488 nm], and spectral-domain optical coherence tomography (SD-OCT). For analysis, custom written FIJI plugins were used for image processing, multimodal image stacks assembling, and QAF calculation.

Results

Thirty patients (28 without BEM and 2 with BEM, age range = 25-69 years) were followed up (370 ± 63 days). QAF values in patients taking CQ/HCQ showed a significant increase between baseline and follow-up examination: 282.0 ± 67.9 to 297.7 ± 70.0 (QAF a.u.), P = 0.002. An increase up to 10% was observed in the superior macular hemisphere. Eight individuals (including 1 patient with BEM) had a pronounced QAF increase of up to 25%. Compared to healthy controls, QAF levels in patients taking CQ/HCQ were significantly increased (P = 0.04).

Conclusions

Our study confirms our previous finding of increased QAF in patients taking CQ/HCQ with a further significant QAF increase from baseline to follow-up. Whether pronounced QAF increase might predispose for rapid progression toward structural changes and BEM development is currently investigated in ongoing studies.

Translational Relevance

In addition to standard screening tools during systemic CQ/HCQ treatment, QAF imaging might be useful in CQ/HCQ monitoring and could serve as a screening tool in the future.

Unmet needs and future perspectives in hydroxychloroquine retinopathy

Retinopathy is a well-recognized toxic effect of hydroxychloroquine treatment. As hydroxychloroquine retinopathy is potentially a vision-threatening condition, early detection is imperative to minimize vision loss due to drug toxicity. However, early detection of hydroxychloroquine retinopathy is still challenging even with modern retinal imaging techniques. No treatment has been established for this condition, except for drug cessation to minimize further damage. In this perspective article, we aimed to summarize the knowledge gaps and unmet needs in current clinical practice and research in hydroxychloroquine retinopathy. The information presented in this article may help guide the future directions of screening practices and research in hydroxychloroquine retinopathy.

Review of Retinal Imaging Modalities for Hydroxychloroquine Retinopathy

This review provides an overview of conventional and novel retinal imaging modalities for hydroxychloroquine (HCQ) retinopathy. HCQ retinopathy is a form of toxic retinopathy resulting from HCQ use for a variety of autoimmune diseases, such as rheumatoid arthritis and systemic lupus erythematosus. Each imaging modality detects a different aspect of HCQ retinopathy and shows a unique complement of structural changes. Conventionally, spectral-domain optical coherence tomography (SD-OCT), which shows loss or attenuation of the outer retina and/or retinal pigment epithelium-Bruch's membrane complex, and fundus autofluorescence (FAF), which shows parafoveal or pericentral abnormalities, are used to assess HCQ retinopathy. Additionally, several variations of OCT (retinal and choroidal thickness measurements, choroidal vascularity index, widefield OCT, en face imaging, minimum intensity analysis, and artificial intelligence techniques) and FAF techniques (quantitative FAF, near-infrared FAF, fluorescence lifetime imaging ophthalmoscopy, and widefield FAF) have been applied to assess HCQ retinopathy. Other novel retinal imaging techniques that are being studied for early detection of HCQ retinopathy include OCT angiography, multicolour imaging, adaptive optics, and retromode imaging, although further testing is required for validation.

Automated Identification and Segmentation of Ellipsoid Zone At-Risk Using Deep Learning on SD-OCT for Predicting Progression in Dry AMD

BACKGROUND

The development and testing of a deep learning (DL)-based approach for detection and measurement of regions of Ellipsoid Zone (EZ) At-Risk to study progression in nonexudative age-related macular degeneration (AMD).

METHODS

Used in DL model training and testing were 341 subjects with nonexudative AMD with or without geographic atrophy (GA). An independent dataset of 120 subjects were used for testing model performance for prediction of GA progression. Accuracy, specificity, sensitivity, and intraclass correlation coefficient (ICC) for DL-based EZ At-Risk percentage area measurement was calculated. Random forest-based feature ranking of EZ At-Risk was compared to previously validated quantitative OCT-based biomarkers.

RESULTS

The model achieved a detection accuracy of 99% (sensitivity = 99%; specificity = 100%) for EZ At-Risk. Automatic EZ At-Risk measurement achieved an accuracy of 90% (sensitivity = 90%; specificity = 84%) and the ICC compared to ground truth was high (0.83). In the independent dataset, higher baseline mean EZ At-Risk correlated with higher progression to GA at year 5 (p < 0.001). EZ At-Risk was a top ranked feature in the random forest assessment for GA prediction.

CONCLUSIONS

This report describes a novel high performance DL-based model for the detection and measurement of EZ At-Risk. This biomarker showed promising results in predicting progression in nonexudative AMD patients.