Prediction of Visual Field Progression with Baseline and Longitudinal Structural Measurements Using Deep Learning

PURPOSE

Identifying glaucoma patients at high risk of progression based on widely available structural data is an unmet task in clinical practice. We test the hypothesis that baseline or serial structural measures can predict visual field (VF) progression with deep learning (DL).

DESIGN

Development of a DL algorithm to predict VF progression.

METHODS

3,079 eyes (1,765 patients) with various types of glaucoma and ≥5 VFs, and ≥3 years of follow-up from a tertiary academic center were included. Serial VF mean deviation (MD) rates of change were estimated with linear-regression. VF progression was defined as negative MD slope with p<0.05. A Siamese Neural Network with ResNet-152 backbone pre-trained on ImageNet was designed to predict VF progression using serial optic-disc photographs (ODP), and baseline retinal nerve fiber layer (RNFL) thickness. We tested the model on a separate dataset (427 eyes) with RNFL data from different OCT. The Main Outcome Measure was Area under ROC curve (AUC).

RESULTS

Baseline average (SD) MD was 3.4 (4.9)dB. VF progression was detected in 900 eyes (29%). AUC (95% CI) for model incorporating baseline ODP and RNFL thickness was 0.813 (0.757-0.869). After adding the second and third ODPs, AUC increased to 0.860 and 0.894, respectively (p<0.027). This model also had highest AUC (0.911) for predicting fast progression (MD rate <1.0 dB/year). Model's performance was similar when applied to second dataset using RNFL data from another OCT device (AUC=0.893; 0.837-0.948).

CONCLUSIONS

DL model predicted VF progression with clinically relevant accuracy using baseline RNFL thickness and serial ODPs and can be implemented as a clinical tool after further validation.

Data-driven prediction of continuous renal replacement therapy survival

Continuous renal replacement therapy (CRRT) is a form of dialysis prescribed to severely ill patients who cannot tolerate regular hemodialysis. However, as the patients are typically very ill to begin with, there is always uncertainty as to whether they will survive during or after CRRT treatment. Because of outcome uncertainty, a large percentage of patients treated with CRRT do not survive, utilizing scarce resources and raising false hope in patients and their families. To address these issues, we present a machine-learning-based algorithm to predict if patients will survive after being treated with CRRT. We use information extracted from electronic health records from patients who were placed on CRRT at multiple institutions to train a model that predicts CRRT survival outcome; on a held-out test set, the model achieved an area under the receiver operating curve of 0.929 (CI=0.917-0.942). Feature importance, error, and subgroup analyses identified consistently, mean corpuscular volume as a driving feature for model predictions. Overall, we demonstrate the potential for predictive machine-learning models to assist clinicians in alleviating the uncertainty of CRRT patient survival outcomes, with opportunities for future improvement through further data collection and advanced modeling.

Prediction of Central Visual Field Measures From Macular OCT Volume Scans With Deep Learning

Purpose

Predict central 10° global and local visual field (VF) measurements from macular optical coherence tomography (OCT) volume scans with deep learning (DL).

Methods

This study included 1121 OCT volume scans and 10-2 VFs from 289 eyes (257 patients). Macular scans were used to estimate 10-2 VF mean deviation (MD), threshold sensitivities (TS), and total deviation (TD) values at 68 locations. A three-dimensional (3D) convolutional neural network based on the 3D DenseNet121 architecture was used for prediction. We compared DL predictions to those from baseline linear models. We carried out 10-fold stratified cross-validation to optimize generalizability. The performance of the DL and baseline models was compared based on correlations between ground truth and predicted VF measures and mean absolute error (MAE; ground truth - predicted values).

Results

Average (SD) MD was -9.3 (7.7) dB. Average (SD) correlations between predicted and ground truth MD and MD MAE were 0.74 (0.09) and 3.5 (0.4) dB, respectively. Estimation accuracy deteriorated with worsening MD. Average (SD) Pearson correlations between predicted and ground truth TS and MAEs for DL and baseline model were 0.71 (0.05) and 0.52 (0.05) (P < 0.001) and 6.5 (0.6) and 7.5 (0.5) dB (P < 0.001), respectively. For TD, correlation (SD) and MAE (SD) for DL and baseline models were 0.69 (0.02) and 0.48 (0.05) (P < 0.001) and 6.1 (0.5) and 7.8 (0.5) dB (P < 0.001), respectively.

Conclusions

Macular OCT volume scans can be used to predict global central VF parameters with clinically relevant accuracy.

Translational Relevance

Macular OCT imaging may be used to confirm and supplement central VF findings using deep learning.

Prediction of visual field progression with serial optic disc photographs using deep learning

AIM

We tested the hypothesis that visual field (VF) progression can be predicted with a deep learning model based on longitudinal pairs of optic disc photographs (ODP) acquired at earlier time points during follow-up.

METHODS

3919 eyes (2259 patients) with ≥2 ODPs at least 2 years apart, and ≥5 24-2 VF exams spanning ≥3 years of follow-up were included. Serial VF mean deviation (MD) rates of change were estimated starting at the fifth visit and subsequently by adding visits until final visit. VF progression was defined as a statistically significant negative slope at two consecutive visits and final visit. We built a twin-neural network with ResNet50-backbone. A pair of ODPs acquired up to a year before the VF progression date or the last VF in non-progressing eyes were included as input. Primary outcome measures were area under the receiver operating characteristic curve (AUC) and model accuracy.

RESULTS

The average (SD) follow-up time and baseline VF MD were 8.1 (4.8) years and -3.3 (4.9) dB, respectively. VF progression was identified in 761 eyes (19%). The median (IQR) time to progression in progressing eyes was 7.3 (4.5-11.1) years. The AUC and accuracy for predicting VF progression were 0.862 (0.812-0.913) and 80.0% (73.9%-84.6%). When only fast-progressing eyes were considered (MD rate < -1.0 dB/year), AUC increased to 0.926 (0.857-0.994).

CONCLUSIONS

A deep learning model can predict subsequent glaucoma progression from longitudinal ODPs with clinically relevant accuracy. This model may be implemented, after validation, for predicting glaucoma progression in the clinical setting.

Efficacy of COVID-19 vaccines by race and ethnicity

OBJECTIVES

Vaccine uptake amongst ethnic minority populations has been persistently lower, which may be because of socio-economic factors such as health literacy and health insurance status. This review aimed to assess to what extent COVID-19 clinical trials have considered the impact of race and ethnicity on COVID-19 vaccine safety and efficacy.

STUDY DESIGN

This was a systematic review.

METHODS

Data regarding ethnicity in COVID-19 vaccine clinical trials were systematically reviewed according to Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines in this systematic review, which ran from inception until June 2021. Three international databases, PubMed, Scopus and Web of Science, were used to conduct systematic article searches. Only two studies reported vaccine efficacy among ethnic minority groups.

RESULTS

The efficacy of the mRNA-1273 vaccine was confirmed to be 95% in Caucasians and 97.5% in 'people of colour' in a study by Baden et al. In another study by Polack et al., BNT162b2 mRNA vaccine efficacy was reported to be 95.2% in Caucasians, 100% in Afro-Caribbean or African Americans, 94.2% in Hispanic or Latinx and 95.4% in non-Hispanic, non-Latinx people.

CONCLUSIONS

Given the highly differing effect of COVID-19 on the Afro-Caribbean, Hispanic and South Asian populations, it is imperative for COVID-19 vaccine clinical trials to thoroughly assess the safety and efficacy of vaccines in different ethnicities and, if necessary, develop ethnicity-specific protocols, which can minimise the disproportionate effect of COVID-19 on ethnic minority populations.

P5308Mediterranean-style diet for the primary and secondary prevention of cardiovascular disease: Cochrane systematic review and meta-analysis of randomised clinical trials

Background

Observational studies have confirmed the benefits of adherence to a Mediterranean dietary pattern on cardiovascular disease (CVD) but the randomised controlled trial (RCT) evidence is limited.

Objective

To determine the effectiveness of a Mediterranean-style diet for the primary and secondary prevention of CVD.

Methods

We searched the Cochrane Central Register of Controlled Trials, MEDLINE, EMBASE, Web of Science, DARE, HTA, NHS EED and trial registers (September 2018). We selected RCTs in healthy adults and adults at high risk of CVD (primary prevention) and those with established CVD (secondary prevention). Both of the following key components were required for our definition of a Mediterranean-style diet: high monounsaturated/saturated fat ratio and a high intake of plant based foods, including fruits, vegetables, and legumes. The intervention could be dietary advice, provision of relevant foods or both. The comparison group received either no intervention, minimal intervention, usual care or another dietary intervention. Outcomes included clinical events and CVD risk factors. We included only studies with follow-up periods of 3 months or more.

Results

Overall, 30 RCTs (12,461 participants randomised) and 7 ongoing trials met our inclusion criteria, whereas 22 primary prevention trials and 6 secondary prevention trials were analysed. Low quality evidence shows little or no effect of the PREDIMED (7747 randomised) intervention (advice to follow a Mediterranean diet plus supplemental extra virgin olive oil or tree nuts) compared to a low fat diet on CVD mortality (HR 0.81 (95% CI 0.5, 1.32)) or total mortality (HR 1.0 (95% CI 0.81, 1.24)) over 4.8 years. There was however a reduction in the number of strokes with the PREDIMED intervention (HR 0.6 (95% CI 0.45, 0.8), moderate quality evidence). For secondary prevention, in the Lyon Diet Heart Study (605 CVD patients), there was moderate quality evidence of a reduction in CVD mortality (HR 0.35 (95% CI 0.15, 0.82)) and total mortality (HR 0.44 (95% CI 0.21, 0.92)) with the intervention, over 46 months. For CVD risk factors, in primary prevention trials, there was low quality evidence for a possible small reduction in total cholesterol (−0.16 mmol/L (95% CI −0.32, 0.00), and moderate quality evidence for a reduction in SBP (−2.99 mmHg (95% CI −3.45, −2.53)) and DBP (−2.0 mmHg (95% CI −2.29, −1.71)). In secondary prevention trials, there was moderate quality evidence of no effect of a Mediterranean-style diet on lipid levels and low or very low quality evidence for blood pressure.

Conclusions

Despite the relatively large number of studies included in this review, there is still some uncertainty regarding the effects of a Mediterranean-style diet on clinical endpoints and CVD risk factors for both primary and secondary prevention. The ongoing studies may provide more certainty in the future.