Measurement Reliability for Keratitis Morphology

Prediction of Visual Acuity in Patients With Microbial Keratitis

PURPOSE

The purpose of this study was to predict visual acuity (VA) 90 days after presentation for patients with microbial keratitis (MK) from data at the initial clinical ophthalmic encounter.

METHODS

Patients with MK were identified in the electronic health record between August 2012 and February 2021. Random forest (RF) models were used to predict 90-day VA < 20/40 [visual impairment (VI)]. Predictors evaluated included age, sex, initial VA, and information documented in notes at presentation. Model diagnostics are reported with 95% confidence intervals (CIs) for area under the curve (AUC), misclassification rate, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).

RESULTS

One thousand seven hundred ninety-one patients were identified. The presenting logMAR VA was on average 0.86 (Snellen equivalent and standard deviation = 20/144 ± 12.6 lines) in the affected or worse eye, and 43.6% with VI. VI at 90-day follow-up was present in the affected eye or worse eye for 26.9% of patients. The RF model for predicting 90-day VI had an AUC of 95% (CI: 93%-97%) and a misclassification rate of 9% (7%-12%). The percent sensitivity, specificity, PPV, and NPV were 86% (80%-91%), 92% (89%-95%), 81% (74%-86%), and 95% (92%-97%), respectively. Older age, worse presenting VA, and more mentions of "penetrating keratoplasty" and "bandage contact lens" were associated with increased probability of 90-day VI, whereas more mentions of "quiet" were associated with decreased probability of 90-day VI.

CONCLUSIONS

RF modeling yielded good sensitivity and specificity to predict VI at 90 days which could guide clinicians about the risk of poor vision outcomes for patients with MK.

The Role of Topical Povidone-Iodine in the Management of Infectious Keratitis: A Pilot Study

The aim of this prospective explorative study was to evaluate the safety and the effectiveness of topical polyvinylpyrrolidone-iodine (PVP-I) administered during the time-to-results period for pathogen identification and susceptibility testing in patients with infectious keratitis (IK). A corneal swab (CS) for antimicrobial evaluation was performed at enrollment (T0) and topical 0.66%-PVP-I was administered until the laboratory results were available (T1). Ulcer and infiltrate areas and infiltrate depths were compared between T0 and T1 (i.e., time-to-result period). Patients were then shifted to a specific antimicrobial therapy and followed up until resolution of their infiltrates (Tlast-TL). Twenty-five eyes were enrolled, and none showed clinical worsening leading to protocol withdrawal. At T1, ulcer and infiltrate areas showed significant improvement in Gram-positive IK (n = 13–52%; p = 0.027 and p = 0.019, respectively), remained stable in fungal IK (n = 5–20%; both p = 0.98) and increased in those with Gram-negative bacteria (n = 4–16%; p = 0.58 and p = 0.27). Eyes with negative cultures (n = 3–12%) showed complete resolution at T1 and did not initiate any additional antimicrobial therapy. The administration of 0.66% PVP-I during the time-to-result period seems to be a safe strategy in patients with IK while often sparing broad-spectrum antimicrobial agents. In addition, it showed to be effective in eyes with a Gram-positive bacterial infection.

Open-Source Automatic Biomarker Measurement on Slit-Lamp Photography to Estimate Visual Acuity in Microbial Keratitis

Purpose

To assess clinical applicability of automatic image analysis in microbial keratitis (MK) by evaluating the relationship between biomarker measurements on slit-lamp photography (SLP) and best-corrected visual acuity (BCVA).

Methods

Seventy-six patients with MK with SLP images and same-day logarithm of the minimum angle of resolution (logMAR) BCVA were evaluated. MK biomarkers (stromal infiltrate, white blood cell infiltration, corneal edema, hypopyon, epithelial defect) were segmented manually by ophthalmologists and automatically by a novel, open-source, deep learning–based segmentation algorithm. Five measurements (presence, maximum width, total area, proportion of the corneal limbus area affected, centrality) were calculated. Correlations between the measurements and BCVA were calculated. An automatic regression model estimated BCVA from the measurements. Differences in performance between using manual and automatic measurements were evaluated using William's test (for correlation) and the paired-sample t-test (for absolute error).

Results

Measurements had high correlations of 0.86 (manual) and 0.84 (automatic) with true BCVA. Estimated BCVA had average (mean ± SD) absolute errors of 0.39 ± 0.27 logMAR (manual, median: 0.30) and 0.35 ± 0.28 logMAR (automatic, median: 0.30) and high correlations of 0.76 (manual) and 0.80 (automatic) with true BCVA. Differences between using manual and automatic measurements were not statistically significant for correlations of measurements with true BCVA (P = .66), absolute errors of estimated BCVA (P = .15), or correlations of estimated BCVA with true BCVA (P = .60).

Conclusions

The proposed algorithm measured MK biomarkers as accurately as ophthalmologists. Measurements were highly correlated with and estimative of visual acuity.

Translational Relevance

This study demonstrates the potential of developing fully automatic objective and standardized strategies to aid ophthalmologists in the clinical assessment of MK.