RESUMEN

AIMS/HYPOTHESIS: To determine the extent to which diabetic retinopathy severity stage may be classified using machine learning (ML) and commonly used clinical measures of visual function together with age and sex. METHODS: We measured the visual function of 1901 eyes from 1032 participants in the Northern Ireland Sensory Ageing Study, deriving 12 variables from nine visual function tests. Missing values were imputed using chained equations. Participants were divided into four groups using clinical measures and grading of ophthalmic images: no diabetes mellitus (no DM), diabetes but no diabetic retinopathy (DM no DR), diabetic retinopathy without diabetic macular oedema (DR no DMO) and diabetic retinopathy with DMO (DR with DMO). Ensemble ML models were fitted to classify group membership for three tasks, distinguishing (A) the DM no DR group from the no DM group; (B) the DR no DMO group from the DM no DR group; and (C) the DR with DMO group from the DR no DMO group. More conventional multiple logistic regression models were also fitted for comparison. An interpretable ML technique was used to rank the contribution of visual function variables to predictions and to disentangle associations between diabetic eye disease and visual function from artefacts of the data collection process. RESULTS: The performance of the ensemble ML models was good across all three classification tasks, with accuracies of 0.92, 1.00 and 0.84, respectively, for tasks A-C, substantially exceeding the accuracies for logistic regression (0.84, 0.61 and 0.80, respectively). Reading index was highly ranked for tasks A and B, whereas near visual acuity and Moorfields chart acuity were important for task C. Microperimetry variables ranked highly for all three tasks, but this was partly due to a data artefact (a large proportion of missing values). CONCLUSIONS/INTERPRETATION: Ensemble ML models predicted status of diabetic eye disease with high accuracy using just age, sex and measures of visual function. Interpretable ML methods enabled us to identify profiles of visual function associated with different stages of diabetic eye disease, and to disentangle associations from artefacts of the data collection process. Together, these two techniques have great potential for developing prediction models using untidy real-world clinical data.

Asunto(s)

RESUMEN

Purpose: To assess the differences in rod-mediated dark adaptation (RMDA) between different grades of age-related macular degeneration (AMD) severity using an OCT-based criterion compared with those of AMD severity using the Beckman color fundus photography (CFP)-based classification and to assess the association between the presence of subretinal drusenoid deposits (SDDs) and RMDA at different grades of AMD severity using an OCT-based classification. Design: Cross-sectional study. Participants: Participants from the Northern Ireland Sensory Ageing study (Queen's University Belfast). Methods: Complete RMDA (rod-intercept time [RIT]) data, CFP, and spectral-domain OCT images were extracted. Participants were stratified into 4 Beckman groups (omitting late-stage AMD) and 3 OCT-based groups. The presence and stage of SDDs were identified using OCT. Main Outcome Measures: Rod-intercept time data (age-corrected). Results: Data from 459 participants (median [interquartile range] age, 65 [59-71] years) were stratified by both the classifications. Subretinal drusenoid deposits were detected in 109 eyes. The median (interquartile range) RMDA for the Beckman classification (Beckman 0-3, with 3 being intermediate age-related macular degeneration [iAMD]) groups was 6.0 (4.5-8.7), 6.6 (4.7-10.5), 5.7 (4.4-7.4), and 13.2 (6-21.1) minutes, respectively. OCT classifications OCT0-OCT2 yielded different median (interquartile range) values: 5.8 (4.5-8.5), 8.4 (5.2-13.3), and 11.1 (5.3-20.1) minutes, respectively. After correcting for age, eyes in Beckman 3 (iAMD) had statistically significantly worse RMDA than eyes in the other Beckman groups (P ≤ 0.005 for all), with no statistically significant differences between the other Beckman groups. Similarly, after age correction, eyes in OCT2 had worse RMDA than eyes in OCT0 (P ≤ 0.001) and OCT1 (P < 0.01); however, there was no statistically significant difference between eyes in OCT0 and eyes in OCT1 (P = 0.195). The presence of SDDs was associated with worse RMDA in OCT2 (P < 0.01) but not in OCT1 (P = 0.285). Conclusions: Eyes with a structural definition of iAMD have delayed RMDA, regardless of whether a CFP- or OCT-based criterion is used. In this study, after correcting for age, the RMDA did not differ between groups of eyes defined to have early AMD or normal aging, regardless of the classification. The presence of SDDs has some effect on RMDA at different grades of AMD severity.

RESUMEN

Purpose: To provide structural and functional evidence of inner retinal loss in diabetes prior to vascular changes and interpret the structure-function relationship in the context of an established neural model. Methods: Data from one eye of 505 participants (134 with diabetes and no clinically evident vascular alterations of the retina) were included in this analysis. The data were collected as part of a large population-based study. Functional tests included best-corrected visual acuity, Pelli-Robson contrast sensitivity, mesopic microperimetry, and frequency doubling technology perimetry (FDT). Macular optical coherence tomography volume scans were collected for all participants. To interpret the structure-function relationship in the context of a neural model, ganglion cell layer (GCL) thickness was converted to local ganglion cell (GC) counts. Results: The GCL and inner plexiform layer were significantly thinner in participants with diabetes (P < 0.05), with no significant differences in the macular retinal nerve fiber layer or the outer retina. All functional tests except microperimetry showed a significant loss in diabetic patients (P < 0.05). Both FDT and microperimetry showed a significant relationship with the GC count (P < 0.05), consistent with predictions from a neural model for partial summation conditions. However, the FDT captured additional significant damage (P = 0.03) unexplained by the structural loss. Conclusions: Functional and structural measurements support early neuronal loss in diabetes. The structure-function relationship follows the predictions from an established neural model. Functional tests could be improved to operate in total summation conditions in the macula, becoming more sensitive to early loss.

Asunto(s)

RESUMEN

PURPOSE: To compare multicolor (MC) and traditional color fundus photography (CFP) in their ability to detect features of early and late age-related macular degeneration (AMD). METHODS: Study design: Observational case series. PARTICIPANTS: fundus images captured using standard CFP and MC imaging from 33 patients attending hospital clinics and 26 participants from the pilot phase of the Northern Ireland Cohort for the Longitudinal Study of Ageing (NICOLA). Systematic grading of early and late AMD features; (hard drusen, soft drusen, reticular pseudodrusen, pigment clumping, non-geographic atrophy hypopigmentation, atrophy, hemorrhage, and fibrosis) on CFP and MC. RESULTS: There were 105 eyes with gradable images for comparison. Using CFP as the gold standard, sensitivity values for MC ranged from 100% for atrophy, non-geographic atrophy hypopigmentation, and fibrosis to 69.7% for pigment clumping. Specificity values were high: >80% for all features. On using MC as the comparator, CFP had lower sensitivity for the detection of early AMD features (27.8% for reticular drusen to 77.8% for non-geographic atrophy hypopigmention). Analysis of OCT in discrepant cases showed better agreement with MC for all AMD lesions, except hemorrhage and non-geographic atrophy hypopigmentation. For pigment clumping, CFP and MC were in equal agreement with OCT. CONCLUSION: Multicolor retinal imaging allowed for improved detection and definition of AMD features.

Asunto(s)