ORCID Profile
0000-0002-9239-745X
Current Organisations
University College London
,
Moorfields Eye Hospital NHS Foundation Trust
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: Association for Research in Vision and Ophthalmology (ARVO)
Date: 11-2010
DOI: 10.1167/IOVS.09-4846
Publisher: BMJ
Date: 18-05-2022
Publisher: BMJ
Date: 06-02-2023
Abstract: Deep learning systems (DLSs) for diabetic retinopathy (DR) detection show promising results but can underperform in racial and ethnic minority groups, therefore external validation within these populations is critical for health equity. This study evaluates the performance of a DLS for DR detection among Indigenous Australians, an understudied ethnic group who suffer disproportionately from DR-related blindness. We performed a retrospective external validation study comparing the performance of a DLS against a retinal specialist for the detection of more-than-mild DR (mtmDR), vision-threatening DR (vtDR) and all-cause referable DR. The validation set consisted of 1682 consecutive, single-field, macula-centred retinal photographs from 864 patients with diabetes (mean age 54.9 years, 52.4% women) at an Indigenous primary care service in Perth, Australia. Three-person adjudication by a panel of specialists served as the reference standard. For mtmDR detection, sensitivity of the DLS was superior to the retina specialist (98.0% (95% CI, 96.5 to 99.4) vs 87.1% (95% CI, 83.6 to 90.6), McNemar’s test p .001) with a small reduction in specificity (95.1% (95% CI, 93.6 to 96.4) vs 97.0% (95% CI, 95.9 to 98.0), p=0.006). For vtDR, the DLS’s sensitivity was again superior to the human grader (96.2% (95% CI, 93.4 to 98.6) vs 84.4% (95% CI, 79.7 to 89.2), p .001) with a slight drop in specificity (95.8% (95% CI, 94.6 to 96.9) vs 97.8% (95% CI, 96.9 to 98.6), p=0.002). For all-cause referable DR, there was a substantial increase in sensitivity (93.7% (95% CI, 91.8 to 95.5) vs 74.4% (95% CI, 71.1 to 77.5), p .001) and a smaller reduction in specificity (91.7% (95% CI, 90.0 to 93.3) vs 96.3% (95% CI, 95.2 to 97.4), p .001). The DLS showed improved sensitivity and similar specificity compared with a retina specialist for DR detection. This demonstrates its potential to support DR screening among Indigenous Australians, an underserved population with a high burden of diabetic eye disease.
Publisher: Informa UK Limited
Date: 07-04-2020
Publisher: Elsevier BV
Date: 05-2022
DOI: 10.1016/J.ORET.2021.12.021
Abstract: To validate the generalizability of a deep learning system (DLS) that detects diabetic macular edema (DME) from 2-dimensional color fundus photographs (CFP), for which the reference standard for retinal thickness and fluid presence is derived from 3-dimensional OCT. Retrospective validation of a DLS across international datasets. Paired CFP and OCT of patients from diabetic retinopathy (DR) screening programs or retina clinics. The DLS was developed using data sets from Thailand, the United Kingdom, and the United States and validated using 3060 unique eyes from 1582 patients across screening populations in Australia, India, and Thailand. The DLS was separately validated in 698 eyes from 537 screened patients in the United Kingdom with mild DR and suspicion of DME based on CFP. The DLS was trained using DME labels from OCT. The presence of DME was based on retinal thickening or intraretinal fluid. The DLS's performance was compared with expert grades of maculopathy and to a previous proof-of-concept version of the DLS. We further simulated the integration of the current DLS into an algorithm trained to detect DR from CFP. The superiority of specificity and noninferiority of sensitivity of the DLS for the detection of center-involving DME, using device-specific thresholds, compared with experts. The primary analysis in a combined data set spanning Australia, India, and Thailand showed the DLS had 80% specificity and 81% sensitivity, compared with expert graders, who had 59% specificity and 70% sensitivity. Relative to human experts, the DLS had significantly higher specificity (P = 0.008) and noninferior sensitivity (P < 0.001). In the data set from the United Kingdom, the DLS had a specificity of 80% (P 50%) and a sensitivity of 100% (P = 0.02 for sensitivity of > 90%). The DLS can generalize to multiple international populations with an accuracy exceeding that of experts. The clinical value of this DLS to reduce false-positive referrals, thus decreasing the burden on specialist eye care, warrants a prospective evaluation.
Publisher: Public Library of Science (PLoS)
Date: 07-10-2016
Publisher: Oxford University Press (OUP)
Date: 05-02-2021
Abstract: Dementia is one of the most debilitating aspects of Parkinson’s disease. There are no validated biomarkers that can track Parkinson’s disease progression, nor accurately identify patients who will develop dementia and when. Understanding the sequence of observable changes in Parkinson’s disease in people at elevated risk for developing dementia could provide an integrated biomarker for identifying and managing in iduals who will develop Parkinson’s dementia. We aimed to estimate the sequence of clinical and neurodegeneration events, and variability in this sequence, using data-driven statistical modelling in two separate Parkinson’s cohorts, focusing on patients at elevated risk for dementia due to their age at symptom onset. We updated a novel version of an event-based model that has only recently been extended to cope naturally with clinical data, enabling its application in Parkinson’s disease for the first time. The observational cohorts included healthy control subjects and patients with Parkinson’s disease, of whom those diagnosed at age 65 or older were classified as having high risk of dementia. The model estimates that Parkinson’s progression in patients at elevated risk for dementia starts with classic prodromal features of Parkinson’s disease (olfaction, sleep), followed by early deficits in visual cognition and increased brain iron content, followed later by a less certain ordering of neurodegeneration in the substantia nigra and cortex, neuropsychological cognitive deficits, retinal thinning in dopamine layers, and further deficits in visual cognition. Importantly, we also characterize variation in the sequence. We found consistent, cross-validated results within cohorts, and agreement between cohorts on the subset of features available in both cohorts. Our sequencing results add powerful support to the increasing body of evidence suggesting that visual processing specifically is affected early in patients with Parkinson’s disease at elevated risk of dementia. This opens a route to earlier and more precise detection, as well as a more detailed understanding of the pathological mechanisms underpinning Parkinson’s dementia.
Publisher: Springer Science and Business Media LLC
Date: 03-11-2022
DOI: 10.1038/S41433-022-02298-7
Abstract: This study aims to describe the grading methods and baseline characteristics for UK Biobank (UKBB) participants who underwent retinal imaging in 2009–2010, and to characterise in iduals with retinal features suggestive of age-related macular degeneration (AMD), glaucoma and retinopathy. Non-mydriatic colour fundus photographs and macular optical coherence tomography (OCT) scans were manually graded by Central Administrative Research Facility certified graders and quality assured by clinicians of the Network of Ophthalmic Reading Centres UK. Captured retinal features included those associated with AMD (≥1 drusen, pigmentary changes, geographic atrophy or exudative AMD either imaging modality), glaucoma (≥0.7 cup-disc ratio, ≥0.2 cup-disc ratio difference between eyes, other abnormal disc features photographs only) and retinopathy (characteristic features of diabetic retinopathy with or without microaneurysms either imaging modality). Suspected cases of these conditions were characterised with reference to diagnostic records, physical and biochemical measurements. Among 68,514 UKBB participants who underwent retinal imaging, the mean age was 57.3 years (standard deviation 8.2), 45.7% were men and 90.6% were of White ethnicity. A total of 64,367 participants had gradable colour fundus photographs and 68,281 had gradable OCT scans in at least one eye. Retinal features suggestive of AMD and glaucoma were identified in 15,176 and 2184 participants, of whom 125 (0.8%) and 188 (8.6%), respectively, had a recorded diagnosis. Of 264 participants identified to have retinopathy with microaneurysms, 251 (95.1%) had either diabetes or hypertension. This dataset represents a valuable addition to what is currently available in UKBB, providing important insights to both ocular and systemic health.
Publisher: Springer Science and Business Media LLC
Date: 28-05-2018
Publisher: Wiley
Date: 19-05-2021
DOI: 10.1002/ACN3.51320
Abstract: Artificial intelligence (AI)‐based diagnostic algorithms have achieved ambitious aims through automated image pattern recognition. For neurological disorders, this includes neurodegeneration and inflammation. Scalable imaging technology for big data in neurology is optical coherence tomography (OCT). We highlight that OCT changes observed in the retina, as a window to the brain, are small, requiring rigorous quality control pipelines. There are existing tools for this purpose. Firstly, there are human‐led validated consensus quality control criteria (OSCAR‐IB) for OCT. Secondly, these criteria are embedded into OCT reporting guidelines (APOSTEL). The use of the described annotation of failed OCT scans advances machine learning. This is illustrated through the present review of the advantages and disadvantages of AI‐based applications to OCT data. The neurological conditions reviewed here for the use of big data include Alzheimer disease, stroke, multiple sclerosis (MS), Parkinson disease, and epilepsy. It is noted that while big data is relevant for AI, ownership is complex. For this reason, we also reached out to involve representatives from patient organizations and the public domain in addition to clinical and research centers. The evidence reviewed can be grouped in a five‐point expansion of the OSCAR‐IB criteria to embrace AI (OSCAR‐AI). The review concludes by specific recommendations on how this can be achieved practically and in compliance with existing guidelines.
Publisher: Association for Research in Vision and Ophthalmology (ARVO)
Date: 30-11-2020
DOI: 10.1167/TVST.9.12.34
Publisher: Springer Science and Business Media LLC
Date: 19-03-2020
DOI: 10.1038/S42003-020-0802-Y
Abstract: Corneal curvature, a highly heritable trait, is a key clinical endophenotype for myopia - a major cause of visual impairment and blindness in the world. Here we present a trans-ethnic meta-analysis of corneal curvature GWAS in 44,042 in iduals of Caucasian and Asian with replication in 88,218 UK Biobank data. We identified 47 loci (of which 26 are novel), with population-specific signals as well as shared signals across ethnicities. Some identified variants showed precise scaling in corneal curvature and eye elongation (i.e. axial length) to maintain eyes in emmetropia (i.e. HDAC11 / FBLN2 rs2630445, RBP3 rs11204213) others exhibited association with myopia with little pleiotropic effects on eye elongation. Implicated genes are involved in extracellular matrix organization, developmental process for body and eye, connective tissue cartilage and glycosylation protein activities. Our study provides insights into population-specific novel genes for corneal curvature, and their pleiotropic effect in regulating eye size or conferring susceptibility to myopia.
Publisher: Springer Science and Business Media LLC
Date: 05-2022
DOI: 10.1038/S41591-022-01772-9
Abstract: A growing number of artificial intelligence (AI)-based clinical decision support systems are showing promising performance in preclinical, in silico evaluation, but few have yet demonstrated real benefit to patient care. Early-stage clinical evaluation is important to assess an AI system's actual clinical performance at small scale, ensure its safety, evaluate the human factors surrounding its use and pave the way to further large-scale trials. However, the reporting of these early studies remains inadequate. The present statement provides a multi-stakeholder, consensus-based reporting guideline for the Developmental and Exploratory Clinical Investigations of DEcision support systems driven by Artificial Intelligence (DECIDE-AI). We conducted a two-round, modified Delphi process to collect and analyze expert opinion on the reporting of early clinical evaluation of AI systems. Experts were recruited from 20 pre-defined stakeholder categories. The final composition and wording of the guideline was determined at a virtual consensus meeting. The checklist and the Explanation & Elaboration (E&E) sections were refined based on feedback from a qualitative evaluation process. In total, 123 experts participated in the first round of Delphi, 138 in the second round, 16 in the consensus meeting and 16 in the qualitative evaluation. The DECIDE-AI reporting guideline comprises 17 AI-specific reporting items (made of 28 subitems) and ten generic reporting items, with an E&E paragraph provided for each. Through consultation and consensus with a range of stakeholders, we developed a guideline comprising key items that should be reported in early-stage clinical studies of AI-based decision support systems in healthcare. By providing an actionable checklist of minimal reporting items, the DECIDE-AI guideline will facilitate the appraisal of these studies and replicability of their findings.
Publisher: Springer Science and Business Media LLC
Date: 24-02-2021
DOI: 10.1038/S41467-020-20851-4
Abstract: Primary open-angle glaucoma (POAG), is a heritable common cause of blindness world-wide. To identify risk loci, we conduct a large multi-ethnic meta-analysis of genome-wide association studies on a total of 34,179 cases and 349,321 controls, identifying 44 previously unreported risk loci and confirming 83 loci that were previously known. The majority of loci have broadly consistent effects across European, Asian and African ancestries. Cross-ancestry data improve fine-mapping of causal variants for several loci. Integration of multiple lines of genetic evidence support the functional relevance of the identified POAG risk loci and highlight potential contributions of several genes to POAG pathogenesis, including SVEP1, RERE, VCAM1, ZNF638 , CLIC5, SLC2A12, YAP1, MXRA5 , and SMAD6 . Several drug compounds targeting POAG risk genes may be potential glaucoma therapeutic candidates.
Publisher: Springer Science and Business Media LLC
Date: 12-08-2022
Publisher: The Optical Society
Date: 13-01-2017
DOI: 10.1364/BOE.8.000813
Publisher: Association for Research in Vision and Ophthalmology (ARVO)
Date: 12-11-2020
DOI: 10.1167/TVST.9.2.55
Publisher: SPIE
Date: 08-2017
DOI: 10.1117/12.2286057
Publisher: Elsevier BV
Date: 2020
DOI: 10.1016/J.OPHTHA.2019.08.015
Abstract: To describe and compare associations with macular retinal nerve fiber layer (mRNFL), ganglion cell complex (GCC), and ganglion cell-inner plexiform layer (GCIPL) thicknesses in a large cohort. Cross-sectional study. We included 42 044 participants in the UK Biobank. The mean age was 56 years. Spectral-domain OCT macular images were segmented and analyzed. Corneal-compensated intraocular pressure (IOPcc) was measured with the Ocular Response Analyzer (Reichert, Corp., Buffalo, NY). Multivariable linear regression was used to examine associations with mean mRNFL, GCC, and GCIPL thicknesses. Factors examined were age, sex, ethnicity, height, body mass index (BMI), smoking status, alcohol intake, Townsend deprivation index, education level, diabetes status, spherical equivalent, and IOPcc. Thicknesses of mRNFL, GCC, and GCIPL. We identified several novel independent associations with thinner inner retinal thickness. Thinner inner retina was associated with alcohol intake (most significant for GCIPL: -0.46 μm for daily or almost daily intake compared with special occasion only or never [95% confidence interval (CI), 0.61-0.30] P = 1.1×10 The novel associations we identified may be important to consider when using inner retinal parameters as a diagnostic tool. Associations generally were strongest with GCIPL, particularly for IOP. This suggests that GCIPL may be the superior inner retinal biomarker for macular pathophysiologic processes and especially for glaucoma.
Publisher: Medknow
Date: 2014
Publisher: Wiley
Date: 23-01-2015
DOI: 10.1111/AOS.12519
Abstract: Diabetic macular ischaemia (DMI) is an important cause of visual loss in patients with diabetes, but its relationship to the larger retinal vessels is unknown. We examined whether retinal vessel calibre is related to DMI. Clinic-based case-control study of patients with type 2 diabetes. The presence and severity of DMI was assessed using Early Treatment Diabetic Retinopathy Study (ETDRS) protocols from fundus fluorescein angiographic (FFA) images. Custom software was used to quantify the greatest linear dimension and area of the foveal avascular zone (FAZ). Retinal vessel calibre was measured using a semi-automated software on fundus fluorescein images. Of 53 patients examined, 18 (34%), 18 (34%) and 17 (32%) had no/mild, moderate and severe DMI, respectively. Persons with moderate or severe DMI had narrower mean retinal arteriolar calibre than persons with no/mild DMI (140.6 μm 95% confidence interval (CI) 134.7, 146.4 versus 150.7 μm, 95% CI 142.5, 158, p = 0.04). The association remained after multivariate adjustment for age, gender, previous panretinal photocoagulation, neovascularization at the disc and elsewhere and diabetic retinopathy severity. Increased FAZ size was also associated with narrower arteriolar calibre. Retinal venular calibre and arteriole to venule ratio (AVR) were not associated with DMI. Retinal arteriolar narrowing was associated with moderate-to-severe macular ischaemia in eyes with diabetic retinopathy. This suggests that larger vessels other than capillaries may also be associated with DMI.
Publisher: BMJ
Date: 02-2019
DOI: 10.1136/BMJOPEN-2018-025077
Abstract: To describe the rationale, methods and research potential of eye and vision measures available in UK Biobank. UK Biobank is a large, multisite, prospective cohort study. Extensive lifestyle and health questionnaires, a range of physical measures and collection of biological specimens are collected. The scope of UK Biobank was extended midway through data collection to include assessments of other measures of health, including eyes and vision. The eye assessment at baseline included questionnaires detailing past ophthalmic and family history, measurement of visual acuity, refractive error and keratometry, intraocular pressure (IOP), corneal biomechanics, spectral domain optical coherence tomography (OCT) of the macula and a disc–macula fundus photograph. Since recruitment, UK Biobank has collected accelerometer data and begun multimodal imaging data (including brain, heart and abdominal MRI) in 100 000 participants. Dense genotypic data and a panel of 20 biochemistry measures are available, and linkage to medical health records for the full cohort has begun. A total of 502 665 people aged between 40 and 69 were recruited to participate in UK Biobank. Of these, 117 175 took part in baseline assessment of vision, IOP, refraction and keratometry. A subgroup of 67 321 underwent OCT and retinal photography. The introduction of eye and vision measures in UK Biobank was accompanied by intensive training, support and a data monitoring quality control process. UK Biobank is one of the largest prospective cohorts worldwide with extensive data on ophthalmic diseases and conditions. Data collection is an ongoing process and a repeat of the baseline assessment including the questionnaires, measurements and s le collection will be performed in subsets of 25 000 participants every 2–3 years. The depth and breadth of this dataset, coupled with its open-access policy, will create a powerful resource for all researchers to investigate the eye diseases in later life.
Publisher: Elsevier BV
Date: 07-2023
Publisher: Elsevier BV
Date: 2022
Publisher: Springer Science and Business Media LLC
Date: 27-11-2019
DOI: 10.1038/S42003-019-0634-9
Abstract: A new avenue of mining published genome-wide association studies includes the joint analysis of related traits. The power of this approach depends on the genetic correlation of traits, which reflects the number of pleiotropic loci, i.e. genetic loci influencing multiple traits. Here, we applied new meta-analyses of optic nerve head (ONH) related traits implicated in primary open-angle glaucoma (POAG) intraocular pressure and central corneal thickness using Haplotype reference consortium imputations. We performed a multi-trait analysis of ONH parameters cup area, disc area and vertical cup-disc ratio. We uncover new variants rs11158547 in PPP1R36-PLEKHG3 and rs1028727 near SERPINE3 at genome-wide significance that replicate in independent Asian cohorts imputed to 1000 Genomes. At this point, validation of these variants in POAG cohorts is h ered by the high degree of heterogeneity. Our results show that multi-trait analysis is a valid approach to identify novel pleiotropic variants for ONH.
Publisher: Ovid Technologies (Wolters Kluwer Health)
Date: 04-2015
Publisher: Elsevier BV
Date: 05-2021
Publisher: Elsevier BV
Date: 04-2016
DOI: 10.1016/J.OPHTHA.2015.11.009
Abstract: To derive macular thickness measures and their associations by performing rapid, automated segmentation of spectral-domain optical coherence tomography (SD OCT) images collected and stored as part of the UK Biobank (UKBB) study. Large, multisite cohort study in the United Kingdom. Analysis of cross-sectional data. Adults from the United Kingdom aged 40 to 69 years. Participants had nonmydriatic SD OCT (Topcon 3D OCT-1000 Mark II Topcon GB, Newberry, Berkshire, UK) performed as part of the ocular assessment module. Rapid, remote, automated segmentation of the images was performed using custom optical coherence tomography (OCT) image analysis software (Topcon Advanced Boundary Segmentation [TABS] Topcon GB) to generate macular thickness values. We excluded people with a history of ocular or systemic disease (diabetes or neurodegenerative diseases) and eyes with reduced vision (<0.1 logarithm of the minimum angle of resolution) or with low SD OCT signal-to-noise ratio and low segmentation success certainty. Macular thickness values across 9 Early Treatment of Diabetic Retinopathy Study (ETDRS) subfields. The SD OCT scans of 67 321 subjects were available for analysis, with 32 062 people with at least 1 eye meeting the inclusion criteria. There were 17 274 women and 14 788 men, with a mean (standard deviation [SD]) age of 55.2 (8.2) years. The mean (SD) logarithm of the minimum angle of resolution visual acuity was -0.075 (0.087), and the refractive error was -0.071 (+1.91) diopters (D). The mean (SD) central macular thickness (CMT) in the central 1-mm ETDRS subfield was 264.5 (22.9) μm, with 95% confidence limits of 220.8 and 311.5 μm. After adjusting for covariates, CMT was positively correlated with older age, female gender, greater myopia, smoking, body mass index (BMI), and white ethnicity (all P < 0.001). Of note, macular thickness in other subfields was negatively correlated with older age and greater myopia. We report macular thickness data derived from SD OCT images collected as part of the UKBB study and found novel associations among older age, ethnicity, BMI, smoking, and macular thickness.
Publisher: Springer Science and Business Media LLC
Date: 05-01-2023
Location: United Kingdom of Great Britain and Northern Ireland
Location: United Kingdom of Great Britain and Northern Ireland
Location: United Kingdom of Great Britain and Northern Ireland
Location: United Kingdom of Great Britain and Northern Ireland
Location: United Kingdom of Great Britain and Northern Ireland
No related grants have been discovered for Pearse Keane.