Machine learning classification of retinal imaging of neuropsychiatric and healthy cases in a subset of the UK Biobank cohort DOI Open Access
Babatunde Aideyan

Published: Jan. 1, 2023

Deep learning (DL) models trained on retinal imaging has grown into a lively area of research at the intersection medical diagnostics and image analysis (MIA). Numerous studies have shown that convolutional neural networks (CNNs) are capable classifying diabetic retinopathy (DR) from color fundus (CF) with accuracies equivalent to human clinical experts. Several years investigation led first-ever FDA-approved autonomous intelligent system, IDx-DR, which automatically diagnoses DR CF images. Considering ongoing biomarkers associated neuropsychiatric pathologies, potential for computational (RIA) automatic detection disorders (NPDs) is compelling area. This chapter reports methods results DL model development validation study. were classify optical coherence tomography (OCT) individuals NPDs matched healthy controls (HCs). The study sample was obtained UK Biobank (UKBB), large-scale biomedical database containing 85,000 participants. After inclusion exclusion criteria applied, 50 cases identified in NPD group, three HCs each case (total n=200). Low-quality OCT excluded, remaining images split training, validation, test datasets. Ten modality average classification 48.3% 62.9% imaging, respectively. Results this both support refute two also used train tasked - wherein one very high performance another low performance. line still early should be considered preliminary exploratory. However, conjunction larger body concerning identifying neurobiological substrates NPDs, study's indicate limited long-term translation potential.--Author's abstract

Language: Английский

Association Between Retinal Features From Multimodal Imaging and Schizophrenia DOI
Siegfried Wagner, Mario Cortina‐Borja, Steven M. Silverstein

et al.

JAMA Psychiatry, Journal Year: 2023, Volume and Issue: 80(5), P. 478 - 478

Published: March 22, 2023

Importance The potential association of schizophrenia with distinct retinal changes is clinical interest but has been challenging to investigate because a lack sufficiently large and detailed cohorts. Objective To the between biomarkers from multimodal imaging (oculomics) in real-world population. Design, Setting, Participants This cross-sectional analysis used data retrospective cohort 154 830 patients 40 years older AlzEye study, which linked ophthalmic hospital admission across England. Patients attended Moorfields Eye Hospital, secondary care principal central site, 4 district hubs, 5 satellite clinics around London, United Kingdom, had during study period (January 2008 April 2018). Data were analyzed January 2022 July 2022. Main Outcomes Measures Retinovascular optic nerve indices computed color fundus photography. Macular fiber layer (RNFL) ganglion cell–inner plexiform (mGC-IPL) thicknesses extracted optical coherence tomography. Linear mixed-effects models examine biomarkers. Results A total 485 individuals (747 eyes) (mean [SD] age, 64.9 [12.2]; 258 [53.2%] female) 100 931 (165 400 without 65.9 [13.7]; 53 253 [52.8%] included after images underwent quality control potentially confounding conditions excluded. Individuals more likely have hypertension (407 [83.9%] vs 49 971 [48.0%]) diabetes (364 [75.1%] 28 762 [27.6%]). group thinner mGC-IPL (−4.05 μm, 95% CI, −5.40 −2.69; P = 5.4 × 10 −9 ), persisted when investigating only (−3.99 μm; −6.67 −1.30; .004) or just those 55 younger (−2.90 −5.55 −0.24; .03). On adjusted analysis, fractal dimension among vascular variables was reduced (−0.14 units; −0.22 −0.05; .001), although this not present excluding diabetes. Conclusions Relevance In measurable differences neural integrity retina. Differences vasculature mostly higher prevalence schizophrenia. role features as adjunct outcomes warrants further investigation.

Language: Английский

Citations

34
Retina as a potential biomarker in schizophrenia spectrum disorders: a systematic review and meta-analysis of optical coherence tomography and electroretinography DOI Creative Commons
Hiroshi Komatsu,

Goh Onoguchi,

Steven M. Silverstein

et al.

Molecular Psychiatry, Journal Year: 2023, Volume and Issue: 29(2), P. 464 - 482

Published: Dec. 11, 2023

Abstract Introduction Abnormal findings on optical coherence tomography (OCT) and electroretinography (ERG) have been reported in participants with schizophrenia spectrum disorders (SSDs). This study aims to reveal the pooled standard mean difference (SMD) retinal parameters OCT ERG among SSDs healthy controls their association demographic characteristics, clinical symptoms, smoking, diabetes mellitus, hypertension. Methods Using PubMed, Scopus, Web of Science, PSYNDEX, we searched literature from inception March 31, 2023, using specific search terms. was registered PROSPERO (CRD4202235795) conducted according PRISMA 2020. Results We included 65 studies systematic review 44 meta-analysis. Participants showed thinning peripapillary nerve fiber layer (pRNFL), macular ganglion cell layer- inner plexiform layer, thickness all other segments macula. A meta-analysis that excluded SSD hypertension no change results, except for pRNFL inferior nasal thickness. Furthermore, a significant found SMD temporal between left right eyes. Meta-regression analysis revealed an duration illness, positive negative symptoms. In angiography, differences were foveal avascular zone superficial vessel density controls. flash ERG, reduced amplitude both a- b-waves under photopic scotopic conditions participants. latency a-wave significantly shorter comparison HCs. Discussion Considering prior report unaffected first-degree relatives results meta-analysis, suggest changes trait state aspects. Future longitudinal multimodal imaging are needed clarify pathophysiological mechanisms these utility individual patient monitoring efforts.

Language: Английский

Citations

19
Oculomics: A Crusade Against the Four Horsemen of Chronic Disease DOI Creative Commons
Emily J Patterson, Alistair D. Bounds, Siegfried Wagner

et al.

Ophthalmology and Therapy, Journal Year: 2024, Volume and Issue: 13(6), P. 1427 - 1451

Published: April 17, 2024

Chronic, non-communicable diseases present a major barrier to living long and healthy life. In many cases, early diagnosis can facilitate prevention, monitoring, treatment efforts, improving patient outcomes. There is therefore critical need make screening techniques as accessible, unintimidating, cost-effective possible. The association between ocular biomarkers systemic health disease (oculomics) presents an attractive opportunity for detection of diseases, ophthalmic are often relatively low-cost, fast, non-invasive. this review, we highlight the key associations structural in eye four globally leading causes morbidity mortality: cardiovascular disease, cancer, neurodegenerative metabolic disease. We observe that particularly promising target oculomics, with detected multiple structures. Cardiovascular choroid, retinal vasculature, nerve fiber layer, eyelid, tear fluid, lens, vasculature. contrast, only fluid emerged cancer. retina rich source oculomics data, analysis which has been enhanced by artificial intelligence-based tools. Although not all disease-specific, limiting their current diagnostic utility, future research will likely benefit from combining data various structures improve specificity, well active design, development, optimization instruments specific signatures, thus facilitating differential diagnoses. Long-term stop people lives. help prevent, monitor, treat patients' health. order diagnose tools easy patients access, painless, low-cost. may provide solution. discuss link changes types long-term that, together, kill most population: (1) (affecting heart and/or blood). (2) Cancer (abnormal growth cells). (3) Neurodegenerative brain nervous system). (4) Metabolic (problems storing, accessing, using body's fuel). show leaves tell-tale signs lots different parts eye. Signs mostly found back eye, cancer be fluid. seen them tell us what is. believe understand more about how detect it if combine information within develop new these

Language: Английский

Citations

8
Association between polygenic risk for schizophrenia and retinal morphology: A cross-sectional analysis of the United Kingdom Biobank DOI Creative Commons
Brittany A. Blose, Steven M. Silverstein, Kelsey V. Stuart

et al.

Psychiatry Research, Journal Year: 2024, Volume and Issue: 339, P. 116106 - 116106

Published: July 26, 2024

We examined the relationship between genetic risk for schizophrenia (SZ), using polygenic scores (PRSs), and retinal morphological alterations. Retinal structural vascular indices derived from optical coherence tomography (OCT) color fundus photography (CFP) PRSs SZ were analyzed in N = 35,024 individuals prospective cohort study, United Kingdom Biobank (UKB). Results indicated that macular ganglion cell-inner plexiform layer (mGC-IPL) thickness was significantly inversely related to PRS SZ, this strongest within higher quintiles independent of potential confounders age. PRS, however, unrelated characteristics, with exception venular tortuosity, other (macular nerve fiber [mRNFL], inner nuclear [INL], cup-to-disc ratio [CDR]). Additionally, association greater reduced mGC-IPL only significant participants 40-49 50-59 age groups, not those 60-69 group. These findings suggest thinning is associated a predisposition may reflect neurodevelopmental and/or neurodegenerative processes inherent SZ. microvasculature alterations, be secondary consequences do appear

Language: Английский

Citations

6
MIMI-ONET: Multi-Modal image augmentation via Butterfly Optimized neural network for Huntington Disease Detection DOI

S Amudaria,

S. Joseph Jawhar

Brain Research, Journal Year: 2025, Volume and Issue: unknown, P. 149530 - 149530

Published: Feb. 1, 2025

Language: Английский

Citations

0
Retinal Neurovascular Structure in Colombian Patients With Early-Course Schizophrenia Spectrum Disorders DOI
Jairo M. González-Díaz,

Diana C. Zamora,

Alejandro Vallejo

et al.

Revista Colombiana de Psiquiatría, Journal Year: 2025, Volume and Issue: unknown

Published: March 1, 2025

Language: Английский

Citations

0
Other Neurological Disorders: Migraine, Neurosarcoidosis, Schizophrenia, Obstructive Sleep Apnea-Hypopnea Syndrome and Bipolar Disorder DOI

Francisco J. Ascaso,

Javier Mateo,

L CABEZON

et al.

Published: Jan. 1, 2025

Language: Английский

Citations

0
Retinal layers and symptoms and inflammation in schizophrenia DOI
Marcelo Alves Carriello,

Diogo F. Bornancin Costa,

Pedro Henrique Pereira Alvim

et al.

European Archives of Psychiatry and Clinical Neuroscience, Journal Year: 2023, Volume and Issue: 274(5), P. 1115 - 1124

Published: March 16, 2023

Language: Английский

Citations

9
Schizophrenia in Translation: Why the Eye? DOI Creative Commons
Steven M. Silverstein, Joy J. Choi,

Kyle M. Green

et al.

Schizophrenia Bulletin, Journal Year: 2022, Volume and Issue: 48(4), P. 728 - 737

Published: May 9, 2022

Abstract Schizophrenia is increasingly recognized as a systemic disease, characterized by dysregulation in multiple physiological systems (eg, neural, cardiovascular, endocrine). Many of these changes are observed early the first psychotic episode, and people at high risk for disorder. Expanding search biomarkers schizophrenia beyond genes, blood, brain may allow inexpensive, noninvasive, objective markers diagnosis, phenotype, treatment response, prognosis. Several anatomic physiologic aspects eye have shown promise health range neurological disorders, heart, kidney, endocrine, other impairments medical conditions. In schizophrenia, thinning volume loss retinal neural layers been observed, associated with illness progression, loss, cognitive impairment. Retinal microvascular also observed. Abnormal pupil responses corneal nerve disintegration related to function structure schizophrenia. addition, studying can inform about emerging neuroinflammatory, metabolic diseases psychosis, causes several visual Application methods oculomics, or eye-based non-ophthalmological pathology, study has potential provide tools patient monitoring data-driven prediction, well clarifying pathophysiology course illness. Given their demonstrated utility neuropsychiatry, we recommend greater adoption research care.

Language: Английский

Citations

13
Deep retinal layer microvasculature alterations in schizophrenia DOI Creative Commons

Samantha I. Fradkin,

Deepthi Bannai, Paulo Lizano

et al.

Biomarkers in Neuropsychiatry, Journal Year: 2024, Volume and Issue: 10, P. 100084 - 100084

Published: Feb. 3, 2024

A subset of individuals with schizophrenia (SZ) are thought to have a microvascular component their illness studies demonstrating alterations in retinal superficial, deep, and choroidal microvasculature networks. However, the direction location these differed across studies. In recent study, we reported that SZ demonstrated lower superficial layer density than healthy control (HC) group. The current study investigated characteristics deep vascular SZ, including examining consistency findings two layers. We included 28 diagnosis or schizoaffective disorder, 37 HCs. Optical coherence tomography angiography (OCTA) data was collected measure perfusion density, skeletonized vessel diameter index, fractal dimension. conducted between-group comparisons examine differences OCTA variables between HC groups. trend analysis determine if reflected linear according age length Spearman correlations were associations density. Individuals significantly bilateral as well left eye Results showed indices decreased duration, older lowest values younger controls highest for all at least one eye. Lower also associated layer. Overall, results suggest present multiple layers they may be useful visual system biomarkers neurovascular changes disorder.

Language: Английский

Citations

2