-
The Cochrane Database of Systematic... Nov 2023Keratoconus remains difficult to diagnose, especially in the early stages. It is a progressive disorder of the cornea that starts at a young age. Diagnosis is based on... (Review)
Review
BACKGROUND
Keratoconus remains difficult to diagnose, especially in the early stages. It is a progressive disorder of the cornea that starts at a young age. Diagnosis is based on clinical examination and corneal imaging; though in the early stages, when there are no clinical signs, diagnosis depends on the interpretation of corneal imaging (e.g. topography and tomography) by trained cornea specialists. Using artificial intelligence (AI) to analyse the corneal images and detect cases of keratoconus could help prevent visual acuity loss and even corneal transplantation. However, a missed diagnosis in people seeking refractive surgery could lead to weakening of the cornea and keratoconus-like ectasia. There is a need for a reliable overview of the accuracy of AI for detecting keratoconus and the applicability of this automated method to the clinical setting.
OBJECTIVES
To assess the diagnostic accuracy of artificial intelligence (AI) algorithms for detecting keratoconus in people presenting with refractive errors, especially those whose vision can no longer be fully corrected with glasses, those seeking corneal refractive surgery, and those suspected of having keratoconus. AI could help ophthalmologists, optometrists, and other eye care professionals to make decisions on referral to cornea specialists. Secondary objectives To assess the following potential causes of heterogeneity in diagnostic performance across studies. • Different AI algorithms (e.g. neural networks, decision trees, support vector machines) • Index test methodology (preprocessing techniques, core AI method, and postprocessing techniques) • Sources of input to train algorithms (topography and tomography images from Placido disc system, Scheimpflug system, slit-scanning system, or optical coherence tomography (OCT); number of training and testing cases/images; label/endpoint variable used for training) • Study setting • Study design • Ethnicity, or geographic area as its proxy • Different index test positivity criteria provided by the topography or tomography device • Reference standard, topography or tomography, one or two cornea specialists • Definition of keratoconus • Mean age of participants • Recruitment of participants • Severity of keratoconus (clinically manifest or subclinical) SEARCH METHODS: We searched CENTRAL (which contains the Cochrane Eyes and Vision Trials Register), Ovid MEDLINE, Ovid Embase, OpenGrey, the ISRCTN registry, ClinicalTrials.gov, and the World Health Organization International Clinical Trials Registry Platform (WHO ICTRP). There were no date or language restrictions in the electronic searches for trials. We last searched the electronic databases on 29 November 2022.
SELECTION CRITERIA
We included cross-sectional and diagnostic case-control studies that investigated AI for the diagnosis of keratoconus using topography, tomography, or both. We included studies that diagnosed manifest keratoconus, subclinical keratoconus, or both. The reference standard was the interpretation of topography or tomography images by at least two cornea specialists.
DATA COLLECTION AND ANALYSIS
Two review authors independently extracted the study data and assessed the quality of studies using the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool. When an article contained multiple AI algorithms, we selected the algorithm with the highest Youden's index. We assessed the certainty of evidence using the GRADE approach.
MAIN RESULTS
We included 63 studies, published between 1994 and 2022, that developed and investigated the accuracy of AI for the diagnosis of keratoconus. There were three different units of analysis in the studies: eyes, participants, and images. Forty-four studies analysed 23,771 eyes, four studies analysed 3843 participants, and 15 studies analysed 38,832 images. Fifty-four articles evaluated the detection of manifest keratoconus, defined as a cornea that showed any clinical sign of keratoconus. The accuracy of AI seems almost perfect, with a summary sensitivity of 98.6% (95% confidence interval (CI) 97.6% to 99.1%) and a summary specificity of 98.3% (95% CI 97.4% to 98.9%). However, accuracy varied across studies and the certainty of the evidence was low. Twenty-eight articles evaluated the detection of subclinical keratoconus, although the definition of subclinical varied. We grouped subclinical keratoconus, forme fruste, and very asymmetrical eyes together. The tests showed good accuracy, with a summary sensitivity of 90.0% (95% CI 84.5% to 93.8%) and a summary specificity of 95.5% (95% CI 91.9% to 97.5%). However, the certainty of the evidence was very low for sensitivity and low for specificity. In both groups, we graded most studies at high risk of bias, with high applicability concerns, in the domain of patient selection, since most were case-control studies. Moreover, we graded the certainty of evidence as low to very low due to selection bias, inconsistency, and imprecision. We could not explain the heterogeneity between the studies. The sensitivity analyses based on study design, AI algorithm, imaging technique (topography versus tomography), and data source (parameters versus images) showed no differences in the results.
AUTHORS' CONCLUSIONS
AI appears to be a promising triage tool in ophthalmologic practice for diagnosing keratoconus. Test accuracy was very high for manifest keratoconus and slightly lower for subclinical keratoconus, indicating a higher chance of missing a diagnosis in people without clinical signs. This could lead to progression of keratoconus or an erroneous indication for refractive surgery, which would worsen the disease. We are unable to draw clear and reliable conclusions due to the high risk of bias, the unexplained heterogeneity of the results, and high applicability concerns, all of which reduced our confidence in the evidence. Greater standardization in future research would increase the quality of studies and improve comparability between studies.
Topics: Humans; Artificial Intelligence; Keratoconus; Cross-Sectional Studies; Physical Examination; Case-Control Studies
PubMed: 37965960
DOI: 10.1002/14651858.CD014911.pub2 -
Telemedicine Journal and E-health : the... Jun 2024(Review)
Review
Topics: Humans; Internet; Mobile Applications; Telemedicine; Vision Tests; Visual Acuity
PubMed: 38564179
DOI: 10.1089/tmj.2023.0368 -
BMJ Open Ophthalmology Nov 2023To explore the current research about the role of optical coherence tomography (OCT) and optical coherence tomography angiography (OCTA) in dysthyroid optic neuropathy... (Meta-Analysis)
Meta-Analysis
PURPOSE
To explore the current research about the role of optical coherence tomography (OCT) and optical coherence tomography angiography (OCTA) in dysthyroid optic neuropathy (DON).
METHODS
Studies in the literature that focused on OCT, OCTA and DON were retrieved by searching PubMed, EMBASE, Cochrane databases and Clinical Trial before 20 June 2023. The methodological quality was assessed using the Newcastle-Ottawa scale. The quantitative calculation was performed using Review Manager V.5.3.
RESULTS
Twelve studies met the eligibility criteria and were included. DON group presented lower macular ganglion cell complex in the overall, superior and inferior hemifields compared with the non-DON group. Furthermore, the ganglion cell layer and inner plexiform layer in DON group was thinner in contrast to the non-DON group. The optic nerve head vessel density was lower in the DON group than that in the non-DON group. A reduction of radial peripapillary capillary vessel density could be seen in the DON group than the non-DON group in overall, inside disc, peripapillary, superior-hemifield, temporal and nasal. Besides, the macular superficial retinal capillary layer of non-DON and DON is lower than the healthy control group.
CONCLUSIONS
This study supported the potential value of OCT and OCTA metrics as novel biomarkers of DON. Ophthalmologists should comprehensively consider the retinal structure and microvasculature in dealing with DON.
ETHICS AND DISSEMINATION
This systematic review included data from published literature and was exempt from ethics approval. Results would be disseminated through peer-reviewed publication and presented at academic conferences engaging clinicians.
PROSPERO REGISTRATION NUMBER
CRD42023414907.
Topics: Humans; Tomography, Optical Coherence; Optic Disk; Angiography; Retinal Ganglion Cells; Optic Nerve Diseases
PubMed: 37996119
DOI: 10.1136/bmjophth-2023-001379 -
Graefe's Archive For Clinical and... Jan 2024The association of obstructive sleep apnea (OSA) with development of eye diseases is unclear. This current systematic review and meta-analysis attempts to summarize and... (Meta-Analysis)
Meta-Analysis Review
BACKGROUND
The association of obstructive sleep apnea (OSA) with development of eye diseases is unclear. This current systematic review and meta-analysis attempts to summarize and analyze associations between OSA and ocular disorders in the literature.
METHODS
PubMed, EMBASE, Google Scholar, Web Of Science, and Scopus databases were searched from 1901 to July 2022 in accordance with the Preferred Reporting in Systematic Review & Meta-Analysis (PRISMA). Our primary outcome assessed the association between OSA and the odds of developing floppy eyelid syndrome (FES), glaucoma, non-arteritic anterior ischemic optic neuropathy (NAION), retinal vein occlusion (RVO), keratoconus (KC), idiopathic intracranial hypertension (IIH), age-related macular degeneration (AMD), and central serous chorioretinopathy (CSR) through odds ratio calculated at the 95% confidence interval.
RESULTS
Forty-nine studies were included for systematic review and meta-analysis. The pooled OR estimate was highest for NAION [3.98 (95% CI 2.38, 6.66)], followed by FES [3.68 (95% CI 2.18, 6.20)], RVO [2.71(95% CI 1.83, 4.00)], CSR [2.28 (95% CI 0.65, 7.97)], KC [1.87 (95% CI 1.16, 2.99)], glaucoma [1.49 (95% CI 1.16, 1.91)], IIH [1.29 (95% CI 0.33, 5.01)], and AMD [0.92 [95% CI 0.24, 3.58] All observed associations were significant (p < 0.001) aside from IIH and AMD.
CONCLUSION
OSA is significantly associated with NAION, FES, RVO, CSR, KC, and glaucoma. Clinicians should be informed of these associations so early recognition, diagnosis, and treatment of eye disorders can be addressed in at-risk groups, and early referral to ophthalmic services is made to prevent vision disturbances. Similarly, ophthalmologists seeing patients with any of these conditions should consider screening and referring patients for assessment of possible OSA.
Topics: Humans; Eyelid Diseases; Glaucoma; Keratoconus; Optic Neuropathy, Ischemic; Retinal Vein Occlusion; Sleep Apnea, Obstructive
PubMed: 37227479
DOI: 10.1007/s00417-023-06103-3 -
Therapeutic Advances in Ophthalmology 2024New developments in artificial intelligence, particularly with promising results in early detection and management of keratoconus, have favorably altered the natural... (Review)
Review
BACKGROUND
New developments in artificial intelligence, particularly with promising results in early detection and management of keratoconus, have favorably altered the natural history of the disease over the last few decades. Features of artificial intelligence in different machine such as anterior segment optical coherence tomography, and femtosecond laser technique have improved safety, precision, effectiveness, and predictability of treatment modalities of keratoconus (from contact lenses to keratoplasty techniques). These options ingrained in artificial intelligence are already underway and allow ophthalmologist to approach disease in the most non-invasive way.
OBJECTIVES
This study comprehensively describes all of the treatment modalities of keratoconus considering machine learning strategies.
DESIGN
A multidimensional comprehensive systematic narrative review.
DATA SOURCES AND METHODS
A comprehensive search was done in the five main electronic databases (PubMed, Scopus, Web of Science, Embase, and Cochrane), without language and time or type of study restrictions. Afterward, eligible articles were selected by screening the titles and abstracts based on main mesh keywords. For potentially eligible articles, the full text was also reviewed.
RESULTS
Artificial intelligence demonstrates promise in keratoconus diagnosis and clinical management, spanning early detection (especially in subclinical cases), preoperative screening, postoperative ectasia prediction after keratorefractive surgery, and guiding surgical decisions. The majority of studies employed a solitary machine learning algorithm, whereas minor studies assessed multiple algorithms that evaluated the association of various keratoconus staging and management strategies. Last but not least, AI has proven effective in guiding the implantation of intracorneal ring segments in keratoconus corneas and predicting surgical outcomes.
CONCLUSION
The efficient and widespread clinical translation of machine learning models in keratoconus management is a crucial goal of potential future approaches to better visual performance in keratoconus patients.
TRIAL REGISTRATION
The article has been registered through PROSPERO, an international database of prospectively registered systematic reviews, with the ID: CRD42022319338.
PubMed: 38516169
DOI: 10.1177/25158414241232258 -
Survey of Ophthalmology 2023Seeking treatment for bothersome vitreous floaters is patient driven. To measure the impact of floaters and treatment on an individual's quality of life,... (Review)
Review
Seeking treatment for bothersome vitreous floaters is patient driven. To measure the impact of floaters and treatment on an individual's quality of life, patient-reported outcome measurements (PROMs) are essential. We review all studies using a PROM for patients with floaters. We evaluated content coverage against quality-of-life domains previously identified in other ophthalmic disorders, and against a qualitative study investigating quality-of-life issues in patients with floaters. We assessed measurement properties of PROMs using an extensive range of psychometric quality criteria. We identified 59 studies using 28 different PROMs. Many PROMs were not specifically developed for patients with floaters. Floater-specific PROMs were mostly based on content validation from an ophthalmologist or researcher perspective; two included a patient perspective. Using the outcomes of the qualitative study, we found that the floater-specific PROMs were narrow in their content coverage, with most items relating to visual symptoms and activity limitations. Testing the psychometric quality of PROMs was rare, and when employed mostly limited to responsiveness and known group validity. The remarkable high number of floater-specific PROMs reveals a need for such measurements in ophthalmology. Unfortunately, reporting on psychometric quality is limited, and content development is most often done without patient involvement.
PubMed: 37315741
DOI: 10.1016/j.survophthal.2023.06.003 -
Eye (London, England) Sep 2023Amblyopia is an important public health concern. While home-based screening may present an effective solution, this has not been rigorously assessed in a systematic... (Review)
Review
Amblyopia is an important public health concern. While home-based screening may present an effective solution, this has not been rigorously assessed in a systematic review. A systematic review was performed using Ovid MEDLINE, PubMed, The Cochrane Library, Embase, Web of Science Core Collection, and Clinicaltrials.gov. All studies reporting the diagnostic accuracy of home-based screening tools for amblyopia among children were included. Studies involving orthoptist or ophthalmologist-led screening and adult subjects were excluded. The main outcome measure was the diagnostic accuracy expressed as sensitivity and specificity. Among 3670 studies identified, 28 were eligible for inclusion in our systematic review. The age range of patients were less than 1 month to 16 years old. 7 studies used internet-based tools, 16 used smartphone/tablet applications, 3 used digital cameras, and 3 used home-based questionnaires and visual acuity tools. All studies included a reference standard except one, which was a longitudinal study. 21 studies had full ophthalmological examination whilst 6 studies had validated visual acuity measurement tools as gold standards. Of the 27 studies which compared against a reference test, only 25 studies reported sensitivity and specificity values. Using the QUADAS-2 tool, 50% of studies were deemed to have applicability concern due to patient selection from tertiary centres and unclear methods for recruitment. There is a need to improve the quality of diagnostic accuracy studies, standardise thresholds for detecting amblyopia, and ensure consistent reporting of results. Further research is needed to evaluate the suitability of these tools for amblyopia screening.
Topics: Adult; Child; Humans; Infant; Amblyopia; Longitudinal Studies; Sensitivity and Specificity; Physical Examination
PubMed: 36828959
DOI: 10.1038/s41433-023-02412-3 -
Clinical Ophthalmology (Auckland, N.Z.) 2023Recent advances in telemedicine have led to increased use of digital ophthalmoscopes (DO) in clinical settings. This review aims to assess commercially available DOs,... (Review)
Review
PURPOSE
Recent advances in telemedicine have led to increased use of digital ophthalmoscopes (DO) in clinical settings. This review aims to assess commercially available DOs, including smartphone (SP), desktop, and handheld ophthalmoscopes, and evaluate their applications.
METHODS
A literature review was performed by searching PubMed (pubmed.ncbi.nlm.nih.gov), Web of Science (webofknowledge.com), and Science Direct (sciencedirect.com). All English-language papers that resulted from the search terms "digital ophthalmoscope", "screening tool", "glaucoma screening", "diabetic retinopathy screening", "cataract screening", and "papilledema screening" were reviewed. Studies that contained randomized clinical trials with human participants between January 2010 and December 2020 were included. The Risk of Bias in Systematic Reviews (ROBIS) tool was used to assess the methodological quality of each included paper.
RESULTS
Of the 1307 studies identified, 35 met inclusion and exclusion criteria. The ROBIS tool determined that 29/35 studies (82.8%) had a low risk of bias, 3/35 (8.5%) had a moderate risk of bias, and 3/35 (8.5%) had a high risk of bias.
CONCLUSION
The continued adoption of DOs remains uncertain because of concerns about the image quality for non-mydriatic eyes and the confidence in data captured from the device. Likewise, there is a lack of guidelines for the use of DOs, which makes it difficult for providers to determine the best device for their practice and to ensure appropriate use. Even so, DOs continue to gain acceptance as technology and practice integration improve, especially in underserved areas with limited access to ophthalmologists.
PubMed: 37822326
DOI: 10.2147/OPTH.S423845 -
Optometry and Vision Science : Official... Sep 2023This study summarized primary angle-closure glaucoma (PACG)-related factors across different dimensions. (Meta-Analysis)
Meta-Analysis
SIGNIFICANCE
This study summarized primary angle-closure glaucoma (PACG)-related factors across different dimensions.
OBJECTIVES
This review aimed at systematically summarizing the associated factors of PACG in published literatures.
METHODS
A systematic review and meta-analysis were conducted by searching the electronic databases including PubMed, EMBASE, and Web of Science from their inception to November 2021. The pooled risk estimates of continuous and categorical variables were calculated using weighted mean difference (WMD) and odds ratio (OR; 95% confidence intervals [CIs]), respectively.
RESULTS
We included 45 studies in this review. In the meta-analysis, intraocular pressure (WMD, 3.13; 95% CI, 2.37 to 3.89), anterior chamber depth (WMD, -0.52; 95% CI, -0.70 to -0.34), axial length (WMD, -0.77; 95% CI, -1.26 to -0.28), retinal nerve fiber layer (WMD, -21.23; 95% CI, -30.21 to -12.25), and spherical equivalent (WMD, 1.02; 95% CI, 0.66 to 1.38) were the most common ophthalmic anatomic factors, and lower body weight (WMD, -3.65; 95% CI, -6.48 to -0.82) was the most significant general morphological indicators. The presence of cataract (OR, 3.77; 95% CI, 3.46 to 4.11) and hyperlipidemia (OR, 1.10; 95% CI, 1.02 to 1.20) were significantly associated with PACG. Increased level of triglyceride (WMD, 0.17; 95% CI, 0.06 to 0.27) was associated with PACG. In addition, an association between short-term antidepressant exposure (OR, 1.36; 95% CI, 1.08 to 1.70) and acute angle-closure glaucoma was observed.
CONCLUSIONS AND IMPLICATIONS OF KEY FINDINGS
This review identified a few consistent factors related to PACG, providing important information for primary care physicians, general ophthalmologists, and public health professionals to counsel their patients on PACG risks.
Topics: Humans; Glaucoma, Angle-Closure; Intraocular Pressure; Tonometry, Ocular; Acute Disease; Risk Factors
PubMed: 37747945
DOI: 10.1097/OPX.0000000000002050 -
Eye (London, England) Oct 2023In most cases, glaucoma patients require long-term medical and/or surgical treatment. Preference studies investigate how different aspects of glaucoma management, such... (Review)
Review
BACKGROUND
In most cases, glaucoma patients require long-term medical and/or surgical treatment. Preference studies investigate how different aspects of glaucoma management, such as health or process outcomes, are valued and herewith help stakeholders make care more responsive to patients' needs. As, to our knowledge, no overview of these studies is currently available, this study aims to systematically review and critically appraise these studies.
METHODS
A systematic literature review was conducted using keywords for stated-preference studies and glaucoma up to October 2021. Studies were included if they were original research and used a stated-preference methodology to investigate preferences in patients or healthcare professionals for different aspects of glaucoma management. Data were extracted and summarized. Furthermore, a quality appraisal of the included studies was performed using two validated checklists.
RESULTS
The search yielded 1214 articles after removal of duplicates. Of those, 11 studies fulfilled the inclusion criteria. Studies aimed to elicit preferences for glaucoma treatment (27%), glaucoma related health state valuation (36%), and services (36%) from the patient (91%) or ophthalmologists' perspective (9%). Altogether studies included 69 attributes. The majority of attributes were outcome related (62%), followed by process (32%) and cost attributes (6%). Outcome attributes (e.g., effectiveness) were most often of highest importance to the population.
CONCLUSIONS
This systematic review provides an up-to-date and critical review of stated-preference studies in the field of glaucoma, suggesting that patients have preferences and are willing to trade-off between characteristics, and revealed that outcome attributes are the most influential characteristics of glaucoma management.
Topics: Humans; Glaucoma; Patient Preference
PubMed: 36944711
DOI: 10.1038/s41433-023-02482-3