Ophthalmology Optical Coherence Tomography Databases for Artificial Intelligence Algorithm: A Review.

BACKGROUND: Imaging plays a pivotal role in eye assessment. With the introduction of advanced machine learning and artificial intelligence (AI), the focus has shifted to imaging datasets in ophthalmology. While disparities and health inequalities hidden within data are well-documented, the ophthalmology field faces specific challenges to the creation and maintenance of datasets. Optical Coherence Tomography (OCT) is useful for the diagnosis and monitoring of retinal pathologies, making it valuable for AI applications. This review aims to identify and compare the landscape of publicly available optical coherence tomography databases for AI applications. METHODS: We conducted a literature review on OCT and AI articles with publicly accessible datasets, using PubMed, Scopus, and Web of Science databases. The review retrieved 183 articles, and after full-text analysis, 50 articles were included. From the included articles were identified 8 publicly available OCT datasets, focusing on patient demographics and clinical details for thorough assessment and comparison. RESULTS: The resulting datasets encompass 154,313 images collected from Spectralis, Cirrus HD, Topcon 3D, and Bioptigen devices. These datasets included normal exams, age-related macular degeneration, and diabetic maculopathy, among others. Comprehensive demographic information is available in one dataset and the USA is the most represented population. DISCUSSION: Current publicly available OCT databases for AI applications exhibit limitations, stemming from their non-representative nature and the lack of comprehensive demographic information. Limited datasets hamper research and equitable AI development. To promote equitable AI algorithmic development in ophthalmology, there is a need for the creation and dissemination of more representative datasets.

Clinical review of cerebral venous thrombosis in the context of COVID-19 vaccinations: Evaluation, management, and scientific questions.

BACKGROUND: Vaccine induced immune mediated thrombocytopenia or VITT, is a recent and rare phenomenon of thrombosis with thrombocytopenia, frequently including cerebral venous thromboses (CVT), that has been described following vaccination with adenovirus vaccines ChAdOx1 nCOV-19 (AstraZeneca) and Ad26.COV2·S Johnson and Johnson (Janssen/J&J). The evaluation and management of suspected cases of CVT post COVID-19 vaccination are critical skills for a broad range of healthcare providers. METHODS: A collaborative comprehensive review of literature was conducted among a global group of expert neurologists and hematologists. FINDINGS: Strategies for rapid evaluation and treatment of the CVT in the context of possible VITT exist, including inflammatory marker measurements, PF4 assays, and non-heparin anticoagulation.

Novel Definition of Stroke "Good Responders" Predicts 90-Day Outcome after Thrombolysis.

INTRODUCTION: Identifying predictors of good response in thrombolytic-treated stroke is important to clinical care, resource allocation, and research design. We developed a simple, novel measure of "Good Responders" to assess if 2 short-term variables could predict 90-day outcomes after thrombolysis in stroke. METHODS: Intravenous thrombolysis-treated stroke cases from June 2004 to June 2018 were analyzed from a stroke registry. Intraarterial treatment cases were excluded. Good responders (GR++) were defined as those with length of stay less than or equal to 3 days and discharge to home. Poor responders (GR- -) had length of stay more than 3 days and discharge other than home. Mixed responders (GR+/-) composed the remainder. Baseline characteristics and predictors of 90-day outcome were assessed. RESULTS: Of 261 patients, there were 101(38.7%) GR++, 67(25.7%) GR- -, and 93(35.6%) GR+/-. For GR++ versus GR- - versus GR+/-, there were differences in mean age (62.7, 71.2, 69.2; P = .0016), and baseline modified Rankin score (mRS) 0-2 (%: 94.9, 74.6, 84.8; P = .008). Younger age, male sex, lower values for systolic BP, glucose, and baseline mRS were associated with good responders. Older age, atrial fibrillation, symptomatic intracerebral hemorrhage, and baseline mRS greater than 2 were associated with poor responders. At 90 days, mortality was reduced in GR++ versus GR- - versus GR+/- (%alive: 92.6, 72, 86; P = .04), and mRS(0-2) (%: 36.8, 0, 11.8; P < .001). CONCLUSIONS: Good responders to thrombolysis are younger and have better baseline functional status. Our novel definition of "Good Responders", using 2 early variables of home disposition and short length of stay, may help predict 90-day post-thrombolytic outcome. Future work should focus on validating this definition.

Constipation is reduced by beta-blockers and increased by dopaminergic medications in Parkinson's disease.

BACKGROUND: Constipation is one of most frequent non-motor symptoms of Parkinson's disease (PD) and it may precede the clinical diagnosis of PD by years, with negative effects on quality of life. In contrast to motor features, levodopa is ineffective and possibly detrimental on constipation. Treatment of constipation in PD is non-specific and frequently unsuccessful. Stemming from a clinical observation of unexpected relief of bothersome constipation, abdominal bloating and pain after treatment with the beta-blocker carvedilol in one patient, we have evaluated the association between the use of beta-blockers and the presence of constipation in a large, unselected PD cohort. METHODS: Retrospective review of the medical records of every patient with a diagnosis of PD seen in the Movement Disorders clinic at Cedars-Sinai Medical Center from October 2010 to April 2014. RESULTS: 341 medical records with a primary diagnosis of PD were reviewed, 336 of which contained information about constipation. Overall, 205/336 patients (61%) reported constipation. Among the 66 subjects treated with beta-blockers at the time of the encounter of record, only 28 (42.4%) reported constipation. By comparison, among the 270 subjects not treated with beta-blockers, 177 (65.5%) had constipation (χ(2) test p value = 0.001). Multivariate logistic analysis showed an odds ratio (OR) of 0.293 for beta-blockers (95% C.I. 0.161-0.535, p = 0.0001), 2.287 for levodopa (95% C.I. 1.271-4.117, p = 0.006) and 1.805 for dopamine agonists (95% C.I. 1.039-3.136, p = 0.036). CONCLUSIONS: Beta-blockers are associated with a lower risk of constipation, while dopaminergic treatments appear to increase risk of constipation.