RESUMEN
BACKGROUND: This study proposes a decision support system created in collaboration with machine learning experts and ophthalmologists for detecting keratoconus (KC) severity. The system employs an ensemble machine model and minimal corneal measurements. METHODS: A clinical dataset is initially obtained from Pentacam corneal tomography imaging devices, which undergoes pre-processing and addresses imbalanced sampling through the application of an oversampling technique for minority classes. Subsequently, a combination of statistical methods, visual analysis, and expert input is employed to identify Pentacam indices most correlated with severity class labels. These selected features are then utilized to develop and validate three distinct machine learning models. The model exhibiting the most effective classification performance is integrated into a real-world web-based application and deployed on a web application server. This deployment facilitates evaluation of the proposed system, incorporating new data and considering relevant human factors related to the user experience. RESULTS: The performance of the developed system is experimentally evaluated, and the results revealed an overall accuracy of 98.62%, precision of 98.70%, recall of 98.62%, F1-score of 98.66%, and F2-score of 98.64%. The application's deployment also demonstrated precise and smooth end-to-end functionality. CONCLUSION: The developed decision support system establishes a robust basis for subsequent assessment by ophthalmologists before potential deployment as a screening tool for keratoconus severity detection in a clinical setting.
RESUMEN
With advancements in the implementation of artificial intelligence (AI) in different ophthalmology disciplines, it continues to have a significant impact on glaucoma diagnosis and screening. This article explores the distinct roles of AI in specialized ophthalmology clinics and general practice, highlighting the critical balance between sensitivity and specificity in diagnostic and screening models. Screening models prioritize sensitivity to detect potential glaucoma cases efficiently, while diagnostic models emphasize specificity to confirm disease with high accuracy. AI applications, primarily using machine learning (ML) and deep learning (DL), have been successful in detecting glaucomatous optic neuropathy from colored fundus photographs and other retinal imaging modalities. Diagnostic models integrate data extracted from various forms of modalities (including tests that assess structural optic nerve damage as well as those evaluating functional damage) to provide a more nuanced, accurate and thorough approach to diagnosing glaucoma. As AI continues to evolve, the collaboration between technology and clinical expertise should focus more on improving specificity of glaucoma diagnostic models to assess ophthalmologists to revolutionize glaucoma diagnosis and improve patients care.
RESUMEN
BACKGROUND: In the era of patient-centered medical care, using objective clinical measures to assess patient-centered outcomes in all aspects became a necessity, and pars plana vitrectomy (PPV) is a major ophthalmic surgical procedure used for the treatment of vitreoretinal disorders aiming to improve their vision-related quality of life. PURPOSE: To study the impact of PPV on visual quality of life by assessing its effect on common daily activities, to assess its association with various factors, and to explore the relations between these factors and postoperative visual function. METHODS: Vision-related quality of life for 87 patients who underwent PPV was assessed using the 25-item National Eye Institute Visual Function Questionnaire (NEI VFQ-25) by phone call interviews. Variables assessed include age, gender, indication of surgery, duration since surgery, preoperative best-corrected visual acuity (BCVA), postoperative BCVA, fellow eye BCVA, medical history and lens status. RESULTS: The factors significantly affecting the total score were postoperative visual acuity and fellow eye VA. Upon analyzing the effect of the indication on total score, a significant difference was found with the highest being for those who had dropped lens as the indication for surgery and the lowest was for those with tractional retinal detachment (TRDs) and inflammatory indications. Subscale analysis and visual acuity improvement were also varying between indications. CONCLUSION: VRQOL significantly improves after PPV, the improvement is variable with different indications, being the greatest for those with dropped lens and the least for TRDs and endophthalmitis, with postoperative VA being the most important factor affecting the VRQOL score.
RESUMEN
PURPOSE: To assess the impact of Jordanian's Corona Virus Disease (COVID-19) lockdown on visual acuity and macular thickness in patients with macular edema receiving intravitreal injections, and to assess the ethical endeavor of lockdown among serious sight threatening conditions. PATIENTS AND METHODS: This retrospective observational study included patients planned for intravitreal injections who did not complete the planned course before the lockdown (ie, before 20th of March 2020). Data included demographics, indication for the intravitreal injection, corrected distance visual acuity (CDVA), and central macular thickness on Optical Coherence Tomography (OCT) before and after the lockdown. RESULTS: One-hundred and sixty-six eyes of 125 patients were studied, 68 (54.4%) patients were males, and the mean (± standard deviation, SD) age was 64.79 (±9.41) years. Mean (±SD) duration of delay in the planned injection was 60.97 (±24.35) days. The change in visual acuity was statistically significant for patients with diabetic macular edema (p= 0.045 improvement), patients with central retinal vein thrombosis (CRVO) (p= 0.05 deterioration), and patients with age-related macular degeneration (AMD) (p= 0.005 deterioration). Of interest, delay of more than 2 months and the previous need for 3 or more injections were significant poor prognostic factors for visual outcome for patients with diabetic macular edema (p=0.027 and 0.045). CONCLUSION: The impact of delay in the scheduled intravitreal injections resulted in variable outcomes depending on the indication. Triaging the urgency of patients should be based on the indication to support the equity principle of bioethics, where those in need are prioritized against others, depending on potential adverse outcome.