ABSTRACT
PURPOSE: To analyze the demographics, etiology, complications, treatment modalities, and visual outcomes in pediatric uveitis patients at a tertiary eye care hospital. METHODS: A retrospective review of medical records of pediatric uveitis patients who presented with us from January 2014 to January 2020 was evaluated. RESULTS: Out of the 178 pediatric uveitis patients, 65 children were included in the study. The most common age group was 6-10 years (46%). Of the included patients, 36 (55.4%) were male and 29 (44.6%) were female. Presentation was bilateral in 39 (60%) and unilateral in 26 (40%). Anterior uveitis was seen in 19 (29.23%), intermediate in 18 (27.69%), posterior in 16 (24.62%), and panuveitis in 12 (18.46%) patients. There were 2 cases of masquerades. Non-infectious uveitis was the most commonly seen, in 48 (73.84%) of total cases, among which 21 (43.75%) were idiopathic and 7 (14.58%) were associated with juvenile idiopathic (JIA) arthritis. Infectious uveitis was present in 17 (26.15%); the most common etiology was toxoplasmosis. Baseline visual acuity was low in 22 (33.84%) children. After initiating treatment, 37 (56.92%) showed improvement in vision and 10 (15.38%) had worsening of vision. Intraocular pressure (IOP) rise was seen in 5 (7.69%) children; 51 (78.46%) children required medical management and 16 (24.61%) children required surgical intervention; 46 (70.76%) children had uveitis related complications out of which most of them 30 (65.21%) were present at baseline. CONCLUSIONS: Anterior and intermediate uveitis were the most common types observed in our study. Toxoplasmosis was the most common type of infectious uveitis and JIA the most common cause in non-infectious type apart from idiopathic uveitis. Posterior uveitis had low visual acuity at baseline and follow-up. Children presented to us with poor visual acuity and complications at baseline, hence an early referral to a tertiary eye hospital and management accordingly can improve the quality of vision and visual rehabilitation.
ABSTRACT
Purpose: Amblyopia is a significant public health problem. Photoscreeners have been shown to have significant potential for screening; however, most are limited by cost and display low accuracy. The purpose of this study was validate a novel artificial intelligence (AI) and machine learning-based facial photoscreener "Kanna," and to determine its effectiveness in detecting amblyopia risk factors. Methods: A prospective study that included 654 patients aged below 18 years was conducted in our outpatient clinic. Using an android smartphone, three images of each the participants' face were captured by trained optometrists in dark and ambient light conditions and uploaded onto Kanna. Deep learning was used to create an amblyopia risk score based on our previous study. The algorithm generates a risk dashboard consisting of six values: five normalized risk scores for ptosis, strabismus, hyperopia, myopia and media opacities; and one binary value denoting if a child is "at-risk" or "not at-risk." The presence of amblyopia risk factors (ARF) as determined on the ophthalmic examination was compared with the Kanna photoscreener. Results: Correlated patient data for 654 participants were analyzed. The mean age of the study population was 7.87 years. The algorithm had an F-score, 85.9%; accuracy, 90.8%; sensitivity, 83.6%; specificity, 94.5%; positive predictive value, 88.4%; and negative predictive value, 91.9% in identifying amblyopia risk factors. The P value for the amblyopia risk calculation was 8.5 × 10-142 implying strong statistical significance. Conclusion: The Kanna photo-based screener that uses deep learning to analyze photographs is an effective alternative for screening children for amblyopia risk factors.
