The BONSAI (Brain and Optic Nerve Study with Artificial Intelligence) deep learning system can accurately identify pediatric papilledema on standard ocular fundus photographs.

BACKGROUND: Pediatric papilledema often reflects an underlying severe neurologic disorder and may be difficult to appreciate, especially in young children. Ocular fundus photographs are easy to obtain even in young children and in nonophthalmology settings. The aim of our study was to ascertain whether an improved deep-learning system (DLS), previously validated in adults, can accurately identify papilledema and other optic disk abnormalities in children. METHODS: The DLS was tested on mydriatic fundus photographs obtained in a multiethnic pediatric population (<17 years) from three centers (Atlanta-USA; Bucharest-Romania; Singapore). The DLS's multiclass classification accuracy (ie, normal optic disk, papilledema, disks with other abnormality) was calculated, and the DLS's performance to specifically detect papilledema and normal disks was evaluated in a one-vs-rest strategy using the AUC, sensitivity and specificity, with reference to expert neuro-ophthalmologists. RESULTS: External testing was performed on 898 fundus photographs: 447 patients; mean age, 10.33 (231 patients ≤10 years of age; 216, 11-16 years); 558 normal disks, 254 papilledema, 86 other disk abnormalities. Overall multiclass accuracy of the DLS was 89.6% (range, 87.8%-91.6%). The DLS successfully distinguished "normal" from "abnormal" optic disks (AUC 0.99 [0.98-0.99]; sensitivity, 87.3% [84.9%-89.8%]; specificity, 98.5% [97.6%-99.6%]), and "papilledema" from "normal and other" (AUC 0.99 [0.98-1.0]; sensitivity, 98.0% [96.8%-99.4%]; specificity, 94.1% (92.4%-95.9%)]. CONCLUSIONS: Our DLS reliably distinguished papilledema from normal optic disks and other disk abnormalities in children, suggesting it could be utilized as a diagnostic aid for the assessment of optic nerve head appearance in the pediatric age group.

Application of a Deep Learning System to Detect Papilledema on Nonmydriatic Ocular Fundus Photographs in an Emergency Department.

PURPOSE: The Fundus photography vs Ophthalmoscopy Trial Outcomes in the Emergency Department (FOTO-ED) studies showed that ED providers poorly recognized funduscopic findings in patients in the ED. We tested a modified version of the Brain and Optic Nerve Study Artificial Intelligence (BONSAI) deep learning system on nonmydriatic fundus photographs from the FOTO-ED studies to determine if the deep learning system could have improved the detection of papilledema had it been available to ED providers as a real-time diagnostic aid. DESIGN: Retrospective secondary analysis of a cohort of patients included in the FOTO-ED studies. METHODS: The testing data set included 1608 photographs obtained from 828 patients in the FOTO-ED studies. Photographs were reclassified according to the optic disc classification system used by the deep learning system ("normal optic discs," "papilledema," and "other optic disc abnormalities"). The system's performance was evaluated by calculating the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity using a 1-vs-rest strategy, with reference to expert neuro-ophthalmologists. RESULTS: The BONSAI deep learning system successfully distinguished normal from abnormal optic discs (AUC 0.92 [95% confidence interval {CI} 0.90-0.93]; sensitivity 75.6% [73.7%-77.5%] and specificity 89.6% [86.3%-92.8%]), and papilledema from normal and others (AUC 0.97 [0.95-0.99]; sensitivity 84.0% [75.0%-92.6%] and specificity 98.9% [98.5%-99.4%]). Six patients with missed papilledema in 1 eye were correctly identified by the deep learning system as having papilledema in the other eye. CONCLUSIONS: The BONSAI deep learning system was able to reliably identify papilledema and normal optic discs on nonmydriatic photographs obtained in the FOTO-ED studies. Our deep learning system has excellent potential as a diagnostic aid in EDs and non-ophthalmology clinics equipped with nonmydriatic fundus cameras. NOTE: Publication of this article is sponsored by the American Ophthalmological Society.

An unusual presentation of neurosarcoidosis: Concurrent optic perineuritis and optic neuritis.

Neurosarcoidosis is a rare complication of sarcoidosis and typically presents as acute cranial neuropathies. Neurosarcoidosis can rarely cause an inflammatory optic neuropathy, resembles an optic neuritis and even more rarely can cause an optic perineuritis. Although concomitant optic neuritis and optic perineuritis have been reported in other inflammatory conditions, such as myelin oligodendrocyte antibody-associated disease, spatially-distinct optic neuritis, and optic perineuritis has not been previously described in neurosarcoidosis. Here, we present a case of spatially-distinct concomitant optic neuritis and optic perineuritis from neurosarcoidosis in a 51-year-old man initially suspected to harbor metastatic disease based on imaging findings.

Combination of lidocaine gel and povidone-iodine to decrease acquired infections in procedures performed using topical anesthesia.

PURPOSE: To test the antiseptic efficacy of povidone-iodine when mixed with topical lidocaine gel. SETTING: Emory School of Medicine, Atlanta, Georgia, USA. DESIGN: Experimental study. METHODS: Staphylococcus epidermidis, Staphylococcus aureus, viridans streptococci (Streptococcus sanguinis), Escherichia coli, and Pseudomonas aeruginosa were grown on blood agar plates with povidone-iodine and/or lidocaine gel. The efficacy of sterilization was quantified by surviving bacterial colony-forming units. RESULTS: Combination of povidone-iodine and lidocaine gel prevented bacterial growth to levels similar to povidone-iodine alone. Application of lidocaine gel to bacteria before povidone-iodine treatment allowed bacterial growth similar to controls not exposed to povidone-iodine. CONCLUSIONS: Povidone-iodine must be applied before lidocaine gel for effective antisepsis, but admixture of povidone-iodine with lidocaine gel was also effective and may reduce the risk of endophthalmitis associated with lidocaine gel use. This strategy offers a practice-changing alternative for preoperative prophylaxis in procedures requiring topical anesthesia.

Differential effects of non-nicotine tobacco constituent compounds on nicotine self-administration in rats.

Tobacco smoking has been shown to be quite addictive in people. However, nicotine itself is a weak reinforcer compared to other commonly abused drugs, leading speculation that other factors contribute to the high prevalence of tobacco addiction in the human population. In addition to nicotine, there are over 5000 chemical compounds that have been identified in tobacco smoke, and more work is needed to ascertain their potential contributions to tobacco's highly addictive properties, or as potential candidates for smoking cessation treatment. In this study, we examined seven non-nicotine tobacco constituent compounds (anabasine, anatabine, nornicotine, myosmine, harmane, norharmane, and tyramine) for their effects on nicotine self-administration behavior in rats. Young adult female Sprague-Dawley rats were allowed to self-administer nicotine (0.03 mg/kg/50 µl infusion) under a fixed ratio-1 schedule of reinforcement. Each self-administration session lasted 45 min. Doses of each tobacco constituent compound were administered subcutaneously 10 min prior to the start of each session in a repeated measures, counterbalanced order two times. Anabasine displayed a biphasic dose-effect function. Pretreatment with 0.02 mg/kg anabasine resulted in a 25% increase in nicotine self-administration, while 2.0mg/kg of anabasine reduced nicotine infusions per session by over 50%. Pretreatment with 2.0mg/kg anatabine also significantly reduced nicotine self-administration by nearly half. These results suggest that some non-nicotine tobacco constituents may enhance or reduce nicotine's reinforcing properties. Also, depending upon the appropriate dose, some of these compounds may also serve as potential smoking cessation agents.