Diabetic Retinopathy Screening Using Smartphone-Based Fundus Photography and Deep-Learning Artificial Intelligence in the Yucatan Peninsula: A Field Study.

BACKGROUND: To compare the performance of Medios (offline) and EyeArt (online) artificial intelligence (AI) algorithms for detecting diabetic retinopathy (DR) on images captured using fundus-on-smartphone photography in a remote outreach field setting. METHODS: In June, 2019 in the Yucatan Peninsula, 248 patients, many of whom had chronic visual impairment, were screened for DR using two portable Remidio fundus-on-phone cameras, and 2130 images obtained were analyzed, retrospectively, by Medios and EyeArt. Screening performance metrics also were determined retrospectively using masked image analysis combined with clinical examination results as the reference standard. RESULTS: A total of 129 patients were determined to have some level of DR; 119 patients had no DR. Medios was capable of evaluating every patient with a sensitivity (95% confidence intervals [CIs]) of 94% (88%-97%) and specificity of 94% (88%-98%). Owing primarily to photographer error, EyeArt evaluated 156 patients with a sensitivity of 94% (86%-98%) and specificity of 86% (77%-93%). In a head-to-head comparison of 110 patients, the sensitivities of Medios and EyeArt were 99% (93%-100%) and 95% (87%-99%). The specificities for both were 88% (73%-97%). CONCLUSIONS: Medios and EyeArt AI algorithms demonstrated high levels of sensitivity and specificity for detecting DR when applied in this real-world field setting. Both programs should be considered in remote, large-scale DR screening campaigns where immediate results are desirable, and in the case of EyeArt, online access is possible.

Traumatic Submacular Hemorrhage with Macular Hole Repaired by Pneumatic Displacement and Intravitreal t-PA Injection.

This paper presents a case demonstrating repair of traumatic macular hole and submacular hemorrhage with intravitreal gas tamponade and t-PA in an office setting.

Pachydermoperiostosis: a rare cause of marked blepharoptosis and floppy eyelid syndrome.

A 34-year-old African-American man was referred for eyelid swelling and ocular discomfort. He was found to have floppy hypertrophic eyelids and marked bilateral mechanical ptosis that was present since childhood. Systemic examination was significant for furrows on his forehead and scalp, coarse facial features, and enlarged hands and feet with clubbing of the fingers and toes. Radiographic imaging of the long bones demonstrated periostosis, and MRI of the head revealed a pituitary macroadenoma. Pituitary and thyroid hormone levels were normal. The patient was diagnosed with pachydermoperiostosis and a non-secreting pituitary macroadenoma. Bilateral upper lid tightening via wedge resection was followed by bilateral external levator advancement ptosis repair in a staged manner. The patient achieved symptom relief and improved lid position postoperatively.

Is distal locking necessary? A biomechanical investigation of intramedullary nailing constructs for intertrochanteric fractures.

OBJECTIVES: Unstable intertrochanteric fractures in the elderly occur frequently. Several studies have evaluated the biomechanical impact of distally locking long cephalomedullary nails under axial loading; however, the impact of torsional loading has not been investigated. The purpose of this study is to determine the rotational load to failure of unstable intertrochanteric fractures treated with long cephalomedullary nails, with and without distal interlocking. METHODS: Eleven paired cadaveric femora treated with long cephalomedullary nails were randomized into 2 groups. Group 1 was left unlocked, whereas group 2 was distally locked. Osteotomies were completed to create unstable 4-part fractures. The femora were anatomically fixed proximally and distally and secured to the biomechanical testing machine to undergo internal rotation. Torque and rotational angle were measured until failure. RESULTS: The locked group had a mean maximal torsional load of 57.9 ± 19.0 N·m and a mean rotational stiffness of 119.4 ± 35.7 N·m/rad. The femora treated with unlocked nails had a mean maximal torsional load of 29.1 ± 12.2 N·m and a mean rotational stiffness of 77.2 ± 31.3 N·m/rad. Distal locking resulted in a significant increase in maximal rotational load (P = 0.001) and rotational stiffness (P = 0.004) before failure. No significant difference was found in mean rotational angle at failure between groups (26.0 ± 9.6 degrees, P = 0.263). CONCLUSIONS: Maximal torsional load to failure for the unlocked group is within the functional range of rotational loads experienced at the hip for an average adult. The results show that distal locking significantly increases rotational load to failure. The authors highly recommend routine use of distal interlocking screws during cephalomedullary nail placement in unstable intertrochanteric fractures.