SignificanceHistorically, computer-assisted detection (CAD) in radiology has failed to achieve improvements in diagnostic accuracy, decreasing clinician sensitivity and leading to unnecessary further diagnostic tests. With the advent of deep learning approaches to CAD, there is great excitement about its application to medicine, yet there is little evidence demonstrating improved diagnostic accuracy in clinically-relevant applications. We trained a deep learning model to detect fractures on radiographs with a diagnostic accuracy similar to that of senior subspecialized orthopedic surgeons. We demonstrate that when emergency medicine clinicians are provided with the assistance of the trained model, their ability to accurately detect fractures significantly improves.

No abstract

Twenty-eight patients with advanced neovascular age-related macular degeneration (AMD) were given a single intravitreous injection of an E1-, partial E3-, E4-deleted adenoviral vector expressing human pigment epithelium- derived factor (AdPEDF.11). Doses ranging from 10(6) to 10(9.5) particle units (PU) were investigated. There were no serious adverse events related to AdPEDF.11 and no dose-limiting toxicities. Signs of mild, transient intraocular inflammation occurred in 25% of patients, but there was no severe inflammation. Six patients experienced increased intraocular pressure that was easily controlled by topical medication. All adenoviral cultures were negative. At 3 and 6 months after injection, 55 and 50%, respectively, of patients treated with 10(6)-10(7.5) PU and 94 and 71% of patients treated with 10(8)-10(9.5) PU had no change or improvement in lesion size from baseline. The median increase in lesion size at 6 and 12 months was 0.5 and 1.0 disk areas in the low-dose group compared with 0 and 0 disk areas in the high-dose group. These data suggest the possibility of antiangiogenic activity that may last for several months after a single intravitreous injection of doses greater than 10(8) PU of AdPEDF.11. This study provides evidence that adenoviral vector-mediated ocular gene transfer is a viable approach for the treatment of ocular disorders and that further studies investigating the efficacy of AdPEDF.11 in patients with neovascular AMD should be performed.

Electromyographic monitoring of the RLN using a postcricoid surface electrode provides a safe, simple, and effective method for intraoperative monitoring during thyroid or parathyroid surgery. Further, evoked electromyography confirms RLN integrity at the conclusion of surgery.