Obstructive sleep apnea (OSA) has been a common sleep disorder for years, and polysomnography (PSG) remains the gold standard for diagnosing OSA. Nevertheless, PSG is a time and money consuming test, and patients have to wait long for arranging a PSG test in a hospital. In light of this, portable and wearable tools for OSA classification have been developed recently as a low‐cost and easy‐to‐use screening method before undergoing PSG. Using unsegmented electrocardiogram (ECG) signals, a deep neural network (DNN)‐based model is developed here to categorize OSA severity with the following features. First, the model takes unsegmented ECG signals recorded overnight as input, and then generates a four‐level scale as output. Since all the input ECG signals are unsegmented, the tremendous amount of effort spent on signal annotation can be fully saved. Second, the largest amount of data is used to test the model and consequently provide a high generalization ability, as compared with others in the literature. The overall outperformance of this work is highlighted at the end of this article, and this work is validated as an easy‐to‐use and effective screening tool for OSA accordingly.
Background: Competency-based medical education has emerged as a mainstream method for educating and assessing the next generation of physicians. This study aims to initiate and examine the preliminary results of an integrated Traditional Chinese Otolaryngology Milestone Project in Taiwan. Methods: This prospective study enrolled 18 participants in an academic hospital setting from July 2017 to August 2019. Participants included twelve attending and six resident physicians. Using the Integrated Traditional Chinese Otolaryngology Milestones (ITCOM), five biannual evaluations involved independent self-assessments by the resident doctors, which the chief resident and attending physicians independently reevaluated. A Kruskal–Wallis test was used to compare the results of the five assessments. Results: The average scores of attained milestones for the five assessments were as follows for residents PGY1– PGY6: PGY1 (1.48 ± 0.24; 1.69 ± 0.10, P = 0.01), PGY2 ( 1.24 ± 0.12; 1.51 ± 0.23; 1.75 ± 0.06; 1.98 ± 0.21; 2.47 ± 0.18 , P < 0.0001), PGY3 (2.19 ± 0.24; 2.36 ± 0.25; 2.80 ± 0.19; 2.96 ± 0.24; 3.33 ± 0.23, P < 0.0001), PGY4 (2.68 ± 0.17; 2.96 ± 0.09; 3.35 ± 0.13; 3.58 ± 0.10; 4.17 ± 0.08, P < 0.0001), PGY5 (3.07 ± 0.24; 3.38 ± 0.12; 3.58 ± 0.10; 4.05 ± 0.09, P < 0.0001) and PGY6 ( 3.30 ± 0.27; 3.61 ± 0.28; 4.22 ± 0.20, P = 0.0001). The score results for patient care, medical knowledge, and professionalism were more likely to indicate heightened attainment of milestone levels as the program progressed. However, the curves of the score results for system-based practice, problem-based learning and improvement, and interpersonal and communication skills were more horizontal, showing that the milestones might indicate a better performance than expected, even in residents with low training seniority. Conclusions: The results of the five biannual assessments revealed that all resident physicians demonstrated a significant improvement. Further study involving large-scale participants and multiple institutions is warranted.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.