The role of automatic electrocardiogram (ECG) analysis in clinical practice is limited by the accuracy of existing models. Deep Neural Networks (DNNs) are models composed of stacked transformations that learn tasks by examples. This technology has recently achieved striking success in a variety of task and there are great expectations on how it might improve clinical practice. Here we present a DNN model trained in a dataset with more than 2 million labeled exams analyzed by the Telehealth Network of Minas Gerais and collected under the scope of the CODE (Clinical Outcomes in Digital Electrocardiology) study. The DNN outperform cardiology resident medical doctors in recognizing 6 types of abnormalities in 12-lead ECG recordings, with F1 scores above 80% and specificity over 99%. These results indicate ECG analysis based on DNNs, previously studied in a single-lead setup, generalizes well to 12-lead exams, taking the technology closer to the standard clinical practice.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7145824PMC
http://dx.doi.org/10.1038/s41467-020-15432-4DOI Listing

Publication Analysis

Top Keywords

clinical practice
12
12-lead ecg
8
deep neural
8
ecg analysis
8
automatic diagnosis
4
diagnosis 12-lead
4
ecg
4
ecg deep
4
neural network
4
network role
4

Similar Publications

Background: For esophageal squamous cell carcinoma (ESCC), universally accepted pathological criteria for classification by differentiation degree are lacking. Tumor budding, single-cell invasion, and nuclear grade, recognized as prognostic factors in other carcinomas, have rarely been investigated for their correlation with differentiation and prognosis in ESCC. This study aims to determine if pathological findings can predict differentiation degree and prognosis in ESCC.

View Article and Find Full Text PDF

Background Ankle fractures are one of the most common presentations in orthopaedic surgery and represent the third most frequent musculoskeletal injury in the elderly population. Syndesmotic injuries can be associated with ankle fractures, and surgical intervention is critical in these injuries to restore stability and prevent long-term disability. Traditionally, syndesmotic screw fixation has been the standard treatment for acute traumatic syndesmotic injuries, but controversies regarding this fixation method remain.

View Article and Find Full Text PDF

Introduction: Graduate medical education is being reformed in many countries, with a focus on the principles of competency-based medical education (CBME). A main novel aspect in this context is the implementation of entrustable professional activities (EPAs). The introduction of EPAs aims to better align training curricula with clinical practice, provide individualized supervision, and enhance the quality of feedback.

View Article and Find Full Text PDF

Objective: The purpose of this study was to determine what activities and skills interprofessional health science preceptors (IHSPs) perform and value as a part of their pedagogical practice in order to support the development of a preceptor self-assessment tool and assist in preceptor training.

Methods: We administered an online survey to identify core preceptor activities across health sciences disciplines that interact with nursing. The initial survey items were developed based on the Interprofessional Education Collaborative (IPEC) core competencies as well as a search of literature on expected preceptor competencies and activities across individual health sciences professions.

View Article and Find Full Text PDF

Methemoglobinemia (MetHb) is a life-threatening condition that reduces the oxygen-carrying ability of hemoglobin. Acquired methemoglobinemia usually results from exposure to specific oxidizing agents. Symptoms and complications depend on the MetHb level, which can sometimes be fatal.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!