Evaluating atrial fibrillation artificial intelligence for the ED: statistical and clinical implications.

OBJECTIVE: An artificial intelligence (AI) algorithm has been developed to detect the electrocardiographic signature of atrial fibrillation (AF) present on an electrocardiogram (ECG) obtained during normal sinus rhythm. We evaluated the ability of this algorithm to predict incident AF in an emergency department (ED) cohort of patients presenting with palpitations without concurrent AF. METHODS: This retrospective study included patients 18 years and older who presented with palpitations to one of 15 ED sites and had a 12­lead ECG performed. Patients with prior AF or newly diagnosed AF during the ED visit were excluded. Of the remaining patients, those with a follow up ECG or Holter monitor in the subsequent year were included. We evaluated the performance of the AI-ECG output to predict incident AF within one year of the index ECG by estimating an area under the receiver operating characteristics curve (AUC). Sensitivity, specificity, and positive and negative predictive values were determined at the optimum threshold (maximizing sensitivity and specificity), and thresholds by output decile for the sample. RESULTS: A total of 1403 patients were included. Forty-three (3.1%) patients were diagnosed with new AF during the following year. The AI-ECG algorithm predicted AF with an AUC of 0.74 (95% CI 0.68-0.80), and an optimum threshold with sensitivity 79.1% (95% Confidence Interval (CI) 66.9%-91.2%), and specificity 66.1% (95% CI 63.6%-68.6%). CONCLUSIONS: We found this AI-ECG AF algorithm to maintain statistical significance in predicting incident AF, with clinical utility for screening purposes limited in this ED population with a low incidence of AF.

Emergency Medical Services Provider Self-Reported Occupational Safety.

BACKGROUND: Emergency medical services (EMS) providers are at high risk for occupational violence, and some tactical EMS providers carry weapons. METHODS: Anonymous surveys were administered to tactical and nontactical prehospital providers at 180 prehospital agencies in northeast Ohio between September 2018 and March 2019. Demographics were collected, and survey questions asked about workplace violence and comfort level with tactical EMS carrying weapons. RESULTS: Of 432 respondents, 404 EMS providers (94%) reported a history of verbal or physical assault on scene, and 395 (91%) reported working in a setting with a direct active threat at least rarely. Of those reporting a history of assault on scene, 46.5% reported that it occurred at least sometimes. Higher rates of assault on scene were associated with being younger, white, or an emergency medical technician-paramedic, working in an urban environment, having more frequent direct active threats, and having more comfort with tactical EMS carrying firearms (p ≤ .03). Most respondents (306; 71%) reported that they were prepared to defend themselves from someone who originally called for help. Most (303; 70%) reported a comfort level of 8 or higher (from 1, not comfortable to 10, completely comfortable) with tactical EMS providers carrying weapons. Comfort with tactical EMS providers carrying weapons was associated with being white, not having a bachelor's degree, and feeling prepared to defend oneself from a patient (p ≤ .02). CONCLUSION: EMS providers in the survey report high rates of verbal and physical violence while on scene and are comfortable with tactical EMS providers carrying weapons.