Validation of an automated artificial intelligence system for 12­lead ECG interpretation.

BACKGROUND: The electrocardiogram (ECG) is one of the most accessible and comprehensive diagnostic tools used to assess cardiac patients at the first point of contact. Despite advances in computerized interpretation of the electrocardiogram (CIE), its accuracy remains inferior to physicians. This study evaluated the diagnostic performance of an artificial intelligence (AI)-powered ECG system and compared its performance to current state-of-the-art CIE. METHODS: An AI-powered system consisting of 6 deep neural networks (DNN) was trained on standard 12­lead ECGs to detect 20 essential diagnostic patterns (grouped into 6 categories: rhythm, acute coronary syndrome (ACS), conduction abnormalities, ectopy, chamber enlargement and axis). An independent test set of ECGs with diagnostic consensus of two expert cardiologists was used as a reference standard. AI system performance was compared to current state-of-the-art CIE. The key metrics used to compare performances were sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and F1 score. RESULTS: A total of 932,711 standard 12­lead ECGs from 173,949 patients were used for AI system development. The independent test set pooled 11,932 annotated ECG labels. In all 6 diagnostic categories, the DNNs achieved high F1 scores: Rhythm 0.957, ACS 0.925, Conduction abnormalities 0.893, Ectopy 0.966, Chamber enlargement 0.972, and Axis 0.897. The diagnostic performance of DNNs surpassed state-of-the-art CIE for the 13 out of 20 essential diagnostic patterns and was non-inferior for the remaining individual diagnoses. CONCLUSIONS: Our results demonstrate the AI-powered ECG model's ability to accurately identify electrocardiographic abnormalities from the 12­lead ECG, highlighting its potential as a clinical tool for healthcare professionals.

The ventricular tachycardia prediction model: Derivation and validation data.

In a recent publication [1], we introduced and described a novel means (i.e. VT Prediction Model) to correctly categorize wide complex tachycardias (WCTs) into ventricular tachycardia (VT) and supraventricular wide complex tachycardia (SWCT) using routine measurements shown on electrocardiogram (ECG) paper recordings. In this article, we summarize data components relating to the derivation and validation of the VT Prediction Model.

The WCT Formula: A novel algorithm designed to automatically differentiate wide-complex tachycardias.

BACKGROUND: The accurate differentiation of wide complex tachycardias (WCTs) into ventricular tachycardia (VT) or supraventricular wide complex tachycardia (SWCT) remains problematic despite numerous manually-operated electrocardiogram (ECG) interpretation methods. We sought to create a new WCT differentiation method that could be automatically implemented by computerized ECG interpretation (CEI) software. METHODS: In a two-part study, we developed and validated a logistic regression model (i.e. WCT Formula) that utilizes computerized measurements and computations derived from patients' paired WCT and subsequent baseline ECGs. In Part 1, a derivation cohort of paired WCT and baseline ECGs was examined to identify independent VT predictors to be incorporated into the WCT Formula. In Part 2, a separate validation cohort of paired WCT and baseline ECGs was used to prospectively evaluate the WCT Formula's diagnostic performance. RESULTS: The derivation cohort was comprised of 317 paired WCT (157 VT, 160 SWCT) and baseline ECGs. A logistic regression model (i.e. WCT Formula) incorporating WCT QRS duration (ms) (p < 0.001), frontal percent amplitude change (%) (p < 0.001), and horizontal percent amplitude change (%) (p < 0.001) yielded effective WCT differentiation (AUC of 0.96). The validation cohort consisted of 284 paired WCT (116 VT, 168 SWCT) and baseline ECGs. The WCT Formula achieved favorable accuracy (91.5%) with strong sensitivity (89.7%) and specificity (92.9%) for VT. CONCLUSION: The WCT Formula is an example of how contemporary CEI software could be used to successfully differentiate WCTs. The incorporation of similar automated methods into CEI software may improve clinicians' ability to accurately distinguish VT and SWCT.

Computerized electrocardiogram in agoutis (Dasyprocta prymnolopha Wagler, 1831) anesthetized with ketamine and midazolam / Eletrocardiografia computadorizada em cutias (Dasyprocta prymnolopha Wagler, 1831) anestesiadas com cetamina e midazolam

An electrocardiogram is a test that assesses heart electrical activity and is applied more frequently in the veterinary care of wild animals. The present study aimed to define the electrocardiogram pattern of agoutis (Dasyprocta prymnolopha Wagler, 1831) anesthetized with ketamine and midazolam. Eighteen clinically healthy agoutis (D. prymnolopha) were used from the Nucleus for Wild Animal Studies and Conservation (NEPAS) of the Federal University of Piauí, Brazil. The animals were chemically restrained with 5% ketamine hydrochloride at a dose of 15mg/kg and midazolam at a dose of 1mg/kg by intramuscular injection. Electrocardiogram tests were carried out by a computerized method with the veterinary electrocardiogram [Acquisition Model for Computer (ECG - PC version Windows 95) Brazilian Electronic Technology (TEB) consisting of an electronic circuit externally connected to a notebook computer with ECGPC-VET (TEB) software installed on the hard disc. In analysing the EKG results, significant differences were observed for QRS complex duration, PR and QT intervals and for R wave millivoltage between the genders; but we observed a significant influence of weight despite the gender. In the present experiment, the anaesthetic protocol was shown to be well tolerated by the agoutis, and no arrhythmias occurred during the time the animals were monitored. The reference values obtained should be used to better understand the cardiac electrophysiology of the species and for its clinical and surgical management.(AU)

O eletrocardiograma computadorizado é um dos meios de diagnóstico utilizado para avaliação do coração e vem sendo cada vez mais presente na rotina veterinária. Este trabalho teve por objetivo definir o padrão eletrocardiográfico de cutias (D. prymnolopha) anestesiadas com cetamina e midazolam. Foram utilizadas 18 cutias clinicamente saudáveis, provenientes do Núcleo de Estudos e Preservação de Animais Silvestres (NEPAS) da Universidade Federal do Piauí. Os animais foram submetidos à contenção química com cloridrato de cetamina a 5% na dosagem de 15mg/kg associado ao midazolam, na dosagem de 1mg/kg, por via intramuscular. Os exames eletrocardiográficos foram realizados pelo método computadorizado, com o eletrocardiógrafo veterinário (Módulo de Aquisição de ECG Para Computador (ECG - PC versão Windows 95) Tecnologia Eletrônica Brasileira (TEB) composto por um circuito eletrônico ligado externamente a um notebook, e de um software instalado no disco rígido do computador. Os valores de duração do complexo QRS, intervalos PR e QT, comparados entre machos e fêmeas, apresentaram diferença significativa. Em milivoltagem a onda R foi o único parâmetro que apresentou diferença significativa entre machos e fêmeas. O peso dos animais também foi significativamente diferente entre os gêneros. O protocolo anestésico mostrou-se bem tolerado pelos animais deste experimento, não ocorrendo quadros de arritmias durante o tempo de monitoramento dos animais.(AU)

Métodos eletrocardiográficos em equinos American Miniature Horse / Electrocardiographic methods in equines American Miniature Horse

O objetivo deste estudo foi analisar e comparar os registros eletrocardiográficos de 50 equinos American Miniature Horse, clinicamente saudáveis, obtidos pelos métodos convencional e computadorizado, para a padronização do método informatizado. As medidas de duração e amplitude das ondas e intervalos e frequência cardíaca foram analisadas nas derivações do plano frontal e na derivação base-ápice. Diferenças quanto à duração da onda P, foram encontradas nas derivações I e aVL, e do complexo QRS, em todas as derivações do plano frontal. Quanto à derivação base-ápice, houve diferença na duração do intervalo QT e da onda T, assim como na amplitude da onda S. Concluiu-se, portanto, que ocorre superestimação da duração do complexo QRS no método computadorizado e que, devido às diferenças inerentes de cada método, torna-se importante a utilização de valores de referência para o método computadorizado também na espécie equina.

The aim of this study was to analyze and compare electrocardiographic records of 50 horses American Miniature Horse, clinically healthy, obtained by conventional methods and computerized, to the standardization of the computerized method. The measures of duration and amplitude of waves and intervals and heart rate were analyzed in the leads of the frontal plane and base-apical lead. Differences about the duration of the P wave were found in I and aVL derivations, and QRS complex, in all derivations of the frontal plane. As for basis-apical derivation, there was no difference in the duration of the QT interval and the T wave and the amplitude of the S wave, therefore concluding that overestimation occurs in the duration of the QRS complex in computerized method and that due to inherent differences of each method, it becomes important the use of reference values for the computerized method also in the equine species.