A Multivariate Model for Prediction of Obstructive Coronary Disease in Patients
            with Acute Chest Pain: Development and Validation

Correia, Luís Cláudio Lemos; Cerqueira, Maurício; Carvalhal, Manuela; Ferreira, Fábio de Oliveira; Garcia, Guilherme; Silva, André Barcelos da; Sá, Nicole de; Lopes, Fernanda; Barcelos, Ana Clara; Noya-Rabelo, Márcia

doi:10.5935/abc.20170037

Cited by 3 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“… 18 , 19 , 20 , 21 , 22 Predicting models may better estimate the pretest probability for coronary artery disease in individuals with acute chest discomfort during SVT and would help to conduct these scenarios more appropriately. 23 Although we claim that chest pain favors a coronary disease work up bias, we lack any objective data to support it and we recognize that the cognitive bias hypothesis is speculative and should be evaluated in future studies.…”

Section: Discussionmentioning

confidence: 87%

Underuse of Catheter Ablation as First‐Line Therapy for Supraventricular Tachycardia

Oliveira

Viana

Luize

et al. 2022

JAHA

View full text Add to dashboard Cite

Background Catheter ablation (CA) is a safe, effective, cost‐effective technique and may be considered a first‐line strategy for the treatment of symptomatic supraventricular tachycardias (SVT). Despite the high prospect of cure and the recommendations of international guidelines in considering CA as a first‐line treatment strategy, the average time between diagnosis and the procedure may be long. The present study aims to evaluate predictors related to non‐referral for CA as first‐line treatment in patients with SVT. Methods and Results The model was derived from a retrospective cohort of patients with SVT or ventricular pre‐excitation referred for CA in a tertiary center. Clinical and demographical features were used as independent variables and non‐referral for CA as first‐line treatment the dependent variable in a stepwise logistic regression analysis. Among 20 clinical‐demographic variables from 350 patients, 10 were included in initial logistic regression analysis: age, women, presence of pre‐excitation on ECG, palpitation, dyspnea and chest discomfort, number of antiarrhythmic drugs before ablation, number of concomitant symptoms, symptoms’ duration and evaluations in the emergency room due to SVT. After multivariable adjusted analysis, age (odds ratio [OR], 1.2; 95% CI 1.01–1.32; P =0.04), chest discomfort during supraventricular tachycardia (OR, 2.7; CI 1.6–4.7; P <0.001) and number of antiarrhythmic drugs before ablation (OR, 1.8; CI 1.4–2.3; P <0.001) showed a positive independent association for non‐referral for CA as SVT first‐line treatment. Conclusions The independent predictors of non‐referral for CA as first‐line treatment in our logistic regression analysis indicate the existence of biases in the decision‐making process in the referral process of patients who would benefit the most from catheter ablation. They very likely suggest a skewed medical decision‐making process leading to catheter ablation underuse.

show abstract

Section: Discussionmentioning

confidence: 87%

Underuse of Catheter Ablation as First‐Line Therapy for Supraventricular Tachycardia

Oliveira

Viana

Luize

et al. 2022

JAHA

View full text Add to dashboard Cite

show abstract

“…4 Nesse processo, a probabilidade de DAC obstrutiva deve conduzir a tomada de decisão médica. 5 No presente estudo, utilizamos dados de um registro prospectivo de dor torácica para construir um modelo de machine learning para predizer doença coronariana obstrutiva. Nosso objetivo foi avaliar se um algoritmo de inteligência artificial é um melhor preditor que a regressão logística em um conjunto tradicional de dados epidemiológicos simples, considerando tanto propriedades discriminatórias como de calibração.…”

Section: Introductionunclassified

“…In the present study, we utilized data from a prospective registry of chest pain 5 to build a machine learning model to predict obstructive coronary disease. We aimed to evaluate whether an artificial intelligence algorithm is a better predictor than logistic regression in a traditional set of simple epidemiological data, considering both discrimination and calibration properties.…”

Section: Introductionmentioning

confidence: 99%

Validação de um Algoritmo de Inteligência Artificial para a Predição Diagnóstica de Doença Coronariana: Comparação com um Modelo Estatístico Tradicional

Correia¹,

Lopes²,

Oliveira³

et al. 2021

Arquivos Brasileiros De Cardiologia

View full text Add to dashboard Cite

Fundamento: A análise prognóstica multivariada tem sido realizada tradicionalmente por modelos de regressão. No entanto, muitos algoritmos surgiram, capazes de traduzir uma infinidade de padrões em probabilidades. A acurácia dos modelos de inteligência artificial em comparação à de modelos estatísticos tradicionais não foi estabelecida na área médica. Objetivo: Testar a inteligência artificial como um algoritmo preciso na predição de doença coronariana no cenário de dor torácica aguda, e avaliar se seu desempenho é superior a do modelo estatístico tradicional. Métodos: Foi analisada uma amostra consecutiva de 962 pacientes admitidos com dor torácica. Dois modelos probabilísticos de doença coronariana foram construídos com os primeiros 2/3 dos pacientes: um algoritmo machine learning e um modelo logístico tradicional. O desempenho dessas duas estratégias preditivas foi avaliado no último terço de pacientes. O modelo final de regressão logística foi construído somente com variáveis significativas a um nível de significância de 5%. Resultados: A amostra de treinamento tinha idade média de 59 ± 15 anos, 58% do sexo masculino, e uma prevalência de doença coronariana de 52%. O modelo logístico foi composto de nove preditores independentes. O algoritmo machine learning foi composto por todos os candidatos a preditores. Na amostra teste, a área sob a curva ROC para predição de doença coronariana foi de 0,81 (IC95% = 0,77 -0,86) para o algoritmo machine learning, similar à obtida no modelo logístico (0,82; IC95% = 0,77 -0,87), p = 0,68. Conclusão: O presente estudo sugere que um modelo machine learning acurado não garante superioridade à um modelo estatístico tradicional

show abstract

“…2 A probabilidade de DAC obstrutiva deve orientar as decisões médicas. 3 Algoritmos de aprendizado de máquina ( machine learning — ML) podem complementar as capacidades diagnósticas e prognósticas dos métodos de regressão convencionais. A disparidade entre a aplicabilidade de tais métodos e os resultados alcançados com eles se deve às plataformas de software de análise de dados utilizadas.…”

unclassified

“…2 The likelihood of obstructive CAD should guide medical decisions. 3 Machine learning (ML) algorithms can supplement the diagnostic and prognostic capabilities of conventional regression methods. The disparity between the applicability of such methods and the outcomes achieved with them was due to the data analysis software platforms used.…”

mentioning

confidence: 99%

Algoritmos Artificiais Superam os Modelos Tradicionais na Predição de Doença Arterial Coronariana

Aşkın¹,

Tanrıverdi²,

Çetın³

2021

Arquivos Brasileiros De Cardiologia

View full text Add to dashboard Cite

Recent clinical recommendations indicate that additional tests for assessing anatomical (extent, severity, morphology) or functional (ventricular function, presence/extent of ischemia) aspects of chronic and symptomatic coronary artery disease (CAD) may be helpful in certain cases. 1 Emergency physicians must determine whether to release the patient, do further non-invasive testing, or perform invasive angiography on patients with acute chest discomfort. Accepting anybody with chest pain may have unintended effects if discharged with unstable coronary disease. 2 The likelihood of obstructive CAD should guide medical decisions. 3 Machine learning (ML) algorithms can supplement the diagnostic and prognostic capabilities of conventional regression methods. The disparity between the applicability of such methods and the outcomes achieved with them was due to the data analysis software platforms used. 4

show abstract

A Multivariate Model for Prediction of Obstructive Coronary Disease in Patients with Acute Chest Pain: Development and Validation

Cited by 3 publications

References 16 publications

Underuse of Catheter Ablation as First‐Line Therapy for Supraventricular Tachycardia

Underuse of Catheter Ablation as First‐Line Therapy for Supraventricular Tachycardia

Validação de um Algoritmo de Inteligência Artificial para a Predição Diagnóstica de Doença Coronariana: Comparação com um Modelo Estatístico Tradicional

Algoritmos Artificiais Superam os Modelos Tradicionais na Predição de Doença Arterial Coronariana

Contact Info

Product

Resources

About