Deep learning to detect significant coronary artery disease from plain chest radiographs AI4CAD

D’Ancona, Giuseppe; Massussi, Mauro; Savardi, Mattia; Signoroni, Alberto; Bacco, Lorenzo Di; Farina, Davide; Metra, Marco; Maroldi, Roberto; Muneretto, Claudio; İnce, Hüseyin; Costabile, Davide; Murero, Monica; Chizzola, Giuliano; Curello, Salvatore; Benussi, Stefano

doi:10.1016/j.ijcard.2022.10.154

Cited by 13 publications

(8 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This obviously requires high-quality data sources to avoid sampling and observer bias (Table 2). Artificial intelligence and deep learning support coronary artery disease early diagnosis from plain chest radiographs so as to contain costs and prevent the occurrence of adverse events 85 …”

Section: Artificial Intelligence and Machine Learning In Cardiovascul...mentioning

confidence: 99%

See 1 more Smart Citation

The Italian Society of Cardiology and Working Group on Telecardiology and Informatics 2023 updated position paper on telemedicine and artificial intelligence in cardiovascular disease

Brunetti

Curcio

Nodari

et al. 2023

Journal of Cardiovascular Medicine

View full text Add to dashboard Cite

In 2015, the Italian Society of Cardiology and its Working Group on Telemedicine and Informatics issued a position paper on Telecardiology, resuming the most eminent evidence supporting the use of information and communication technology in principal areas of cardiovascular care, ranked by level of evidence. More than 5 years later and after the global shock inflicted by the SARS-CoV-2 pandemic, an update on the topic is warranted. Recent evidence and studies on principal areas of cardiovascular disease will be therefore reported and discussed, with particular focus on telemedicine for cardiovascular care in the COVID-19 context. Novel perspectives and opportunities disclosed by artificial intelligence and its applications in cardiovascular disease will also be discussed. Finally, modalities by which machine learning have realized remote patient monitoring and long-term care in recent years, mainly filtering critical clinical data requiring selective hospital admission, will be provided.

show abstract

Section: Artificial Intelligence and Machine Learning In Cardiovascul...mentioning

confidence: 99%

“…Artificial intelligence and deep learning support coronary artery disease early diagnosis from plain chest radiographs so as to contain costs and prevent the occurrence of adverse events. 85…”

Section: Artificial Intelligence and Machine Learning In Cardiovascul...mentioning

confidence: 99%

The Italian Society of Cardiology and Working Group on Telecardiology and Informatics 2023 updated position paper on telemedicine and artificial intelligence in cardiovascular disease

Brunetti

Curcio

Nodari

et al. 2023

Journal of Cardiovascular Medicine

View full text Add to dashboard Cite

show abstract

“…4 Several investigations have focused on the critical role of noninvasive imaging in diagnosing cardiovascular diseases. 5,6 (2) Secondly, as CAD can cause hospitalizations for both acute myocardial infarction and heart failure, younger patients affected by CAD are at a higher risk of recurrent acute cardiac events. Artificial intelligence may integrate patient data, including medical history, diagnostic tests and vital signs in an attempt to predict and possibly prevent major adverse cardiac events.…”

Section: Aimentioning

confidence: 99%

“…Firstly, artificial intelligence aids in developing and implementing sensitive, practical, reproducible and sustainable means of estimating a CAD patient's PTP (pretest probability) to rationalize and expedite triage to more invasive coronary diagnostic procedures 4 . Several investigations have focused on the critical role of noninvasive imaging in diagnosing cardiovascular diseases 5,6 …”

mentioning

confidence: 99%

Revolutionizing healthcare: artificial intelligence detection of coronary artery disease paves the way for future tools

Massussi

Metra

Adamo

2023

Journal of Cardiovascular Medicine

Self Cite

View full text Add to dashboard Cite

“…The latest advances in machine learning show that electrocardiogram and patient data can be used to detect heart disease in the early stages 2 . D’Ancona et al 10 used deep learning to detect coronary artery disease based on patients’ chest X-ray results. Haq et al 11 developed a hybrid intelligent machine learning model based on the Cleveland Heart Disease data set, which can classify heart disease patients and healthy populations.…”

Section: Introductionmentioning

confidence: 99%

Using machine learning algorithms to identify chronic heart disease: National Health and Nutrition Examination Survey 2011–2018

Chen

Guo

Wang

et al. 2023

Journal of Cardiovascular Medicine

View full text Add to dashboard Cite

Objective The number of heart disease patients is increasing. Establishing a risk assessment model for chronic heart disease (CHD) based on risk factors is beneficial for early diagnosis and timely treatment of highrisk populations.Methods Four machine learning models, including logistic regression, support vector machines (SVM), random forests, and extreme gradient boosting (XGBoost), were used to evaluate the CHD among 14 971 participants in the National Health and Nutrition Examination Survey from 2011 to 2018. The area under the receiver-operator curve (AUC) is the indicator that we evaluate the model. ResultsIn four kinds of models, SVM has the best classification performance (AUC U 0.898), and the AUC value of logistic regression and random forest were 0.895 and 0.894, respectively. Although XGBoost performed the worst with an AUC value of 0.891. There was no significant difference among the four algorithms. In the importance analysis of variables, the three most important variables were taking low-dose aspirin, chest pain or discomfort, and total amount of dietary supplements taken. ConclusionAll four machine learning classifiers can identify the occurrence of CHD based on population survey data. We also determined the contribution of variables in the prediction, which can further explore their effectiveness in actual clinical data.

show abstract

Deep learning to detect significant coronary artery disease from plain chest radiographs AI4CAD

Cited by 13 publications

References 25 publications

The Italian Society of Cardiology and Working Group on Telecardiology and Informatics 2023 updated position paper on telemedicine and artificial intelligence in cardiovascular disease

The Italian Society of Cardiology and Working Group on Telecardiology and Informatics 2023 updated position paper on telemedicine and artificial intelligence in cardiovascular disease

Revolutionizing healthcare: artificial intelligence detection of coronary artery disease paves the way for future tools

Using machine learning algorithms to identify chronic heart disease: National Health and Nutrition Examination Survey 2011–2018

Contact Info

Product

Resources

About