Inteligência Artificial em Cardiologia: Conceitos, Ferramentas e Desafios – “Quem Corre é o Cavalo, Você Precisa ser o Jóquei”

Filho, Érito Marques de Souza; Fernandes, Fernando de Amorim; Soares, Carlos Alberto Lidizia; Seixas, Flávio Luiz; Santos, Alair Augusto Sarmet Moreira Damas dos; Gismondi, Ronaldo Altenburg; Mesquita, Evandro Tinoco; Mesquita, Cláudio Tinoco

doi:10.36660/abc.20180431

Cited by 17 publications

(7 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Rather, the results of fully automated volumetric analysis should be checked and corrected, if necessary, by a human reader. As with other applications of artificial intelligence, the role of humans imaging experts shifts from performing mechanical tasks to critically reflecting the results of algorithms and developing a professional relationship between physicians, patients and machine-generated data [21].…”

Section: Discussionmentioning

confidence: 99%

Fully automated quantification of left ventricular volumes and function in cardiac MRI: clinical evaluation of a deep learning-based algorithm

Böttcher

Beller

Busse

et al. 2020

Int J Cardiovasc Imaging

View full text Add to dashboard Cite

To investigate the performance of a deep learning-based algorithm for fully automated quantification of left ventricular (LV) volumes and function in cardiac MRI. We retrospectively analysed MR examinations of 50 patients (74% men, median age 57 years). The most common indications were known or suspected ischemic heart disease, cardiomyopathies or myocarditis. Fully automated analysis of LV volumes and function was performed using a deep learning-based algorithm. The analysis was subsequently corrected by a senior cardiovascular radiologist. Manual volumetric analysis was performed by two radiology trainees. Volumetric results were compared using Bland–Altman statistics and intra-class correlation coefficient. The frequency of clinically relevant differences was analysed using re-classification rates. The fully automated volumetric analysis was completed in a median of 8 s. With expert review and corrections, the analysis required a median of 110 s. Median time required for manual analysis was 3.5 min for a cardiovascular imaging fellow and 9 min for a radiology resident (p < 0.0001 for all comparisons). The correlation between fully automated results and expert-corrected results was very strong with intra-class correlation coefficients of 0.998 for end-diastolic volume, 0.997 for end-systolic volume, 0.899 for stroke volume, 0.972 for ejection fraction and 0.991 for myocardial mass (all p < 0.001). Clinically meaningful differences between fully automated and expert corrected results occurred in 18% of cases, comparable to the rate between the two manual readers (20%). Deep learning-based fully automated analysis of LV volumes and function is feasible, time-efficient and highly accurate. Clinically relevant corrections are required in a minority of cases.

show abstract

Section: Discussionmentioning

confidence: 99%

Fully automated quantification of left ventricular volumes and function in cardiac MRI: clinical evaluation of a deep learning-based algorithm

Böttcher

Beller

Busse

et al. 2020

Int J Cardiovasc Imaging

View full text Add to dashboard Cite

show abstract

“…However, "garbage in / garbage out" highlights the real possibility of embedding human errors and biases in AI For example, the Correctional Offender Management Profiling for Alternative Sanctions (COMPAS) system, an algorithm designed to aid the judicial system, replicated common biases and errors [106]. Only the most careful attention will allow us to make those errors and biases visible so that they can be recognized and addressed [107,108].…”

Section: Weaknesses Of Aimentioning

confidence: 99%

What Can COVID-19 Teach Us about Using AI in Pandemics?

et al. 2020

View full text Add to dashboard Cite

The COVID-19 pandemic put significant strain on societies and their resources, with the healthcare system and workers being particularly affected. Artificial Intelligence (AI) offers the unique possibility of improving the response to a pandemic as it emerges and evolves. Here, we utilize the WHO framework of a pandemic evolution to analyze the various AI applications. Specifically, we analyzed AI from the perspective of all five domains of the WHO pandemic response. To effectively review the current scattered literature, we organized a sample of relevant literature from various professional and popular resources. The article concludes with a consideration of AI’s weaknesses as key factors affecting AI in future pandemic preparedness and response.

show abstract

“…ML is usually divided into supervised learning where the algorithm is trained on labeled datasets to map known inputs and outputs and unsupervised learning where the algorithm processes raw, This article is part of the Topical Collection on Cardiac PET, CT, and MRI unlabeled datasets to find patterns for classification. Examples of supervised learning include support vector machines (SVM), naïve Bayes (NB), random forest (RF), and k-nearest neighbors (KNN) [6], among others. Convolutional neural networks (CNN) are a special type of supervised learning that use convolutional (pooling and dense) layers with adaptive filters for extra data features to recognize specific patterns in data [10,11].…”

Section: Machine Learning Overviewmentioning

confidence: 99%

“…As a subset of artificial intelligence (AI), machine learning (ML) can identify complex patterns within datasets too complex for human brains [6,7]. Recently, ML has been increasingly used in medical research and clinical applications [8,9].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning in Electrocardiography and Echocardiography: Technological Advances in Clinical Cardiology

2020

View full text Add to dashboard Cite

Purpose of Review Electrocardiography (ECG) and echocardiography are the most widely used diagnostic tools in clinical cardiology. This review focuses on recent advancements in applying machine learning (ML) in ECG and echocardiography and potential synergistic ML integration of ECG and echocardiography. Recent Findings ML algorithms have been used in ECG for technical quality assurance, arrhythmia identification, and prognostic predictions, and in echocardiography to recognize image views, quantify measurements, and identify pathologic patterns. Synergistic application of ML in ECG and echocardiograph has demonstrated the potential to optimize therapeutic response, improve risk stratification, and generate new disease classification. There is mounting evidence that ML potentially outperforms in disease diagnoses and outcome prediction with ECG and echocardiography when compared with trained healthcare professionals. Summary The applications of ML in ECG and echocardiography are playing increasingly greater roles in medical research and clinical practice, particularly for their contributions to developing novel diagnostic/prognostic prediction models. The automation in data acquisition, processing, and interpretation help streamline the workflows of ECG and echocardiography in contemporary cardiology practice.

show abstract

Inteligência Artificial em Cardiologia: Conceitos, Ferramentas e Desafios – “Quem Corre é o Cavalo, Você Precisa ser o Jóquei”

Cited by 17 publications

References 36 publications

Fully automated quantification of left ventricular volumes and function in cardiac MRI: clinical evaluation of a deep learning-based algorithm

Fully automated quantification of left ventricular volumes and function in cardiac MRI: clinical evaluation of a deep learning-based algorithm

What Can COVID-19 Teach Us about Using AI in Pandemics?

Machine Learning in Electrocardiography and Echocardiography: Technological Advances in Clinical Cardiology

Contact Info

Product

Resources

About