Deep Learning for Detecting and Locating Myocardial Infarction by Electrocardiogram: A Literature Review

Xiong, Ping; Lee, Simon Ming‐Yuen; Chan, Ging

doi:10.3389/fcvm.2022.860032

Cited by 46 publications

(13 citation statements)

References 143 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The LSTM and GRU algorithms were able to better understand the relationship between time variables and their in uence on the future due to the algorithm characteristics. In addition, linear regression, XGBoost and Neural Network commonly show more di culty in predicting abrupt changes, although linear regression may be one of the largely used methods, with a variety application in healthcare 29,30 .…”

Section: Discussionmentioning

confidence: 99%

Predicting hospital admissions and its cost due to respiratory diseases in Brazil using Machine Learning Time Series Forecasting

Ferreira¹,

Goularte²,

Paté³

et al. 2022

Preprint

View full text Add to dashboard Cite

Background: Respiratory diseases (RD) impose an immense health burden and over 1 billion people suffer from acute or chronic RD. Artificial Intelligence (AI) can improve the quality of healthcare, with the potential of assisting in the medical diagnosis of many diseases and reducing unnecessary hospitalizations and costs. This article aims to develop a Machine Learning (ML) model to predict the healthcare resources utilization (HCRU) and costs associated to RD hospitalizations in the Brazilian public health system (SUS). Methods: Data were extracted from three public databases: Hospital Information System (SIH), “e-saúde” database and Meteorological Database, in the city of Curitiba, between 2017 and 2019. All analyzes considered the number of hospitalizations per day. The outcomes predicted by ML were the cost and the number of hospitalizations in the next seven days after a RD claim. The models were created by data mining process. Different algorithms were tested by the model building process up to five times. The best model for the seven-day cost and utilization forecasts was defined according to mean absolute percentage error (MAPE), mean absolute error (MAE), root mean squared error (RMSE). The SHAP method was used to analyze the interpretability of the best selected model. Results: There were, on average, 315.41 hospitalizations and 97,596 primary care services for RD per week in the city of Curitiba between 2017 and 2019, with an average cost of 246,390.30 US dollars (R$ 549,332.87). The Recurrent Neural Network (RNN) methods (LSTM and GRU) presented the best results for forecasting costs and HCRU. LSTM model outperformed all other algorithms in both models with a RMSE of 0.07 and 0.04 respectively. The most impacting variables in the model (SHAP analysis) were the meteorological ones. However, the forward to specialist, type of attendance and medical specialty on the ambulatorial records were also important. High average temperatures support the model to make a prediction of a smaller number of hospitalization days for that period. Conclusion: The prediction model used was robust enough to predict information about hospitalization and costs related to RD, demonstration its applicability as a tool to optimize resources allocation and health promotion strategies.

show abstract

Section: Discussionmentioning

confidence: 99%

Predicting hospital admissions and its cost due to respiratory diseases in Brazil using Machine Learning Time Series Forecasting

Ferreira¹,

Goularte²,

Paté³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The framework used active learning (AL) to enhance the classification ability of the initial model, and then spatial matching self-training (STSM) to enhance the model performance. The deep learning methods can effectively improve the performance of MI, but it is still very challenging to interpret the obtained features and results, which to some extent limits its use in real clinical practice (Jahmunah et al 2022, Xiong et al 2022. In contrast, feature engineering-based methods can extract ECG features with interpretability, but these features are mostly static and do not consider dynamic changes.…”

Section: Introductionmentioning

confidence: 99%

An interpretable shapelets-based method for myocardial infarction detection using dynamic learning and deep learning

Qu,

Sun,

et al. 2024

Physiol. Meas.

View full text Add to dashboard Cite

Objective. Myocardial infarction (MI) is a prevalent cardiovascular disease that contributes to global mortality rates. Timely diagnosis and treatment of MI are crucial in reducing its fatality rate. Currently, electrocardiography (ECG) serves as the primary tool for clinical diagnosis. However, detecting MI accurately through ECG remains challenging due to the complex and subtle pathological ECG changes it causes. To enhance the accuracy of ECG in detecting MI, a more thorough exploration of ECG signals is necessary to extract significant features. Approach. In this paper, we propose an interpretable shapelet-based approach for MI detection using dynamic learning and deep learning. Firstly, the intrinsic dynamics of ECG signals are learned through dynamic learning. Then, a deep neural network is utilized to extract and select shapelets from ECG dynamics, which can capture locally specific ECG changes, and serve as discriminative features for identifying MI patients. Finally, the ensemble model for MI detection is built by integrating shapelets of multi-dimensional ECG dynamic signals. Main results. The performance of the proposed method is evaluated on the public PTB dataset with accuracy, sensitivity, and specificity of 94.11%, 94.97%, and 90.98%. Significance. The shapelets obtained in this study exhibit significant morphological differences between MI and healthy subjects.

show abstract

“…Network models such as CNN [4] and residual network [5] have excellent performance in diagnosing disease types and accuracy. Many studies have focused on detecting myocardial infarction [6][7], and network models such as CNN, RNN, and ResNet have been used. However, compared to machine learning methods based on fixed features with clear meaning [8][9], doctors and patients often consider deep learning methods "black boxes" [10], and their reliability at the medical level has been widely questioned.…”

Section: Introductionmentioning

confidence: 99%

An Interpretable Residual Neural Network for the Diagnosis of Myocardial Infarction

Wei,

Wang,

Jin

et al. 2023

Fuzzy Systems and Data Mining IX

View full text Add to dashboard Cite

Acute myocardial infarction (AMI) is a kind of heart disease with a high mortality rate and easy to ignore the early symptoms. Patients need to obtain timely and accurate diagnosis at the onset of the disease. Automatic ECG diagnosis based on deep learning method is significant for treating such patients because of its timeliness and ease of use. However, the “black box” nature of deep learning methods affects the confidence of doctors and patients and seriously restricts the popularity of its clinical applications. Therefore, it is necessary to study its explainability. This paper uses a residual neural network to realize the end-to-end diagnosis of myocardial infarction disease in a 12-lead electrocardiogram. By designing a specific data processing method, the residual network is used to preserve the characteristics of the feature time order. With the time attention mechanism, we can realize the interpretability of the channel between 12 leads and the time interpretability of the signal segments in each lead. This study reveals the reliability of deep learning methods in clinical Settings.

show abstract

Deep Learning for Detecting and Locating Myocardial Infarction by Electrocardiogram: A Literature Review

Cited by 46 publications

References 143 publications

Predicting hospital admissions and its cost due to respiratory diseases in Brazil using Machine Learning Time Series Forecasting

Predicting hospital admissions and its cost due to respiratory diseases in Brazil using Machine Learning Time Series Forecasting

An interpretable shapelets-based method for myocardial infarction detection using dynamic learning and deep learning

An Interpretable Residual Neural Network for the Diagnosis of Myocardial Infarction

Contact Info

Product

Resources

About