Submitted Successfully!
To reward your contribution, here is a gift for you: A free trial for our video production service.
Thank you for your contribution! You can also upload a video entry or images related to this topic.
Version Summary Created by Modification Content Size Created at Operation
1 -- 2734 2023-05-22 18:33:17 |
2 only format change Meta information modification 2734 2023-05-23 04:07:57 |

Video Upload Options

Do you have a full video?

Confirm

Are you sure to Delete?
Cite
If you have any further questions, please contact Encyclopedia Editorial Office.
Ledziński, �.; Grześk, G. The Implementation of Artificial Intelligence Technologies in Cardiology. Encyclopedia. Available online: https://encyclopedia.pub/entry/44678 (accessed on 13 June 2024).
Ledziński �, Grześk G. The Implementation of Artificial Intelligence Technologies in Cardiology. Encyclopedia. Available at: https://encyclopedia.pub/entry/44678. Accessed June 13, 2024.
Ledziński, Łukasz, Grzegorz Grześk. "The Implementation of Artificial Intelligence Technologies in Cardiology" Encyclopedia, https://encyclopedia.pub/entry/44678 (accessed June 13, 2024).
Ledziński, �., & Grześk, G. (2023, May 22). The Implementation of Artificial Intelligence Technologies in Cardiology. In Encyclopedia. https://encyclopedia.pub/entry/44678
Ledziński, Łukasz and Grzegorz Grześk. "The Implementation of Artificial Intelligence Technologies in Cardiology." Encyclopedia. Web. 22 May, 2023.
The Implementation of Artificial Intelligence Technologies in Cardiology
Edit

Artificial Intelligence (AI) technologies have been increasingly used in cardiology to improve the accuracy and efficiency of diagnosis, treatment, and management of cardiovascular diseases. AI-based image analysis algorithms can quickly and accurately detect abnormalities in medical images, and predictive models can analyze vast amounts of patient data to identify patterns and predict the likelihood of developing certain cardiovascular diseases.

artificial intelligence cardiology machine learning

1. Introduction

Cardiology is a complex field of medicine that focuses on the diagnosis, treatment, and management of cardiovascular diseases. Due to its complexity, the diagnosis and treatment of cardiovascular diseases can be challenging. Cardiovascular diseases include a wide range of conditions that affect the heart and blood vessels, such as coronary artery disease, heart failure, arrhythmia, and valvular heart disease. These diseases can cause a range of symptoms, including chest pain, shortness of breath, fatigue, dizziness, and many deviations in laboratory parameters.
Medical imaging techniques, such as echocardiography, cardiac magnetic resonance imaging (MRI), and computed tomography (CT) scans, are among the primary diagnostic tools used in cardiology. These imaging methods provide detailed information about the heart’s structure and function, enabling clinicians to detect abnormalities and diagnose cardiovascular diseases. Cardiac catheterization is another diagnostic procedure that is used to assess the heart’s blood vessels and the blood flow to and from the heart.
The treatment of cardiovascular diseases varies, depending on the type and severity of the condition. Treatment options range from lifestyle modifications, such as diet and exercise, to medications, surgery, and medical devices such as pacemakers and implantable cardioverter-defibrillators (ICDs). Cardiac rehabilitation programs may also be recommended to help patients recover after a cardiac event and to improve their overall cardiovascular health.
Cardiology analysis differs from the analysis of other areas of the body, due to the heart’s unique anatomy and physiology. The heart is a dynamic organ that constantly adapts to changes in the body’s demand for oxygen and nutrients. The heart’s intricate system of valves, chambers, and blood vessels requires specialized expertise to interpret and diagnose cardiovascular diseases accurately.
In recent years, AI technologies have been increasingly used in cardiology to improve the accuracy and efficiency of diagnosis, treatment, and management of cardiovascular diseases. AI-based image analysis algorithms can quickly and accurately detect abnormalities in medical images, and predictive models can analyze vast amounts of patient data to identify patterns and predict the likelihood of developing certain cardiovascular diseases. AI-based decision support systems can also assist clinicians in making treatment decisions, and wearable devices can monitor heart health and detect early signs of cardiovascular disease. With ongoing developments in AI technologies, the field of cardiology is poised to continue making significant advances in the diagnosis and management of cardiovascular diseases, ultimately leading to better patient outcomes.

2. The Implementation of Artificial Intelligence in Cardiology

2.1. Implementation of AI Technologies in Cardiology

Artificial intelligence has revolutionized various fields of medicine, including cardiology. With the advancements in technology, the use of AI in cardiology has become more sophisticated and its applications have widened. AI has the potential to improve the diagnosis, treatment management, and risk prediction of cardiac diseases, as well as the analysis of medical images such as echocardiograms or cardiac MRI scans.
Machine learning (ML) algorithms can be applied to clinical data, such as electrocardiograms (ECGs), echocardiograms, and medical imaging, to predict outcomes, stratify risk, and diagnose cardiovascular diseases. ML can also be used to identify patterns in data that may be invisible to the human eye, such as subtle changes in the heart’s electrical activity, and to develop personalized treatment plans.
Deep learning (DL) is a subset of ML that has revolutionized the field of medical-imaging analysis. DL models can analyze large amounts of cardiovascular images, such as computed tomography (CT) scans and magnetic resonance imaging (MRI) scans, and can detect abnormalities with high accuracy. DL can also be used to create 3D reconstructions of the heart from multiple 2D images, enabling detailed analysis of the heart’s structure and function.
Natural language processing technologies can be used to extract data from clinical documents such as electronic health records (EHRs) and physician notes, enabling the creation of large-scale clinical databases. NLP can also be used to develop algorithms that can identify and track specific cardiovascular risk factors, such as smoking, hypertension, and diabetes.
Computer-aided diagnosis (CAD) systems can be used to analyze medical images and provide diagnostic suggestions to clinicians. For example, CAD can be used to detect coronary artery disease by analyzing images of the coronary arteries and identifying areas of stenosis. CAD can also be used to analyze ECGs and identify abnormalities, such as arrhythmia.
Machine learning (ML) algorithms used in cardiology include the following:
  • The logistic regression algorithm is a type of regression analysis that is used for predicting the probability of a binary outcome. Logistic regression can be used in cardiology to predict the probability of a patient developing a cardiovascular disease based on various risk factors such as age, gender, and blood pressure.
Logistic regression models can be used to predict the likelihood of various cardiovascular events, including myocardial infarction (heart attack), stroke, and heart failure. Logistic regression models have been shown to be useful in identifying high-risk patients who may benefit from targeted interventions such as lifestyle modifications or medical therapy.
2.
The decision trees algorithm is a machine learning method used for classification and regression analysis. In cardiology, decision trees can be used to create a model that can classify patients based on various cardiovascular risk factors, such as smoking status, blood pressure, and cholesterol levels.
Decision trees can be used to create decision support systems for clinicians to help them make more informed decisions about patient care. Decision trees can be used to identify patients who may be at high risk of developing cardiovascular disease and to develop personalized treatment plans for individual patients.
3.
The random forest algorithm is an ensemble learning method that combines multiple decision trees to create a more accurate prediction model. In cardiology, random forests can be used to classify patients based on multiple decision trees, each tree using different combinations of risk factors.
Random forests can be used to create prediction models that are more accurate than individual decision trees. Random forests can identify the most important risk factors for cardiovascular disease and can help clinicians develop more effective treatment plans.
4.
Support vector machines (SVMs)algorithms are supervised learning algorithms that are used for classification and regression analysis. In cardiology, SVMs can be used to identify patients at risk of developing cardiovascular disease by analyzing data such as age, blood pressure, and cholesterol levels.
SVM models can be used to identify patients at high risk of developing cardiovascular disease and to develop personalized treatment plans for these patients. SVM models can help clinicians make better-informed decisions about patient care and can improve patient outcomes.
Deep learning (DL) algorithms used in cardiology include the following:
  • Convolutional neural networks (CNNs) are a type of deep learning algorithm that is commonly used for image classification and recognition tasks. In cardiology, CNNs can analyze medical images such as CT scans, MRI scans, and echocardiograms, and identify various cardiovascular abnormalities such as heart disease and arrhythmia.
CNNs can be used to identify subtle changes in cardiac images that may indicate the presence of cardiovascular disease. CNNs can be used to develop more accurate and reliable diagnostic tools for clinicians, which can improve patient outcomes.
2.
Recurrent neural networks (RNNs) are deep learning algorithms that are used for analyzing sequential data, such as time series. In cardiology, RNNs can analyze electrocardiogram (ECG) data and detect patterns and abnormalities that may indicate cardiovascular disease.
RNNs can be used to identify subtle changes in ECG data that may indicate the presence of cardiovascular disease. RNNs can be used to develop more accurate and reliable diagnostic tools for clinicians, which can improve patient outcomes.
Natural Language Processing (NLP) algorithms used in cardiology include the following:
  • Named entity recognition (NER) algorithms are NLP algorithms that are used to extract specific items such as diseases, symptoms, and medications from clinical documents such as electronic health records (EHRs). In cardiology, NER can be used to extract relevant information from patient records and help clinicians make better-informed decisions about patient care.
NER can be used to extract data from clinical documents such as EHRs and medical reports, which can be used to identify patterns and trends in patient data. NER can help clinicians identify patients who may be at high risk of developing cardiovascular disease and develop personalized treatment plans for these patients.
2.
Sentiment analysis algorithms are NLP algorithms that are used to analyze text data and identify the sentiments or emotions conveyed by the text. In cardiology, sentiment analysis can be used to analyze patient feedback and reviews of cardiac treatments and procedures.
Sentiment analysis can be used to identify areas of patient care that may need improvement and to develop more patient-centered approaches to cardiac care. Sentiment analysis can help clinicians understand the patient experience and improve patient outcomes.
Data mining techniques used in cardiology include the following:
  • Association rule mining is a data mining technique that is used to identify patterns and relationships among different variables in a dataset. In cardiology, association rule mining can be used to identify risk factors and their relationships to various cardiovascular diseases.
Association rule mining can be used to identify complex patterns and relationships among different risk factors that may be missed by traditional statistical analysis. Association rule mining can help clinicians develop more effective risk prediction models and treatment plans for patients.
2.
Clustering analysis is a data mining technique that is used to group similar data points together based on their characteristics. In cardiology, clustering analysis can be used to identify groups of patients with similar cardiovascular risk profiles.
Clustering analysis can be used to identify patient subgroups who may benefit from targeted interventions such as lifestyle modifications or medical therapy. Clustering analysis can help clinicians develop personalized treatment plans for individual patients and improve patient outcomes.
Computer-aided diagnosis (CAD) algorithms used in cardiology include the following:
  • Image segmentation is a type of algorithm used to separate an image into its component parts. In cardiology, image segmentation can be used to identify abnormalities in medical images, such as images of the heart and surrounding tissue.
  • Feature extraction is a type of algorithm used to identify specific features within an image. In cardiology, feature extraction can be used to identify specific features within medical images, such as the narrowing of coronary arteries.
  • Pattern recognition is a type of algorithm used to identify patterns in medical images such as the presence of plaques or blockages in arteries. In cardiology, pattern recognition can be used to identify patients who may be at risk of developing cardiovascular disease.
Examples of the usage of different AI technologies are briefly described in next section of this work.

2.2. Examples of Deployed Technologies

2.2.1. Supervised Learning

Supervised learning had been found to be useful for many applications in cardiovascular medicine [1][2][3][4]. Moghaddasi et al. [5] created an SVM-based model for the detection of the severity of mitral regurgitation by video analysis of 2D echocardiography with 99.38% sensitivity, 99.63% specificity, and 99.45% accuracy. Attia et al. [6] used paired 12-lead electrocardiogram and echocardiogram data from 44,959 patients to train a convolutional neural network for the identification of patients with ventricular dysfunction. They tested a created network on an independent dataset of 52,870 patients that yielded results of 86.3% sensitivity, 85.7% specificity, and 85.7% accuracy. Porumb et al. [7] proposed an innovative approach to predict the occurrence of hypoglycemia based on electrocardiography. They trained two deep learning models—a convolutional neural network (CNN) and a convolutional neural network combined with a recurrent neural network (CNN + RNN)—to show that a hypoglycemic event can be automatically detected using electrocardiography. The received results presented as follows: CNN model—81.7% sensitivity, 87.5% specificity, and 82.4% accuracy; CNN + RNN model—84.7% sensitivity, 84.5% specificity, and 85.7% accuracy. Echocardiography images were used for developing automatic measurements of left ventricular strain. Salte et al. created a pipeline of an artificial neural network that was able to estimate motion as an alternative to traditional speckle-tracking-based measures of strain, successfully classifying cardiac views and performing the timing of cardiac events [8]. Another application of CNN was proposed by Kusunose et al. [9], who trained a model for the detection of regional wall motion abnormalities in echocardiography view, which yielded an AUC similar to that of cardiologists (0.99 vs. 0.98).
Artificial neural networks have been successfully implemented for electrocardiogram interpretation. Their ability to find life-threatening arrythmias provides for many applications of artificial neural networks [10]. Galloway et al. [11] reported the possibility of enabling the usage of a trained CNN model to screen hyperkalemia in patients with renal disease from electrocardiograms, achieving an AUC above 0.85. Decision trees were found to be helpful in discriminating between patients with pulmonary vein drivers and those with extra pulmonary vein drivers of atrial fibrillation based on electrocardiogram, to aid in the identification of patients with high acute success rates due to pulmonary vein isolation [12]. A comparison approach of AI application for the diagnosis of acute coronary syndrome was undertaken by Berikal et al. [13]. The parallel training of four different algorithms yielded an advantage of SVM over ANN, NB, and logistic regression, with respective accuracies of 99.13%, 90.10%, 88.75%, and 91.26%. A decision trees algorithm variation—LogitBoost—was used by Motwani et al. [14] for the prediction of mortality in patients with coronary artery disease. The proposed model outperformed the standard Framingham risk score (AUC 0.79 vs. AUC 0.61). Machine learning algorithms were sown to be better than conventional statistical models used in everyday clinical practice for the discrimination of readmission and mortality of heart-failure patients [15]. In addition, as Kakadiaris et al. [16] reported, an SVM-based trained model outperformed an American College of Cardiology/American Heart Association (ACC/AHA) risk calculator by overlooking fewer cardiovascular disease (CVD) events and recommending fewer drug therapies. ANN algorithms enable the identification of high-risk patients after a myocardial infarction. This allows for the preparation of personalized therapy [17]. A gradient boosting model was applied by Kogan et al. [18] for the classification of patients with pulmonary hypertension using EHR. AI can be used for identifying predictors of acute coronary syndrome events or for risk stratification and the diagnosis of pulmonary arterial hypertension [19][20][21][22][23][24][25].

2.2.2. Unsupervised Learning

Unsupervised learning was mainly used for clustering and grouping and as a preprocessing method for dimensional reduction. Karwath et al. [26] proposed the implementation of hierarchical clustering for distinguishing prognostic responses for β-blocker therapy in patients with heart failure and reduced the left ventricular ejection fraction. Cikes et al. [27] suggested that unsupervised learning algorithms can be used to combine standard clinical parameters and echocardiographic images to achieve an interpretable measure for clinicians’ classification of a phenotypical heterogeneous heart failure cohort and to identify patients who are more likely to respond to treatment. Unsupervised ML is still underrated in comparison to supervised ML, but it has been found to be an application in the analysis of EHR or genetic data for the automatization of data extraction [28][29]. An unsupervised algorithm called topological data analysis, used on combined EHR and genetic data, allowed Li et al. to reveal the presence of three separate subtypes of diabetes type 2 [30].

2.2.3. Reinforcement Learning

The reinforcement learning state-action-reward-state-action (SARSA) algorithm performed a selection of dofetilide dose adjustments based on a negative reward for unsuccessful initiation [31]. Ghesu et al. [32] presented a novel method for real-time anatomical landmarks detection that was high in performance and robustness. Unfortunately, there are still only a few applications of reinforcement learning in cardiology. A possible niche for RL is the personalization of therapy for certain patient characteristics, because of the algorithm’s inherent decision-making construction.

2.2.4. Natural Language Processing

NLP is a pre-processing method that makes native text understandable for machines. There are many nonmedicinal applications of natural language processing e.g., chatboxes and search engines. There is hope for more studies using NLP in the future, due to previously demonstrated improvement in algorithm performance with unstructured data [33][34][35][36][37][38][39]. Afzal et al. [40] recommended NLP as a tool for the rapid and efficient testing of peripheral arterial diseases based on clinical narrative notes. The NLP model outperformed billing code algorithms, yielding 91.2% sensitivity, 92.5% specificity, and 91.8% accuracy. Another example of improvement achieved by deploying NLP was reported by Ashburner et al. [41], whose study demonstrated that merging clinical and demographic features with incorporating narrative data from the EHR can greatly improve the efficiency of a model. Deploying NLP to studies may reduce misclassifications cause of the extraction of additional information available only in EHR.

References

  1. Johnson, K.W.; Torres Soto, J.; Glicksberg, B.S.; Shameer, K.; Miotto, R.; Ali, M.; Ashley, E.; Dudley, J.T. Artificial Intelligence in Cardiology. J. Am. Coll. Cardiol. 2018, 71, 2668–2679.
  2. Krittanawong, C.; Zhang, H.J.; Wang, Z.; Aydar, M.; Kitai, T. Artificial Intelligence in Precision Cardiovascular Medicine. J. Am. Coll. Cardiol. 2017, 69, 2657–2664.
  3. Itchhaporia, D. Artificial Intelligence in Cardiology. Trends Cardiovasc. Med. 2022, 32, 34–41.
  4. Al’Aref, S.J.; Anchouche, K.; Singh, G.; Slomka, P.J.; Kolli, K.K.; Kumar, A.; Pandey, M.; Maliakal, G.; van Rosendael, A.R.; Beecy, A.N.; et al. Clinical Applications of Machine Learning in Cardiovascular Disease and Its Relevance to Cardiac Imaging. Eur. Heart J. 2019, 40, 1975–1986.
  5. Moghaddasi, H.; Nourian, S. Automatic Assessment of Mitral Regurgitation Severity Based on Extensive Textural Features on 2D Echocardiography Videos. Comput. Biol. Med. 2016, 73, 47–55.
  6. Attia, Z.I.; Kapa, S.; Lopez-Jimenez, F.; McKie, P.M.; Ladewig, D.J.; Satam, G.; Pellikka, P.A.; Enriquez-Sarano, M.; Noseworthy, P.A.; Munger, T.M.; et al. Screening for Cardiac Contractile Dysfunction Using an Artificial Intelligence–Enabled Electrocardiogram. Nat. Med. 2019, 25, 70–74.
  7. Porumb, M.; Stranges, S.; Pescapè, A.; Pecchia, L. Precision Medicine and Artificial Intelligence: A Pilot Study on Deep Learning for Hypoglycemic Events Detection Based on ECG. Sci. Rep. 2020, 10, 170.
  8. Salte, I.M.; Østvik, A.; Smistad, E.; Melichova, D.; Nguyen, T.M.; Karlsen, S.; Brunvand, H.; Haugaa, K.H.; Edvardsen, T.; Lovstakken, L.; et al. Artificial Intelligence for Automatic Measurement of Left Ventricular Strain in Echocardiography. JACC Cardiovasc. Imaging 2021, 14, 1918–1928.
  9. Kusunose, K.; Abe, T.; Haga, A.; Fukuda, D.; Yamada, H.; Harada, M.; Sata, M. A Deep Learning Approach for Assessment of Regional Wall Motion Abnormality From Echocardiographic Images. JACC Cardiovasc. Imaging 2020, 13, 374–381.
  10. Feeny, A.K.; Chung, M.K.; Madabhushi, A.; Attia, Z.I.; Cikes, M.; Firouznia, M.; Friedman, P.A.; Kalscheur, M.M.; Kapa, S.; Narayan, S.M.; et al. Artificial Intelligence and Machine Learning in Arrhythmias and Cardiac Electrophysiology. Circ. Arrhythmia Electrophysiol. 2020, 13, E007952.
  11. Galloway, C.D.; Valys, A.V.; Shreibati, J.B.; Treiman, D.L.; Petterson, F.L.; Gundotra, V.P.; Albert, D.E.; Attia, Z.I.; Carter, R.E.; Asirvatham, S.J.; et al. Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia from the Electrocardiogram. JAMA Cardiol. 2019, 4, 428–436.
  12. Luongo, G.; Azzolin, L.; Schuler, S.; Rivolta, M.W.; Almeida, T.P.; Martínez, J.P.; Soriano, D.C.; Luik, A.; Müller-Edenborn, B.; Jadidi, A.; et al. Machine Learning Enables Noninvasive Prediction of Atrial Fibrillation Driver Location and Acute Pulmonary Vein Ablation Success Using the 12-Lead ECG. Cardiovasc. Digit. Health J. 2021, 2, 126–136.
  13. Berikol, G.B.; Yildiz, O.; Özcan, T. Diagnosis of Acute Coronary Syndrome with a Support Vector Machine. J. Med. Syst. 2016, 40, 84.
  14. Motwani, M.; Dey, D.; Berman, D.S.; Germano, G.; Achenbach, S.; Al-Mallah, M.H.; Andreini, D.; Budoff, M.J.; Cademartiri, F.; Callister, T.Q.; et al. Machine Learning for Prediction of All-Cause Mortality in Patients with Suspected Coronary Artery Disease: A 5-Year Multicentre Prospective Registry Analysis. Eur. Heart J. 2017, 38, 500.
  15. Shin, S.; Austin, P.C.; Ross, H.J.; Abdel-Qadir, H.; Freitas, C.; Tomlinson, G.; Chicco, D.; Mahendiran, M.; Lawler, P.R.; Billia, F.; et al. Machine Learning vs. Conventional Statistical Models for Predicting Heart Failure Readmission and Mortality. ESC Heart Fail 2021, 8, 106–115.
  16. Kakadiaris, I.A.; Vrigkas, M.; Yen, A.A.; Kuznetsova, T.; Budoff, M.; Naghavi, M. Machine Learning Outperforms ACC/AHA CVD Risk Calculator in MESA. J. Am. Heart Assoc. 2018, 7, e009476.
  17. Mohammad, M.A.; Olesen, K.K.W.; Koul, S.; Gale, C.P.; Rylance, R.; Jernberg, T.; Baron, T.; Spaak, J.; James, S.; Lindahl, B.; et al. Development and Validation of an Artificial Neural Network Algorithm to Predict Mortality and Admission to Hospital for Heart Failure after Myocardial Infarction: A Nationwide Population-Based Study. Lancet Digit. Health 2022, 4, e37–e45.
  18. Kogan, E.; Didden, E.M.; Lee, E.; Nnewihe, A.; Stamatiadis, D.; Mataraso, S.; Quinn, D.; Rosenberg, D.; Chehoud, C.; Bridges, C. A Machine Learning Approach to Identifying Patients with Pulmonary Hypertension Using Real-World Electronic Health Records. Int. J. Cardiol. 2023, 374, 95–99.
  19. Benza, R.L.; Gomberg-Maitland, M.; Miller, D.P.; Frost, A.; Frantz, R.P.; Foreman, A.J.; Badesch, D.B.; McGoon, M.D. The REVEAL Registry Risk Score Calculator in Patients Newly Diagnosed with Pulmonary Arterial Hypertension. Chest 2012, 141, 354–362.
  20. D’Ascenzo, F.; de Filippo, O.; Gallone, G.; Mittone, G.; Deriu, M.A.; Iannaccone, M.; Ariza-Solé, A.; Liebetrau, C.; Manzano-Fernández, S.; Quadri, G.; et al. Machine Learning-Based Prediction of Adverse Events Following an Acute Coronary Syndrome (PRAISE): A Modelling Study of Pooled Datasets. Lancet 2021, 397, 199–207.
  21. Kanwar, M.K.; Gomberg-Maitland, M.; Hoeper, M.; Pausch, C.; Pittow, D.; Strange, G.; Anderson, J.J.; Zhao, C.; Scott, J.V.; Druzdzel, M.J.; et al. Risk Stratification in Pulmonary Arterial Hypertension Using Bayesian Analysis. Eur. Respir. J. 2020, 56, 2000008.
  22. Zhu, F.; Xu, D.; Liu, Y.; Lou, K.; He, Z.; Zhang, H.; Sheng, Y.; Yang, R.; Li, X.; Kong, X.; et al. Machine Learning for the Diagnosis of Pulmonary Hypertension. Kardiologiya 2020, 60, 96–101.
  23. Kwon, J.m.; Kim, K.H.; Medina-Inojosa, J.; Jeon, K.H.; Park, J.; Oh, B.H. Artificial Intelligence for Early Prediction of Pulmonary Hypertension Using Electrocardiography. J. Heart Lung Transplant. 2020, 39, 805–814.
  24. Leha, A.; Hellenkamp, K.; Unsöld, B.; Mushemi-Blake, S.; Shah, A.M.; Hasenfuß, G.; Seidler, T. A Machine Learning Approach for the Prediction of Pulmonary Hypertension. PLoS ONE 2019, 14, e0224453.
  25. Kiely, D.G.; Doyle, O.; Drage, E.; Jenner, H.; Salvatelli, V.; Daniels, F.A.; Rigg, J.; Schmitt, C.; Samyshkin, Y.; Lawrie, A.; et al. Utilising Artificial Intelligence to Determine Patients at Risk of a Rare Disease: Idiopathic Pulmonary Arterial Hypertension. Pulm. Circ. 2019, 9, 2045894019890549.
  26. Karwath, A.; Bunting, K.v.; Gill, S.K.; Tica, O.; Pendleton, S.; Aziz, F.; Barsky, A.D.; Chernbumroong, S.; Duan, J.; Mobley, A.R.; et al. Redefining β-Blocker Response in Heart Failure Patients with Sinus Rhythm and Atrial Fibrillation: A Machine Learning Cluster Analysis. Lancet 2021, 398, 1427–1435.
  27. Cikes, M.; Sanchez-Martinez, S.; Claggett, B.; Duchateau, N.; Piella, G.; Butakoff, C.; Catherine Pouleur, A.; Knappe, D.; Biering-Sørensen, T.; Kutyifa, V.; et al. Machine Learning-Based Phenogrouping in Heart Failure to Identify Responders to Cardiac Resynchronization Therapy. Eur. J. Heart Fail. 2019, 21, 74–85.
  28. Miotto, R.; Li, L.; Kidd, B.A.; Dudley, J.T. Deep Patient: An Unsupervised Representation to Predict the Future of Patients from the Electronic Health Records OPEN; Nature Publishing Group: Berlin, Germany, 2016.
  29. Shomorony, I.; Cirulli, E.T.; Huang, L.; Napier, L.A.; Heister, R.R.; Hicks, M.; Cohen, I.v.; Yu, H.-C.; Swisher, C.L.; Schenker-Ahmed, N.M.; et al. An Unsupervised Learning Approach to Identify Novel Signatures of Health and Disease from Multimodal Data. Genome Med. 2020, 12, 7.
  30. Li, L.; Cheng, W.-Y.; Glicksberg, B.S.; Gottesman, O.; Tamler, R.; Chen, R.; Bottinger, E.P.; Dudley, J.T. Identification of Type 2 Diabetes Subgroups through Topological Analysis of Patient Similarity. Sci. Transl. Med. 2015, 7, 311ra174.
  31. Levyid, A.E.; Biswas, M.; Weber, R.; Tarakji, K.; Chung, M.; Noseworthy, P.A.; Newton-Cheh, C.; Rosenbergid, M.A. Applications of Machine Learning in Decision Analysis for Dose Management for Dofetilide. PLoS ONE 2019, 14, e0227324.
  32. Ghesu, F.C.; Georgescu, B.; Zheng, Y.; Grbic, S.; Maier, A.; Hornegger, J.; Comaniciu, D. Multi-Scale Deep Reinforcement Learning for Real-Time 3D-Landmark Detection in CT Scans. IEEE Trans. Pattern Anal. Mach. Intell. 2019, 41, 176–189.
  33. Garvin, J.H.; Kim, Y.; Gobbel, G.T.; Matheny, M.E.; Redd, A.; Bray, B.E.; Heidenreich, P.; Bolton, D.; Heavirland, J.; Kelly, N.; et al. Automating Quality Measures for Heart Failure Using Natural Language Processing: A Descriptive Study in the Department of Veterans Affairs. JMIR Med. Inform. 2018, 6, e5.
  34. Shah, R.U.; Mukherjee, R.; Zhang, Y.; Jones, A.E.; Springer, J.; Hackett, I.; Steinberg, B.A.; Lloyd-Jones, D.M.; Chapman, W.W. Impact of Different Electronic Cohort Definitions to Identify Patients With Atrial Fibrillation From the Electronic Medical Record. J. Am. Heart Assoc. 2020, 9, e014527.
  35. Kaspar, M.; Fette, G.; Güder, G.; Seidlmayer, L.; Ertl, M.; Dietrich, G.; Greger, H.; Puppe, F.; Störk, S. Underestimated Prevalence of Heart Failure in Hospital Inpatients: A Comparison of ICD Codes and Discharge Letter Information. Clin. Res. Cardiol. 2018, 107, 778–787.
  36. Patel, Y.R.; Robbins, J.M.; Kurgansky, K.E.; Imran, T.; Orkaby, A.R.; McLean, R.R.; Ho, Y.L.; Cho, K.; Michael Gaziano, J.; Djousse, L.; et al. Development and Validation of a Heart Failure with Preserved Ejection Fraction Cohort Using Electronic Medical Records. BMC Cardiovasc. Disord. 2018, 18, 128.
  37. Mahajan, S.M.; Ghani, R. Combining Structured and Unstructured Data for Predicting Risk of Readmission for Heart Failure Patients. Stud. Health Technol. Inform. 2019, 264, 238–242.
  38. Galper, B.Z.; Beery, D.E.; Leighton, G.; Englander, L.L. Comparison of Adverse Event and Device Problem Rates for Transcatheter Aortic Valve Replacement and Mitraclip Procedures as Reported by the Transcatheter Valve Therapy Registry and the Food and Drug Administration Postmarket Surveillance Data. Am. Heart J. 2018, 198, 64–74.
  39. Reading Turchioe, M.; Volodarskiy, A.; Pathak, J.; Wright, D.N.; Tcheng, J.E.; Slotwiner, D. Systematic Review of Current Natural Language Processing Methods and Applications in Cardiology. Heart 2022, 108, 909–916.
  40. Afzal, N.; Sohn, S.; Abram, S.; Scott, C.G.; Chaudhry, R.; Liu, H.; Kullo, I.J.; Arruda-Olson, A.M. Mining Peripheral Arterial Disease Cases from Narrative Clinical Notes Using Natural Language Processing. J. Vasc. Surg. 2017, 65, 1753–1761.
  41. Ashburner, J.M.; Chang, Y.; Wang, X.; Khurshid, S.; Anderson, C.D.; Dahal, K.; Weisenfeld, D.; Cai, T.; Liao, K.P.; Wagholikar, K.B.; et al. Natural Language Processing to Improve Prediction of Incident Atrial Fibrillation Using Electronic Health Records. J. Am. Heart Assoc. Cardiovasc. Cerebrovasc. Dis. 2022, 11, 26014.
More
Information
Contributors MDPI registered users' name will be linked to their SciProfiles pages. To register with us, please refer to https://encyclopedia.pub/register : ,
View Times: 261
Revisions: 2 times (View History)
Update Date: 23 May 2023
1000/1000
Video Production Service