New artificial intelligence prediction model using serial prothrombin time international normalized ratio measurements in atrial fibrillation patients on vitamin K antagonists: GARFIELD-AF

Goto, Shinichi; Pieper, Karen S.; Bassand, Jean‐Pierre; Camm, A. John; Fitzmaurice, David; Goldhaber, Samuel Z.; Haas, Sylvia; Parkhomenko, Alexander; Oto, Ali̇; Misselwitz, Frank; Turpie, Alexander G. G.; Verheugt, Freek W.A.; Fox, Keith; Gersh, Bernard J.; Kakkar, Ajay K.

doi:10.1093/ehjcvp/pvz076

Cited by 37 publications

(25 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There have been multiple applications of deep learning-based AI algorithms in the field of cardiology [20][21][22] . There are existing studies, using 12-lead ECG data to detect aortic stenosis [23] and mitral regurgitation [ [9]].…”

Section: Discussionmentioning

confidence: 99%

Deep learning model to detect significant aortic regurgitation using electrocardiography

Sawano

Kodera

Katsushika

et al. 2022

Journal of Cardiology

View full text Add to dashboard Cite

Background: Aortic regurgitation (AR) is a common heart disease, with a relatively high prevalence of 4.9% in the Framingham Heart Study. Because the prevalence increases with advancing age, an upward shift in the age distribution may increase the burden of AR. To provide an effective screening method for AR, we developed a deep learning-based artificial intelligence algorithm for the diagnosis of significant AR using electrocardiography (ECG). Methods: Our dataset comprised 29,859 paired data of ECG and echocardiography, including 412 AR cases, from January 2015 to December 2019. This dataset was divided into training, validation, and test datasets. We developed a multi-input neural network model, which comprised a two-dimensional convolutional neural network (2D-CNN) using raw ECG data and a fully connected deep neural network (FC-DNN) using ECG features, and compared its performance with the performances of a 2D-CNN model and other machine learning models. In addition, we used gradient-weighted class activation mapping (Grad-CAM) to identify which parts of ECG waveforms had the most effect on algorithm decision making. Results: The area under the receiver operating characteristic curve of the multi-input model (0.802; 95% CI, 0.762-0.837) was significantly greater than that of the 2D-CNN model alone (0.734; 95% CI, 0.679-0.783; p < 0.001) and those of other machine learning models. Grad-CAM demonstrated that the multiinput model tended to focus on the QRS complex in leads I and aVL when detecting AR. Conclusions: The multi-input deep learning model using 12-lead ECG data could detect significant AR with modest predictive value.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep learning model to detect significant aortic regurgitation using electrocardiography

Sawano

Kodera

Katsushika

et al. 2022

Journal of Cardiology

View full text Add to dashboard Cite

show abstract

“…It is of note that the guideline recommendation is only a guide. Recently developed computer-based artificial intelligence found more precise prediction of future clinical events from serially measured PT-INR [30], but a one-time measurement is still the standard.…”

Section: Discussionmentioning

confidence: 99%

Variability of PT-INR values measured by point of care devices INRatio/INRatio 2 and CoaguChek XS and standard laboratory method. A cross-sectional study

et al. 2020

Self Cite

View full text Add to dashboard Cite

Introduction: Various point-of-care (POC) devices are available for measurement of PT-INR with whole blood in patients receiving vitamin K antagonists (VKAs). However, the variability in values measured with various POC devices and traditional plasma-based laboratory measurement in clinical practice has yet to be clarified. Material and methods: PT-INR values measured with the same blood sample by POC devices of INRatio/INRatio 2 (INRatio) and the CoaguChek XS portable INR monitor (CoaguChek) were compared with those measured with traditional plasma-based laboratory measurement (lab-INR) in 1,347 measurements from 393 patients. The difference between the PT-INR values obtained from Lab-INR and POC devicees were expressed as Δ. To quantify the relationships among values obtained by various methods, regression analysis and the Bland-Altman method were applied. Results: PT-INR values measured with INRatio were higher than lab-INR with Δ =-0.33 ±0.38 (mean ± SD; 95%

show abstract

“…Goto et al . 113 developed a model for predicting clinical outcomes, such as major bleeding, stroke/systemic embolism, and death, in newly diagnosed AF patients who were treated with vitamin K antagonists, using serial prothrombin time international normalized ratio values collected within 1 month after starting treatment. In a different article, Feeny et al .…”

Section: Risk Prediction Modelling With Ai/ml Methodsmentioning

confidence: 99%

How machine learning is impacting research in atrial fibrillation: implications for risk prediction and future management

Olier

Ortega‐Martorell

Pieroni

et al. 2021

Cardiovascular Research

View full text Add to dashboard Cite

There has been an exponential growth of artificial intelligence (AI) and machine learning (ML) publications aimed at advancing our understanding of atrial fibrillation (AF), which has been mainly driven by the confluence of two factors: the advances in deep neural networks (DeepNNs) and the availability of large, open access databases. It is observed that most of the attention has centered on applying ML for detecting AF, particularly using electrocardiograms (ECGs) as the main data modality. Nearly a third of them used DeepNNs to minimize or eliminate the need for transforming the ECGs to extract features prior to ML modeling; however, we did not observe a significant advantage in following this approach. We also found a fraction of studies using other data modalities, and others centered in aims such as risk prediction, AF management, and others. From the clinical perspective, AI/ML can help expand the utility of AF detection and risk prediction, especially for patients with additional comorbidities. The use of AI/ML for detection and risk prediction into applications and smart mobile health (mHealth) technology would enable ‘real time’ dynamic assessments. AI/ML could also adapt to treatment changes over time, as well as incident risk factors. Incorporation of a dynamic AI/ML model into mHealth technology would facilitate ‘real time’ assessment of stroke risk, facilitating mitigation of modifiable risk factors (e.g., blood pressure control). Overall, this would lead to an improvement in clinical care for patients with AF.

show abstract

New artificial intelligence prediction model using serial prothrombin time international normalized ratio measurements in atrial fibrillation patients on vitamin K antagonists: GARFIELD-AF

Cited by 37 publications

References 44 publications

Deep learning model to detect significant aortic regurgitation using electrocardiography

Deep learning model to detect significant aortic regurgitation using electrocardiography

Variability of PT-INR values measured by point of care devices INRatio/INRatio 2 and CoaguChek XS and standard laboratory method. A cross-sectional study

How machine learning is impacting research in atrial fibrillation: implications for risk prediction and future management

Contact Info

Product

Resources

About