|
|
|
|
LEADER |
03848nam a2200721Ia 4500 |
001 |
10.1148-ryai.210221 |
008 |
220425s2022 CNT 000 0 und d |
020 |
|
|
|a 26386100 (ISSN)
|
245 |
1 |
0 |
|a Development and Validation of Artificial Intelligence– based Method for Diagnosis of Mitral Regurgitation from Chest Radiographs
|
260 |
|
0 |
|b Radiological Society of North America Inc.
|c 2022
|
856 |
|
|
|z View Fulltext in Publisher
|u https://doi.org/10.1148/ryai.210221
|
520 |
3 |
|
|a Purpose: To develop an artificial intelligence–based model to detect mitral regurgitation on chest radiographs. Materials and Methods: This retrospective study included echocardiographs and associated chest radiographs consecutively collected at a single institution between July 2016 and May 2019. Associated radiographs were those obtained within 30 days of echocardiography. These radiographs were labeled as positive or negative for mitral regurgitation on the basis of the echocardiographic reports and were divided into training, validation, and test datasets. An artificial intelligence model was developed by using the training dataset and was tuned by using the validation dataset. To evaluate the model, the area under the curve, sensitivity, specificity, accuracy, positive predictive value, and negative predictive value were assessed by using the test dataset. Results: This study included a total of 10 367 images from 5270 patients. The training dataset included 8240 images (4216 patients), the validation dataset included 1073 images (527 patients), and the test dataset included 1054 images (527 patients). The area under the curve, sensitivity, specificity, accuracy, positive predictive value, and negative predictive value in the test dataset were 0.80 (95% CI: 0.77, 0.82), 71% (95% CI: 67, 75), 74% (95% CI: 70, 77), 73% (95% CI: 70, 75), 68% (95% CI: 64, 72), and 77% (95% CI: 73, 80), respectively. Conclusion: The developed deep learning–based artificial intelligence model may possibly differentiate patients with and without mitral regurgitation by using chest radiographs. © RSNA, 2022.
|
650 |
0 |
4 |
|a accuracy
|
650 |
0 |
4 |
|a aged
|
650 |
0 |
4 |
|a area under the curve
|
650 |
0 |
4 |
|a Article
|
650 |
0 |
4 |
|a artificial intelligence
|
650 |
0 |
4 |
|a Cardiac
|
650 |
0 |
4 |
|a cardiovascular parameters
|
650 |
0 |
4 |
|a Computer-aided Diagnosis (CAD)
|
650 |
0 |
4 |
|a conceptual framework
|
650 |
0 |
4 |
|a controlled study
|
650 |
0 |
4 |
|a Convolutional Neural Network (CNN)
|
650 |
0 |
4 |
|a deep learning
|
650 |
0 |
4 |
|a Deep Learning Algorithms
|
650 |
0 |
4 |
|a development
|
650 |
0 |
4 |
|a diagnostic accuracy
|
650 |
0 |
4 |
|a diagnostic test accuracy study
|
650 |
0 |
4 |
|a electronic health record
|
650 |
0 |
4 |
|a female
|
650 |
0 |
4 |
|a Heart
|
650 |
0 |
4 |
|a heart function
|
650 |
0 |
4 |
|a heart left ventricle ejection fraction
|
650 |
0 |
4 |
|a human
|
650 |
0 |
4 |
|a human tissue
|
650 |
0 |
4 |
|a image analysis
|
650 |
0 |
4 |
|a image processing
|
650 |
0 |
4 |
|a image reconstruction
|
650 |
0 |
4 |
|a imaging
|
650 |
0 |
4 |
|a machine learning
|
650 |
0 |
4 |
|a Machine Learning Algorithms
|
650 |
0 |
4 |
|a major clinical study
|
650 |
0 |
4 |
|a male
|
650 |
0 |
4 |
|a mitral valve regurgitation
|
650 |
0 |
4 |
|a predictive value
|
650 |
0 |
4 |
|a receiver operating characteristic
|
650 |
0 |
4 |
|a sensitivity and specificity
|
650 |
0 |
4 |
|a Supervised Learning
|
650 |
0 |
4 |
|a thorax radiography
|
650 |
0 |
4 |
|a training
|
650 |
0 |
4 |
|a validation process
|
650 |
0 |
4 |
|a Valves
|
700 |
1 |
|
|a Abo, K.
|e author
|
700 |
1 |
|
|a Ehara, S.
|e author
|
700 |
1 |
|
|a Iwata, S.
|e author
|
700 |
1 |
|
|a Matsumoto, T.
|e author
|
700 |
1 |
|
|a Miki, Y.
|e author
|
700 |
1 |
|
|a Shimazaki, A.
|e author
|
700 |
1 |
|
|a Ueda, D.
|e author
|
700 |
1 |
|
|a Walston, S.L.
|e author
|
700 |
1 |
|
|a Yamamoto, A.
|e author
|
700 |
1 |
|
|a Yoshiyama, M.
|e author
|
773 |
|
|
|t Radiology: Artificial Intelligence
|