Improving Valvular Pathologies and Ventricular Dysfunction Diagnostic Efficiency Using Combined Auscultation and Electrocardiography Data: A Multimodal AI Approach.

Simple sensor-based procedures, including auscultation and electrocardiography (ECG), can facilitate early diagnosis of valvular diseases, resulting in timely treatment. This study assessed the impact of combining these sensor-based procedures with machine learning on diagnosing valvular abnormalities and ventricular dysfunction. Data from auscultation at three distinct locations and 12-lead ECGs were collected from 1052 patients undergoing echocardiography. An independent cohort of 103 patients was used for clinical validation. These patients were screened for severe aortic stenosis (AS), severe mitral regurgitation (MR), and left ventricular dysfunction (LVD) with ejection fractions ≤ 40%. Optimal neural networks were identified by a fourfold cross-validation training process using heart sounds and various ECG leads, and their outputs were combined using a stacking technique. This composite sensor model had high diagnostic efficiency (area under the receiver operating characteristic curve (AUC) values: AS, 0.93; MR, 0.80; LVD, 0.75). Notably, the contribution of individual sensors to disease detection was found to be disease-specific, underscoring the synergistic potential of the sensor fusion approach. Thus, machine learning models that integrate auscultation and ECG can efficiently detect conditions typically diagnosed via imaging. Moreover, this study highlights the potential of multimodal artificial intelligence applications.

Efficient screening for severe aortic valve stenosis using understandable artificial intelligence: a prospective diagnostic accuracy study.

Aims: The medical need for screening of aortic valve stenosis (AS), which leads to timely and appropriate medical intervention, is rapidly increasing because of the high prevalence of AS in elderly population. This study aimed to establish a screening method using understandable artificial intelligence (AI) to detect severe AS based on heart sounds and to package the built AI into a smartphone application. Methods and results: In this diagnostic accuracy study, we developed multiple convolutional neural networks (CNNs) using a modified stratified five-fold cross-validation to detect severe AS in electronic heart sound data recorded at three auscultation locations. Clinical validation was performed with the developed smartphone application in an independent cohort (model establishment: n = 556, clinical validation: n = 132). Our ensemble technique integrating the heart sounds from multiple auscultation locations increased the detection accuracy of CNN model by compensating detection errors. The established smartphone application achieved a sensitivity, specificity, accuracy, and F1 value of 97.6% (41/42), 94.4% (85/90), 95.7% (126/132), and 0.93, respectively, which were higher compared with the consensus of cardiologists (81.0%, 93.3%, 89.4%, and 0.829, respectively), implying a good utility for severe AS screening. The Gradient-based Class Activation Map demonstrated that the built AIs could focus on specific heart sounds to differentiate the severity of AS. Conclusions: Our CNN model combining multiple auscultation locations and exported on smartphone application could efficiently identify severe AS based on heart sounds. The visual explanation of AI decisions for heart sounds was interpretable. These technologies may support medical training and remote consultations.

Performance of a convolutional neural network derived from an ECG database in recognizing myocardial infarction.

Artificial intelligence (AI) is developing rapidly in the medical technology field, particularly in image analysis. ECG-diagnosis is an image analysis in the sense that cardiologists assess the waveforms presented in a 2-dimensional image. We hypothesized that an AI using a convolutional neural network (CNN) may also recognize ECG images and patterns accurately. We used the PTB ECG database consisting of 289 ECGs including 148 myocardial infarction (MI) cases to develop a CNN to recognize MI in ECG. Our CNN model, equipped with 6-layer architecture, was trained with training-set ECGs. After that, our CNN and 10 physicians are tested with test-set ECGs and compared their MI recognition capability in metrics F1 (harmonic mean of precision and recall) and accuracy. The F1 and accuracy by our CNN were significantly higher (83 ± 4%, 81 ± 4%) as compared to physicians (70 ± 7%, 67 ± 7%, P < 0.0001, respectively). Furthermore, elimination of Goldberger-leads or ECG image compression up to quarter resolution did not significantly decrease the recognition capability. Deep learning with a simple CNN for image analysis may achieve a comparable capability to physicians in recognizing MI on ECG. Further investigation is warranted for the use of AI in ECG image assessment.