Design Considerations for High Impact, Automated Echocardiogram Analysis
Wiebke Toussaint, Dave Van Veen, Courtney Irwin, Yoni Nachmany, Manuel Barreiro-Perez, Elena Díaz-Peláez, Sara Guerreiro de Sousa, Liliana Millán, Pedro L. Sánchez, Antonio Sánchez-Puente, Jesús Sampedro-Gómez, P. Ignacio Dorado-Díaz
arXiv:2006.06292v25 citations
Originality Synthesis-oriented
AI Analysis
This addresses workflow efficiency for cardiologists, but appears incremental as it builds on existing deep learning approaches with a design modification.
The study tackled automating echocardiogram analysis for early heart disease detection by proposing to predict normal heart function rather than disease, which accounts for data quality bias and increases efficiency in cardiologists' workflows.
Deep learning has the potential to automate echocardiogram analysis for early detection of heart disease. Based on a qualitative analysis of design concerns, this study suggests that predicting normal heart function instead of disease accounts for data quality bias and significantly increases efficiency in cardiologists' workflows.