Predicting post-operative right ventricular failure using video-based deep learning
Autor: | Patpilai Kasinpila, Xiu Tang, Myriam Amsallem, Rohan Shad, Francois Haddad, Sangjin Lee, Eddie Suarez, Ashrith Guha, John P. Cunningham, William Hiesinger, Theodore Boeve, Cayley Bowles, Yasuhiro Shudo, Stefan Jovinge, Miguel Castro, Y. Joseph Woo, Robyn Fong, Jeffrey J. Teuteberg, Curtis P. Langlotz, Nicolas Quach |
---|---|
Rok vydání: | 2021 |
Předmět: |
FOS: Computer and information sciences
medicine.medical_specialty Computer science Computer Science - Artificial Intelligence Science Computer Vision and Pattern Recognition (cs.CV) Ventricular Dysfunction Right Cardiac wall motion Computer Science - Computer Vision and Pattern Recognition Video Recording General Physics and Astronomy Predictive markers General Biochemistry Genetics and Molecular Biology Article Task (project management) Physical medicine and rehabilitation Deep Learning Clinical decision making Preoperative Care Machine learning medicine Humans cardiovascular diseases Postoperative Period Post operative Video based Retrospective Studies Video recording Heart Failure Multidisciplinary business.industry Deep learning Heart General Chemistry Artificial Intelligence (cs.AI) Echocardiography cardiovascular system Right ventricular failure Artificial intelligence business |
Zdroj: | Nature Communications Nature Communications, Vol 12, Iss 1, Pp 1-8 (2021) |
ISSN: | 2041-1723 |
Popis: | Non-invasive and cost effective in nature, the echocardiogram allows for a comprehensive assessment of the cardiac musculature and valves. Despite progressive improvements over the decades, the rich temporally resolved data in echocardiography videos remain underutilized. Human reads of echocardiograms reduce the complex patterns of cardiac wall motion, to a small list of measurements of heart function. Furthermore, all modern echocardiography artificial intelligence (AI) systems are similarly limited by design - automating measurements of the same reductionist metrics rather than utilizing the wealth of data embedded within each echo study. This underutilization is most evident in situations where clinical decision making is guided by subjective assessments of disease acuity, and tools that predict disease onset within clinically actionable timeframes are unavailable. Predicting the likelihood of developing post-operative right ventricular failure (RV failure) in the setting of mechanical circulatory support is one such clinical example. To address this, we developed a novel video AI system trained to predict post-operative right ventricular failure (RV failure), using the full spatiotemporal density of information from pre-operative echocardiography scans. We achieve an AUC of 0.729, specificity of 52% at 80% sensitivity and 46% sensitivity at 80% specificity. Furthermore, we show that our ML system significantly outperforms a team of human experts tasked with predicting RV failure on independent clinical evaluation. Finally, the methods we describe are generalizable to any cardiac clinical decision support application where treatment or patient selection is guided by qualitative echocardiography assessments. 12 pages, 3 figures |
Databáze: | OpenAIRE |
Externí odkaz: |