Using intravascular ultrasound image-based fluid-structure interaction models and machine learning methods to predict human coronary plaque vulnerability change. Issue 15 (17th November 2020)

• Record Type: Journal Article
• Authors: Wang, Liang; Tang, Dalin; Maehara, Akiko; Wu, Zheyang; Yang, Chun; Muccigrosso, David; Matsumura, Mitsuaki; Zheng, Jie; Bach, Richard; Billiar, Kristen L.; Stone, Gregg W.; Mintz, Gary S.
• Is Part Of: Computer methods in biomechanics and biomedical engineering. Volume 23:Issue 15(2020)
• Page Start: 1267
• Page End: 1276
• Publication Date: 2020-11-17
• Subjects: Coronary artery disease -- fluid-structure interaction -- machine learning -- plaque vulnerability prediction -- intravascular ultrasound; Biomechanics -- Data processing -- Periodicals; Biomedical engineering -- Periodicals; Biomechanics -- Periodicals; Biomedical Engineering -- methods -- Periodicals; Computing Methodologies -- Periodicals; 612.7
• DOI: 10.1080/10255842.2020.1795838
• Languages: English
• ISSNs: 1025-5842

Abstract

Abstract: Plaque vulnerability prediction is of great importance in cardiovascular research. In vivo follow-up intravascular ultrasound (IVUS) coronary plaque data were acquired from nine patients to construct fluid-structure interaction models to obtain plaque biomechanical conditions. Morphological plaque vulnerability index (MPVI) was defined to measure plaque vulnerability. The generalized linear mixed regression model (GLMM), support vector machine (SVM) and random forest (RF) were introduced to predict MPVI change (ΔMPVI = MPVIfollow-up ‒MPVIbaseline ) using ten risk factors at baseline. The combination of mean wall thickness, lumen area, plaque area, critical plaque wall stress, and MPVI was the best predictor using RF with the highest prediction accuracy 91.47%, compared to 90.78% from SVM, and 85.56% from GLMM. Machine learning method (RF) improved the prediction accuracy by 5.91% over that from GLMM. MPVI was the best single risk factor using both GLMM (82.09%) and RF (78.53%) while plaque area was the best using SVM (81.29%).