AUTHOR=Guo Xiaoya , Maehara Akiko , Yang Mingming , Wang Liang , Zheng Jie , Samady Habib , Mintz Gary S. , Giddens Don P. , Tang Dalin
TITLE=Predicting Coronary Stenosis Progression Using Plaque Fatigue From IVUS-Based Thin-Slice Models: A Machine Learning Random Forest Approach
JOURNAL=Frontiers in Physiology
VOLUME=13
YEAR=2022
URL=https://www.frontiersin.org/journals/physiology/articles/10.3389/fphys.2022.912447
DOI=10.3389/fphys.2022.912447
ISSN=1664-042X
ABSTRACT=Introduction: Coronary stenosis due to atherosclerosis restricts blood flow. Stenosis progression would lead to increased clinical risk such as heart attack. Although many risk factors were found to contribute to atherosclerosis progression, factors associated with fatigue is underemphasized. Our goal is to investigate the relationship between fatigue and stenosis progression based on in vivo intravascular ultrasound (IVUS) images and finite element models.
Methods: Baseline and follow-up in vivo IVUS and angiography data were acquired from seven patients using Institutional Review Board approved protocols with informed consent obtained. Three hundred and five paired slices at baseline and follow-up were matched and used for plaque modeling and analysis. IVUS-based thin-slice models were constructed to obtain the coronary biomechanics and stress/strain amplitudes (stress/strain variations in one cardiac cycle) were used as the measurement of fatigue. The change of lumen area (DLA) from baseline to follow-up were calculated to measure stenosis progression. Nineteen morphological and biomechanical factors were extracted from 305 slices at baseline. Correlation analyses of these factors with DLA were performed. Random forest (RF) method was used to fit morphological and biomechanical factors at baseline to predict stenosis progression during follow-up.
Results: Significant correlations were found between stenosis progression and maximum stress amplitude, average stress amplitude and average strain amplitude (p < 0.05). After factors selection implemented by random forest (RF) method, eight morphological and biomechanical factors were selected for classification prediction of stenosis progression. Using eight factors including fatigue, the overall classification accuracy, sensitivity and specificity of stenosis progression prediction with RF method were 83.61%, 86.25% and 80.69%, respectively.
Conclusion: Fatigue correlated positively with stenosis progression. Factors associated with fatigue could contribute to better prediction for atherosclerosis progression.