Open Access from Numerical Methods in Biomedical Engineering: A classification approach to improve out of sample predictability of structure-based constitutive models for ascending thoracic aortic tissue

Every week, we select a recently published Open Access article to feature. This week’s article is from the International Journal for Numerical Methods in Biomedical Engineering and develops a pipeline assessment for the predictive capability of structure-based models of ascending aortic tissue. 

The article’s abstract is given below, with the full article available to read here.

Tong, T-TNightingale, MScott, MB, et al. A classification approach to improve out of sample predictability of structure-based constitutive models for ascending thoracic aortic tissueInt J Numer Meth Biomed Engng2023;e3708. doi:10.1002/cnm.3708

In this research, a pipeline was developed to assess the out-of-sample predictive capability of structure-based constitutive models of ascending aortic aneurysmal tissue. The hypothesis being tested is that a biomarker can help establish similarities among tissues sharing the same level of a quantifiable property, thus enabling the development of biomarker-specific constitutive models. Biomarker-specific averaged material models were constructed from biaxial mechanical tests of specimens that shared similar biomarker properties such as level of blood-wall shear stress or microfiber (elastin or collagen) degradation in the extracellular matrix. Using a cross-validation strategy commonly used in classification algorithms, biomarker-specific averaged material models were assessed in contrast to individual tissue mechanics of out of sample specimens that fell under the same category but did not contribute to the averaged model’s generation. The normalized root means square errors (NRMSE) calculated on out-of-sample data were compared with average models when no categorization was performed versus biomarker-specific models and among different level of a biomarker. Different biomarker levels exhibited statistically different NRMSE when compared among each other, indicating more common features shared by the specimens belonging to the lower error groups. However, no specific biomarkers reached a significant difference when compared to the average model created when No Categorization was performed, possibly on account of unbalanced number of specimens. The method developed could allow for the screening of different biomarkers or combinations/interactions in a systematic manner leading the way to larger datasets and to more individualized constitutive approaches.

More Details