Synergistic Biophysics and Machine Learning Modeling to Rapidly Predict Cardiac Growth Probability.

Computational models that can predict growth and remodeling of the heart could have important clinical applications. However, the time it takes to calibrate and run current models while considering data uncertainty and variability makes them impractical for routine clinical use. This study aims to address this need by creating a computational framework to efficiently predict cardiac growth probability. We utilized a biophysics model to rapidly simulate cardiac growth following mitral valve regurgitation (MVR). Here we developed a two-tiered Bayesian History Matching approach augmented with Gaussian process emulators for efficient calibration of model parameters to align with growth outcomes within a 95% confidence interval. We first generated a synthetic data set to assess the accuracy of our framework, and the effect of changes in data uncertainty on growth predictions. We then calibrated our model to match baseline and chronic canine MVR data and used an independent data set to successfully validate the ability of our calibrated model to accurately predict cardiac growth probability. The combined biophysics and machine learning modeling framework we proposed in this study can be easily translated to predict patient-specific cardiac growth.

Evaluation of silk fibroin-based urinary conduits in a porcine model of urinary diversion.

Background: The primary strategy for urinary diversion in radical cystectomy patients involves incorporation of autologous gastrointestinal conduits into the urinary tract which leads to deleterious consequences including chronic infections and metabolic abnormalities. This report investigates the efficacy of an acellular, tubular bi-layer silk fibroin (BLSF) graft to function as an alternative urinary conduit in a porcine model of urinary diversion. Materials and methods: Unilateral urinary diversion with stented BLSF conduits was executed in five adult female, Yucatan mini-swine over a 3 month period. Longitudinal imaging analyses including ultrasonography, retrograde ureteropyelography and video-endoscopy were carried out monthly. Histological, immunohistochemical (IHC), and histomorphometric assessments were performed on neoconduits at harvest. Results: All animals survived until scheduled euthanasia and displayed moderate hydronephrosis (Grades 1-3) in reconstructed collecting systems over the course of the study period. Stented BLSF constructs supported formation of vascularized, retroperitoneal tubes capable of facilitating external urinary drainage. By 3 months post-operative, neoconduits contained α-smooth muscle actin+ and SM22α+ smooth muscle as well as uroplakin 3A+ and pan-cytokeratin + urothelium. However, the degree of tissue regeneration in neotissues was significantly lower in comparison to ureteral controls as determined by histomorphometry. In addition, neoconduit stenting was necessary to prevent stomal occlusion. Conclusion: BLSF biomaterials represent emerging platforms for urinary conduit construction and may offer a functional replacement for conventional urinary diversion techniques following further optimization of mechanical properties and regenerative responses.