Hybrid feature engineering of medical data via variational autoencoders with triplet loss: a COVID-19 prognosis study.

Medical machine learning frameworks have received much attention in recent years. The recent COVID-19 pandemic was also accompanied by a surge in proposed machine learning algorithms for tasks such as diagnosis and mortality prognosis. Machine learning frameworks can be helpful medical assistants by extracting data patterns that are otherwise hard to detect by humans. Efficient feature engineering and dimensionality reduction are major challenges in most medical machine learning frameworks. Autoencoders are novel unsupervised tools that can perform data-driven dimensionality reduction with minimum prior assumptions. This study, in a novel approach, investigated the predictive power of latent representations obtained from a hybrid autoencoder (HAE) framework combining variational autoencoder (VAE) characteristics with mean squared error (MSE) and triplet loss for forecasting COVID-19 patients with high mortality risk in a retrospective framework. Electronic laboratory and clinical data of 1474 patients were used in the study. Logistic regression with elastic net regularization (EN) and random forest (RF) models were used as final classifiers. Moreover, we also investigated the contribution of utilized features towards latent representations via mutual information analysis. HAE Latent representations model achieved decent performance with an area under ROC curve of 0.921 (±0.027) and 0.910 (±0.036) with EN and RF predictors, respectively, over the hold-out data in comparison with the raw (AUC EN: 0.913 (±0.022); RF: 0.903 (±0.020)) models. The study aims to provide an interpretable feature engineering framework for the medical environment with the potential to integrate imaging data for efficient feature engineering in rapid triage and other clinical predictive models.

Crossing Phylums: Butterfly Wing as a Natural Perfusable Three-Dimensional (3D) Bioconstruct for Bone Tissue Engineering.

Despite the advent of promising technologies in tissue engineering, finding a biomimetic 3D bio-construct capable of enhancing cell attachment, maintenance, and function is still a challenge in producing tailorable scaffolds for bone regeneration. Here, osteostimulatory effects of the butterfly wings as a naturally porous and non-toxic chitinous scaffold on mesenchymal stromal cells are assessed. The topographical characterization of the butterfly wings implied their ability to mimic bone tissue microenvironment, whereas their regenerative potential was validated after a 14-day cell culture. In vivo analysis showed that the scaffold induced no major inflammatory response in Wistar rats. Topographical features of the bioconstruct upregulated the osteogenic genes, including COL1A1, ALP, BGLAP, SPP1, SP7, and AML3 in differentiated cells compared to the cells cultured in the culture plate. However, butterfly wings were shown to provide a biomimetic microstructure and proper bone regenerative capacity through a unique combination of various structural and material properties. Therefore, this novel platform can be confidently recommended for bone tissue engineering applications.