Machine-Learning-Enabled Diagnostics with Improved Visualization of Disease Lesions in Chest X-ray Images.

The class activation map (CAM) represents the neural-network-derived region of interest, which can help clarify the mechanism of the convolutional neural network's determination of any class of interest. In medical imaging, it can help medical practitioners diagnose diseases like COVID-19 or pneumonia by highlighting the suspicious regions in Computational Tomography (CT) or chest X-ray (CXR) film. Many contemporary deep learning techniques only focus on COVID-19 classification tasks using CXRs, while few attempt to make it explainable with a saliency map.

Electromembrane extraction of peptides based on charge, hydrophobicity, and size - A large-scale fundamental study of the extraction window.

This study investigated the capability of electromembrane extraction (EME) as a general technique for peptides, by extracting complex pools of peptides comprising in total of 5953 different substances, varying in size from seven to 16 amino acids. Electromembrane extraction was conducted from a sample adjusted to pH 3.0 and utilized a liquid membrane consisting of 2-nitrophenyl octyl ether and carvacrol (1:1 w/w), containing 2% (w/w) di(2-ethylhexyl) phosphate.

Glucose ingestion before and after resistance training sessions does not augment ribosome biogenesis in healthy moderately trained young adults.

Purpose: Resistance training-induced skeletal muscle hypertrophy seems to depend on ribosome biogenesis and content. High glucose treatment may augment ribosome biogenesis through potentiating resistance training-induced adaptations. This was investigated with total RNA and ribosomal RNA abundances as main outcomes, with relevant transcriptional/translational regulators (c-Myc/UBF/rpS6) as a secondary outcome.

Multi-modal learning for inpatient length of stay prediction.

Predicting inpatient length of stay (LoS) is important for hospitals aiming to improve service efficiency and enhance management capabilities. Patient medical records are strongly associated with LoS. However, due to diverse modalities, heterogeneity, and complexity of data, it becomes challenging to effectively leverage these heterogeneous data to put forth a predictive model that can accurately predict LoS.