Hierarchical Label Distribution Learning for Disease Prediction.

The prediction of disease can facilitate early intervention, comprehensive diagnosis and treatment, thereby benefiting healthcare and reducing medical costs. While single class and multi-class learning methods have been applied for disease prediction, they are inadequate in distinguishing between primary and secondary diagnoses, which is crucial for treatments. In this paper, label distribution is suggested to describe the diagnosis, which assigns the description degree to quantify the diagnosis. Additionally, a novel hierarchical label distribution learning (HLDL) model is proposed to make fine-grained predictions based on the hierarchical classification of diseases, taking into account the relationship among diseases. The experimental results on real-world datasets demonstrate that the HLDL model outperforms the baselines with statistical significance.

Extracting Dynamic Information of Temporal Clinical Data to Predict the Outcome in Critically Ill Patients.

Outcome prediction is essential for the administration and treatment of critically ill patients. For those patients, clinical measurements are continuously monitored and the time-varying data contains rich information for assessing the patients' status. However, it is unclear how to capture the dynamic information effectively. In this work, multiple feature extraction methods, i.e. statistical feature classification methods and temporal modeling methods, such as recurrent neural network (RNN), were analyzed on a critical illness dataset with 18415 cases. The experimental results show when the dimension increases from 10 to 50, the RNN algorithm is gradually superior to the statistical feature classification methods with simple logic. The RNN model achieves the largest AUC value of 0.8463. Therefore, the temporal modeling methods are promising to capture temporal features which are predictive of the patients' outcome and can be extended in more clinical applications.

Towards an Environmentally Robust Speech Assistant System for Emergency Medical Services.

Automated speech recognition technology with robust performance in various environments is highly needed by emergency clinicians, but there are few successful cases. One main challenge is the wide variety of environmental interference involved during a typical prehospital care emergency service such as background noises and overlapping speech. To solve this problem, we try to establish an environmentally robust speech assistant system with the help of the proposed personalized speech enhancement (PSE) method, which utilizes the target physician's voiceprint feature to suppress non-target signal components. We demonstrate its potential value using both general public test set and our real EMS test set by evaluating the objective speech quality metrics, DNSMOS, and the recognition accuracy. Hopefully, the proposed method will raise EMS efficiency and security against non-target speech.

The type III secretion system facilitates systemic infections of Pseudomonas aeruginosa in the clinic.

IMPORTANCE: The identification of decisive virulence-associated genes in highly pathogenic P. aeruginosa isolates in the clinic is essential for diagnosis and the start of appropriate treatment. Over the past decades, P. aeruginosa ST463 has spread rapidly in East China and is highly resistant to ß-lactams. Given the poor clinical outcome caused by this phenotype, detailed information regarding its decisive virulence genes and factors affecting virulence expression needs to be deciphered. Here, we demonstrate that the T3SS effector ExoU has toxic effects on mammalian cells and is required for virulence in the murine bloodstream infection model. Moreover, a functional downstream SpcU is required for ExoU secretion and cytotoxicity. This work highlights the potential role of ExoU in the pathogenesis of disease and provides a new perspective for further research on the development of new antimicrobials with antivirulence ability.

Analysis of the oxygen evolution activity of layered double hydroxides (LDHs) using machine learning guidance.

Layered double hydroxides (LDHs) are excellent catalysts for the oxygen evolution reaction (OER) because of their tunable properties, including chemical composition and structural morphology. An interplay between these adjustable properties and other (including external) factors might not always benefit the OER catalytic activity of LDHs. Therefore, we applied machine learning algorithms to simulate the double-layer capacitance to understand how to design/tune LDHs with targeted catalytic properties. The key factors of solving this task were identified using the Shapley Additive explanation and cerium was identified as an effective element to modify the double-layer capacitance. We also compared different modelling methods to identify the most promising one and the results revealed that binary representation is better than directly applying atom numbers as inputs for chemical compositions. Overpotentials of LDH-based materials as predicted targets were also carefully examined and evaluated, and it turns out that overpotentials can be predicted when measurement conditions about overpotentials are added as features. Finally, to confirm our findings, we reviewed additional experimental literature data and used them to test our machine algorithms to predict LDH properties. This analysis confirmed the very credible and robust generalization ability of our final model capable of achieving accurate results even with a relatively small dataset.

A Weak Acidic and Strong Coordinated Deep Eutectic Solvent for Recycling of Cathode from Spent Lithium-Ion Batteries.

The leaching and recycling of valuable metals via environmentally benign solvents is important because of the ever-increasing waste lithium-ion batteries, but it remains a challenge. Herein, a multi-functional deep eutectic solvent (DES) based on lactic acid (LA) and guanidine hydrochloride (GHC) was used to extract cobalt and lithium ions from LiCoO2 . Due to the strong acidity (protons) and abundant chlorine coordinating ions of LA/GHC, the solubility of LiCoO2 in LA/GHC could reach as high as 19.9 mg g-1 (stirred at 80 °C for 24 h), and a little LiCoO2 powder even could be dissolved at room temperature without stirring. Oxalic acid was used to strip and separate the oxalates of cobalt and lithium. Furthermore, LA/GHC could be recycled with a similar dissolving performance. This work avoided using corrosive acids and could be realized at low temperature (80 °C), making it energy-saving and cost-effective. It shows DESs have great potential in extracting strategically important metals from LiCoO2 cathodes and provides an efficient and green alternative for sustainable recycling of spent lithium-ion batteries.

Isolation, characterization, genomic sequencing, and GFP-marked insertional mutagenesis of a high-performance nitrogen-fixing bacterium, Kosakonia radicincitans GXGL-4A and visualization of bacterial colonization on cucumber roots.

A gram-negative bacterium GXGL-4A was originally isolated from maize roots. It displayed nitrogen-fixing (NF) ability under nitrogen-free culture condition, and had a significant promotion effect on cucumber growth in the pot inoculation test. The preliminary physiological and biochemical traits of GXGL-4A were characterized. Furthermore, a phylogenetic tree was constructed based on 16S ribosomal DNA (rDNA) sequences of genetically related species. To determine the taxonomic status of GXGL-4A and further utilize its nitrogen-fixing potential, genome sequence was obtained using PacBio RS II technology. The analyses of average nucleotide identity based on BLAST+ (ANIb) and correlation indexes of tetra-nucleotide signatures (Tetra) showed that the NF isolate GXGL-4A is closely related to the Kosakonia radicincitans type strain DSM 16656. Therefore, the isolate GXGL-4A was eventually classified into the species of Kosakonia radicincitans and designated K. radicincitans GXGL-4A. A high consistency in composition and gene arrangement of nitrogen-fixing gene cluster I (nif cluster I) was found between K. radicincitans GXGL-4A and other Kosakonia NF strains. The mutants tagged with green fluorescence protein (GFP) were obtained by transposon Tn5 mutagenesis, and then, the colonization of gfp-marked K. radicincitans GXGL-4A cells on cucumber seedling root were observed under fluorescence microscopy. The preferential sites of the labeled GXGL-4A cell population were the lateral root junctions, the differentiation zone, and the elongation zone. All these results should benefit for the deep exploration of nitrogen fixation mechanism of K. radicincitans GXGL-4A and will definitely facilitate the genetic modification process of this NF bacterium in sustainable agriculture.