Development of a predictive model for 1-year postoperative recovery in patients with lumbar disk herniation based on deep learning and machine learning.

Background: The aim of this study is to develop a predictive model utilizing deep learning and machine learning techniques that will inform clinical decision-making by predicting the 1-year postoperative recovery of patients with lumbar disk herniation. Methods: The clinical data of 470 inpatients who underwent tubular microdiscectomy (TMD) between January 2018 and January 2021 were retrospectively analyzed as variables. The dataset was randomly divided into a training set (n = 329) and a test set (n = 141) using a 10-fold cross-validation technique. Various deep learning and machine learning algorithms including Random Forests, Extreme Gradient Boosting, Support Vector Machines, Extra Trees, K-Nearest Neighbors, Logistic Regression, Light Gradient Boosting Machine, and MLP (Artificial Neural Networks) were employed to develop predictive models for the recovery of patients with lumbar disk herniation 1 year after surgery. The cure rate score of lumbar JOA score 1 year after TMD was used as an outcome indicator. The primary evaluation metric was the area under the receiver operating characteristic curve (AUC), with additional measures including decision curve analysis (DCA), accuracy, sensitivity, specificity, and others. Results: The heat map of the correlation matrix revealed low inter-feature correlation. The predictive model employing both machine learning and deep learning algorithms was constructed using 15 variables after feature engineering. Among the eight algorithms utilized, the MLP algorithm demonstrated the best performance. Conclusion: Our study findings demonstrate that the MLP algorithm provides superior predictive performance for the recovery of patients with lumbar disk herniation 1 year after surgery.

Production of artificial humic acid from corn straw acid hydrolysis residue with biogas slurry impregnation for fertilizer application.

This study investigated hydrothermal humification of corn straw acid hydrolysis residue with biogas slurry impregnation, aiming at producing water-soluble artificial humic acid fertilizer for fertilizer application and soil remediation. Hydrothermal humification parameters, including potassium hydroxide concentration (1-3 mol/L), retention time (2-6 h), and temperature (140-180 °C), were investigated using water as the liquid phase. The selected hydrothermal humification condition was 1.5 mol/L potassium hydroxide at 180 °C for 4 h. Moreover, biogas slurry impregnation (0-30 days) was evaluated to improve humic acid yield without introducing additional chemicals or energy input. Biogas slurry as the liquid phase increased the humic acid production by 73.24% with 5 days of impregnation compared to the control due to the alkalinity. The humic acid concentration was sufficient for China's national standard of water-soluble humic acid fertilizers in such conditions. The organic components in biogas slurry were involved in artificial humification as a precursor, forming C-N bonds with humic acid. The product with fortified nitrogen-containing functional groups enhanced the nutrient slow-release characteristics and water retention capabilities. The pot experiment further confirmed that artificial humic acid prepared in this study not only promoted the growth of plants but also achieved soil remediation.

Bioaugmentation on humification during co-composting of corn straw and biogas slurry.

In order to increase the nutrients and humic acid (HA) contents of corn straw (CS) derived organic fertilizer and recover resources from biogas slurry (BS) simultaneously, the co-composting of CS and BS was carried out with the addition of biochar and microbial agents including lignocellulose degrading and ammonia assimilating bacteria. The results showed that 1 kg straw could treat 2.5 L BS by recovering nutrients and bio-heat introduced evaporation. The bioaugmentation strengthened both the polyphenol and Maillard humification pathways by promoting the polycondensation of precursors (reducing sugars, polyphenols, and amino acids). HA obtained in the microbial-enhanced group (20.83 g/kg), biochar-enhanced group (19.34 g/kg), and combined-enhanced group (21.66 g/kg) were significantly higher than that in the control group (16.26 g/kg). The bioaugmentation achieved directional humification and reduced the loss of C and N by promoting the CN formation of HA. The humified co-compost had nutrient slow-release effect in agricultural production.

Systematic Bioinformatics Analysis Based on Public and Second-Generation Sequencing Transcriptome Data: A Study on the Diagnostic Value and Potential Mechanisms of Immune-Related Genes in Acute Myocardial Infarction.

Acute myocardial infarction (AMI) is one of the most serious cardiovascular diseases worldwide. Advances in genomics have provided new ideas for the development of novel molecular biomarkers of potential clinical value for AMI. Methods: Based on microarray data from a public database, differential analysis and functional enrichment analysis were performed to identify aberrantly expressed genes in AMI and their potential functions. CIBERSORT was used for immune landscape analysis. We also obtained whole blood samples of 3 patients with AMI and performed second-generation sequencing (SGS) analysis. Weighted gene co-expression network analysis (WGCNA) and cross-tabulation analysis identified AMI-related key genes. Receiver operating characteristic (ROC) curves were used to assess the diagnostic power of key genes. Single-gene gene set enrichment analysis (GSEA) revealed the molecular mechanisms of diagnostic indicators. Results: A total of 53 AMI-related DEGs from a public database were obtained and found to be involved in immune cell activation, immune response regulation, and cardiac developmental processes. CIBERSORT confirmed that the immune microenvironment was altered between AMI and normal samples. A total of 77 hub genes were identified by WGCNA, and 754 DEGs were obtained from own SGS data. Seven diagnostic indicators of AMI were obtained, namely GZMA, NKG7, TBX21, TGFBR3, SMAD7, KLRC4, and KLRD1. The single-gene GSEA suggested that the diagnostic indicators seemed to be closely implicated in cell cycle, immune response, cardiac developmental, and functional regulatory processes. Conclusion: The present study provides new diagnostic indicators for AMI and further confirms the feasibility of the results of genome-wide gene expression analysis.

Augmentation characteristics and microbial community dynamics of low temperature resistant composite strains LTF-27.

Biogas production in the cold regions of China is hindered by low temperatures, which led to slow lignocellulose biotransformation. Cold-adapted lignocellulose degrading microbial complex community LTF-27 was used to investigate the influence of hydrolysis on biogas production. After 5 days of hydrolysis at 15 ± 1 °C, the hydrolysis conversion rate of the corn straw went up to 22.64%, and the concentration of acetic acid increased to 2596.56 mg/L. The methane production rates of total solids (TS) inoculated by LTF-27 reached 204.72 mL/g, which was higher than the biogas (161.34 mL/g), and the control group (CK) inoculated with cultural solution (121.19 mL/g), the methane production rate of volatile solids (VS) increased by 26.88% and 68.92%, respectively. Parabacteroides, Lysinibacillus, and Citrobacter were the main organisms that were responsible for hydrolysis. While numerous other bacteria genera in the gas-producing phase, Macellibacteroides were the most commonly occurring one. Methanosarcina and Methanobacteriaceae contributed 86.25% and 11.80% of the total Archaea abundance during this phase. This study proves the psychrotrophic LTF-27's applicability in hydrolysis and biomass gas production in low temperatures.