Identification and validation of cuproptosis related genes and signature markers in bronchopulmonary dysplasia disease using bioinformatics analysis and machine learning.

BACKGROUND: Bronchopulmonary Dysplasia (BPD) has a high incidence and affects the health of preterm infants. Cuproptosis is a novel form of cell death, but its mechanism of action in the disease is not yet clear. Machine learning, the latest tool for the analysis of biological samples, is still relatively rarely used for in-depth analysis and prediction of diseases. METHODS AND RESULTS: First, the differential expression of cuproptosis-related genes (CRGs) in the GSE108754 dataset was extracted and the heat map showed that the expression of NFE2L2 gene was significantly higher in the control group whereas the expression of GLS gene was significantly higher in the treatment group. Chromosome location analysis showed that both the genes were positively correlated and associated with chromosome 2. The results of immune infiltration and immune cell differential analysis showed differences in the four immune cells, significantly in Monocytes cells. Five new pathways were analyzed through two subgroups based on consistent clustering of CRG expression. Weighted correlation network analysis (WGCNA) set the screening condition to the top 25% to obtain the disease signature genes. Four machine learning algorithms: Generalized Linear Models (GLM), Random Forest (RF), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGB) were used to screen the disease signature genes, and the final five marker genes for disease prediction. The models constructed by GLM method were proved to be more accurate in the validation of two datasets, GSE190215 and GSE188944. CONCLUSION: We eventually identified two copper death-associated genes, NFE2L2 and GLS. A machine learning model-GLM was constructed to predict the prevalence of BPD disease, and five disease signature genes NFATC3, ERMN, PLA2G4A, MTMR9LP and LOC440700 were identified. These genes that were bioinformatics analyzed could be potential targets for identifying BPD disease and treatment.

ISMAC: An Intelligent System for Customized Clinical Case Management and Analysis.

Clinical cases are primary and vital evidence for Traditional Chinese Medicine (TCM) clinical research. A great deal of medical knowledge is hidden in the clinical cases of the highly experienced TCM practitioner. With a deep Chinese culture background and years of clinical experience, an experienced TCM specialist usually has his or her unique clinical pattern and diagnosis idea. Preserving huge clinical cases of experienced TCM practitioners as well as exploring the inherent knowledge is then an important but arduous task. The novel system ISMAC (Intelligent System for Management and Analysis of Clinical Cases in TCM) is designed and implemented for customized management and intelligent analysis of TCM clinical data. Customized templates with standard and expert-standard symptoms, diseases, syndromes, and Chinese Medince Formula (CMF) are constructed in ISMAC, according to the clinical diagnosis and treatment characteristic of each TCM specialist. With these templates, clinical cases are archived in order to maintain their original characteristics. Varying data analysis and mining methods, grouped as Basic Analysis, Association Rule, Feature Reduction, Cluster, Pattern Classification, and Pattern Prediction, are implemented in the system. With a flexible dataset retrieval mechanism, ISMAC is a powerful and convenient system for clinical case analysis and clinical knowledge discovery.

Intelligent ZHENG Classification of Hypertension Depending on ML-kNN and Information Fusion.

Hypertension is one of the major causes of heart cerebrovascular diseases. With a good accumulation of hypertension clinical data on hand, research on hypertension's ZHENG differentiation is an important and attractive topic, as Traditional Chinese Medicine (TCM) lies primarily in "treatment based on ZHENG differentiation." From the view of data mining, ZHENG differentiation is modeled as a classification problem. In this paper, ML-kNN-a multilabel learning model-is used as the classification model for hypertension. Feature-level information fusion is also used for further utilization of all information. Experiment results show that ML-kNN can model the hypertension's ZHENG differentiation well. Information fusion helps improve models' performance.

An Algorithm for Automatic Rib Fracture Recognition Combined with nnU-Net and DenseNet.

Rib fracture is the most common thoracic clinical trauma. Most patients have multiple different types of rib fracture regions, so accurate and rapid identification of all trauma regions is crucial for the treatment of rib fracture patients. In this study, a two-stage rib fracture recognition model based on nnU-Net is proposed. First, a deep learning segmentation model is trained to generate candidate rib fracture regions, and then, a deep learning classification model is trained in the second stage to classify the segmented local fracture regions according to the candidate fracture regions generated in the first stage to determine whether they are fractures or not. The results show that the two-stage deep learning model proposed in this study improves the accuracy of rib fracture recognition and reduces the false-positive and false-negative rates of rib fracture detection, which can better assist doctors in fracture region recognition.

Numerical Simulation and Experimental Study on Residual Stress in the Curved Surface Forming of 12CrNi2 Alloy Steel by Laser Melting Deposition.

The performance and service life of the nuclear emergency diesel engine shaft made of 12CrNi2 alloy steel is very important for the safety of nuclear power. Laser melting deposition (LMD) is a challenging camshaft-forming technology due to its high precision, rapid prototyping, and excellent parts performance. However, LMD is an unsteady process under the local action of laser, especially for curved surface forming, which is more likely to generate large residual stress on components, resulting in cracks and other defects. At present, the stress research on LMD curved surface forming is relatively insufficient. In the present paper, material parameter testing, high-temperature mechanical properties analysis, single-track sample preparation, and heat source checks are conducted. At the same time, the ABAQUS software and the DFLUX heat source subroutine are used to compile the curved double-ellipsoidal moving heat source, and the effects of the temperature-dependent thermophysical parameters and phase change latent heat on the temperature field are considered. A three-dimensional finite element model is established to analyze the thermal stress evolution and residual stress distribution of multi-track multi-layer on a curved surface by LMD, and the effect of the scanning method and interlayer cooling time on the residual stress of the formed components is studied. The results show that with the increase in temperature, the strength of the material reduces, and the fracture morphology of the material gradually transitions from ductile fracture to creep fracture. The material parameters provide a guarantee for the simulation, and the errors of the width and depth of the melt pool are 4% and 9.6%, respectively. The simulation and experiment fit well. After cooling, the maximum equivalent stress is 686 MPa, which appears at the junction of the substrate and the deposited layer. The larger residual stress is mainly concentrated in the lower part of the deposited layer, where the maximum circumferential stress and axial stress are the tensile stress. Compared with the axial parallel lap scanning method, the arc copying lap scanning method has a relatively smaller maximum thermal stress and residual stress after cooling. The residual stress in the deposited layer is increased to some extent with the increase in the interlayer cooling time.

Inner surface of Nepenthes slippery zone: ratchet effect of lunate cells causes anisotropic superhydrophobicity.

Inner surface of Nepenthes slippery zone shows anisotropic superhydrophobic wettability. Here, we investigate what factors cause the anisotropy via sliding angle measurement, morphology/structure observation and model analysis. Static contact angle of ultrapure-water droplet exhibits the value of 154.80°-156.83°, and sliding angle towards pitcher bottom and up is 2.82 ± 0.45° and 5.22 ± 0.28°, respectively. The slippery zone under investigation is covered by plenty of lunate cells with both ends bending downward, and a dense layer of wax coverings without directional difference in morphology/structure. Results indicate that the slippery zone has a considerable anisotropy in superhydrophobic wettability that is most likely caused by the lunate cells. A model was proposed to quantitatively analyse how the structure characteristics of lunate cells affect the anisotropic superhydrophobicity, and found that the slope/precipice structure of lunate cells forms a ratchet effect to cause ultrapure-water droplet to roll towards pitcher bottom/up in different order of difficulty. Our investigation firstly reveals the mechanism of anisotropic superhydrophobic wettability of Nepenthes slippery zone, and inspires the bionic design of superhydrophobic surfaces with anisotropic properties.

End-to-End Models to Imitate Traditional Chinese Medicine Syndrome Differentiation in Lung Cancer Diagnosis: Model Development and Validation.

BACKGROUND: Traditional Chinese medicine (TCM) has been shown to be an efficient mode to manage advanced lung cancer, and accurate syndrome differentiation is crucial to treatment. Documented evidence of TCM treatment cases and the progress of artificial intelligence technology are enabling the development of intelligent TCM syndrome differentiation models. This is expected to expand the benefits of TCM to lung cancer patients. OBJECTIVE: The objective of this work was to establish end-to-end TCM diagnostic models to imitate lung cancer syndrome differentiation. The proposed models used unstructured medical records as inputs to capitalize on data collected for practical TCM treatment cases by lung cancer experts. The resulting models were expected to be more efficient than approaches that leverage structured TCM datasets. METHODS: We approached lung cancer TCM syndrome differentiation as a multilabel text classification problem. First, entity representation was conducted with Bidirectional Encoder Representations from Transformers and conditional random fields models. Then, five deep learning-based text classification models were applied to the construction of a medical record multilabel classifier, during which two data augmentation strategies were adopted to address overfitting issues. Finally, a fusion model approach was used to elevate the performance of the models. RESULTS: The F1 score of the recurrent convolutional neural network (RCNN) model with augmentation was 0.8650, a 2.41% improvement over the unaugmented model. The Hamming loss for RCNN with augmentation was 0.0987, which is 1.8% lower than that of the same model without augmentation. Among the models, the text-hierarchical attention network (Text-HAN) model achieved the highest F1 scores of 0.8676 and 0.8751. The mean average precision for the word encoding-based RCNN was 10% higher than that of the character encoding-based representation. A fusion model of the text-convolutional neural network, text-recurrent neural network, and Text-HAN models achieved an F1 score of 0.8884, which showed the best performance among the models. CONCLUSIONS: Medical records could be used more productively by constructing end-to-end models to facilitate TCM diagnosis. With the aid of entity-level representation, data augmentation, and model fusion, deep learning-based multilabel classification approaches can better imitate TCM syndrome differentiation in complex cases such as advanced lung cancer.

Effect of Thermal Cycle on Microstructure Evolution and Mechanical Properties of Selective Laser Melted Low-Alloy Steel.

Low-alloy steel samples were successfully fabricated by selective laser melting (SLM). The evolution of the microstructure and the mechanical properties were investigated with different values of the energy area density (EAD). The results revealed that the initial solidification microstructures of the single tracks with different EADs were all martensite. However, the microstructures of bulk samples under different EADs were not martensite and differed significantly even from one another. When EAD increased from 47 to 142 J/mm2, the mixed lower bainite and martensite austenite microstructure changed to granular bainite; further, the morphology of bainite ferrite gradually changed from lath to multilateral. Moreover, with the increase of EAD, the grain size was remarkably reduced because of the increasing austenitizing periods and temperature during thermal cycling. The average grain size was 1.56 µm, 3.98 µm, and 6.31 µm with EADs of 142 J/mm2, 71 J/mm2, and 47 J/mm2, respectively. Yield strength and tensile strength of the SLM low-alloy steel increased with the increase in EAD; these values were significantly more than those of the alloys prepared by traditional methods. The microstructure of the SLM low-alloy steel samples is not uniform, and the inhomogeneity becomes more significant as EAD decreases. Simultaneously, when EAD decreases, the fracture mechanism changes from ductile to a mixture of ductile and brittle fracture; this is in contrast to the samples prepared by traditional methods. This study also found a stress concentration mechanism around large pores during plastic deformation that resulted in a brittle fracture. This indicates that large-sized pores significantly degrade the mechanical properties of the specimens.