Search

A good AI algorithm can make accurate predictions and provide reasonable explanations for the field in which it is applied. However, the application of deep models makes the black box problem, i.e., the lack of interpretability of a model, more prominent. In particular, when there are multiple features in an application domain and complex interactions between these features, it is difficult for a deep model to intuitively explain its prediction results. Moreover, in practical applications, multiorder feature interactions are ubiquitous. To break the interpretation limitations of deep models, we argue that a multiorder linearly separable deep model can be divided into different orders to explain its prediction results. Inspired by the interpretability advantage of tree models, we design a feature representation mechanism that can consistently represent the features of both trees and deep models. Based on the consistent representation, we propose a multiorder feature-tracking strategy to provide a prediction-oriented multiorder explanation for a linearly separable deep model. In experiments, we have empirically verified the effectiveness of our approach in two binary classification application scenarios: education and marketing. Experimental results show that our model can intuitively represent complex relationships between features through diversified multiorder explanations.

The specific mechanisms underlying bacteria‐triggered cell death and osteogenic dysfunction in host bone marrow mesenchymal stem cells (BMSCs) remain unclear, posing a significant challenge to the repair of infected bone defects. This study identifies ferroptosis as the predominant cause of BMSCs death in the infected bone microenvironment. Mechanistically, the bacteria‐induced activation of the innate immune response in BMSCs leads to upregulation and phosphorylation of interferon regulatory factor 7 (IRF7), thus facilitating IRF7‐dependent ferroptosis of BMSCs through the transcriptional upregulation of acyl‐coenzyme A synthetase long‐chain family member 4 (ACSL4). Moreover, it is found that intervening in ferroptosis can partially rescue cell injuries and osteogenic dysfunction. Based on these findings, a hydrogel composite 3D‐printed scaffold is designed with reactive oxygen species (ROS)‐responsive release of antibacterial quaternized chitosan and sustained delivery of the ferroptosis inhibitor Ferrostatin‐1 (Fer‐1), capable of eradicating pathogens and promoting bone regeneration in a rat model of infected bone defects. Together, this study suggests that ferroptosis of BMSCs is a promising therapeutic target for infected bone defect repair. [ABSTRACT FROM AUTHOR]

Background: Clinical studies have shown that diabetic peripheral neuropathy (DPN) has been on the rise, with most patients presenting with severe and progressive symptoms. Currently, most of the available prediction models for DPN are derived from general clinical information and laboratory indicators. Several Traditional Chinese medicine (TCM) indicators have been utilised to construct prediction models. In this study, we established a novel machine learning‐based multi‐featured Chinese–Western medicine‐integrated prediction model for DPN using clinical features of TCM. Materials and Methods: The clinical data of 1581 patients with Type 2 diabetes mellitus (T2DM) treated at the Department of Endocrinology of the First Affiliated Hospital of Anhui University of Chinese Medicine were collected. The data (including general information, laboratory parameters and TCM features) of 1142 patients with T2DM were selected after data cleaning. After baseline description analysis of the variables, the data were divided into training and validation sets. Four prediction models were established and their performance was evaluated using validation sets. Meanwhile, the accuracy, precision, recall, F1 score and area under the curve (AUC) of ROC were calculated using ten‐fold cross‐validation to further assess the performance of the models. An explanatory analysis of the results of the DPN prediction model was carried out using the SHAP framework based on machine learning‐based prediction models. Results: Of the 1142 patients with T2DM, 681 had a comorbidity of DPN, while 461 did not. There was a significant difference between the two groups in terms of age, cause of disease, systolic pressure, HbA1c, ALT, RBC, Cr, BUN, red blood cells in the urine, glucose in the urine, and protein in the urine (p < 0.05). T2DM patients with a comorbidity of DPN exhibited diverse TCM symptoms, including limb numbness, limb pain, hypodynamia, thirst with desire for drinks, dry mouth and throat, blurred vision, gloomy complexion, and unsmooth pulse, with statistically significant differences (p < 0.05). Our results showed that the proposed multi‐featured Chinese–Western medicine‐integrated prediction model was superior to conventional models without characteristic TCM indicators. The model showed the best performance (accuracy = 0.8109, precision = 0.8029, recall = 0.9060, F1 score = 0.8511, and AUC = 0.9002). SHAP analysis revealed that the dominant risk factors that caused DPN were TCM symptoms (limb numbness, thirst with desire for drinks, blurred vision), age, cause of disease, and glycosylated haemoglobin. These risk factors were exerted positive effects on the DPN prediction models. Conclusions: A multi‐feature, Chinese–Western medicine‐integrated prediction model for DPN was established and validated. The model improves early‐stage identification of high‐risk groups for DPN in the diagnosis and treatment of T2DM, while also providing informative support for the intelligent management of chronic conditions such as diabetes. [ABSTRACT FROM AUTHOR]

Compared to integrated large screen displays, the splicing scheme that uses multiple display units for splicing has significant advantages in various aspects to achieve large screen displays. This article is based on MLCD (Mini LCD) display scheme that combines LCD and LED, and proposes various algorithms to improve the image quality of the splicing. It effectively solves the image quality problems that occur in MLCD display schemes, while taking into account the advantages of cost and maintenance, it can also fully leverage the image quality advantages. The splicing image quality improvement algorithm not only fills the gap in display effect improvement methods in the splicing display field, but also provides new ideas for the development of large screen image quality improvement technology. [ABSTRACT FROM AUTHOR]

Osteoarthritis (OA) is a chronic joint disease characterized by progressive degeneration of articular cartilage. A challenge in the development of disease-modifying drugs is effective delivery to chondrocytes. The unique structure of the joint promotes rapid clearance of drugs through synovial fluid, and the dense and avascular cartilage extracellular matrix (ECM) limits drug penetration. Here, we show that poly(lactide-co-glycolic acid) nanoparticles coated in chondrocyte membranes (CM-NPs) were preferentially taken up by rat chondrocytes ex vivo compared with uncoated nanoparticles. Internalization of the CM-NPs was mediated primarily by E-cadherin, clathrin-mediated endocytosis, and micropinocytosis. These CM-NPs adhered to the cartilage ECM in rat knee joints in vivo and penetrated deeply into the cartilage matrix with a residence time of more than 34 days. Simulated synovial fluid clearance studies showed that CM-NPs loaded with a Wnt pathway inhibitor, adavivint (CM-NPs-Ada), delayed the catabolic metabolism of rat and human chondrocytes and cartilage explants under inflammatory conditions. In a surgical model of rat OA, drug-loaded CM-NPs effectively restored gait, attenuated periarticular bone remodeling, and provided chondroprotection against cartilage degeneration. OA progression was also mitigated by CM-NPs-Ada in a canine model of anterior cruciate ligament transection. These results demonstrate the feasibility of using chondrocyte membrane–coated nanoparticles to improve the pharmacokinetics and efficacy of anti-OA drugs. Editor's summary: Osteoarthritis (OA) lacks effective disease-modifying treatments partially because of the difficulty of delivering drugs to dense and avascular cartilage tissue. Here, Deng et al. disguised drug-carrying nanoparticles with chondrocyte membranes to increase the interaction of the nanoparticles with cartilage. These membrane-coated nanoparticles retained critical chondrocyte proteins that supported cell and matrix interactions in explanted rat and human cartilage. These nanoparticles were retained in rat knee in vivo for at least 34 days. In rat and canine models of injury-induced OA, release of a Wnt-pathway inhibitor from these nanoparticles improved cartilage and subchondral bone morphology. These findings support the further development of chondrocyte-mimicking particles for cartilage drug delivery and OA therapy. —Molly Ogle [ABSTRACT FROM AUTHOR]

To observe the effect of Danzhi Jiangtang capsule (DJC) on the clinical indexes and vascular endothelial function indexes in patients with impaired glucose tolerance (IGT). A total of 106 patients were enrolled and randomly assigned to the treatment group and control group following a four-week washout period. The patients in the control group received a general lifestyle intervention, while those in the treatment group received DJC (2.0 g 3× a day) in conjunction with the intervention given to the control group patients. The physiological and biochemical levels, vascular endothelial function indices, and traditional Chinese medicine (TCM) syndrome ratings of the patients in the two groups were compared after 12 weeks of therapy. In the control group, the diastolic blood pressure (DBP) was significantly improved compared with those before treatment (83.31 ± 6.47 vs. 79.21 ± 6.17, p <.01) (CI: 1.45, 6.73; Cohen's d: 10.51), as was the case with the nitric oxide (NO) levels and TCM syndrome points (35.71 ± 4.58 vs. 43.96 ± 5.17, 9.57 ± 2.63 vs. 5.38 ± 1.79, p <.001) (CI: –10.28, –6.24; 3.12, 5.18; Cohen's d: 0.90). In the treatment group, the levels of fasting blood glucose, endothelin and vascular endothelial growth factor were significantly improved compared with control group (4.92 ± 0.21 vs. 5.59 ± 0.31, 59.37 ± 13.25 vs. 72.13 ± 12.37, 19.25 ± 2.80 vs. 26.76 ± 1.88, p <.001) (CI: 0.55, 0.78; 7.40, 18.13; 6.52, 8.50; Cohen's d: 4.94, 0.41, 1.32), as was the case with 2-h post-load plasma glucose and total cholesterol (TC) (8.33 ± 0.62 vs. 8.89 ± 1.55, 4.61 ± 1.05 vs. 5.22 ± 1.12, p <.05) (CI: 0.07, 1.07; 0.15, 1.06; Cohen's d: 0.40, 0.51). Treatment with DJC could significantly improve the physiological and biochemical indicators, vascular endothelial function, and TCM syndrome points of IGT patients, indicating that DJC could be a potential drug to treat patients with IGT of Qi–Yin deficiency type. [ABSTRACT FROM AUTHOR]

Previous findings have shown a strong relationship between sports and interpersonal cooperative behavior. Physical activity is the basic form of sport. In this study, we investigated the effect of physical activity on interpersonal cooperative behavior and its inter‐brain correlates. Eighty college students were recruited and randomly divided into the experimental or control group (20 dyads per each). The experimental group performed a 30‐min of moderate intensity single‐person cycling exercise, while the control group performed a 30‐min single‐person sitting. Interpersonal cooperative behavior was measured by a Prisoner's Dilemma task before and after the intervention, while neural activities in the frontal cortex in each dyad were measured by the near‐infrared spectroscopy‐based hyperscanning approach. The results showed that the average cooperation rate and cooperation efficiency of the experimental dyads were significantly higher after the exercise intervention compared to that before intervention, but not in control group. Meanwhile, the interpersonal neural synchronization (INS) in the left frontal cortex was significantly increased after intervention only in experimental dyads. Moreover, the INS increased in left frontal cortex was positively correlated with the cooperation improvement. Taken together, these results indicate that one single‐person bicycling can improve interpersonal cooperation behavior, which may be associated with enhanced interpersonal neural synchronization in the left frontal cortex. [ABSTRACT FROM AUTHOR]

Si3N4 is a promising material for heat dissipation substrate due to its excellent thermal conductivity and mechanical properties. However, its application is limited by the difficulties in surface metallization. In this work, surface metallization of Si3N4 ceramic substrate is realized by thick film method for the first time. Conductive silver paste containing Bi2O3-B2O3-ZnO glass frit as glass binder was prepared, and high-performance silver thick films were formed on Si3N4 ceramic surface. The mechanical and electrical properties of silver films were significantly promoted with increasing sintering temperature, and silver films with high shear strength of 23.35 MPa and low resistivity of 3.41 μΩ·cm were obtained when sintered at 600 °C. In the meanwhile, the silver films exist high reliability under thermal cycles. The bonding between the silver thick film and Si3N4 ceramic substrate was considerably enhanced as a result of interfacial reaction, forming Bi2Si2O5 phase at the interface during sintering process. The formation mechanism was discussed and it is of great significance for the interfacial design in future studies. The results suggest that thick film method is a promising technology for obtaining high-quality surface metallization for Si3N4 ceramic substrate. [ABSTRACT FROM AUTHOR]

Analogical reasoning is important for human. We have found that a short executive attention intervention improved analogical reasoning performance in healthy young adults. Nevertheless, previous electrophysiological evidence was limited for comprehensively characterizing the neural mechanisms underlying the improvement. And although we hypothesized that the intervention improved active inhibitory control and attention shift first and then relation integration, it is still unclear whether there are two sequential cognitive neural activities were indeed changed during analogical reasoning. In the present study, we combined hypothesis with multivariate pattern analysis (MVPA) to explore the effects of the intervention on electrophysiology. Results showed that in the resting state after the intervention, alpha and high gamma power and the functional connectivity between the anterior and middle in the alpha band could discriminate the experimental group from the active control group, respectively. These indicated that the intervention influenced the activity of multiple bands and the interaction of frontal and parietal regions. In the analogical reasoning, alpha, theta, and gamma activities could also fulfill such discrimination, and furthermore, they were sequential (alpha first, theta, and gamma later). These results directly supported our previous hypothesis. The present study deepens our understanding about how executive attention contributes to higher‐order cognition. [ABSTRACT FROM AUTHOR]

Osteosarcoma is the most prevalent bone malignant tumor in children and teenagers. The bone defect, recurrence, and metastasis after surgery severely affect the life quality of patients. Clinically, bone grafts are implanted. Primary bioceramic scaffolds show a monomodal osteogenesis function. With the advances in three-dimensional printing technology and materials science, while maintaining the osteogenesis ability, scaffolds become more patient-specific and obtain additional anti-tumor ability with functional agents being loaded. Anti-tumor therapies include photothermal, magnetothermal, old and novel chemo-, gas, and photodynamic therapy. These strategies kill tumors through novel mechanisms to treat refractory osteosarcoma due to drug resistance, and some have shown the potential to reverse drug resistance and inhibit metastasis. Therefore, multifunctional three-dimensional printed bioceramic scaffolds hold excellent promise for osteosarcoma treatments. To better understand, we review the background of osteosarcoma, primary 3D-printed bioceramic scaffolds, and different therapies and have a prospect for the future. [ABSTRACT FROM AUTHOR]

This article considers a federated temporal difference (TD) learning algorithm and provides both asymptotic and finite-time analyses. To protect each worker agent's cost information from being acquired by possible attackers, we propose a privacy-preserving variant of the algorithm by adding perturbation to the exchanged information. We show the rigorous differential privacy guarantee by using moments accountant and derive an upper bound of the utility loss for the privacy-preserving algorithm. Evaluations are also provided to corroborate the efficiency of the algorithms. [ABSTRACT FROM AUTHOR]

In order to solve the problem that violin performance evaluation is too subjective, this paper proposes a violin performance evaluation system based on mobile terminal technology. Violin sound evaluation mainly includes two indicators such as pronunciation quality and distance transmission ability. LabVIEW 8.2 is used to collect data, and fast Fourier transform (FFT) is used to analyze the time-domain signal in frequency domain, and the pronunciation process of violin is discussed in depth. Using statistical methods to process the test data of pronunciation distance transmission, a parameter model representing the pronunciation distance transmission ability is proposed, and finally the WeChat applet is used to control the recording and display. The results show that the process of violin sound production is accompanied by the weakening of octave peaks and the development of overtone peaks. The stable stage is marked by the stability of each octave peak and overtone peak. The sound head initially presents a simple excitation response, with only one near octave overtone and three cycles. Its maximum overtone peak/dominant frequency peak ratio coefficient is k = 0.36; the back entry complex excitation response has about nine cycles, with k = 0.735. Then enter the quasi-stable excitation response, whose waveform is similar to the typical A-string empty string pull waveform in the later stage, with k = 0.36; the maximum overtone peak/main frequency peak proportional coefficient is k = 0.39 in the rising section of the start, k = 0.2 in the loudest section, and k = 0.26 in the stable section. Conclusion. The system has initially established a new instrumented evaluation method, which provides a way of thinking for improving the quantifiable evaluation system in the future. [ABSTRACT FROM AUTHOR]