Contrast-enhanced CT radiomics combined with multiple machine learning algorithms for preoperative identification of lymph node metastasis in pancreatic ductal adenocarcinoma.

Objectives: This research aimed to assess the value of radiomics combined with multiple machine learning algorithms in the diagnosis of pancreatic ductal adenocarcinoma (PDAC) lymph node (LN) metastasis, which is expected to provide clinical treatment strategies. Methods: A total of 128 patients with pathologically confirmed PDAC and who underwent surgical resection were randomized into training (n=93) and validation (n=35) groups. This study incorporated a total of 13 distinct machine learning algorithms and explored 85 unique combinations of these algorithms. The area under the curve (AUC) of each model was computed. The model with the highest mean AUC was selected as the best model which was selected to determine the radiomics score (Radscore). The clinical factors were examined by the univariate and multivariate analysis, which allowed for the identification of factors suitable for clinical modeling. The multivariate logistic regression was used to create a combined model using Radscore and clinical variables. The diagnostic performance was assessed by receiver operating characteristic curves, calibration curves, and decision curve analysis (DCA). Results: Among the 233 models constructed using arterial phase (AP), venous phase (VP), and AP+VP radiomics features, the model built by applying AP+VP radiomics features and a combination of Lasso+Logistic algorithm had the highest mean AUC. A clinical model was eventually constructed using CA199 and tumor size. The combined model consisted of AP+VP-Radscore and two clinical factors that showed the best diagnostic efficiency in the training (AUC = 0.920) and validation (AUC = 0.866) cohorts. Regarding preoperative diagnosis of LN metastasis, the calibration curve and DCA demonstrated that the combined model had a good consistency and greatest net benefit. Conclusions: Combining radiomics and machine learning algorithms demonstrated the potential for identifying the LN metastasis of PDAC. As a non-invasive and efficient preoperative prediction tool, it can be beneficial for decision-making in clinical practice.

Low temperature exposure influences nitrogen metabolism resulting in decreased Cry1Ac insecticidal endotoxin content in cotton seeds.

BACKGROUND: Sudden temperature drops, resulting from extreme weather events, often occur during the boll-setting period of cotton in Xinjiang, China, causing decreased expression of Bacillus thuringiensis (Bt) insecticidal proteins in cotton bolls. The precise threshold temperatures and durations that lead to significant changes in Cry1Ac endotoxin levels under low temperatures remain unclear. To address this, we investigated the effects of different temperatures and stress durations on Cry1Ac endotoxin levels in cotton bolls. In 2020-2021, two Bt transgenic cotton varieties, conventional Sikang1 and hybrid Sikang3, were selected as experimental materials. Various low temperatures (ranging from 16 to 20 °C) with different durations (12 h, 24 h and 48 h) were applied during the peak boll-setting period. RESULTS: As the temperature decreased, the Cry1Ac endotoxin content in the boll shell, fiber, and seed exhibited a declining trend. Moreover, the threshold temperature which caused a significant reduction in Cry1Ac endotoxin content increased with the prolonged duration of low-temperature stress. Among the components of cotton bolls, seeds were most affected by low-temperature stress, with the threshold temperature for a significant reduction in Cry1Ac endotoxin content ranging from 17 °C to 19 °C. Correlation analysis indicated that low temperatures led to a decrease in protein synthesis capacity and an increase in degradation ability, resulting in reduced Cry1Ac endotoxin content. Pathway analysis revealed that both free amino acid and peptidase had significant negative effects on Cry1Ac endotoxin content. CONCLUSION: In summary, when the daily average temperature was ≤ 19 °C, implementing cultural practices to reduce free amino acid content and peptidase activity could serve as effective cold defense strategies for Bt cotton production.

Multi-transcriptomics analysis of microvascular invasion-related malignant cells and development of a machine learning-based prognostic model in hepatocellular carcinoma.

Background: Microvascular invasion (MVI) stands as a pivotal pathological hallmark of hepatocellular carcinoma (HCC), closely linked to unfavorable prognosis, early recurrence, and metastatic progression. However, the precise mechanistic underpinnings governing its onset and advancement remain elusive. Methods: In this research, we downloaded bulk RNA-seq data from the TCGA and HCCDB repositories, single-cell RNA-seq data from the GEO database, and spatial transcriptomics data from the CNCB database. Leveraging the Scissor algorithm, we delineated prognosis-related cell subpopulations and discerned a distinct MVI-related malignant cell subtype. A comprehensive exploration of these malignant cell subpopulations was undertaken through pseudotime analysis and cell-cell communication scrutiny. Furthermore, we engineered a prognostic model grounded in MVI-related genes, employing 101 algorithm combinations integrated by 10 machine-learning algorithms on the TCGA training set. Rigorous evaluation ensued on internal testing sets and external validation sets, employing C-index, calibration curves, and decision curve analysis (DCA). Results: Pseudotime analysis indicated that malignant cells, showing a positive correlation with MVI, were primarily concentrated in the early to middle stages of differentiation, correlating with an unfavorable prognosis. Importantly, these cells showed significant enrichment in the MYC pathway and were involved in extensive interactions with diverse cell types via the MIF signaling pathway. The association of malignant cells with the MVI phenotype was corroborated through validation in spatial transcriptomics data. The prognostic model we devised demonstrated exceptional sensitivity and specificity, surpassing the performance of most previously published models. Calibration curves and DCA underscored the clinical utility of this model. Conclusions: Through integrated multi-transcriptomics analysis, we delineated MVI-related malignant cells and elucidated their biological functions. This study provided novel insights for managing HCC, with the constructed prognostic model offering valuable support for clinical decision-making.

Intranasal PAMAM-G3 scavenges cell-free DNA attenuating the allergic airway inflammation.

Allergic airway inflammation (AAI), including allergic rhinitis (AR) and allergic asthma, is driven by epithelial barrier dysfunction and type 2 inflammation. However, the underlying mechanism remains uncertain and available treatments are constrained. Consequently, we aim to explore the role of cell-free DNA (cfDNA) in AAI and assess the potential alleviating effects of cationic polymers (CPs) through cfDNA elimination. Levels of cfDNA were evaluated in AR patients, allergen-stimulated human bronchial epithelium (BEAS-2B cells) and primary human nasal epithelium from both AR and healthy control (HC), and AAI murine model. Polyamidoamine dendrimers-generation 3 (PAMAM-G3), a classic type of cationic polymers, were applied to investigate whether the clearance of cfDNA could ameliorate airway epithelial dysfunction and inhibit AAI. The levels of cfDNA in the plasma and nasal secretion from AR were higher than those from HC (P < 0.05). Additionally, cfDNA levels in the exhaled breath condensate (EBC) were positively correlated with Interleukin (IL)-5 levels in EBC (R = 0.4191, P = 0.0001). Plasma cfDNA levels negatively correlated with the duration of allergen immunotherapy treatment (R = -0.4297, P = 0.006). Allergen stimulated cfDNA secretion in vitro (P < 0.001) and in vivo (P < 0.0001), which could be effectively scavenged with PAMAM-G3. The application of PAMAM-G3 inhibited epithelial barrier dysfunction in vitro and attenuated the development of AAI in vivo. This study elucidates that cfDNA, a promising biomarker for monitoring disease severity, aggravates AAI and the application of intranasal PAMAM-G3 could potentially be a novel therapeutic intervention for AAI. Allergen stimulates the secretion of cell-free DNA (cfDNA) in both human and mouse airway. Intranasal polyamidoamine dendrimers-generation 3 (PAMAM-G3) scavenges cfDNA and alleviates allergic airway inflammation.

Patterns, Risk Factors, and Outcomes of Recurrence After Hepatectomy for Hepatocellular Carcinoma with and without Microvascular Invasion.

Purpose: The patterns and risk factors of postsurgical recurrence of patient with hepatocellular carcinoma (HCC) with microvascular invasion (MVI) are not clarified. This study aimed to decipher and compare the postoperative recurrent patterns and the risk factors contributing to recurrence between MVI positive (MVI(+)) and MVI negative (MVI(-)) HCC after hepatectomy. Patients and methods: Patients with HCC who underwent hepatectomy in three Chinese academic hospitals between January 1, 2009, and December 31, 2018, were enrolled. Recurrent patterns included early (≤2 years) or late (>2 years) recurrence, recurrent sites and number, and risk factors of recurrence were compared between the MVI(+)and MVI(-) groups by propensity score-matching (PSM). Results: Of 1756 patients included, 581 (33.1%) were MVI(+), and 875 (49.8%) patients developed early recurrence. Compared with the MVI(-) group, the MVI(+) group had a higher 2-year recurrence rate in the PSM cohort (hazard ratio [HR], 1.82; 95% confidence interval [CI], 1.59-2.10; P < 0.001), and more patients with multiple tumor recurrence. Patients with early recurrence in the MVI(+) group had a worse overall survival (OS) than those in the MVI(-) group (HR, 1.24; 95% CI, 1.02-1.50; P = 0.034). Resection margin (RM) ≤1.0 cm is a surgical predictor of early recurrence for the MVI(+) group (HR, 0.68; 95% CI, 0.54-0.87; P = 0.002), but not for the MVI(-) group. Conclusion: Compared to MVI(-) HCC, MVI(+) HCC tends to be early, multiple recurrence and lung and lymph node metastasis after resection. RM ≤1.0 cm is a surgical risk factor of early recurrence for patient with MVI.

Generating lymphoma ultrasound image description with transformer model.

Lymphoma, the most prevalent hematologic tumor originating from the lymphatic hematopoietic system, can be accurately diagnosed using high-resolution ultrasound. Microscopic ultrasound performance enables clinicians to identify suspected tumors and subsequently obtain a definitive pathological diagnosis through puncture biopsy. However, the complex and diverse ultrasonographic manifestations of lymphoma pose challenges for accurate characterization by sonographers. To address these issues, this study proposes a Transformer-based model for generating descriptive ultrasound images of lymphoma, aiming to provide auxiliary guidance for ultrasound doctors during screening procedures. Specifically, deep stable learning is integrated into the model to eliminate feature dependencies by training sample weights. Additionally, a memory module is incorporated into the model decoder to enhance semantic information modeling in descriptions and utilize learned semantic tree branch structures for more detailed image depiction. Experimental results on an ultrasonic diagnosis dataset from Shanghai Ruijin Hospital demonstrate that our proposed model outperforms relevant methods in terms of prediction performance.

Small extracellular vesicles derived from human mesenchymal stem cells prevent Th17-dominant neutrophilic airway inflammation via immunoregulation on Th17 cells.

Type 17 helper T cells (Th17)-dominant neutrophilic airway inflammation is critical in the pathogenesis of steroid-resistant airway inflammation such as severe asthma. Small extracellular vesicles (sEV) derived from human mesenchymal stem cells (MSCs) display extensive therapeutic effects and advantages in many diseases. However, the role of MSC-sEV in Th17-dominant neutrophilic airway inflammation and the related mechanisms are still poorly studied. Here we found that MSC-sEV significantly alleviated the infiltration of inflammatory cells in peribronchial interstitial tissues and reduced levels of inflammatory cells, especially neutrophils, in bronchoalveolar lavage fluids (BALF) of mice with neutrophilic airway inflammation. Consistently, MSC-sEV significantly decreased levels of IL-17A in BALF and Th17 in lung tissues. Furthermore, we found that labelled MSC-sEV were taken up by human CD4+ T cells most obviously at 12 h after incubation, and distributed mostly in mouse lungs. More importantly, potential signaling pathways involved in the MSC-sEV mediated inhibition of Th17 polarization were found using RNA sequencing. Using Western blot, JAK2-STAT3 pathway was identified as an important role in the inhibition of Th17 polarization by MSC-sEV. We found that proteins in MSC-sEV were mostly involved in the therapeutic effects of MSC-sEV. In total, our study suggested that MSC-sEV could be a potential therapeutic strategy for the treatment of neutrophilic airway inflammation.

Optimized Design of Lithium Niobate Tuning Forks for the Measurement of Fluid Characteristic Parameters.

The unique double-cantilever beam structure and vibration mode of the tuning fork enable the measuring of fluid density and viscosity synchronously in a decoupling manner. Therefore, it is widely employed in oil and gas development and in petrochemical, food, textile, and other industries. In this paper, quality factors are used to characterize the energy losses of lithium niobate tuning forks when vibrating in a fluid, and the influence parameters, such as length, width, and thickness of the tuning fork arm, etc., of different quality factors are examined with a focus on the viscous quality factor of the fluid. The optimized design of lithium niobate tuning fork dimensions is carried out on this premise, and the analytical solution of the optimal dimension of the lithium niobate tuning fork in the air is obtained. Secondly, the optimal dimension of the lithium niobate tuning fork in fluids is given out by finite element simulation, and the sensitivity of the optimized fork to the viscosity of fluids is investigated. The results show that the optimized tuning fork has a higher quality factor, and thus has a larger parameter measurement range as well as being more sensitive to the change in the fluid density and viscosity. Therefore, the results are of great significance for guiding the preparation and practical application of lithium niobate tuning forks.

Multi-bubble scattering acoustic fields in viscoelastic tissues under dual-frequency ultrasound.

Bubbles are widely used in the medical field due to their strong acoustic scattering properties, and the interaction between bubbles affects the scattering acoustic field caused by the bubble cluster. In this study, the dynamic equations of bubbles oscillating in viscoelastic tissues are solved numerically. The effect of bubble interaction on the scattered acoustic pressure under dual-frequency ultrasound is analyzed. In addition, the frequency spectra of the scattered acoustic waves due to the bubbles with and without considering the interaction are compared. The results show that the suppression or enlargement of the scattered sound pressure caused by the interaction between bubbles is related to the bubble radius and the incident frequency. Moreover, when the incident frequency is equal to the resonant frequency of the bubble with equilibrium radius R0, the effect of resonant bubbles is stronger than that of non-resonant bubbles. Meanwhile, for the multi-bubble system with a small bubble number density, the total response of the bubble cluster can be approximated as an algebraic sum of the dynamical behavior of individual bubbles.

Dendritic cells mediated by small extracellular vesicles derived from MSCs attenuated the ILC2 activity via PGE2 in patients with allergic rhinitis.

BACKGROUND: Mesenchymal stromal cells-derived small extracellular vesicles (MSC-sEVs) have recently attracted considerable attention because of their therapeutic potential in various immune diseases. We previously reported that MSC-sEVs could exert immunomodulatory roles in allergic airway inflammation by regulating group 2 innate lymphoid cell (ILC2) and dendritic cell (DC) functions. Therefore, this study aimed to investigate the indirect effects of MSC-sEVs on ILC2s from patients with allergic rhinitis (AR) via DCs. METHODS: Here, we isolated sEVs from induced pluripotent stem cells-MSCs using anion-exchange chromatography and mature DCs (mDCs) were treated with MSC-sEVs. sEV-mDCs were co-cultured with peripheral blood mononuclear cells from patients with AR or purified ILC2s. The levels of IL-13 and GATA3 in ILC2s were examined by flow cytometry. Bulk RNA sequence for mDCs and sEV-mDCs was employed to further probe the potential mechanisms, which were then validated in the co-culture systems. RESULTS: sEV-mDCs showed impaired capacity in priming the levels of IL-13 and GATA3 in ILC2s when compared with mDCs. Furthermore, there was higher PGE2 and IL-10 production from sEV-mDCs, and the blockade of them especially the former one reversed the inhibitory effects of sEV-mDCs. CONCLUSIONS: We demonstrated that MSC-sEVs were able to dampen the activating effects of mDCs on ILC2s in patients with AR. Mechanismly, the PGE2-EP2/4 axis played an essential role in the immunomodulatory effects of sEV-mDCs on ILC2s. Herein, we provided new insights into the mechanism underlying the therapeutic effects of MSC-sEVs in allergic airway inflammation.

Type 17 mucosal-associated invariant T cells contribute to neutrophilic inflammation in patients with nasal polyps.

BACKGROUND: Immune regulation in chronic rhinosinusitis with nasal polyps (CRSwNP) with a neutrophilic endotype remains unclear. Mucosal-associated invariant T (MAIT) cells are tissue-resident innate T lymphocytes that respond quickly to pathogens and promote chronic mucosal inflammation. OBJECTIVE: We aimed to investigate the roles of MAIT cells in neutrophilic CRSwNP. METHODS: Nasal tissues were obtained from 113 patients with CRSwNP and 29 control subjects. Peripheral and tissue MAIT cells and their subsets were analyzed by flow cytometry. Polyp-derived MAIT cells were analyzed by RNA sequencing to study their effects on neutrophils. RESULTS: Endotypes of CRSwNP were classified as paucigranulocytic (n = 21), eosinophilic (n = 29), neutrophilic (n = 39), and mixed granulocytic (n = 24). Frequencies of MAIT cells were significantly higher in neutrophilic (3.62%) and mixed granulocytic (3.60%) polyps than in control mucosa (1.78%). MAIT cell percentages positively correlated with local neutrophil counts. MAIT cells were more enriched in tissues than in matched PBMCs. The frequencies of MAIT1 subset or IFN-γ+ MAIT cells were comparable among control tissues and CRSwNP subtypes. The proportions of MAIT17 subset or IL-17A+ MAIT cells were significantly increased in neutrophilic or mixed granulocytic polyps compared with controls. RNA sequencing revealed type 17 and pro-neutrophil profiles in neutrophilic polyp-derived MAIT cells. In patients with neutrophilic CRSwNP, the proportions of MAIT and MAIT17 cells were positively correlated with local proinflammatory cytokines and symptom severity. In vitro experiments demonstrated that neutrophilic polyp-derived MAIT cells promoted neutrophil migration, survival, and activation. CONCLUSIONS: MAIT cells from neutrophilic CRSwNP demonstrate type 17 functional properties and promote neutrophil infiltration in nasal mucosa.

Sensitive dynamics of brain cognitive networks and its resource constraints.

It is well known that brain functions are closely related to the synchronization of brain networks, but the underlying mechanisms are still not completely understood. To study this problem, we here focus on the synchronization of cognitive networks, in contrast to that of a global brain network, as individual brain functions are in fact performed by different cognitive networks but not the global network. In detail, we consider four different levels of brain networks and two approaches, i.e., either with or without resource constraints. For the case of without resource constraints, we find that global brain networks have fundamentally different behaviors from that of the cognitive networks; i.e., the former has a continuous synchronization transition, while the latter shows a novel transition of oscillatory synchronization. This feature of oscillation comes from the sparse links among the communities of cognitive networks, resulting in coupling sensitive dynamics of brain cognitive networks. While for the case of resource constraints, we find that at the global level, the synchronization transition becomes explosive, in contrast to the continuous synchronization for the case of without resource constraints. At the level of cognitive networks, the transition also becomes explosive and the coupling sensitivity is significantly reduced, thus guaranteeing the robustness and fast switch of brain functions. Moreover, a brief theoretical analysis is provided.

Effect of Low Temperature on Insecticidal Protein Contents of Cotton (Gossypium herbaceum L.) in the Boll Shell and Its Physiological Mechanism.

Low temperature is the main factor for global natural disasters affecting the growth and distribution of plants, and cotton may be affected by low temperature and cold damage at all growth stages. In addition, the insecticidal resistance of cultivars has been reported to perform poorly or unstably due to adverse environments. The present study aimed to investigate the impact of low temperature on the levels of insecticidal protein in Bacillus thuringiensis (Bt) transgenic cotton plants during the peak boll stage. To achieve this, two Bt cotton cultivars, Sikang1 (SK1) and Sikang3 (SK3), were subjected to different temperature regimes and durations. The findings of the study demonstrated that the expression of insecticidal protein in the boll shell of Bt transgenic cotton plants was significantly inhibited under low-temperature stress. Specifically, in 2020, compared to the CK (27 °C), the insecticidal protein content in the boll shell of SK3 decreased by 28.19% after a 48 h of a 16 °C temperature. These results suggest that low-temperature stress can negatively impact the expression of insecticidal protein in Bt transgenic cotton, highlighting the need for appropriate measures to minimize its adverse effects on cotton production. In addition, the threshold temperature that leads to a significant decrease in the content of insecticidal proteins symbolizes an upward trend as the duration of stress prolongs. Decreased Bt protein content at low temperatures is associated with changes in the N metabolism. The present study revealed a significant positive correlation between the levels of glutamate oxaloacetate transaminase (GOT) and glutamate pyruvate transaminase (GPT) activities, as well as in the soluble protein levels in the boll shell and the content of the Bt protein. On the other hand, a significant negative correlation was observed between the levels of free amino acids, peptidase, and protease activities, as well as of Bt protein content. These findings suggest that, in Bt cotton production, it is crucial to remain vigilant of prolonged low-temperature disasters, which last for over 12 h and drop below 17-20 °C during the peak boll stage. Such conditions may reduce insecticidal resistance, leading to substantial economic losses.

A method for extracting tumor events from clinical CT examination reports.

Accurate and efficient extraction of key information related to diseases from medical examination reports, such as X-ray and ultrasound images, CT scans, and others, is crucial for accurate diagnosis and treatment. These reports provide a detailed record of a patient's health condition and are an important part of the clinical examination process. By organizing this information in a structured way, doctors can more easily review and analyze the data, leading to better patient care. In this paper, we introduce a new technique for extracting useful information from unstructured clinical text examination reports, which we refer to as a medical event extraction (EE) task. Our approach is based on Machine Reading Comprehension (MRC) and involves two sub-tasks: Question Answerability Judgment (QAJ) and Span Selection (SS). We use BERT to build a question answerability discriminator (Judger) that determines whether a reading comprehension question can be answered or not, thereby avoiding the extraction of arguments from unanswerable questions. The SS sub-task first obtains the encoding of each word in the medical text from the final layer of BERT's Transformer, then utilizes the attention mechanism to identify important information related to the answer from these word encodings. This information is then input into a bidirectional LSTM (BiLSTM) module to obtain a global representation of the text, which is used, along with the softmax function, to predict the span of the answer (i.e., the start and end positions of the answer in the text report). We use interpretable methods to calculate the Jensen-Shannon Divergence (JSD) score between various layers of the network and confirm that our model has strong word representation capabilities, enabling it to effectively extract contextual information from medical reports. Our experiments demonstrate that our method outperforms existing medical event extraction methods, achieving state-of-the-art results with a notable F1 score.

Apparent Diffusion Coefficient in the Differentiation of Common Pediatric Brain Tumors in the Posterior Fossa: Different Region-of-Interest Selection Methods for Time Efficiency, Measurement Reproducibility, and Diagnostic Utility.

OBJECTIVES: This study aimed to explore the diagnostic ability of apparent diffusion coefficient (ADC) values obtained from different region of interest (ROI) measurements in tumor parenchyma for differentiating posterior fossa tumors (PFTs) and the correlations between ADC values and Ki-67. METHODS: Seventy-three pediatric patients with PFTs who underwent conventional diffusion-weighted imaging were recruited in this study. Five different ROIs were manually drawn by 2 radiologists (ROI-polygon, ROI-3 sections, ROI-3-5 ovals, ROI-more ovals, and ROI-whole). The interreader/intrareader repeatability, time required, diagnostic ability, and Ki-67 correlation analysis of the ADC values based on these ROI strategies were calculated. RESULTS: Both interreader and intrareader reliabilities were excellent for ADC values among the different ROI strategies (intraclass correlation coefficient, 0.899-0.992). There were statistically significant differences in time consumption among the 5 ROI selection methods ( P < 0.001). The time required for the ROI-3-5 ovals was the shortest (32.23 ± 5.14 seconds), whereas the time required for the ROI-whole was the longest (204.52 ± 92.34 seconds). The diagnostic efficiency of the ADC values showed no significant differences among the different ROI measurements ( P > 0.05). The ADC value was negatively correlated with Ki-67 ( r = -0.745 to -0.798, all P < 0.0001). CONCLUSIONS: The ROI-3-5 ovals method has the best interobserver repeatability, the shortest amount of time spent, and the best diagnostic ability. Thus, it is considered an effective measurement to produce ADC values in the evaluation of pediatric PFTs.

Phase frustration induced remote synchronization.

Remote synchronization (RS) may take an important role in brain functioning and its study has attracted much attention in recent years. So far, most studies of RS are focused on the Stuart-Landau oscillators with mean-field coupling. However, realistic cases may have more complicated couplings and behaviors, such as the brain networks. To make the study of RS a substantial progress toward realistic situations, we here present a model of RS with phase frustration and show that RS can be induced for those systems where no RS exists when there is no phase frustration. By numerical simulations on both the Stuart-Landau and Kuramoto oscillators, we find that the optimal range of RS depends on the match of phase frustrations between the hub and leaf nodes and a fixed relationship of this match is figured out. While for the non-optimal range of RS, we find that RS exists only in a linear band between the phase frustrations of the hub and leaf nodes. A brief theoretical analysis is provided to explain these results.

Chinese Guideline on Allergen Immunotherapy for Allergic Rhinitis: The 2022 Update.

In the last few decades, there has been a progressive increase in the prevalence of allergic rhinitis (AR) in China, where it now affects approximately 250 million people. AR prevention and treatment include allergen avoidance, pharmacotherapy, allergen immunotherapy (AIT), and patient education, among which AIT is the only curative intervention. AIT targets the disease etiology and may potentially modify the immune system as well as induce allergen-specific immune tolerance in patients with AR. In 2017, a team of experts from the Chinese Society of Allergy (CSA) and the Chinese Allergic Rhinitis Collaborative Research Group (C2AR2G) produced the first English version of Chinese AIT guidelines for AR. Since then, there has been considerable progress in basic research of and clinical practice for AIT, especially regarding the role of follicular regulatory T (TFR) cells in the pathogenesis of AR and the use of allergen-specific immunoglobulin E (sIgE) in nasal secretions for the diagnosis of AR. Additionally, potential biomarkers, including TFR cells, sIgG4, and sIgE, have been used to monitor the incidence and progression of AR. Moreover, there has been a novel understanding of AIT during the coronavirus disease 2019 pandemic. Hence, there was an urgent need to update the AIT guideline for AR by a team of experts from CSA and C2AR2G. This document aims to serve as professional reference material on AIT for AR treatment in China, thus improving the development of AIT across the world.

Estimation of Mycophenolic Acid Exposure in Chinese Renal Transplant Patients by a Joint Deep Learning Model.

BACKGROUND: To predict mycophenolic acid (MPA) exposure in renal transplant recipients using a deep learning model based on a convolutional neural network with bilateral long short-term memory and attention methods. METHODS: A total of 172 Chinese renal transplant patients were enrolled in this study. The patients were divided into a training group (n = 138, Ruijin Hospital) and a validation group (n = 34, Zhongshan Hospital). Fourteen days after renal transplantation, rich blood samples were collected 0-12 hours after MPA administration. The plasma concentration of total MPA was measured using an enzyme-multiplied immunoassay technique. A limited sampling strategy based on a convolutional neural network-long short-term memory with attention (CALS) model for the prediction of the area under the concentration curve (AUC) of MPA was established. The established model was verified using the data from the validation group. The model performance was compared with that obtained from multiple linear regression (MLR) and maximum a posteriori (MAP) methods. RESULTS: The MPA AUC 0-12 of the training and validation groups was 54.28 ± 18.42 and 41.25 ± 14.53 µg·ml -1 ·h, respectively. MPA plasma concentration after 2 (C 2 ), 6 (C 6 ), and 8 (C 8 ) hours of administration was the most significant factor for MPA AUC 0-12 . The predictive performance of AUC 0-12 estimated using the CALS model of the validation group was better than the MLR and MAP methods in previous studies (r 2 = 0.71, mean prediction error = 4.79, and mean absolute prediction error = 14.60). CONCLUSIONS: The CALS model established in this study was reliable for predicting MPA AUC 0-12 in Chinese renal transplant patients administered mycophenolate mofetil and enteric-coated mycophenolic acid sodium and may have good generalization ability for application in other data sets.

Integrated CNN and Federated Learning for COVID-19 Detection on Chest X-Ray Images.

Currently, Coronavirus Disease 2019 (COVID-19) is still endangering world health and safety and deep learning (DL) is expected to be the most powerful method for efficient detection of COVID-19. However, patients' privacy concerns prohibit data sharing between medical institutions, leading to unexpected performance of deep neural network (DNN) models. Fortunately, federated learning (FL), as a novel paradigm, allows participating clients to collaboratively train models without exposing source data outside original location. Nevertheless, the current FL-based COVID-19 detection methods prefer optimizing secondary objectives including delay, energy consumption and privacy, while few works focus on improving the model accuracy and stability. In this paper, we propose a federated learning framework with dynamic focus for COVID-19 detection on CXR images, named FedFocus. Specifically, to improve the training efficiency and accuracy, the training loss of each model is taken as the basis for parameter aggregation weights. As training layer deepens, a constantly updated dynamic factor is designed to stabilize the aggregation process. In addition, to highly restore the real dataset, the training sets in our experiments are divided based on the population and the infection of three real cities. Extensive experiments conducted on the real-world CXR images dataset demonstrate that FedFocus outperforms the baselines in model training efficiency, accuracy and stability.