Alzheimer’s disease (AD) is a slowly progressing and irreversible neurodegenerative disorder, and early diagnosis is critical for slowing its progression. Most deep learning algorithms and computer-aided diagnosis (CAD) methods for MRI focus on local feature extraction, but it is often difficult to effectively integrate global features and fine-grained details. At the same time, the high cost of training and deploying models remains a major challenge in the field. In this study, we propose a multi-kernel pyramid hybrid adaptive attention convolutional neural network (MKP-H2Anet), a lightweight network contributing to early AD diagnosis. Specifically, the proposed network uses a residual network as the backbone, integrating the multi-kernel pyramid (MKP) and hybrid adaptive attention (H2A) to improve feature extraction without increasing computational complexity. The MKP block is designed to capture detailed information on multiple scales flexibly. The H2A layer is proposed to enhance the importance of channels, focus on the feature region of prominent locations to model context information, and extract discriminative features. An extensive series of experimental evaluations of the MKP-H2ANet method was conducted on baseline MRI slices from 395 subjects in the public dataset. The outcomes of these evaluations indicated that the technique attained accuracies of 99.46% and 99.06% in binary classification tasks for AD vs. CN and CN vs. MCI, and 98.38% in the three-class classification of AD, CN, and MCI, validating its effectiveness in AD diagnosis.

Objective:Invasive lung adenocarcinoma（ILA） with micropapillary (MPP)/solid (SOL) components has a poor prognosis. Preoperative identification is essential for decision-making for subsequent treatment. This study aims to construct and evaluate a super-resolution（SR） enhanced radiomics model designed to predict the presence of MPP/SOL components preoperatively to provide more accurate and individualized treatment planning. Methods:Between March 2018 and November 2023, patients who underwent curative intent ILA resection were included in the study. We implemented a deep transfer learning network on CT images to improve their resolution, resulting in the acquisition of preoperative super-resolution CT (SR-CT) images. Models were developed using radiomic features extracted from CT and SR-CT images. These models employed a range of classifiers, including Logistic Regression (LR), Support Vector Machines (SVM), k-Nearest Neighbors (KNN), Random Forest, Extra Trees, Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Multilayer Perceptron (MLP). The diagnostic performance of the models was assessed by measuring the area under the curve (AUC). Result:A total of 245 patients were recruited, of which 109 (44.5 %) were diagnosed with ILA with MPP/SOL components. In the analysis of CT images, the SVM model exhibited outstanding effectiveness, recording AUC scores of 0.864 in the training group and 0.761 in the testing group. When this SVM approach was used to develop a radiomics model with SR-CT images, it recorded AUCs of 0.904 in the training and 0.819 in the test cohorts. The calibration curves indicated a high goodness of fit, while decision curve analysis (DCA) highlighted the model's clinical utility. Conclusion:The study successfully constructed and evaluated a deep learning（DL）-enhanced SR-CT radiomics model. This model outperformed conventional CT radiomics models in predicting MPP/SOL patterns in ILA. Continued research and broader validation are necessary to fully harness and refine the clinical potential of radiomics when combined with SR reconstruction technology.

This paper proposes a discriminative transfer feature learning method for MCI conversion prediction using data from the target domain and the auxiliary domain. A transfer component analysis method based on the Maximum Mean Discrepancy (MMD) is proposed at first, which is used to weaken the difference of data distribution between the relevant domain and the target domain. Next, the discriminant optimization term is added to measure the correlation between the sample categories and the sample features of the auxiliary domain, and to improve the inter-class separability of the algorithm. Finally, the support vector machine (SVM) is used to classify MCI patients.

Background and Objective: Accurate identification of suspected Coronavirus disease (COVID-19) cases is of great significance in controlling the spread of the disease and timely treatment. The main purpose of this study is to propose an effective diagnosis model to detect COVID-19.Methods: We propose an automated COVID-19 diagnosis process using Stacking-based integrated classification with a fusion-based feature extraction model, called LBP-DCNN. Firstly, the local binary pattern (LBP) algorithm is used to extract the detailed texture features of the CT image. The depth features are extracted using DenseNet201, a deep neural network pre-trained on the ImageNet dataset. Next, we use a parallel fusion method to fuse texture features and deep convolutional neural network (DCNN) features. Finally, propose a Stacking-based integrated classification method, selection of base learners and meta-learners through extensive experimentation. The performance of our proposed classification method is compared with other potential strategies and state-of-the-art models.Results: The proposed method was trained and tested on the prepared dataset, and the experimental results show that this approach achieves an overall accuracy of 99.27%, precision of 98.40% and sensitivity of 99.83%. In addition, the method outperformed 9 state-of-the-art COVID-19 detection methods.Conclusion: This study proposed a COVID-19 diagnosis model obtained promising results using first-line clinical imaging, and it can help radiologists to make accurate diagnoses based on CT images.

Anxiety and depression are important risk factors for chronic obstructive pulmonary disease (COPD). The aim of this study was to develop a prediction model to predict anxiety or depression in COPD patients. The retrospective study was conducted in COPD patients receiving stable treatment between 2018 and 2020 to develop prediction model. The variables, were readily available in clinical practice, were analysed. After data preprocessing, model training and performance evaluation were performed. Validity of the prediction model was verified in 3 comparative model training. Between 2018 and 2020, 375 eligible patients were analysed. Thirteen variables were included into the final model: gender, age, marital status, education level, long-term residence, per capita annual household income, payment method of medical expenses, direct economic costs of treating COPD in the past year, smoking, COPD progression, number of acute exacerbation of COPD in the last year, regular treatment with inhalants and family oxygen therapy. Risk score threshold in each sample in the training set was 1.414. The area under the curve value was respectively 0.763 and 0.702 in the training set and test set, which were higher than three comparative models. The simple prediction model to predict anxiety or depression in patients with COPD has been developed. Based on 13 available data in clinical indicators, the model may serve as an instrument for clinical decision-making for COPD patients who may have anxiety or depression.Key messagesThirteen variables were included into the prediction model.The AUC value was, respectively, 0.763 and 0.702 in the training set and test set, which were higher than three comparative models.The simple prediction model to predict anxiety or depression in patients with COPD has been developed.

Alzheimer's disease (AD) is the main cause of dementia in the elderly. To date, it remains largely unknown whether and how dynamic characteristics of the functional networks differ from cognitively normal (CN) to AD. Here, we propose an AD dynamic network complexity intelligent detecting algorithm based on visibility graph. The focal regions that caused the dynamic abnormality of the connection mode were intelligently detected by creating a dynamic complexity network on the basis of the dynamic functional network. The results showed that the brain areas with different dynamic complexity gradually shifted from the frontal lobe to the temporal lobe and the occipital lobe. This was significantly related to the disorder of clinical patients from mood to memory and language. The increased dynamic complexity illustrates the compensatory effect of the brain area of AD lesions. In addition, the small-world topological properties of the dynamic complexity network have significant differences from CN to AD. To the best of our knowledge, this is the first time that such a concept is proposed. Our method of intelligently detecting the complexity of AD dynamic network provides new insights for understanding the internal dynamic mechanism of AD brain.

Objective:To investigate the sleep quality of elderly patients with overlap syndrome (OS) of chronic obstructive pulmonary disease (COPD) and obstructive sleep apnea (OSA).Methods:166 elderly patients admitted to Zhejiang Hospital from February 2018 to February 2019 were selected, including 45 COPD patients (COPD group), 45 OSA patients (OSA group), 48 OS patients (OS group), and 28 healthy volunteers in the same period (healthy control group). The clinical data of all subjects were collected, Pittsburgh sleep quality index scale and polysomnography (PSG) were used to evaluate subjective and objective sleep quality. Univariate analysis of variance and rank sum test were used for comparison among multiple groups, LSD-t test and Bonferroni method were used for pairwise comparison, and counting data were compared by χ2 inspection.Results:There were significant differences in BMI, neck circumference, ESS score, percentage of forced expiratory volume in one second (FEV1) and FEV1/forced vital capacity (FVC) among the four groups (F=5.693, 12.804, 4.805, 195.050, 452.290, P < 0.01). The BMI of OS group and OSA group was significantly higher than that of healthy control group (P < 0.05), and the BMI of OS group was significantly higher than that of COPD group (P < 0.05). The neck circumference of OS group and OSA group was significantly higher than that of healthy control group and COPD group (P < 0.05). The ESS score of OS group and OSA group was significantly higher than that of healthy control group (P < 0.05), and the ESS score of OSA group was significantly higher than that of COPD group (P < 0.05). The FEV1% and FEV1/FVC in OS group and COPD group were significantly higher than those in healthy control group and OSA group (P < 0.05). There were significant differences in PSG monitoring indexes among the four groups (F=806.326, 59.965, 8.916, 24.168, 81.969, 15.666, P < 0.01). The apnea hypopnea index and the longest apnea time in OS group and OSA group were significantly higher than those in healthy control group and COPD group (P < 0.05). The apnea hypopnea index and the longest apnea time in OS group were significantly higher than those in OSA group (P < 0.05). The micro arousal index, mean blood oxygen saturation, minimum blood oxygen saturation and the percentage of blood oxygen saturation < 90% in the total monitoring time in OS group were significantly higher than those in other groups (P < 0.05). There were significant differences in other indexes except subjective total sleep time and objective sleep latency among the four groups (F=5.196, 6.470, 10.444, 6.785, 2.947, 8.591, 7.452, P < 0.05 or 0.01). The total time of subjective awakening and objective awakening after falling asleep in OS group, OSA group and COPD group were significantly higher than those in healthy control group (P < 0.05), and the subjective sleep efficiency, objective total sleep time and objective sleep efficiency were significantly lower than those in healthy control group (P<0.05).Conclusion:There is a significant decline in sleep quality in elderly patients with COPD and OSA overlap syndrome, which may be the cause and effect of sleep quality, affecting the course of the disease.

Diabetes mellitus is a group of complex metabolic disorders which has affected hundreds of millions of patients world-widely. The underlying pathogenesis of various types of diabetes is still unclear, which hinders the way of developing more efficient therapies. Although many genes have been found associated with diabetes mellitus, more novel genes are still needed to be discovered towards a complete picture of the underlying mechanism. With the development of complex molecular networks, network-based disease-gene prediction methods have been widely proposed. However, most existing methods are based on the hypothesis of guilt-by-association and often handcraft node features based on local topological structures. Advances in graph embedding techniques have enabled automatically global feature extraction from molecular networks. Inspired by the successful applications of cutting-edge graph embedding methods on complex diseases, we proposed a computational framework to investigate novel genes associated with diabetes mellitus. There are three main steps in the framework: network feature extraction based on graph embedding methods; feature denoising and regeneration using stacked autoencoder; and disease-gene prediction based on machine learning classifiers. We compared the performance by using different graph embedding methods and machine learning classifiers and designed the best workflow for predicting genes associated with diabetes mellitus. Functional enrichment analysis based on Human Phenotype Ontology (HPO), KEGG, and GO biological process and publication search further evaluated the predicted novel genes.

Objective:To investigate the effects of pulmonary rehabilitation on anxiety/depression and subjective/objective sleep quality of elderly patients with stable chronic obstructive pulmonary disease(COPD).Methods:From February 2018 to February 2019, 120 elderly patients with stable COPD were selected and randomly divided into the experimental group (pulmonary rehabilitation exercise combined with conventional COPD treatment) and the control group (simple COPD conventional treatment). Sixty cases in each group were intervened for 8 weeks. Before and after treatment, Hamilton anxiety scale (HAMA) was used to evaluate anxiety, Hamilton depression scale(HAMD)was used to evaluate depression, Pittsburgh sleep quality index(PSQI)and sleep log were used to evaluate subjective sleep quality, and objective sleep quality was monitored by multi-channel sleep monitor.SPSS 21.0 software was used to analyze and process the data. Chi square test, independent sample t test and paired t test were used for statistical analysis. Results:After 8 weeks of intervention, the HAMA and HAMD scores of the experimental group were lower than those of the control group (HAMA: (7.57±3.19) vs (10.15±4.89), t=-3.428, P=0.001; HAMD: (8.22±4.73) vs (10.60±6.49), t=-2.300, P=0.023). COPD patients with anxiety decreased (χ 2=7.566, P=0.006). After treatment, the subjective sleep latency of the experimental group was shorter than that of the control group ((42.00±9.88)min vs (47.25±10.27)min, t=-2.854, P=0.005). The subjective sleep efficiency was higher than that of the control group ((76.00±4.50)% vs (74.00±5.20)%, t=2.272, P=0.025), and the objective sleep latency was shorter than that of the control group ((28.02±5.59)min vs (32.95±6.21)min, t=-4.575, P<0.05). Conclusion:Pulmonary rehabilitation exercise can improve the anxiety and depression of elderly patients with stable COPD, and improve the subjective and objective sleep quality.

Accurate classification of Alzheimer's disease (AD) and its prodromal stage mild cognitive impairment (MCI) play key roles in computer-assisted intervention for the diagnosis of AD. However, not all features of AD data will lead to a good classification result, because there are always some unrelated and redundant features. To solve this problem, an adaptive LASSO logistic regression model based on particle swarm optimization(PSO-ALLR)is proposed. This algorithm consists of two stages. In the first stage, the particle swarm optimization (PSO) algorithm is used for global search to remove redundant features and reduces the computational time for the later stage. In the second stage, the adaptive LASSO serves as a local search to select the most relevant features for AD classification.We evaluate the performance of the proposed method on 197 subjects from the baseline MRI data of ADNI database. The proposed method achieves a classification accuracy of 96.27%, 84.81%, and 76.13%, for AD vs. HC, MCI vs. HC, and cMCI vs. sMCI, respectively.

目的 探讨自噬抑制剂3-甲基腺嘌呤对荜茇酰胺抗肿瘤作用的影响.方法 实验分为对照组:采用生理盐水处理A549细胞48h;荜茇酰胺组:3μM荜茇酰胺处理细胞48h;荜茇酰胺+N-乙酰-L-半胱氨酸(NAC)组:3μM荜茇酰胺和10mM NAC处理细胞48h;3-甲基腺嘌呤+荜茇酰胺组:3μM荜茇酰胺和3mM 3-甲基腺嘌呤处理细胞48h.采用CCK-8法测定细胞活力,使用流式细胞仪测定细胞内活性氧(ROS)水平,蛋白质印迹法检测细胞自噬蛋白(LC3B)表达.结果 3μM荜茇酰胺处理A549细胞后,细胞ROS水平显著升高至(1.49±0.18)(P<0.05),细胞活力显著下降至(60.1±10.2)％(P<0.05),LC3B-II表达显著增加(P<0.05).荜茇酰胺与10mM NAC合用后,细胞ROS水平为(0.98±0.04),细胞活力为(97.7±4.0)％,LC3B-II表达下降至用药前水平(P<0.05).自噬抑制剂3-甲基腺嘌呤处理肺癌细胞后,LC3B-II表达显著降低.3-甲基腺嘌呤+荜茇酰胺组A549细胞活力为(24.8±1.3)％,显著低于荜茇酰胺组(60.1±10.2)％(P<0.05).结论 荜茇酰胺通过ROS依赖途径促进A549细胞自噬.自噬抑制剂3-甲基腺嘌呤可增强荜茇酰胺的抗肿瘤作用.

Objective To investigate the relationship between homocysteine level and cognitive function in elderly patients with severe obstructive sleep apnea syndrome (OSAS). Methods 30 elderly patients with severe OSAS and 30 controls were recruited from October 2017 to April 2018 in Zhejiang Hospital, they were monitored by polysomnography (PSG) , serum HCY levels were tested, cognitive function was measured by mini mental state examination (MMSE). The apnea hypopnea index (AHI), minimum oxygen saturation (LSO2), mean oxygen saturation (MSO2), MMSE score and HCY level were compared between the two groups, and correlation analysis was performed. The T test was used for comparison between groups, and the correlation was analyzed by Pearson correlation analysis. Results The levels of AHI and HCY in OSAS patients were significantly higher than those in controls (t=29.169, 4.132, P 0.05), and there was no significant correlation between MMSE score and HCY level (r=0.203, P>0.05). Conclusion Cognitive impairment in elderly patients with OSAS is caused by multiple factors and links, the increased HCY level may be one of the risk factors. Key words: obstructive sleep apnea syndrome; homocysteine; cognitive function; aged

阻塞性睡眠呼吸暂停(obstructive sleep apnea, OSA)是由于患者睡眠时上气道完全或部分阻塞,导致呼吸暂停和睡眠结构紊乱、引起夜间反复低氧血症和高碳酸血症.根据其临床症状,归属于中医"鼾症"范畴.隋代巢元方《诸病源候论·鼾眠候》首次将鼾症作为一个独立病证,认为痰湿内生是其重要的发病因素.

目的 探讨气道持续正压通气(CPAP)对阻塞性睡眠呼吸暂停低通气综合征(OSAHS)伴认知功能障碍患者的疗效和血同型半胱氨酸(Hcy)水平的影响.方法 对经多导睡眠仪监测、蒙特利尔认知评估量表(MoCA)和简易智精神能量表(MMSE)确诊的中重度OSAHS伴认知功能障碍患者50例给予CPAP治疗6个月,比较治疗前后MoCA评分、MMSE评分和血Hcy水平.结果 与治疗前比较,治疗后患者MoCA评分、MMSE评分均明显改善,血Hcy水平明显降低,差异均有统计学意义(均P＜0.01).血Hcy水平降低化值与MMSE改善值、MoCA改善值均呈正相关(r=0.55和0.53,均P＜0.05).结论 CPAP能改善OSAHS伴认知功能障碍患者的认知功能,其机制可能与降低血Hcy水平有关.

孔子有云:食不语,寝不言.这句话中更多的含义是希望后人从行为细节上讲究"礼"的教导,实际上也有现实意义:吃饭时如果分散注意力去说话、做其他事,就会增加发生意外的风险. 吃虾从不靠手剥 这回却误入"气"途 近日,37岁的于女士就因为口中含着一只虾与家人说话时,误将这只虾连壳带肉吸进了气管,多方医生利用支气管镜及时治疗,这才化险为夷.

The study was conducted to test the hypothesis that oxidative stress leads to the release of proinflammatory cytokines by activating the Nod-like receptor protein (NLRP)3 inflammasome in patients with obstructive sleep apnoea (OSA).

目的 探讨荜茇酰胺对Kirsten鼠肉瘤病毒癌基因(KRAS)突变肺腺癌细胞增殖和凋亡的影响.方法 使用不同浓度梯度的荜茇酰胺干预KRAS突变肺腺癌细胞A549,然后采用CCK-8法检测A549细胞活力,Annexin V-FITC和PI双染色法检测细胞凋亡率,Western blot法检测细胞凋亡相关蛋白PARP、BCL2和自噬相关蛋白LC3B的表达水平.结果 荜茇酰胺干预A549细胞后,细胞活力降低,细胞凋亡率升高,且荜茇酰胺浓度越高,细胞活力越低,细胞凋亡率越高.荜茇酰胺可上调细胞PARP、LC3BⅡ表达水平,下调BCL2表达水平.结论 荜茇酰胺可抑制KRAS突变肺腺癌细胞增殖,诱导细胞凋亡,或可成为治疗KRAS突变肺腺癌的新靶向药物.

The aim of the current study was to assess the underlying mechanism of endoplasmic reticulum protein 29 (ERp29) in lung adenocarcinoma chemosensitivity to gemcitabine. Western blot analysis was performed to detect ERp29 expression following lung adenocarcinoma cell treatment with gemcitabine. The effects of gemcitabine in combination with ERp29 siRNA on cell apoptosis, cell cycle and heat shock protein 27 (HSP27) expression were assessed. The results demonstrated that ERp29 expression was increased on exposure to gemcitabine. The apoptotic rate of lung adenocarcinoma cells were also increased following gemcitabine treatment and the combined application of gemcitabine and ERp29 siRNA synergistically increased apoptotic rates further. It was also revealed that gemcitabine and ERp29 siRNA synergistically increased the ratio of phosphorylated to total HSP27 protein. In addition, downregulation of HSP27 significantly reduced lung adenocarcinoma chemosensitivity to gemcitabine. These data indicate that ERp29 affects lung adenocarcinoma cell chemosensitivity to gemcitabine by regulating phosphorylated HSP27. ERp29 is a novel target, which may be used to enhance the therapeutic effect of lung adenocarcinoma treatment with gemcitabine.

The present study aimed to examine how the long non‑coding RNA (lncRNA) RP11‑543N12.1 interacted with microRNA (miR)‑324‑3p to modify microglials (MIs)‑induced neuroblastoma cell apoptosis, which may pose benefits to the treatment of Alzhemier's disease (AD). The cell model of AD was established by treating SH‑SY5Y cells with amyloid β (Aβ)25‑35, and MI were acquired using primary cell culture technology. The lncRNAs that were differentially expressed between SH‑SY5Y and control cells were screened through a microarray assay and confirmed via polymerase chain reaction. In addition, overexpression of RP11‑543N12.1 and miR‑324‑3p was established by transfection of SH‑SY5Y cells with pcDNA3.1(+)‑RP11‑543N12.1 and miR‑324‑3p mimics, respectively, while downregulation of RP11‑543N12.1 and miR‑324‑3p was achieved by transfection with RP11‑543N12.1‑small interfering RNA (siRNA) and miR‑324‑3p inhibitor, respectively. The interaction between RP11‑543N12.1 and miR‑324‑3p was confirmed with a dual‑luciferase reporter gene assay. The results revealed that the expression levels of total and phosphorylated tau in SH‑SY5Y cells were significantly elevated following Aβ25‑35 treatment (P<0.05), and RP11‑543N12.1 was found to be differentially expressed between the control and Aβ25‑35‑treated cells (P<0.05). Furthermore, the targeted association of RP11‑543N12.1 and miR‑324‑3p was predicted based on miRDB4.0 and PITA databases, and then validated via the dual‑luciferase reporter gene assay. SH‑SY5Y cells transfected with siRNA or inhibitor, and treated with Aβ25‑35 displayed cellular survival and apoptosis that were similar to the normal levels (P<0.05). Finally, co‑culture of MI and SH‑SY5Y cells transfected with RP11‑543N12.1‑siRNA/miR‑324‑3p inhibitor significantly enhanced cell apoptosis (P<0.05). In conclusion, RP11‑543N12.1 targeted miR‑324‑3p to suppress proliferation and promote apoptosis in the AD cell model, suggesting that RP11‑543N12.1 and miR‑324‑3p may be potential biomarkers and therapeutic targets for AD.