Search

Abstract Diagnosing pneumoconiosis is challenging because the lesions are not easily visible on chest X-rays, and the images often lack clear details. Existing deep detection models utilize Feature Pyramid Networks (FPNs) to identify objects at different scales. However, they struggle with insufficient perception of small targets and gradient inconsistency in medical image detection tasks, hindering the full utilization of multi-scale features. To address these issues, we propose an Optimized Multi-Scale Feature Fusion learning framework, OMSF2, which includes the following components: (1) Data specificity augmentation module is introduced to capture intrinsic data representations and introduce diversity by learning morphological variations and lesion locations. (2) Multi-scale feature learning module is utilized that refines micro-feature localization guided by heatmaps, enabling full extraction of multi-directional features of subtle diffuse targets. (3) Multi-scale feature fusion module is employed that facilitates the fusion of high-level and low-level features to better understand subtle differences between disease stages. Notably, this paper innovatively proposes a method for fine learning of low-resolution micro-features in pneumoconiosis, addressing the issue of maintaining cross-layer gradient consistency under multi-scale feature fusion. We established an enhanced pneumoconiosis X-ray dataset to optimize the lesion detection capability of the OMSF2 model. We also introduced an external dataset to evaluate other chest X-rays with complex lesions. On the AP-50 and R-50 evaluation metrics, OMSF2 improved by 3.25% and 3.31% on the internal dataset, and by 2.28% and 0.24% on the external dataset, respectively. Experimental results show that OMSF2 achieves significantly better performance than state-of-the-art baselines in medical image detection tasks. more...

BackgroundCognitive impairment is an important public health challenge among older adults, particularly in long-term care facilities (LTCFs), where prevalence is higher due to staffing shortages, limited resources, and difficulty maintaining structured exercise programs. Furthermore, older adults often lose interest in repetitive interventions. The exergame “WarioWare: Move It!” (Nintendo) offers a novel solution by combining aerobic exercise, motor coordination, balance training, and cognitive engagement into an immersive experience. ObjectiveThis study aimed to assess the clinical efficacy of an exergame-based training program delivered via “WarioWare: Move It!” in improving physical flexibility, joint range of motion, motor coordination, hand dexterity, and cognitive function in older adults living in LTCFs. MethodsThe training program was conducted across multiple rural LTCFs in Shanxi Province, China. Participants were randomly assigned to the intervention or control group. The intervention protocol encompassed two 60-minute sessions per week over 12 weeks, using motion-sensing exercises such as waving, jumping, arm swinging, rotational movements, and object-mimicking postures with Joy-Con controllers. Primary outcome measures were derived through clinical tests, including the sit and reach test, shoulder flexibility test, trunk rotation flexibility test, shoulder and elbow range of motion, figure-of-8 walk test, standing balance test, hand dexterity test, and cognitive function tests. Statistical analysis was performed using mixed ANOVA, with time as the within-participant factor and intervention group as the between-participant factor, to assess the training effects on the various outcome measures. ResultsA total of 232 participants were recruited, including 32 (13.8%) patients with mild dementia, 18 (7.8%) with moderate dementia, and 182 (78.4%) with mild cognitive impairment, all of whom completed the study. The mixed ANOVA revealed significant group × time interactions across multiple physical flexibility assessments, including the remaining distance between the hands and toes during the forward bend (F2,156=8.484; P more...

BackgroundThe prompt and accurate identification of mild cognitive impairment (MCI) is crucial for preventing its progression into more severe neurodegenerative diseases. However, current diagnostic solutions, such as biomarkers and cognitive screening tests, prove costly, time-consuming, and invasive, hindering patient compliance and the accessibility of these tests. Therefore, exploring a more cost-effective, efficient, and noninvasive method to aid clinicians in detecting MCI is necessary. ObjectiveThis study aims to develop an ensemble learning framework that adaptively integrates multimodal physiological data collected from wearable wristbands and digital cognitive metrics recorded on tablets, thereby improving the accuracy and practicality of MCI detection. MethodsWe recruited 843 participants aged 60 years and older from the geriatrics and neurology departments of our collaborating hospitals, who were randomly divided into a development dataset (674/843 participants) and an internal test dataset (169/843 participants) at a 4:1 ratio. In addition, 226 older adults were recruited from 3 external centers to form an external test dataset. We measured their physiological signals (eg, electrodermal activity and photoplethysmography) and digital cognitive parameters (eg, reaction time and test scores) using the clinically certified Empatica 4 wristband and a tablet cognitive screening tool. The collected data underwent rigorous preprocessing, during which features in the time, frequency, and nonlinear domains were extracted from individual physiological signals. To address the challenges (eg, the curse of dimensionality and increased model complexity) posed by high-dimensional features, we developed a dynamic adaptive feature selection optimization algorithm to identify the most impactful subset of features for classification performance. Finally, the accuracy and efficiency of the classification model were improved by optimizing the combination of base learners. ResultsThe experimental results indicate that the proposed MCI detection framework achieved classification accuracies of 88.4%, 85.5%, and 84.5% on the development, internal test, and external test datasets, respectively. The area under the curve for the binary classification task was 0.945 (95% CI 0.903-0.986), 0.912 (95% CI 0.859-0.965), and 0.904 (95% CI 0.846-0.962) on these datasets. Furthermore, a statistical analysis of feature subsets during the iterative modeling process revealed that the decay time of skin conductance response, the percentage of continuous normal-to-normal intervals exceeding 50 milliseconds, the ratio of low-frequency to high-frequency (LF/HF) components in heart rate variability, and cognitive time features emerged as the most prevalent and effective indicators. Specifically, compared with healthy individuals, patients with MCI exhibited a longer skin conductance response decay time during cognitive testing (P more...

ObjectiveIn order to reduce the price and increase the accessibility of innovative medicines, China has implemented the National Drug Price Negotiation (NDPN) since 2016. Anticancer drug is the largest category of NDPN and the number continue to increase. This study evaluated the impact of this policy on the price, utilization rate and affordability of anticancer drugs based on the experiences of Shandong province.Methods25 anticancer drugs were included in this study involved the NDPN in the year 2018 and 2019. Data on prices and utilization of the policy related drugs from 2017 to 2022 were collected from Shandong Province, using an adaptation of the WHO/HAI methodology. Prices were measured as Median Price Ratio (MPR). Usage was measured as Defined Daily Doses (DDDs). Affordability was measured as days of daily per capita disposable income required for the cost of 1 month’s treatment. The Mann–Whitney U test was used to estimate the significance of the difference in the change in the MPRs before and after the negotiation.ResultsThe data of this study come from 42 key monitoring medical institutions in Shandong Province, including 31 tertiary medical institutions and 11 secondary medical institutions. There has been a significant reduction in the MPR following NDPN, with a median MPR of 0.57 in 2022, and the prices of anticancer medicines were generally lower than IPR. During the period from 2017 to 2022, the total usage of the 25 negotiated medicines continued to rise. With the implementation of negotiation policy, the average number of days of disposable income per capita required for 1 month of medicine costs changed from 104 days to 36 days and 256 days to 80 days for urban and rural residents, respectively. The affordable proportion of anticancer medicines is still not high.ConclusionThe NDPN policy has reduced the prices of anticancer drugs and greatly improved their affordability. More attention should be paid to improve the affordability to the rural and the poor patients. It is essential to encourage the research and development of high-quality generic drugs to strengthen reasonable market competition, as well as improve the multi-tiered medical security system. more...

Abstract Drug combination therapy is generally more effective than monotherapy in the field of cancer treatment. However, screening for effective synergistic combinations from a wide range of drug combinations is particularly important given the increase in the number of available drug classes and potential drug-drug interactions. Existing methods for predicting the synergistic effects of drug combinations primarily focus on extracting structural features of drug molecules and cell lines, but neglect the interaction mechanisms between cell lines and drug combinations. Consequently, there is a deficiency in comprehensive understanding of the synergistic effects of drug combinations. To address this issue, we propose a drug combination synergy prediction model based on multi-source feature interaction learning, named MFSynDCP, aiming to predict the synergistic effects of anti-tumor drug combinations. This model includes a graph aggregation module with an adaptive attention mechanism for learning drug interactions and a multi-source feature interaction learning controller for managing information transfer between different data sources, accommodating both drug and cell line features. Comparative studies with benchmark datasets demonstrate MFSynDCP's superiority over existing methods. Additionally, its adaptive attention mechanism graph aggregation module identifies drug chemical substructures crucial to the synergy mechanism. Overall, MFSynDCP is a robust tool for predicting synergistic drug combinations. The source code is available from GitHub at https://github.com/kkioplkg/MFSynDCP . more...

Introduction Smoking is an independent and modifiable risk factor for the onset and development of psoriasis; however, evidence on the association between tobacco smoking and psoriasis treatment efficacy is limited. This study aimed to explore the influence of smoking on treatment efficacy in a cohort of patients with psoriasis in Shanghai, China. Methods Patients with psoriasis were recruited from the Shanghai Skin Disease Hospital between 2021 and 2022. The treatment for patients with psoriasis includes acitretin, methotrexate, narrow-band ultraviolet/benvitimod, and biologics. Data were collected using a structured questionnaire, physical examination, and disease severity estimation at baseline, week four, and week eight. The achievement of a ≥75% reduction in psoriasis area and severity index (PASI 75 ) score from baseline to week 8 was set as the primary outcome for treatment efficacy estimation. Data were analyzed using SAS 9.4. Results A total of 560 patients with psoriasis were enrolled in this study, who were predominantly males (72.9%). The average age of patients was 48.4 years, and 38.8% of them were current smokers, 5.0% of them were former smokers. The median score of PASI among patients changed from 11.1 (interquartile range, IQR: 7.9–16.6) at baseline to 6.2 at week 4 and 3.1 at week 8, and 13.8% and 47.3% of patients with psoriasis achieved PASI 75 at weeks 4 and 8, respectively. Logistic regression indicated that patients without tobacco smoking had a higher proportion of PASI 75 achievement at week 8. The adjusted odds ratio (AOR) was 11.43 (95% CI: 6.91–18.89), 14.14 (95% CI: 8.27–24.20), and 3.05 (95% CI: 1.20–7.76) for non-smokers compared with smokers, current smokers, and former smokers, respectively. Moreover, former smokers had higher PASI 75 achievement than current smokers (AOR=3.37), and patients with younger smoking initiation age, longer smoking duration, and higher smoking intensity had lower PASI 75 achievement. Conclusions Tobacco smoking was negatively associated with PASI 75 achievement both in current and former smokers, and former smokers had higher PASI 75 achievement than current smokers. The implementation of tobacco control measures is beneficial for improving treatment responses. more...

ObjectiveShared decision-making (SDM) is a collaborative process in which patients and healthcare providers jointly make a medical decision. This cross-sectional study aimed to identify the implementation status of shared decision-making among dermatologists engaging in medical esthetics in China and to identify factors associated with the good practice of SDM among them.MethodsFrom January to June 2023, a total of 1,287 dermatologists engaging in medical esthetics in China were recruited and completed the online interviews about their implementation of SDM based on the Shared Decision-Making Questionnaire for Doctors (SDM-Q-Doc). Logistic regression was used to calculate the odds ratio (OR) and 95% confidence interval (CI) to explore factors associated with the higher SDM score achievement among dermatologists with medical esthetic practice.ResultsThe median value of the total SDM score was 39, and 48% (621/1278) of dermatologists with medical esthetic practice achieved at least 40 out of 45 scores. Logistic regression indicated that dermatologists aged 40–49 or ≥ 50 years and those engaging in medical esthetic practice for ≥5 years were more likely to achieve at least 40 out of 45 scores compared to dermatologists aged more...

Abstract Background Pancreatic cancer (PCA) is an extremely aggressive malignant cancer with an increasing incidence and a low five‐year survival rate. The main reason for this high mortality is that most patients are diagnosed with PCA at an advanced stage, missing early treatment options and opportunities. As important nutrients of the human body, trace elements play an important role in maintaining normal physiological functions. Moreover, trace elements are closely related to many diseases, including PCA. Review This review systematically summarizes the latest research progress on selenium, copper, arsenic, and manganese in PCA, elucidates their application in PCA, and provides a new reference for the prevention, diagnosis and treatment of PCA. Conclusion Trace elements such as selenium, copper, arsenic and manganese are playing an important role in the risk, pathogenesis, diagnosis and treatment of PCA. Meanwhile, they have a certain inhibitory effect on PCA, the mechanism mainly includes: promoting ferroptosis, inducing apoptosis, inhibiting metastasis, and inhibiting excessive proliferation. more...

An accurate ultra-short-term time series prediction of a power load is an important guarantee for power dispatching and the safe operation of power systems. Problems of the current ultra-short-term time series prediction algorithms include low prediction accuracy, difficulty capturing the local mutation features, poor stability, and others. From the perspective of series decomposition, a multi-scale sequence decomposition model (TFDNet) based on power spectral density and the Morlet wavelet transform is proposed that combines the multidimensional correlation feature fusion strategy in the time and frequency domains. By introducing the time-frequency energy selection module, the "prior knowledge" guidance module, and the sequence denoising decomposition module, the model not only effectively delineates the global trend and local seasonal features, completes the in-depth information mining of the smooth trend and fluctuating seasonal features, but more importantly, realizes the accurate capture of the local mutation seasonal features. Finally, on the premise of improving the forecasting accuracy, single-point load forecasting and quantile probabilistic load forecasting for ultra-short-term load forecasting are realized. Through the experiments conducted on three public datasets and one private dataset, the TFDNet model reduces the mean square error (MSE) and mean absolute error (MAE) by 19.80 and 11.20% on average, respectively, as compared with the benchmark method. These results indicate the potential applications of the TFDNet model. more...

Abstract Novel methods are required to enhance lung cancer detection, which has overtaken other cancer-related causes of death as the major cause of cancer-related mortality. Radiologists have long-standing methods for locating lung nodules in patients with lung cancer, such as computed tomography (CT) scans. Radiologists must manually review a significant amount of CT scan pictures, which makes the process time-consuming and prone to human error. Computer-aided diagnosis (CAD) systems have been created to help radiologists with their evaluations in order to overcome these difficulties. These systems make use of cutting-edge deep learning architectures. These CAD systems are designed to improve lung nodule diagnosis efficiency and accuracy. In this study, a bespoke convolutional neural network (CNN) with a dual attention mechanism was created, which was especially crafted to concentrate on the most important elements in images of lung nodules. The CNN model extracts informative features from the images, while the attention module incorporates both channel attention and spatial attention mechanisms to selectively highlight significant features. After the attention module, global average pooling is applied to summarize the spatial information. To evaluate the performance of the proposed model, extensive experiments were conducted using benchmark dataset of lung nodules. The results of these experiments demonstrated that our model surpasses recent models and achieves state-of-the-art accuracy in lung nodule detection and classification tasks. more...

Vehicle-to-Vehicle (V2V) energy trading has emerged as a promising scheme to relieve the load imposed on the grid without intermediaries. The blockchain has always been regarded as the most potential solution for addressing the security and privacy issues of the Internet of Electric Vehicles (IoEV). The consensus mechanism is the core of the blockchain, it determines the security, efficiency, and scalability of the system. However, consensus mechanisms currently employed in V2V energy trading are traditional algorithms, which are unsuitable for the IoEV due to their high computational power and communication overhead. Therefore, we are motivated to propose a Block Alliance Consensus (BAC) mechanism based on Hashgraph. BAC can maintain the high throughput of the Hashgraph, and it solves the problem that the Hashgraph cannot support the dynamic addition and deletion of nodes if it is directly applied to V2V energy trading. We utilize the sharding technique, and each shard generates a consortium blockchain in accordance with the characteristic of the IoEV. The centralized component is retained to ensure macroeconomic control by state and local governments. We design a cryptography-based leader election combined with a reputation incentive mechanism to fairly elect centralized leader committee and motivate honest electric vehicles (EVs). We implement the BAC consensus and V2V energy trading blockchain (ETB) on the Hyperledger Fabric. The performance and practicality of BAC and the V2V ETB are verified through experiments. more...

Abstract The emergence of image-based systems to improve diagnostic pathology precision, involving the intent to label sets or bags of instances, greatly hinges on Multiple Instance Learning for Whole Slide Images(WSIs). Contemporary works have shown excellent performance for a neural network in MIL settings. Here, we examine a graph-based model to facilitate end-to-end learning and sample suitable patches using a tile-based approach. We propose MIL-GNN to employ a graph-based Variational Auto-encoder with a Gaussian mixture model to discover relations between sample patches for the purposes to aggregate patch details into an individual vector representation. Using the classical MIL dataset MUSK and distinguishing two lung cancer sub-types, lung cancer called adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC), we exhibit the efficacy of our technique. We achieved a 97.42% accuracy on the MUSK dataset and a 94.3% AUC on the classification of lung cancer sub-types utilizing features. more...

BackgroundEarly detection of cognitive impairment or dementia is essential to reduce the incidence of severe neurodegenerative diseases. However, currently available diagnostic tools for detecting mild cognitive impairment (MCI) or dementia are time-consuming, expensive, or not widely accessible. Hence, exploring more effective methods to assist clinicians in detecting MCI is necessary. ObjectiveIn this study, we aimed to explore the feasibility and efficiency of assessing MCI through movement kinetics under tablet-based “drawing and dragging” tasks. MethodsWe iteratively designed “drawing and dragging” tasks by conducting symposiums, programming, and interviews with stakeholders (neurologists, nurses, engineers, patients with MCI, healthy older adults, and caregivers). Subsequently, stroke patterns and movement kinetics were evaluated in healthy control and MCI groups by comparing 5 categories of features related to hand motor function (ie, time, stroke, frequency, score, and sequence). Finally, user experience with the overall cognitive screening system was investigated using structured questionnaires and unstructured interviews, and their suggestions were recorded. ResultsThe “drawing and dragging” tasks can detect MCI effectively, with an average accuracy of 85% (SD 2%). Using statistical comparison of movement kinetics, we discovered that the time- and score-based features are the most effective among all the features. Specifically, compared with the healthy control group, the MCI group showed a significant increase in the time they took for the hand to switch from one stroke to the next, with longer drawing times, slow dragging, and lower scores. In addition, patients with MCI had poorer decision-making strategies and visual perception of drawing sequence features, as evidenced by adding auxiliary information and losing more local details in the drawing. Feedback from user experience indicates that our system is user-friendly and facilitates screening for deficits in self-perception. ConclusionsThe tablet-based MCI detection system quantitatively assesses hand motor function in older adults and further elucidates the cognitive and behavioral decline phenomenon in patients with MCI. This innovative approach serves to identify and measure digital biomarkers associated with MCI or Alzheimer dementia, enabling the monitoring of changes in patients’ executive function and visual perceptual abilities as the disease advances. more...

Abstract Recently, lung cancer prediction based on imaging genomics has attracted great attention. However, such studies often have many challenges, such as small sample size, high-dimensional information redundancy, and the inefficiency of multimodal fusion. Therefore, in this paper, a deep convolution cascade attention fusion network (DCCAFN) based on imaging genomics is proposed for the prediction of lung cancer patients’ survival. The network consists of three modules: an image feature extraction module (IFEM), a gene feature extraction module (GFEM), and an attention fusion network (AFN). In the IFEM, a pretrained residual network based on transfer learning is used to extract deep image features to fully capture the computed tomography (CT) image information conducive to prognosis prediction. In the GFEM, the F-test is first used for gene screening to eliminate redundant information, and then, a cascade network with the convolution cascade module (CCM) that contains a convolution operation, a pooling operation, and an ensemble forest classifier is designed to better extract the gene features. In the AFN, a bimodal attention fusion mechanism is proposed to fuse deep image features and gene features to improve the performance of predicting lung cancer survival. The experimental results show that the DCCAFN model achieves good performance, and its accuracy and AUC are 0.831 and 0.816, respectively. It indicates that the model is an effective multimodal data fusion method for predicting the survival prognosis of lung cancer, which can greatly help physicians stratify patients' risks, and achieve personalized treatment for improving the quality of patients' lives. more...

Abstract Aiming at the problems of long time, high cost, invasive sampling damage, and easy emergence of drug resistance in lung cancer gene detection, a reliable and non-invasive prognostic method is proposed. Under the guidance of weakly supervised learning, deep metric learning and graph clustering methods are used to learn higher-level abstract features in CT imaging features. The unlabeled data is dynamically updated through the k-nearest label update strategy, and the unlabeled data is transformed into weak label data and continue to update the process of strong label data to optimize the clustering results and establish a classification model for predicting new subtypes of lung cancer imaging. Five imaging subtypes are confirmed on the lung cancer dataset containing CT, clinical and genetic information downloaded from the TCIA lung cancer database. The successful establishment of the new model has a significant accuracy rate for subtype classification (ACC = 0.9793), and the use of CT sequence images, gene expression, DNA methylation and gene mutation data from the cooperative hospital in Shanxi Province proves the biomedical value of this method. The proposed method also can comprehensively evaluate intratumoral heterogeneity based on the correlation between the final lung CT imaging features and specific molecular subtypes. more...

An ultrasonic thyroid nodule segmentation model based on conditional segmentation adversarial network (cSegAN) was proposed to achieve more accurate segmentation of thyroid nodules. The model is composed of two parts: a segmenter network and a discriminator network. The segmenter network design uses a multi-expansion rate convolution block to accurately locate the nodule area, learn to extract the depth and shallow feature information of the nodule, and obtain binary mask of nodule area; the discriminator network compares the gap between the segmentation result and the gold standard to evaluate the segmentation result. Through multiple adversarial training, the experimental results show that the pixel accuracy of the proposed model reaches 0.953 1, which is better than other segmentation models, and can achieve ultrasonic thyroid nodule segmentation more accurately. more...

As the traditional power drive circuit is difficult to meet the requests of high-power high-frequency proportional solenoid fast drive, this paper proposes a push-pull energy storage pulse width modulation (PWM) power drive circuit. The circuit is equipped with an energy storage module, which releases energy when the proportional solenoid coil is charged, supplements the output of the power supply current, and shortens the arrival time of the steady-state current. When the coil is discharged, it recovers energy and shortens the time for the coil current to return to zero. In this paper, a theoretical model of push-pull energy storage power drive circuit is established, and simulation analysis and experimental verification are carried out for a proportional solenoid coil with rated current of 3.3A and power of 79W. The results show that the push-pull storage PWM power drive has excellent input-output linearity, minimal ripple, and good steady-state current output performance. Compared with the traditional single switch and reverse discharging power drives, the coil charging speed under the push-pull energy storage type power drive is increased by 25%, and the discharge speed is increased by 95% and 45% respectively. more...

Under the usage of new technologies, Internet of Things (IoT) develops rapidly and provides a great convenience for our lives. It is critical for ensuring security to IoT systems as the tremendous growth of IoT applications. Although many cryptography tools (such as identity-based encryption) have been given to provide appropriate security in IoT covering various application fields such as smart home, how to guarantee data confidentiality, provide reasonable data source identification, and resist quantum attacks simultaneously has been a challenging problem. To address this problem, we propose a matchmaking encryption scheme named lattice-based matchmaking identity-based encryption (LMIBE) which can provide bilateral access control for both sender and receiver in IoT systems, and resist quantum attacks. Moreover, we give a formal definition and a security definition for our scheme. Security proof shows that our scheme is secure under the proposed security definition. Finally, by comparing the performance of our scheme with existing works, our proposed scheme has a broad application prospect in IoT environment. more...

The generation of Traditional Chinese Medicine (TCM) prescription is one of the most challenging tasks in the research of intelligent TCM. Current researches usually use transfer learning methods to apply the relevant technology of text generation to this task simply and roughly. Either they need to train a model with large number of standardized data set, or they ignore the domain knowledge and expertise of TCM. In order to solve these problems, we propose a hybrid neural network architecture for TCM prescription generation—PreGenerator. It includes a novel hierarchical retrieval mechanism, which can automatically extract prescription and herbal templates to facilitate accurate clinical prescription generation. Firstly, PreGenerator uses the Symptom-Prescription Retrieval (SHR) module to retrieve the most relevant prescriptions for a given patient’s symptoms. In order to follow the rule of compatibility of herbs, the Herb-Herb Retrieval (HHR) module is introduced to retrieve the next most relevant herb according to the conditioned generated herbs. Finally, the prescription decoder (PreD) fuses the symptom features, the retrieved prescription and herbal template features to generate the most relevant and effective Chinese medicine prescription. The validity of the model is verified by automatic evaluation and manual evaluation on the real medical case dataset. In addition, our model can recommend herbs that do not appear on the prescription label but are useful for relieving symptoms, which shows that our model can learn some interactions between herbs and symptoms. This research also lays a foundation for the future research on intelligent query and prescription generation of traditional Chinese medicine. more...

Computed tomography (CT) is a medical image widely used in clinical medicine that visualizes the fine structural details inside human body. In clinical practice, to prevent the tissue damage caused by patient exposure to high-radiation X-ray beams, X-rays are usually minimized to obtain CT images, which results in a severe deterioration in imaging quality. To solve the above contradictions, how to reconstruct CT images that meet clinical needs has become a challenging problem widely concerned by researchers at home and abroad. With the vigorous development of deep learning technology in the field of artificial intelligence, the use of deep learning technology to improve the quality of CT reconstruction has become a hot topic in the current research under the drive of big data. In this paper, the mechanism of CT image reconstruction was analyzed. According to the imaging process of deep learning methods, the existing methods were divided into 4 categories, the basic ideas of 4 types of method introduced in turn, and the advantages and disadvantages of reconstruction methods summarized. The currently published public data set and the method of increasing training samples were summarized, and the diversity of loss functions; The problems that still exist in this emerging field are discussed, and the key problems that need to be solved in the follow-up research are looked forward so that relevant researchers can understand the research status in the field of CT reconstruction and promote the rapid development of the field. more...

Introduction Smoking remains one of the biggest public health challenges worldwide, quitting tobacco smoking can lead to substantial health gains, even later in life. Previous studies indicate that illness can be a powerful motivation to quit and physicians’ advice on smoking cessation has been shown to improve quit rates, but evidence on the role of non-communicable diseases in smoking cessation is limited. This cross-sectional study aims to evaluate the prevalence of non-communicable diseases and to explore its role in smoking cessation intention in smokers in Shanghai. Methods From January to June 2021, 1104 current smokers were recruited in the Songjiang and Fengxian districts of Shanghai. We used an Android assisted electronic questionnaire for data collection, and implemented logistic regression for odds ratio (OR) and 95% confidence interval (CI) calculation to explore how smoking cessation intention would be influenced by non-communicable diseases comorbidity among smokers. Results The 1104 current smokers included 914 males (82.8%), with an average age of 43.6 years. Approximately 22% of smokers had at least 1 type of noncommunicable disease, with 17.8% for non-respiratory system related noncommunicable diseases and 6.6% for respiratory system related non-communicable diseases. The prevalence of non-communicable diseases comorbidity ranged from 0.5% to 13.9%, and was higher in male smokers; 41.8% of current smokers had intention to quit smoking in a recent year, and the percentage of smoking cessation intention was higher in smokers with non-communicable diseases. Logistic regression indicated that smokers with non-communicable diseases had 1.3 (95% CI: 1.0–1.8) times higher smoking cessation intention than those without non-communicable disease. The findings were consistent in respiratory system related and non-respiratory system related non-communicable diseases. Conclusions The prevalence of non-communicable diseases was high among current smokers in Shanghai, and their smoking cessation intention was associated with non-communicable diseases comorbidity. Physicians should treat illness as a powerful motivation and provide professional cessation service to tobacco users to reverse the severe tobacco epidemic. more...

This paper presents a novel Adaptive Mutation Quantum-inspired Squirrel Search Algorithm (AM-QSSA). Firstly, based on the population mutation, a location-update of quantum state correlative and attractor method is proposed. By introducing a random process to modify the sliding factor of the local attractor, the inevitable lack of diversity in the population renewal method is solved. The premature convergence problem of adaptive mutation rate improvement algorithm based on squirrel position update mode is introduced. Meanwhile, the paper decomposes the location update process of the SSA, and improves it with quantum-behavior. Furthermore, it proposes a novel quantum-inspired squirrels search algorithm. This method finds the complementary effect between quantum behavior and squirrel search algorithm, and solves the problem of premature convergence probability of SSA. In addition, it improves population diversity, and achieves the balance between global and local search. The efficiency of the proposed AM-QSSA is evaluated using exploitation analysis, exploration analysis, success rate analysis, convergence rate analysis on classical benchmark functions as well as Congress on Evolutionary Computation (CEC) 2017 test functions. For further study, AM-QSSA optimizes an image registration problem for an extensive study to check its applicability. The results reveal that AM-QSSA is more efficient and stable than SSA. And it is comparable to the most advanced optimization algorithms. more...

Background: Multiparous women are at a higher risk of gestational diabetes mellitus (GDM) than primiparas. Physical activity during pregnancy has been shown to be beneficial for GDM, but there is little evidence on the association between physical activity and glycemic control among women with GDM, whether primiparas or multiparas. Thus, the objective of the present study was to examine the association between physical activity and glycemic control in women with GDM and to determine what, if any, effects result from number of parous events. Methods: A prospective cohort of 1162 women with GDM was recruited, with 604 multiparas (51.98%). The general linear model was used to calculate the risk difference and its 95% confidence interval (95%CI) to quantify the impact of parous events on glycemic control in pregnancy as well as the association between physical activity time and glycemic control. Results: Among 1162 women with GDM, the median daily activity time was 65 min (interquartile range (IQR): 45–90 min), and the abnormal plasma glucose (PG) percentage, calculated as number of abnormal PG tests divided by the total number of PG tests, was 40.00% (IQR: 22.22%–66.67%). The percentage of abnormal PG was stabilized and statistically lower with daily physical activity time exceeding 60 min among primiparas (IQR: 30.89%–44.43%) and exceeding 90 min among multiparas (ranged from 27.76% to 38.82%). After adjusting for potential confounders, primiparas tended to have a lower percentage of abnormal PG than do multiparas (rate difference = –0.39, 95%CI: –3.61 to 2.84). The same amount of physical activity time was significantly less effective for multiparas than for primiparas (trend p-value < 0.01). Conclusion: In women with GDM, being multiparous is associated with less effective glycemic control through physical activity, such that multiparas need more physical activity to achieve glycemic control at a similar level to primiparas. more...

Resident load is one of the important components of seasonal peak load and has huge demand response (DR) potential. But its randomness and decentralization limit the ability to flexibly participate in DR interactions. In view of the characteristics of resident load and the uncertainty of response behavior, the resident load model is established with the characteristics of load curve, historical DR participation and response degree as parameters. And the distribution parameters are identified through actual resident data sets. Furthermore, a method of forming a priority queue based on historical response effects is proposed. On this basis, the resident DR cost model is established, and the optimal resident DR strategy is obtained with the goal of cost minimization, so that the DR cost can be reasonably controlled under the premise of accurately achieving the load reduction target. The priority queue is updated and corrected successively in multiple DR events to realize automatic optimization of response strategies. Finally, the calculation example verifies the effectiveness of the proposed resident load model and the resident DR strategy self-optimization method. more...

COVID-19 analysis from medical imaging is an important task that has been intensively studied in the last years due to the spread of the COVID-19 pandemic. In fact, medical imaging has often been used as a complementary or main tool to recognize the infected persons. On the other hand, medical imaging has the ability to provide more details about COVID-19 infection, including its severity and spread, which makes it possible to evaluate the infection and follow-up the patient’s state. CT scans are the most informative tool for COVID-19 infection, where the evaluation of COVID-19 infection is usually performed through infection segmentation. However, segmentation is a tedious task that requires much effort and time from expert radiologists. To deal with this limitation, an efficient framework for estimating COVID-19 infection as a regression task is proposed. The goal of the Per-COVID-19 challenge is to test the efficiency of modern deep learning methods on COVID-19 infection percentage estimation (CIPE) from CT scans. Participants had to develop an efficient deep learning approach that can learn from noisy data. In addition, participants had to cope with many challenges, including those related to COVID-19 infection complexity and crossdataset scenarios. This paper provides an overview of the COVID-19 infection percentage estimation challenge (Per-COVID-19) held at MIA-COVID-2022. Details of the competition data, challenges, and evaluation metrics are presented. The best performing approaches and their results are described and discussed. more...

In recent years, with the continuous development of artificial intelligence and machine vision technology, computer-assisted technology has increasingly affected the medical field, providing important support means for the development and promotion of informatization, digitization, and standardization of traditional Chinese medicine. In order to facilitate a further and effective exploration of the application of image processing technology in the field of traditional Chinese medicine, the relevant research progress is systematically reviewed. First of all, starting from the development and application of image processing technology, the main research and application directions of image processing technology in the field of image processing in Chinese medicine are clarified, and they are based on the three modules: traditional Chinese medicine inspection, identification of Chinese medicinal materials, and digital meridian three-dimensional reconstruction and visualization. The various research sub-categories in the modules are summarized, and the advantages and disadvantages of traditional and deep learning algorithms in the field of TCM image processing are shown, as well as the problems and challenges they face. Second, the main problems facing by the field of TCM image intelligent processing at this stage is summarized, and an outlook on the future research direction is made. Although TCM intelligent image processing and analysis based on computer image processing technology have achieved a series of meaningful research results, it is still necessary to sort out a unified, standard, and well-labeled TCM image dataset according to the actual clinical needs. Combining artificial intelligence with classic digital image processing algorithms and non-invasive and efficient multi-modal TCM four-diagnosis data, it truly realizes the informatization and intelligentization of TCM diagnosis and treatment technology. more...

Introduction: The nuclear factor kB (NF-κB) pathway emerges as a critical regulator of immune responses and is often dysregulated in human cancers. It consists of a family of transcription factors involved in many biological responses. Activated NF-κB subunits results in the nuclear translocation and activation of transcription, and the NF-κB pathway is known to influence the transcription of many genes. Noncanonical NF-κB and its components have been shown to have effects, usually protumorigenic, in many different cancer types. Besides, NF-κB signaling had diverse and complicated roles in cancer with studies that NF-κB could both contribute to tumor promotion and suppression of oncogenesis relying on the cellular context. RelB, a member of noncanonical NF-κB was abnormally regulated in most cancer types, however the molecular features and clinical signature of RelB expression, as well as its role in cancer immunity in human pan-cancer remains to be elucidated.Methods: We used the open databases to explore RelB expression, clinical features and the association with tumor-infiltration cells in human pan-cancer. In this study, we investigated the aberration expression and prognostic significance of RelB, and the correlation with clinicopathological characters and immune cells infiltration in various cancers. The Cancer Genome Atlas (TCGA) and Genotype-Tissue Expression (GTEx) databases were used to analyze the mRNA expression level in different cancer types. Kaplan-Meier analysis and Cox regression were used to explore the prognostic significance of RelB in human pan-cancer. Then we took advantage of the TCGA database to analyze the relationship between RelB expression and DNA methylation, the infiltration of immune cells, immune checkpoint genes, tumor mutation burden (TMB), microsatellite instability (MSI), mismatch repair (MSS).Results: Higher expression of RelB was significantly detected in human cancer tissues and a high level of RelB expression was significantly linked with a worse outcome in LGG, KIPAN, ACC, UVM, LUAD,THYM, GBM, LIHC and TGCT but associated with a favorable overall survival (OS) in SARC, SKCM and BRCA. According to the Human Protein Altas database, RelB was considered as an independent factor in breast cancer and renal cancer prognosis. GSEA results revealed that RelB was involved in many oncogenesisrelated processes and immunity-related pathways. RelB was significantly correlated with DNA methylation in 13 types of cancer. Meanwhile, RelB expression was associated with TMB in 5 types of cancer and MSI in 8 types of cancer. In the final, we analyzed the relationship between RelB expression and immune-infiltration cells in human pan-cancer, which suggested RelB could be a promising therapeutic target for cancer immunotherapy.Discussion: Our study further provided insights into a deeper understanding of RelB as a prognostic biomarker. more...

IntroductionAdvances in mobile computing platforms and the rapid development of wearable devices have made possible the continuous monitoring of patients with mild cognitive impairment (MCI) and their daily activities. Such rich data can reveal more subtle changes in patients’ behavioral and physiological characteristics, providing new ways to detect MCI anytime, anywhere. Therefore, we aimed to investigate the feasibility and validity of digital cognitive tests and physiological sensors applied to MCI assessment.MethodsWe collected photoplethysmography (PPG), electrodermal activity (EDA) and electroencephalogram (EEG) signals from 120 participants (61 MCI patients, 59 healthy controls) during rest and cognitive testing. The features extracted from these physiological signals involved the time domain, frequency domain, time-frequency domain and statistics. Time and score features during the cognitive test are automatically recorded by the system. In addition, selected features of all modalities were classified by tenfold cross-validation using five different classifiers.ResultsThe experimental results showed that the weighted soft voting strategy combining five classifiers achieved the highest classification accuracy (88.9%), precision (89.9%), recall (88.2%), and F1 score (89.0%). Compared to healthy controls, the MCI group typically took longer to recall, draw, and drag. Moreover, during cognitive testing, MCI patients showed lower heart rate variability, higher electrodermal activity values, and stronger brain activity in the alpha and beta bands.DiscussionIt was found that patients’ classification performance improved when combining features from multiple modalities compared to using only tablet parameters or physiological features, indicating that our scheme could reveal MCI-related discriminative information. Furthermore, the best classification results on the digital span test across all tasks suggest that MCI patients may have deficits in attention and short-term memory that came to the fore earlier. Finally, integrating tablet cognitive tests and wearable sensors would provide a new direction for creating an easy-to-use and at-home self-check MCI screening tool. more...

Aiming at the exposure to radiation dosage in CT imaging possessing cancer-inducing potential, and the use of a single data resulting in the residual noise and excessive smoothness of the structure in reconstruction results, a multi-stage joint denoising model for low-dose CT images based on two different data domains is proposed. In the first stage of the generator, the residual U-net model was used to recover the low-dose projection data. and the multi-scale information was added to the up-sampling by embedding skip connections in the coding and decoding process to accelerate the training convergence speed. After noise removal, the projection data was switched from frequency space to spatial domain by means of filtering back projection. In the second stage, multi-scale convolution was used to denoise CT reconstructed images again to enrich the convolution diversity and improve the reconstruction accuracy. VGG network was introduced to capture the perceptual difference between CT images of different doses, and the ability of network representation was enhanced. Experimental results show that the proposed method has a higher PSNR, and compared with the single domain transformation, it can effectively use the complementary effect of the projection data and image data to suppress noise and artifact, and improve the reconstruction effect. more...

Introduction A number of studies have reported a high correlation between psoriasis and metabolic syndrome (MetS), and tobacco smoking is one independent risk factor accounting for the increased prevalence both for psoriasis and MetS. However, few studies have been conducted to assess the effects of tobacco smoking on co-morbidities of psoriasis and MetS. Methods We conducted a cross-sectional study with 1014 psoriasis patients recruited from January to May 2021. Patients were recruited with a cluster survey method in Yueyang Hospital (affiliated with Shanghai University of Traditional Chinese Medicine) and Shanghai Skin Diseases Hospital (affiliated with Tongji University). Data were collected by face-to-face questionnaire interviews which included basic information, personal life habits, medical history, and clinical examinations. SPSS 24.0 was used for data analysis and a p more...

Abstract Background Tobacco consumption is the leading cause of death worldwide. Overwhelming studies demonstrate graphic warning labels (GWLs) on cigarette packs are effective in eliciting negative response to tobacco smoking, modifying beliefs about tobacco dangers, and increasing reported intention to quit, but the estimated effect of GWLs on smoking cessation intention among smokers is still limited in China. In this study, we aim to understand the smoking intensity, smoking duration and smoking cessation intention among current smokers, and to explore how their smoking cessation intention would be influenced by the GWLs in Shanghai. Methods From January to June 2021, we totally recruited 1104 current smokers in Songjiang district and Fengxian district of Shanghai by multistage sampling design. We used Android pad assisted electronic questionnaire for data collection, and then implemented logistic regression for odds ratio (OR) and 95% confidence interval (CI) calculation to explore how smoking cessation intention would be influenced by the GWLs among current smokers. Results One thousand one hundred four current smokers included 914 males (82.79%), with an average age of 43.61 years. 58.06% of current smokers reported smoking cessation intention due to GWLs. Logistic regression indicated a higher percentage of smoking cessation intention due to GWLs was among female smokers [OR = 2.41, 95% CI (1.61–3.59)], smokers with smoking intensity more...

In this paper we proposed a knowledge tracing method based on Transformer structure, improved the embedded representation of interactive records, designed a gate unit suitable for this model, and optimized the input processing of self-attention sublayer to improve the predictive performance of deep knowledge tracing model. The experimental results on four commonly used public data sets show that compared with previous methods, the model proposed in this paper can better reflect learners’ mastery of knowledge points, and has better performance on data sets with large sample sizes. more...

Significant advances in sensor technology and virtual reality (VR) offer new possibilities for early and effective detection of mild cognitive impairment (MCI), and this wealth of data can improve the early detection and monitoring of patients. In this study, we proposed a non-invasive and effective MCI detection protocol based on electroencephalogram (EEG), speech, and digitized cognitive parameters. The EEG data, speech data, and digitized cognitive parameters of 86 participants (44 MCI patients and 42 healthy individuals) were monitored using a wearable EEG device and a VR device during the resting state and task (the VR-based language task we designed). Regarding the features selected under different modality combinations for all language tasks, we performed leave-one-out cross-validation for them using four different classifiers. We then compared the classification performance under multimodal data fusion using features from a single language task, features from all tasks, and using a weighted voting strategy, respectively. The experimental results showed that the collaborative screening of multimodal data yielded the highest classification performance compared to single-modal features. Among them, the SVM classifier using the RBF kernel obtained the best classification results with an accuracy of 87%. The overall classification performance was further improved using a weighted voting strategy with an accuracy of 89.8%, indicating that our proposed method can tap into the cognitive changes of MCI patients. The MCI detection scheme based on EEG, speech, and digital cognitive parameters proposed in this study provides a new direction and support for effective MCI detection, and suggests that VR and wearable devices will be a promising direction for easy-to-perform and effective MCI detection, offering new possibilities for the exploration of VR technology in the field of language cognition. more...

Abstract Objective To investigate the effect of Acapella training on respiratory function in patients undergoing video‐assisted thoracic surgery (VATS). Methods A total of 60 patients undergoing VATS surgery for lung cancer in the department of thoracic Surgery of our hospital from August 2018 to February 2019 were selected as study subjects, and were divided into observation group (n = 30) and control group (n = 30) according to the random number table method. The control group received routine pulmonary rehabilitation exercise after surgery, and the patients in the observation group received postoperative respiratory function exercise with Acapella therapeutic apparatus on the basis of the control group. Respiratory function, including forced vital capacity (FVC), forced expiratory capacity in the first second (FEV1), peak expiratory flow (PEF), and length of hospital stay, were observed and compared between the two groups before and after using Acapell trainer. Results There was no significant difference in FEV1, FVC, and PEF between the two groups before treatment with Acapella (P >.05), the difference between the above indicators after treatment and before treatment was statistically significant (P more...

Segmentation of liver lesions on non-contrast magnetic resonance imaging (MRI) is critical for patient management and treatment planning. In clinical treatment, the imaging process suffers from high-risk, expensive, and time-consuming due to using contrast agents (CA). Furthermore, manual segmentation has the disadvantages of tedious, low-reproducibility, and high misdiagnosis rate. Although some deep-learning based works have attempted for liver lesions segmentation, they are all limited to the use of contrast-enhanced MRI. To avoid the limitations comes from CA, we proposed a Radiomics-guided Densely-UNet-Nested Generative Adversarial Networks (Radiomics-guided DUN-GAN) for automatic segmentation of liver lesions on non-contrast MRI. Radiomics-guided DUN-GAN includes a DUN segmentor and a Radiomics-guided discriminator. It uses radiomics feature of the multi-phase contrast image as prior knowledge to guide the extraction of key implicit contrast radiomics (ICR) features in non-contrast images, thus achieving the direct lesions segmentation without CA for the first time. In the DUN segmentor, an innovative nested structure of Densely-UNet-connection reliably completes the segmentation. The nested structure extracts global features, semantic features, and ICR features by reasonably sharing features and maximizing information flow. Those features are fused with a new direction strategy of multi-integration features to improve the segmentation ability. In the innovative Radiomics-guided discriminator, the radiomics feature combined with the semantic feature enhances the discrimination of Radiomics-guided discriminator. Moreover, it guides the segmentor for multiple feature extraction via using the adversarial mechanism. Radiomics-guided DUN-GAN learns the mapping relationship between images, extracting the key ICR in the non-contrast image, and finally completing the accurate segmentation. Radiomics-guided DUN-GAN obtained the Dice Similarity Coefficient results of 93.47± 0.83% for the segmentation of lesions in non-contrast images from 250 clinical subjects. The results verify the Radiomics-guided DUN-GAN is accurate and robust, and it has the possibility of becoming a safe, inexpensive, and time-saving medical assistant tool in clinical diagnosis. more...

The prediction of lung tumour growth is the key to early treatment of lung cancer. However, the lack of intuitive and clear judgments about the future development of the tumour often leads patients to miss the best treatment opportunities. Combining the characteristics of the variational autoencoder and recurrent neural networks, this study proposes a tumour growth prediction via a conditional recurrent variational autoencoder. The proposed model uses a variational autoencoder to reconstruct tumour images at different times. Meanwhile, the recurrent units are proposed to infer the relationship between tumour images according to the chronological order. The different tumour development varies in different patients, patients' condition is adopted to achieve personalised prediction. To solve the problem of blurred results, the authors add the total variation regularisation term into the object function. The proposed method was tested on longitudinal studies, National Lung Screening Trial and cooperative hospital dataset, with three points on lung tumours. The precision, recall, and dice similarity coefficient reach 82.22, 79.89 and 82.49%, respectively. Both quantitative and qualitative experimental results show that the proposed method can produce realistic tumour images. more...

This study proposed a GAN‐based reconstruction method‐cascaded data consistency generative adversarial network (CDCGAN) to recover high‐quality PET images from filtered back projection PET images with streaking artifacts and high noise. First, the authors embed defined data consistency layer (DC layer) in their generator network to constrain the reconstruction process and adjust accurately generated faked PET images. Second, to improve the accuracy of reconstruction on average, their generator network was built iteratively to achieve better performance with simple structures. They observed that the proposed CDCGAN allows the preservation of fine anomalous features while eliminating the streaking artifacts and noise. Experimental results show that the reconstructed PET images by their methods perform well comparably to other state‐of‐the‐art methods but at a faster speed. A clinical experiment was also performed to show the validity of the CDCGAN for artifacts reduction. more...

IntroductionHealthy sleep in children is critical for their physical and mental health. Although growing evidence indicates the linkage between preterm birth and neural network that regulates sleep architecture, findings on the association between preterm birth and sleep problems among children are still contradictory. In this study, we aimed to understand the prevalence of sleep problems in children aged 3–6 years and to explore the association between sleep problems and preterm birth among children in Shanghai, China.MethodsWe selected 8,586 kindergarten children aged 3–6 years and their mothers in a rural area of Shanghai. Data were collected by questionnaire interview among mothers with informed consent that was signed ahead. Six types of sleep problems (i.e., insufficient sleep, sleepwalk, nightmare, snore, grind teeth, and cry in sleep) were selected in this study. SAS 9.4 was used for data analysis, and p < 0.05 was considered statistically significant.ResultsIn this study, the prevalence of preterm birth was 9.88% (848/8,586), with a higher prevalence in boys (10.62%) than girls (9.01%). The prevalence of sleep problems was 89.81% among kindergarten children, with 62.50% for snore, 50.35% for grind teeth, 49.20% for cry in sleep, 41.18% for nightmare, 11.67% for insufficient sleep, and 4.44% for sleepwalk. The age of children, family income, and mother's education were associated with the prevalence of sleep problems in children. Logistic regression indicated that sleep problems in preterm children were comparable with the full-term children [odds ratio = 1.13, 95% confidence interval (0.89–1.45)].ConclusionSleep problems were prevalent among children aged 3–6 years in the rural area of Shanghai, and preterm birth was not associated with sleep problems in kindergarten children. We recommend that parents should create limit setting in the home, cultivate similar child-rearing attitudes and beliefs among family members, and encourage children to go to bed earlier. more...

BackgroundThe fusion of PET metabolic images and CT anatomical images can simultaneously display the metabolic activity and anatomical position, which plays an indispensable role in the staging diagnosis and accurate positioning of lung cancer.MethodsIn order to improve the information of PET-CT fusion image, this article proposes a PET-CT fusion method via Siamese Pyramid Fusion Network (SPFN). In this method, feature pyramid transformation is introduced to the siamese convolution neural network to extract multi-scale information of the image. In the design of the objective function, this article considers the nature of image fusion problem, utilizes the image structure similarity as the objective function and introduces L1 regularization to improve the quality of the image.ResultsThe effectiveness of the proposed method is verified by more than 700 pairs of PET-CT images and elaborate experimental design. The visual fidelity after fusion reaches 0.350, the information entropy reaches 0.076.ConclusionThe quantitative and qualitative results proved that the proposed PET-CT fusion method has some advantages. In addition, the results show that PET-CT fusion image can improve the ability of staging diagnosis compared with single modal image. more...

Introduction: Sleep deprivation in children is a global public health problem that affects the physical and mental development of children. Bedtime delay induced by longer screen time and heavy study load is a common cause of sleep deprivation in children. However, the prevalence of insufficient sleep and bedtime delay and related influencing factors among kindergarten children is limited in Shanghai, China.Methods: In 2018, we selected 8,586 children aged 3 to 6 years and their parents in Songjiang District, Shanghai. Data was collected among parents by face-to-face questionnaire interview with signed informed consent. We defined insufficient sleep as those who slept for < 10 h in children aged 3–5 years or 9 h in children aged 6 years within 24 h, and we define bedtime delay as children with bedtime after 21:00. SAS 9.1.3 software was used to calculate the prevalence of bedtime delay and insufficient sleep, and logistic regression was used to explore potential influencing factors.Results: The prevalence of insufficient sleep and bedtime delay among children aged 3 to 6 years was 11.67 and 56.85%, respectively. The prevalence of insufficient sleep among boys was slightly higher than among girls [odds ratio (OR) = 1.18, 95% confidence interval (CI): 1.04–1.35]. With the increase of the age of children, the prevalence of insufficient sleep increased gradually (P < 0.05). The prevalence of insufficient sleep was higher among the only child in the family (OR = 1.18, 95% CI: 1.02–1.36) and those with longer hours of TV watching (OR = 109, 95% CI: 1.02–1.16). Meanwhile, the prevalence of bedtime delay was also higher among the only child in the family (OR = 1.17, 95% CI: 1.06–1.79), among those with parents accompanying for sleep (OR = 1.21, 95% CI: 1.10-1.34), and those with longer TV watching time (OR = 1.13, 95% CI: 1.07–1.18).Conclusions: Insufficient sleep and bedtime delay were prevalent in Chinese children aged 3 to 6 years, especially in boys and older children. TV watching as well as parents accompanying for sleep were associated with insufficient sleep and bedtime delay. We recommend that parents should limit the screen time of children, advocate earlier bedtime and later morning wake-up among children, as well as make their children sleep in separate beds or rooms in younger age. more...

Abstract Background Lung cancer is one of the most common types of cancer, among which lung adenocarcinoma accounts for the largest proportion. Currently, accurate staging is a prerequisite for effective diagnosis and treatment of lung adenocarcinoma. Previous research has used mainly single-modal data, such as gene expression data, for classification and prediction. Integrating multi-modal genetic data (gene expression RNA-seq, methylation data and copy number variation) from the same patient provides the possibility of using multi-modal genetic data for cancer prediction. A new machine learning method called gcForest has recently been proposed. This method has been proven to be suitable for classification in some fields. However, the model may face challenges when applied to small samples and high-dimensional genetic data. Results In this paper, we propose a multi-weighted gcForest algorithm (MLW-gcForest) to construct a lung adenocarcinoma staging model using multi-modal genetic data. The new algorithm is based on the standard gcForest algorithm. First, different weights are assigned to different random forests according to the classification performance of these forests in the standard gcForest model. Second, because the feature vectors generated under different scanning granularities have a diverse influence on the final classification result, the feature vectors are given weights according to the proposed sorting optimization algorithm. Then, we train three MLW-gcForest models based on three single-modal datasets (gene expression RNA-seq, methylation data, and copy number variation) and then perform decision fusion to stage lung adenocarcinoma. Experimental results suggest that the MLW-gcForest model is superior to the standard gcForest model in constructing a staging model of lung adenocarcinoma and is better than the traditional classification methods. The accuracy, precision, recall, and AUC reached 0.908, 0.896, 0.882, and 0.96, respectively. Conclusions The MLW-gcForest model has great potential in lung adenocarcinoma staging, which is helpful for the diagnosis and personalized treatment of lung adenocarcinoma. The results suggest that the MLW-gcForest algorithm is effective on multi-modal genetic data, which consist of small samples and are high dimensional. more...

Background: Tobacco consumption produces a heavy disease burden worldwide, and tobacco price increase, an advertisement for tobacco-induced harm, graphic warning labels on cigarette packages and advice of physicians for quitting are policies that have been proved as effective smoking cessation measures. But evidence on the estimated effect of advice of physicians for quitting and assumed tobacco retail price increase on smoking cessation intention among smokers is still limited in China.Methods: From January to April of 2021, we recruited 664 current smokers in Songjiang district of Shanghai by a multistage sampling design. We implemented a logistic regression analysis to calculate the odds ratio (OR) and 95% confidence interval (CI) to explore how smoking cessation intention would be influenced by the assumed tobacco retail price increase as well as advice of physicians for quitting, and used the paired tabulation method to identify the salient tobacco control measures among smokers as well.Results: A total of 664 current smokers included 548 males (82.53%), with an average smoking duration of 22.50 years (SD: 11.52 years). About 68.79 and 43.67% of current smokers reported smoking cessation intention due to advice of physicians for quitting and the assumed tobacco retail price increase, respectively. Logistic regression analysis indicated that female smokers (OR = 2.85 and 4.55), smokers with previous smoking cessation attempt (OR = 3.71 and 3.07), longer smoking duration (OR = 2.26 and 2.68), lower smoking intensity (OR = 1.82 and 1.69), and heavier tobacco burdens (OR = 1.67 and 2.22) had the higher intention of smoking cessation both due to advice of physicians for quitting and due to assumed tobacco price increase, respectively. Meanwhile, the advice of physicians for quitting was more effective and acceptable (over 80%) than the assumed tobacco price increase for inducing smokers to consider quitting in Shanghai.Conclusions: Smokers have a high intention of smoking cessation in Shanghai, and the advice of physicians for quitting is a potentially more salient tobacco control measure than the assumed tobacco retail price increase. Incorporating smoking duration, intensity, personal burden as well as noncommunicable disease (NCD) status of smokers into the implementation of tobacco control measures is beneficial for descending smoking prevalence. more...

(1) Objective: Identification of potential genetic biomarkers for various glomerulonephritis (GN) subtypes and discovering the molecular mechanisms of GN. (2) Methods: four microarray datasets of GN were downloaded from Gene Expression Omnibus (GEO) database and merged to obtain the gene expression profiles of eight GN subtypes. Then, differentially expressed immune-related genes (DIRGs) were identified to explore the molecular mechanisms of GN, and single-sample gene set enrichment analysis (ssGSEA) was performed to discover the abnormal inflammation in GN. In addition, a nomogram model was generated using the R package “glmnet”, and the calibration curve was plotted to evaluate the predictive power of the nomogram model. Finally, deep learning (DL) based on a multilayer perceptron (MLP) network was performed to explore the characteristic genes for GN. (3) Results: we screened out 274 common up-regulated or down-regulated DIRGs in the glomeruli and tubulointerstitium. These DIRGs are mainly involved in T-cell differentiation, the RAS signaling pathway, and the MAPK signaling pathway. ssGSEA indicates that there is a significant increase in DC (dendritic cells) and macrophages, and a significant decrease in neutrophils and NKT cells in glomeruli, while monocytes and NK cells are increased in tubulointerstitium. A nomogram model was constructed to predict GN based on 7 DIRGs, and 20 DIRGs of each subtype of GN in glomeruli and tubulointerstitium were selected as characteristic genes. (4) Conclusions: this study reveals that the DIRGs are closely related to the pathogenesis of GN and could serve as genetic biomarkers in GN. DL further identified the characteristic genes that are essential to define the pathogenesis of GN and develop targeted therapies for eight GN subtypes. more...

The conventional tourism demand prediction models are currently facing several challenges due to the excess number of search intensity indices that are used as indicators of tourism demand. In this work, the framework for deep learning-based monthly prediction of the volumes of Macau tourist arrivals was presented. The main objective in this study is to predict the tourism growth via one of the deep learning algorithms of extracting new features. The outcome of this study showed that the performance of the adopted deep learning framework was better than that of artificial neural network and support vector regression models. Practitioners can rely on the identified relevant features from the developed framework to understand the nature of the relationships between the predictive factors of tourist demand and the actual volume of tourist arrival. more...

Background: Psoriasis and dementia are both inflammatory diseases. The association between psoriasis and dementia has rarely been investigated, and the existing results are conflicting. Thus, we conducted this study to evaluate whether an association exists between psoriasis and dementia.Methods: We searched for studies from six databases from inception to July 30, 2020, using subject and free words. RevMan 5.4 was used to calculate the risk ratio (RR) of dementia in the subjects with psoriasis. When heterogeneity was present, a random-effects model was used. Subgroup, sensitivity, and meta-regression analyses were performed using Stata 15.1.Results: Nine studies were identified and included in the study, of which seven that involved a total of 3,638,487 participants were included in the meta-analysis. We found that among the patients with psoriasis (RR: 1.14, 95% confidence interval [CI]: 1.06–1.24, p = 0.0009) and psoriatic arthritis (RR: 2.20, 95% CI: 1.29–3.78, p = 0.004), the proportions of those with non-vascular dementia (RR: 1.13, 95% CI: 1.11–1.15, p < 0.00001) and vascular dementia (RR: 1.41, 95% CI: 1.09–1.82, p = 0.009) were higher than that among the patients without psoriasis. Those with dementia were also more likely to develop psoriasis, and those with severe psoriasis were less likely to die from dementia (RR: 1.88, 95% CI: 0.72–4.90, p = 0.020). The meta-regression analysis did not show any significant sources of heterogeneity.Conclusions: The patients with psoriasis and psoriatic arthritis show high prevalence of different types of dementia. Based on the findings of this study, dementia may not be considered a high-risk factor of death from severe psoriasis. However, identification of this potential risk allows for early intervention, thereby reducing comorbidities and deaths. more...