Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

ObjectiveExisting artificial vision devices can be divided into two types: implanted devices and extracorporeal devices, both of which have some disadvantages. The former requires surgical implantation, which may lead to irreversible trauma, while the latter has some defects such as relatively simple instructions, limited application scenarios and relying too much on the judgment of artificial intelligence (AI) to provide enough security. Here we propose a system that has voice interaction and can convert surrounding environment information into tactile commands on head and neck. Compared with existing extracorporeal devices, our device can provide a larger capacity of information and has advantages such as lower cost, lower risk, suitable for a variety of life and work scenarios. MethodsWith the latest remote wireless communication and chip technologies, microelectronic devices, cameras and sensors worn by the user, as well as the huge database and computing power in the cloud, the backend staff can get a full insight into the scenario, environmental parameters and status of the user remotely (for example, across the city) in real time. In the meanwhile, by comparing the cloud database and in-memory database and with the help of AI-assisted recognition and manual analysis, they can quickly develop the most reasonable action plan and send instructions to the user. In addition, the backend staff can provide humanistic care and emotional sustenance through voice dialogs. ResultsThis study originally proposes the concept of “remote virtual companion” and demonstrates the related hardware and software as well as test results. The system can not only achieve basic guide functions, for example, helping a person with visual impairment to shop in supermarkets, find seats at cafes, walk on the streets, construct complex puzzles, and play cards, but also can meet the demand for fast-paced daily tasks such as cycling. ConclusionExperimental results show that this “remote virtual companion” is applicable for various scenarios and demands. It can help blind people with their travels, shopping and entertainment, or accompany the elderlies with their trips, wilderness explorations, and travels.

【Objective】 To investigate the correlation between heart rate variability (HRV) and the degree of nervousness before blood donation. 【Methods】 The psychological state of 253 blood donors before blood donation was assessed by the self-rating anxiety scale (SAS) and the degree of nervousness and their HRV were measured. The correlation between the SAS score, the degree of nervousness and the HRV parameters was analyzed, and the differences were compared among different types of donors by multivariate linear regression. 【Results】 A total of 247 blood donors were included in the study. Five HRV parameters in blood donors aged 18-24 were higher than in those aged 25 years and above(all P<0.05), and the anxiety level was higher in female donors(SAS score 41-46) than in males(SAS score 35-43)(P<0.001); the pre-donation SAS score was consistent with the assessment of the tension level (r=0.970, P<0.001); the pre-donation tension level and the SAS score were all significantly negatively correlated with VLF in HRV parameters(r=0.179, P=0.005), and the associations were independent of confounders such as age, body mass index and gender (P<0.05). 【Conclusion】 Compared with SAS and tension assessment, HRV is more objective, and can be used as one of the tests for assessing the tension level of blood donors. The inclusion of HRV in the routine screening of blood donors deserves further study for its application in assessing the anxiety level of blood donors before blood donation, identifying people prone to blood donation-related vasovagal reaction (DRVR), preventing and reducing the risk of DRVR, and improving the safety of blood donation.

Adaptive immunity is a critical component of the human immune system, playing an essential role in identifying antigens and orchestrating a tailored immune response. This review delves into the significant strides made in the development of epitope prediction tools, their integration into vaccine design, and their pivotal role in enhancing immunotherapy strategies. The review emphasizes the transformative potential of these tools in refining our understanding and application of immune responses. Adaptive immunity distinguishes itself from innate immunity by its ability to recognize specific antigens and remember past infections, leading to quicker and more effective responses upon subsequent exposures. This facet of immunity involves complex interactions between various cell types, primarily B cells and T cells, which recognize distinct epitopes presented by antigens. Epitopes are small sequences or configurations on antigens that are recognized by the immune receptors on B cells and T cells, acting as the focal points of immune recognition and response. Epitopes can be broadly classified into two types: linear (or sequential) epitopes and conformational (or discontinuous) epitopes. Linear epitopes consist of a sequence of amino acids in a protein that are recognized by B cells and T cells in their primary structure form. Conformational epitopes, on the other hand, are formed by spatially distinct amino acids that come together in the tertiary structure of the protein, often recognized by the immune system only when the protein folds into its native conformation. The role of epitopes in the immune response is critical as they are the primary triggers for the activation of B cells and T cells. When an epitope is recognized, it can stimulate B cells to produce antibodies, mobilize helper T cells to secrete cytokines, or prompt cytotoxic T cells to kill infected cells. These actions form the basis of the adaptive immune response, tailored to eliminate specific pathogens or infected cells effectively. The prediction of B cell and T cell epitopes has evolved with advances in computational biology, leading to the development of several sophisticated tools that utilize a variety of algorithms to predict the likelihood of epitope regions on antigens. Tools employing machine learning methods, such as support vector machines (SVMs), XGBoost, random forest, analyze large datasets of known epitopes to classify new sequences as potential epitopes based on their similarity to known data. Moreover, deep learning has emerged as a powerful method in epitope prediction, leveraging neural networks capable of learning high-dimensional data from vast amounts of immunological inputs to identify patterns that may not be evident to other predictive models. Deep learning models, such as convolutional neural networks (CNNs), recurrent neural networks (RNNs) and ESM protein language model have demonstrated superior accuracy in mapping the nonlinear relationships inherent in protein structures and epitope interactions. The application of epitope prediction tools in vaccine design is transformative, enabling the development of epitope-based vaccines that can elicit targeted immune responses against specific parts of the pathogen. These vaccines, by focusing the immune response on highly specific regions of the pathogen, can offer high efficacy and reduced side effects. Similarly, in cancer immunotherapy, epitope prediction tools help identify tumor-specific antigens that can be targeted to develop personalized immunotherapeutic strategies, thereby enhancing the precision of cancer treatments. The future of epitope prediction technology appears promising, with ongoing advancements anticipated to enhance the precision and efficiency of these tools further. The integration of broader immunological data, such as patient-specific immune profiles and pathogen variability, along with advances in AI and machine learning, will likely drive the development of more adaptive, robust, and clinically relevant prediction models. This will not only improve the effectiveness of vaccines and immunotherapies but also contribute to our broader understanding of immune mechanisms, potentially leading to breakthroughs in the treatment and prevention of multiple diseases. In conclusion, the development and refinement of epitope prediction tools stand as a cornerstone in the advancement of immunological research and therapeutic design, highlighting a path toward more precise and personalized medicine. The ongoing integration of computational models with experimental immunology holds the promise of revolutionizing our approach to combating infectious diseases and cancer.

AIM: To determine the patient-related risk factors for pain during phacoemulsification.METHODS: Retrospective case-control study. A total of 62 patients(62 eyes)diagnosed as cataract in the First Affiliated Hospital of Zhengzhou University from December 2023 to January 2024 were included. The numeric rating scale was used to assess the pain level within 5 min postoperatively. The highest pain value was used as the primary outcome during the procedure. Based on pain values, patients were divided into pain group(n=25)and pain-free group(n=37). Subsequently, patients in the pain group were further divided into mild(n=16), moderate(n=7), and severe groups(n=2). Spearman correlation and Logistic regression analysis were conducted to determine risk factors for pain during the phacoemulsification.RESULTS: Binary Logistic regression showed preoperative sleep durations and times of operations were important risk factors for intraoperative pain(all P<0.05). Spearman analysis showed that intraoperative pain was negatively correlated with sleep duration(rs=-0.386, P=0.002), and positively correlated with times of operations(rs=0.421, P<0.001). The results of the ordinal Logistic regression analysis showed that for every additional hour of sleep, the likelihood of experiencing one higher level of intraoperative pain decreased by 37.60%(OR=0.376, P=0.014). In contrast, the times of operations did not show a statistically significant difference(P=0.083). Receiver operating characteristic curve showed a joint prediction model of sleep duration and operative times with an area under the curve of 0.809, 84% sensitivity, and 73% specificity.CONCLUSION: The intraoperative pain during phacoemulsification is negatively correlated with sleep duration and positively correlated with times of operations.

Objective To analyze the acupoint selection rules of acupuncture for the treatment of tic disorders in children based on data mining techniques.Methods A computerized search was conducted for the clinical research literature on acupuncture treatment of tic disorders in children included in the CNKI,Wanfang,VIP,SinoMed,and PubMed databases from January 1992 to December 2022.A database was established by Excel 2019 to count the commonly used treatment methods and analyze the high-frequency application methods acupuncture(high-frequency acupoints,channel entry of acupoints,acupoint association rules,and acupoint clustering),auricular point seed-pressing(high-frequency auricular points,and acupoint association rules),and the high frequency division of cluster needling of scalp point.Results A total of 190 valid literature articles were included,involving 270 acupuncture prescriptions;among them,184 acupoints were counted in the acupuncture method,with a total application frequency of 1 906 times,and the high-frequency application of the acupoints in descending order were Baihui(DU20),Taichong(LR3),Fengchi(GB20),Hegu(LI4),Sanyinjiao(SP6),Neiguan(PC6),Shenmen(HT7),Zusanli(ST36),Yintang(EX-HN3),Sishencong(EX-HN1);and the high-frequency meridians were governor vessol,foot taiyang stomach meridian,foot taiyang stomach meridian,foot shaoyang gallbladder meridian,hand taiyang large intestine meridian,foot taiyang bladder meridian,foot jueyin gallbladder meridian;three sets of strong association rules and five clusters of acupoints were analyzed by SPSS modeler 18.0 and IBM SPSS Statistics 26.0 software.There were 29 acupoints of auricular point seed-pressing,application total frequency was 206 times,high-frequency application of auricular points in descending order of Shenmen(HT7),liver,heart,subcortex,kidney;four groups of acupoint strong association rules were obtained through the analysis of SPSS modeler 18.0 software.A total of 14 zones were involved in the application of cephalic acupoint plexus zoning,of which the high-frequency zones were parietal anterior temporal diagonal,parietal parietal 1,and chorea tremor control zone.Conclusion Acupuncture treatment of tic disorders in children,according to its pathogenesis(liver hyperactivity,kidney depletion,spleen deficiency,phlegm disturbance,etc.)and tic site,select acupoints compatibility,and mostly choose yang meridian acupoints,which is related to the nature and treatment characteristics of wind pathogen.Children's tic disorders are closely related to emotional disorders,therefore acupuncture and auricular acupoints all emphasize the method of soothing the liver and clearing the heart,and regulating the emotional state.Cluster needling of scalp point mostly used parietal temporal anterior oblique line,parietal 1 line,and dance tremor control area for the treatment of tic disorders.For children,auricular point seed-pressing and cluster needling of scalp point has the minimun of pain,the effect of treatment is long,and it is not easy to have dangerous situations such as bent needle,broken needle and so on.