Biomedical named entity recognition based on multi-cross attention feature fusion.

Currently, in the field of biomedical named entity recognition, CharCNN (Character-level Convolutional Neural Networks) or CharRNN (Character-level Recurrent Neural Network) is typically used independently to extract character features. However, this approach does not consider the complementary capabilities between them and only concatenates word features, ignoring the feature information during the process of word integration. Based on this, this paper proposes a method of multi-cross attention feature fusion. First, DistilBioBERT and CharCNN and CharLSTM are used to perform cross-attention word-char (word features and character features) fusion separately. Then, the two feature vectors obtained from cross-attention fusion are fused again through cross-attention to obtain the final feature vector. Subsequently, a BiLSTM is introduced with a multi-head attention mechanism to enhance the model's ability to focus on key information features and further improve model performance. Finally, the output layer is used to output the final result. Experimental results show that the proposed model achieves the best F1 values of 90.76%, 89.79%, 94.98%, 80.27% and 88.84% on NCBI-Disease, BC5CDR-Disease, BC5CDR-Chem, JNLPBA and BC2GM biomedical datasets respectively. This indicates that our model can capture richer semantic features and improve the ability to recognize entities.

Prediction of drug-target interactions via neural tangent kernel extraction feature matrix factorization model.

Drug discovery is a complex and lengthy process that often requires years of research and development. Therefore, drug research and development require a lot of investment and resource support, as well as professional knowledge, technology, skills, and other elements. Predicting of drug-target interactions (DTIs) is an important part of drug development. If machine learning is used to predict DTIs, the cost and time of drug development can be significantly reduced. Currently, machine learning methods are widely used to predict DTIs. In this study neighborhood regularized logistic matrix factorization method based on extracted features from a neural tangent kernel (NTK) to predict DTIs. First, the potential feature matrix of drugs and targets is extracted from the NTK model, then the corresponding Laplacian matrix is constructed according to the feature matrix. Next, the Laplacian matrix of the drugs and targets is used as the condition for matrix factorization to obtain two low-dimensional matrices. Finally, the matrix of the predicted DTIs was obtained by multiplying these two low-dimensional matrices. For the four gold standard datasets, the present method is significantly better than the other methods that is compared to, indicating that the automatic feature extraction method using the deep learning model is competitive compared with the manual feature selection method.

A review of methods for predicting DNA N6-methyladenine sites.

Deoxyribonucleic acid(DNA) N6-methyladenine plays a vital role in various biological processes, and the accurate identification of its site can provide a more comprehensive understanding of its biological effects. There are several methods for 6mA site prediction. With the continuous development of technology, traditional techniques with the high costs and low efficiencies are gradually being replaced by computer methods. Computer methods that are widely used can be divided into two categories: traditional machine learning and deep learning methods. We first list some existing experimental methods for predicting the 6mA site, then analyze the general process from sequence input to results in computer methods and review existing model architectures. Finally, the results were summarized and compared to facilitate subsequent researchers in choosing the most suitable method for their work.

Overexpression of MicroRNA-133a Inhibits Apoptosis and Autophagy in a Cell Model of Parkinson's Disease by Downregulating Ras-Related C3 Botulinum Toxin Substrate 1 (RAC1).

The manuscript is being retracted due to non-original and duplicated content in the figure images, which raise concerns regarding the credibility of the study. Reference: Wusheng Lu, Jinhuang Lin, Dequan Zheng, Chunyong Hong, Laishun Ke, Xinyu Wu, Peineng Chen. Overexpression of MicroRNA-133a Inhibits Apoptosis and Autophagy in a Cell Model of Parkinson's Disease by Downregulating Ras-Related C3 Botulinum Toxin Substrate 1 (RAC1). Med Sci Monit, 2020; 26: e922032. DOI: 10.12659/MSM.922032.

Overexpression of MicroRNA-133a Inhibits Apoptosis and Autophagy in a Cell Model of Parkinson's Disease by Downregulating Ras-Related C3 Botulinum Toxin Substrate 1 (RAC1).

BACKGROUND Parkinson's disease (PD) is a movement disorder. microRNA (miR)-133 expression is reduced in PD patients and in mice with a dopamine neuron deficiency. We aimed to identify the mechanism of miR-133a in apoptosis and autophagy in PD. MATERIAL AND METHODS The optimal concentration of MPP⁺ (1-methyl-4-phenylpyridinium ion) was initially determined to construct a PD cell model. Gain-of function experiments were carried out to evaluate the role of miR-133a in PD. The levels of miR-133a, RAC1 (Ras-related C3 botulinum toxin substrate 1), apoptosis-related factors, and autophagy-related factors were detected after detection of cell proliferation, cell cycle, and apoptosis. Transmission electron microscopy was applied to observe autophagosomes, and immunofluorescence staining was performed to detect LC3 and further analyze the effect of miR-133a on autophagy in a PD cell model. RESULTS Low miR-133a expression was detected in a cell model of MPP⁺-induced PD. After overexpressing miR-133a, cell proliferation increased, and apoptosis (cleaved caspase-3 and Bax levels decreased, while Bcl2 levels increased) and autophagy was inhibited (LC3II/I and Beclin-1 levels decreased, while p62 levels increased). MiR-133a targeted RAC1. RACY upregulation attenuated the inhibitory effects of miR-133a on PC12 cell apoptosis and autophagy. CONCLUSIONS Our data highlighted that miR-133a overexpression prevented apoptosis and autophagy in a cell model of MPP⁺-induced PD by inhibiting RAC1 expression.

Nucleus segmentation of cervical cytology images based on multi-scale fuzzy clustering algorithm.

In the screening of cervical cancer cells, accurate identification and segmentation of nucleus in cell images is a key part in the early diagnosis of cervical cancer. Overlapping, uneven staining, poor contrast, and other reasons present challenges to cervical nucleus segmentation. We propose a segmentation method for cervical nuclei based on a multi-scale fuzzy clustering algorithm, which segments cervical cell clump images at different scales. We adopt a novel interesting degree based on area prior to measure the interesting degree of the node. The application of these two methods not only solves the problem of selecting the categories number of the clustering algorithm but also greatly improves the nucleus recognition performance. The method is evaluated by the IBSI2014 and IBSI2015 public datasets. Experiments show that the proposed algorithm has greater advantages than the state-of-the-art cervical nucleus segmentation algorithms and accomplishes high accuracy nucleus segmentation results.

Endovascular treatment versus standard medical treatment for vertebrobasilar artery occlusion (BEST): an open-label, randomised controlled trial.

BACKGROUND: Previous randomised trials have shown an overwhelming benefit of mechanical thrombectomy for treating patients with stroke caused by large vessel occlusion of the anterior circulation. Whether endovascular treatment is beneficial for vertebrobasilar artery occlusion remains unknown. In this study, we aimed to investigate the safety and efficacy of endovascular treatment of acute strokes due to vertebrobasilar artery occlusion. METHODS: We did a multicentre, randomised, open-label trial, with blinded outcome assessment of thrombectomy in patients presenting within 8 h of vertebrobasilar occlusion at 28 centres in China. Patients were randomly assigned (1:1) to endovascular therapy plus standard medical therapy (intervention group) or standard medical therapy alone (control group). The randomisation sequence was computer-generated and stratified by participating centres. Allocation concealment was implemented by use of sealed envelopes. The primary outcome was a modified Rankin scale (mRS) score of 3 or lower (indicating ability to walk unassisted) at 90 days, assessed on an intention-to-treat basis. The primary safety outcome was mortality at 90 days. Secondary safety endpoints included the rates of symptomatic intracranial haemorrhage, device-related complications, and other severe adverse events. The BEST trial is registered with ClinicalTrials.gov, NCT02441556. FINDINGS: Between April 27, 2015, and Sept 27, 2017, we assessed 288 patients for eligibility. The trial was terminated early after 131 patients had been randomly assigned (66 patients to the intervention group and 65 to the control group) because of high crossover rate and poor recruitment. In the intention-to-treat analysis, there was no evidence of a difference in the proportion of participants with mRS 0-3 at 90 days according to treatment (28 [42%] of 66 patients in the intervention group vs 21 [32%] of 65 in the control group; adjusted odds ratio [OR] 1·74, 95% CI 0·81-3·74). Secondary prespecified analyses of the primary outcome, done to assess the effect of crossovers, showed higher rates of mRS 0-3 at 90 days in patients who actually received the intervention compared with those who received standard medical therapy alone in both per-protocol (28 [44%] of 63 patients with intervention vs 13 [25%] of 51 with standard therapy; adjusted OR 2·90, 95% CI 1·20-7·03) and as-treated (36 [47%] of 77 patients with intervention vs 13 [24%] of 54 with standard therapy; 3·02, 1·31-7·00) populations. The 90-day mortality was similar between groups (22 [33%] of 66 patients in the intervention vs 25 [38%] of 65 in the control group; p=0·54) despite a numerically higher prevalence of symptomatic intracranial haemorrhage in the intervention group. INTERPRETATION: There was no evidence of a difference in favourable outcomes of patients receiving endovascular therapy compared with those receiving standard medical therapy alone. Results might have been confounded by loss of equipoise over the course of the trial, resulting in poor adherence to the assigned study treatment and a reduced sample size due to the early termination of the study. FUNDING: Jiangsu Provincial Special Program of Medical Science.

Ultrasound on Erect Penis Improves Plaque Identification in Patients With Peyronie's Disease.

OBJECTIVES: To compare the sensitivity of identification of penile plaques in the erect and flaccid penises by ultrasound in patients with Peyronie's disease (PD). MATERIALS AND METHODS: A total of 75 PD patients were screened by palpation and ultrasonography for penile lesions in both flaccid and erect penises induced by prostaglandin E1 (PG-1) injection. RESULTS: A total of 138 lesions were identified by ultrasound in the erect penises induced by injection of PG-1. However, only 74.6% of the lesions (103) were detectable by the palpation of the flaccid penises, and 84.1% (116) by ultrasound of the flaccid penises. The ultrasound confirmed 99 of the palpated lesions in the flaccid penises. The detection rate of lesions in drug-induced erect penises by ultrasound was significantly higher than those in the flaccid penises by the ultrasound (P < 0.01) or palpation (P < 0.0005) The type of penile lesions identified by ultrasonography included tunical thickening, calcifications, septal fibrosis, and intracavernosal fibrosis. The ratios of these lesions confirmed by ultrasound were 52.6, 33.6, 6.0, and 7.8%, respectively, in the flaccid penises, and 55.8, 28.3, 8.7, and 7.2%, respectively, in the erect penises. CONCLUSION: Drug-induced erection can be used in suspicious PD patients when penile lesion is not identified by palpation or ultrasound in the flaccid penis.

Leukoaraiosis severity and outcomes after mechanical thrombectomy with stent-retriever devices in acute ischemic stroke.

BACKGROUND AND PURPOSE: The aim of the study was to evaluate whether leukoaraiosis severity is associated with outcome in acute stroke patients undergoing mechanical thrombectomy with stent-retriever devices. METHODS: In this retrospective multicenter study, we evaluated 251 acute stroke patients (pretreatment National Institutes of Health Stroke Scale score ≥8) treated with stent-retriever devices. Leukoaraiosis severity was graded as 0-2 (absent-to-moderate) versus 3-4 (severe) according to the van Swieten scale. The main clinical outcome was the proportion of good functional outcome, defined as a modified Rankin Scale of 0-2 at 90 days. RESULTS: Significantly fewer patients in the severe LA group than in the absent-to-moderate LA group achieved a good functional outcome (18.4% vs 50.2%, P<0.001). In multivariable analysis, severe leukoaraiosis was a significant negative predictor of good functional outcome at 90 days (OR, 0.27; 95% CI 0.10-0.77; P=0.014). CONCLUSIONS: The severity of leukoaraiosis is independently associated with 90-day functional outcome in acute stroke patients undergoing mechanical thrombectomy with stent-retriever devices.

Impact of Relative Blood Glucose Changes on Mortality Risk of Patient with Acute Ischemic Stroke and Treated with Mechanical Thrombectomy.

BACKGROUND AND PURPOSE: The impacts of stress hyperglycemia and hypoglycemia on mortality of acute ischemic stroke patients treated with mechanical thrombectomy (MT) are largely unclear. This study aimed to use stress hyperglycemia ratio (SHR) to evaluate the influence of pretreatment relative blood glucose changes on mortality risk after MT. METHODS: The study retrospectively enrolled 321 acute ischemic stroke patients treated with MT. SHR was calculated as random blood glucose at admission divided by average blood glucose which estimated by glycosylated hemoglobin (HbA1c). Patients with HbAlc greater than or equal to 6.5% were considered to have background hyperglycemia, patients were tertiled according to their SHR. Binary logistic regression was used to analyze 90 days mortality between SHR categories. RESULTS: Compared with the middle tertiles group (Q2) which the blood glucose is closet to baseline glycaemia, patients in the lowest tertiles group (Q1) and highest tertiles group (Q3) have a higher mortality risk (odds ratio [OR], 3.80; 95% confidence interval [CI], 1.31-11.06) (OR, 3.18; 95% CI, 1.25-8.12), the differences is still significant after further adjusted for admission hyperglycemia (≥11.1 mmol/L). In patients without background hyperglycemia, the mortality risk is significantly higher in Q3 group (OR, 3.01; 95% CI, 1.06-8.53), no significant differences was found between three groups after adjusted for admission hyperglycemia (≥11.1 mmol/L). CONCLUSIONS: SHR identified acute ischemic stroke patients with relative hyperglycemia and hypoglycemia may have higher mortality risk after MT.

Primary angioplasty and stenting may be superior to thrombectomy for acute atherosclerotic large-artery occlusion.

Objective The objective of this article is to compare the effectiveness of primary angioplasty and/or stenting with stent retriever thrombectomy in acute anterior large-vessel occlusion due to atherosclerotic disease. Methods Patients were retrospectively reviewed from the endovascular treatment for acute anterior circulation ischemic stroke registry. Patients with large-vessel occlusions due to atherosclerosis were selected. We evaluated modified Rankin Scale (mRS) score at 90 days, modified thrombolysis in cerebral infarction (mTICI) score immediately post-procedure, and symptomatic and asymptomatic intracranial hemorrhage within 72 hours. Results Of 302 patients with acute anterior circulation occlusion due to atherosclerotic disease, 269 were treated with stent retriever thrombectomy as first-line therapy and 33 with angioplasty and/or stenting. Patients who received primary angioplasty treatment showed favorable independent outcome at 90 days (69.7% (23/33) vs 47.6% (128/269), p = 0.02) and lower rate of asymptomatic intracranial hemorrhage (9.1% (3/23) vs 30.5% (82/269), p = 0.01). Recanalization immediately post procedure did not differ (78.8%% (26/33) vs 86.2% (232/269), p = 0.29). Primary angioplasty therapy (OR, 0.27; 95% confidence interval (CI): 0.08-0.90; p = 0.03) and small baseline infarct (OR 0.36: 0.16-0.82; p = 0.02) were protective factors against poor functional outcome, while old age (OR 1.04:1.01-1.07; p = 0.006), severe neurological deficits (OR 3.76: 2.00-7.07; p < 0.001), and high glucose (OR 1.11: 1.01-1.23; p = 0.03) were associated with poor prognosis. Conclusions Patients with acute anterior circulation large-vessel occlusion due to atherosclerosis may benefit from urgent angioplasty and/or stenting as first-line therapy. Randomized controlled trials are warranted.

Clinical Effectiveness and Safety Outcomes of Endovascular Treatment for Acute Anterior Circulation Ischemic Stroke in China.

BACKGROUNDS AND PURPOSE: This study was aimed at investigating the outcomes and predictors for the poor functional outcome after endovascular treatment (EVT) in a large, mostly Asian population. METHODS: Between January 2014 and June 2016, acute stroke patients with anterior circulation occlusion and EVT were retrospectively enrolled from 21 stroke centers in China. The main outcomes were modified Rankin Scale (0-2 as functional independence, 3-6 as poor) at 90 days, symptomatic intracranial hemorrhage (sICH) at 72 h, and death at 90 days. Logistic regression was used to identify predictors for poor functional outcome at 90 days. RESULTS: Of the 698 patients, 304 (43.6%) patients had functional independence at 90 days. The sICH rate was 15.5% (108/698) and mortality rate at 90 days was 25.4% (177/698). Age (OR 1.04, 95% CI 1.02-1.07), National Institutes of Health Stroke Scale score at admission (11-20 vs. ≤10, OR 2.38, 95% CI 1.23-4.59; ≥21 vs. ≤10, OR 3.66, 95% CI 1.72-7.80), baseline glucose level (OR 1.09, 95% CI 1.01-1.18), onset to groin puncture >6 h (OR 1.88, 95% CI 1.06-3.31), sICH (OR 15.49, 95% CI 5.16-46.43), and pneumonia (OR 3.15, 95% CI 1.86-5.32) were independent predictors of poor functional outcomes, while good recanalization (OR 0.26, 95% CI 0.13-0.54), preoperative Alberta Stroke Program Early CT Score 8-10 (OR 0.48, 95% CI 0.28-0.83), and good collateral flow (OR 0.50, 95% CI 0.32-0.79) were protective factors. CONCLUSIONS: This study provides evidence in real world to support the performance of EVT in acute anterior circulation stroke patients in Chinese population. Patients with small infarct core, successful recanalization, good collateral status, and short treatment delay without sICH or pneumonia may benefit from EVT.

Doppler Characteristics of Cavernosal-Spongiosal Communications in Patients with Erectile Dysfunction.

The goal of this work was to characterize the blood flow in cavernosal-spongiosal communications (CSCs) in patients with erectile dysfunction using color Doppler ultrasound. Peak systolic velocity was measured in the CSCs, cavernosal artery and urethral artery in 72 erectile dysfunction patients of the Han ethnic group in southern China. Blood in the CSCs was observed to flow from the cavernosal artery to the urethral artery in all except 5 patients with arteriogenic insufficiency whose blood flow was bidirectional. Peak systolic velocity in erectile dysfunction patients with normal vascular function or veno-occlusive dysfunction was significantly lower in the CSCs than in the cavernosal artery (p < 0.01), but significantly higher than in the urethral artery (p < 0.05). Peak systolic velocities in CSCs in patients with arteriogenic insufficiency were significantly lower than those in the cavernosal (p < 0.01) and urethral (p < 0.01) arteries. The direction of blood flow in the CSCs is determined by the pressure gradient between the cavernosal and urethral arteries.

A novel approach for arrhythmia diagnosis: Self-adaptive and distribution-free mode.

Arrhythmia diagnosis is very significant to ensure human health. In this paper, a new model is developed for arrhythmia diagnosis. A salient feature of the algorithm is a synergistic combination of statistical and fuzzy set-based techniques. It is distribution-free and is realized in an unsupervised mode. Arrhythmia diagnosis is viewed as a certain statistical hypothesis testing. 'Abnormal' is typically a much complex concept, so it can be described with the technology of fuzzy sets which bring a facet of robustness to the overall scheme and play an important role in the successive step of hypothesis testing. Intensive fuzzification is engaged in parameters determination which is self-adaptive and no parameter needs to be specified by the user. The algorithm is validated with a number of experiments, which prove its effectiveness for arrhythmia diagnosis.

[Efficacy and safety of Longjintonglin Capsule for the treatment of type III prostatitis].

OBJECTIVE: To study the therapeutic effect and safety of Longjintonglin Capsule in the treatment of type III prostatitis (chronic prostatitis/chronic pelvic pain syndrome, CP/CPPS). METHOD: We selected 240 patients with type III prostatitis according to the diagnostic standards of the American National Institute of Health (NIH) and treated them with Longjintonglin Capsule orally 3 capsules once tid for 12 weeks. Based on the NIH chronic prostatitis symptom index (NIH-CPSI), traditional Chinese medicine (TCM) syndrome score, and leukocyte count in the expressed prostatic secretion (EPS), we evaluated the results of treatment. RESULTS: Totally 238 patients completed the treatment, including 108 IIIA and 120 III B prostatitis cases. Before and after 4, 8, and 12 weeks of treatment, the total NIH-CPSI scores were 23.12 ± 6.99, 18.22 ± 6.39, 14.12 ± 5.88, and 12.36 ± 6.04 (P < 0.01) in the IIIA prostatitis patients and 22.01 ± 6.28, 17.56 ± 5.89, 13.67 ± 5.18, and 11.45 ± 5.22 in the III prostatitis patients (P < 0.01), the TCM syndrome scores were 52.12 ± 13.08, 48.13 ± 12.11, 43.05 ± 11.19, and 40.78 ± 10. 59 in the former (P < 0.01) and 53.02 ± 12.12, 49.32 ± 12.78, 44.01 ± 11.79, and 39.67 ± 10.26 in the latter (P < 0.01), and the leukocyte counts were 26.09 ± 21.55, 23.02 ± 18.61, 18.25 ± 17.79, and 15.36 ± 16.38 in the IIIA cases (P < 0.01). Neither abnormalities in liver and renal function nor obvious adverse events were observed during the experiment. CONCLUSION: Longjintonglin Capsule, with its advantages of safety, effectiveness, and no obvious adverse reactions in the treatment of type III prostatitis, deserves to be recommended for clinical application.