Signal classification is a key of brain-computer interface (BCI). In this paper, we present a new method for classifying the electroencephalogram (EEG) signals of which the features are heterogeneous. This method is called wrapped elastic net feature selection and classification. Firstly, we used the joint application of time-domain statistic, power spectral density (PSD), common spatial pattern (CSP) and autoregressive (AR) model to extract high-dimensional fused features of the preprocessed EEG signals. Then we used the wrapped method for feature selection. We fitted the logistic regression model penalized with elastic net on the training data, and obtained the parameter estimation by coordinate descent method. Then we selected best feature subset by using 10-fold cross-validation. Finally, we classified the test sample using the trained model. Data used in the experiment were the EEG data from international BCI Competition Ⅳ. The results showed that the method proposed was suitable for fused feature selection with high-dimension. For identifying EEG signals, it is more effective and faster, and can single out a more relevant subset to obtain a relatively simple model. The average test accuracy reached 81.78%.
ObjectiveTo evaluate the predictors of generalized anxiety disorder (GAD) among teachers in 3 months after Lushan earthquake. MethodsA prospective cohort study was conducted to diagnostically evaluate the psychological sequelae and GAD during 14-20 days and 85-95 days after the earthquake. The possible predictive factors of psychological sequelae were assessed by a self-made questionnaire and the GAD was assessed by the GAD symptom criterion of M.I.N.I. in 3 months. The univariate and multivariate logistic regression analysis (ULRA, MLRA) were applied to analyze the predictors of GAD after the two-staged assessments. ResultsThere were a total of 319 teachers completed the two-staged assessments. The total response rate was 51.3%. Seventy teachers were diagnosed as GAD and the prevalence of GAD in 3 months was 21.9%. The predictive factors by ULRA included:male, older than 35 years old, having unlivable house, living in tents, sleeping difficulties, easy to feel sad, physical discomfort, loss of appetite, feeling short of social support, unable to calm down for working, feeling difficult for teaching, observing more inattention of students, and wanting to ask for a leave. The independent predictors by MLRA included:male, having unlivable house, feeling short of social support, and feeling difficult for teaching. ConclusionThe teachers have a higher likelihood of GAD after earthquake. It is essential to pay more attention to those male teachers, who feel short of social support and don't have a livable house thus to prevent the GAD at the early stage of post-earthquake.
Atrial fibrillation (AF) is the most common arrhythmia in clinic, which can cause hemodynamic changes, heart failure and stroke, and seriously affect human life and health. As a self-promoting disease, the treatment of AF can become more and more difficult with the deterioration of the disease, and the early prediction and intervention of AF is the key to curbing the deterioration of the disease. Based on this, in this study, by controlling the dose of acetylcholine, we changed the AF vulnerability of five mongrel dogs and tried to assess it by analyzing the electrophysiology of atrial epicardium under different states of sinus rhythm. Here, indices from four aspects were proposed to study the atrial activation rule. They are the variability of atrial activation rhythm, the change of the earliest atrial activation, the change of atrial activation delay and the left-right atrial dyssynchrony. By using binary logistic regression analysis, multiple indices above were transformed into the AF inducibility, which were used to classify the signals during sinus rhythm. The sensitivity, specificity and accuracy of classification reached 85.7%, 95.8% and 91.7%, respectively. As the experimental results show, the proposed method has the ability to assess the AF vulnerability of atrium, which is of great clinical significance for the early prediction and intervention of AF.
Objective To investigate the association between environmental factors and nonsyndromic cleft lip and palate (NSCLP), and to explore the interaction of main risk factors in Chinese Guangdong population. Methods A hospital-based case-control study was used. NSCLP children were selected from Cleft Lip amp; Palate Treatment Centre of Second Affil iated Hospital of Medical College of Shantou University between September 2009 and March 2010 as cases. And controlswere chosen from other departments in the same hospital during the same period. The parents of cases and controls were inquired regarding the risk factors and the answers were filled in a unification questionnaire by physicians. These data were analysed with chi-square test and multivariate unconditional logistic regression analysis. Results A total of 105 cases and 110 controls with a mean age of 2.2 years and 3.0 years, respectively, were enrolled. Multivariate logistic regression analysis revealed that genetic family history (OR=4.210, P=0.039), mothers’ abnormal reproductive history (OR=2.494, P=0.033), early pregnancy medication (OR=3.488, P=0.000), and maternal stress (OR=3.416, P=0.011) were risk factors. There were positve interactions between genetic family history and mothers’ abnormal reproductive history as well as early pregnancy medication. Conclusion Certain influencing factors including genetic family history, mothers’ abnormal reproductive history, early pregnancy medication, and maternal stress are associated with NSCLP among Chinese Guangdong population. This study suggests that it may reduce the incidence rate of NSCLP through environmental intervention.
ObjectiveTo explore the risk factors for postoperative respiratory failure (RF) in patients with esophageal cancer, construct a predictive model based on the least absolute shrinkage and selection operator (LASSO)-logistic regression, and visualize the constructed model. MethodsA retrospective analysis was conducted on patients with esophageal cancer who underwent surgical treatment in the Department of Thoracic Surgery, Sun Yat-sen University Cancer Center Gansu Hospital from 2020 to 2023. Patients were divided into a RF group and a non-RF (NRF) group according to whether RF occurred after surgery. Clinical data of the two groups were collected, and LASSO-logistic regression was used to optimize feature selection and construct the predictive model. The model was internally validated by repeated sampling 1000 times based on the Bootstrap method. ResultsA total of 217 patients were included, among which 24 were in the RF group, including 22 males and 2 females, with an average age of (63.33±9.10) years; 193 were in the NRF group, including 161 males and 32 females, with an average age of (62.14±8.44) years. LASSO-logistic regression analysis showed that the percentage of forced expiratory volume in one second/forced vital capacity (FEV1/FVC) to predicted value (FEV1/FVC%pred) [OR=0.944, 95%CI (0.897, 0.993), P=0.026], postoperative anastomotic fistula [OR=4.106, 95%CI (1.457, 11.575), P=0.008], and postoperative lung infection [OR=3.776, 95%CI (1.373, 10.388), P=0.010] were risk factors for postoperative RF in patients with esophageal cancer. Based on the above risk factors, a predictive model was constructed, with an area under the receiver operating characteristic curve of 0.819 [95%CI (0.737, 0.901)]. The Hosmer-Lemeshow test for the calibration curve showed that the model had good goodness of fit (P=0.527). The decision curve showed that the model had good clinical net benefit when the threshold probability was between 5% and 50%. Conclusion FEV1/FVC%pred, postoperative anastomotic fistula, and postoperative lung infection are risk factors for postoperative RF in patients with esophageal cancer. The predictive model constructed based on LASSO-logistic regression analysis is expected to help medical staff screen high-risk patients for early individualized intervention.
ObjectiveTo investigate the association of preoperative serum uric acid (UA) levels with postoperative prolonged mechanical ventilation (PMV) in patients undergoing mechanical heart valve replacement.MethodsClinical data of 311 patients undergoing mechanical heart valve replacement in The First Affiliated Hospital of Anhui Medical University from January 2017 to December 2017 were retrospectively analyzed. There were 164 males at age of 55.6±11.4 years and 147 females at age of 54.2±9.8 years. The patients were divided into a PMV group (>48 h) and a control group according to whether the duration of PMV was longer than 48 hours. Spearman's rank correlation coefficient and logistic regression analysis were conducted to evaluate the relationship between preoperative UA and postoperative PMV. The predictive value of UA for PMV was undertaken using the receiver operating characteristic (ROC) curve..ResultsAmong 311 patients, 38 (12.2%) developed postoperative PMV. Preoperative serum UA level mean values were 6.11±1.94 mg/dl, while the mean UA concentration in the PMV group was significantly higher than that in the control group (7.48±2.24 mg/dl vs. 5.92±1.82 mg/dl, P<0.001). Rank correlation analysis showed that UA was positively correlated with postoperative PMV (rs=0.205, P<0.001). Multivariate logistic regression analysis demonstrated that preoperative elevated UA was associated independently with postoperative PMV with odds ratio (OR)=1.44 and confidence interval (CI) 1.15–1.81 (P=0.002). The area under the ROC curve of UA predicting PMV was 0.72, 95% CI0.635–0.806, 6.40 mg/dl was the optimal cut-off value, and the sensitivity and specificity was 76.3% and 63.0% at this time, respectively.ConclusionPreoperative elevated serum UA is an independent risk factor for postoperative PMV in patients undergoing mechanical heart valve replacement and has a good predictive value.
Objective To construct and verify the diagnostic model of preoperative malignant risk of ovarian tumors, so as to improve the diagnostic efficiency of existing test indexes. Methods The related serological indicators and clinical data of patients with ovarian tumors confirmed by pathology who were treated in the Affiliated Hospital of Southwest Medical University between January 2019 and September 2023 were retrospectively collected, and the patients were randomly divided into a training set and a verification set at a 7∶3 ratio. Logistic regression was used to construct a diagnostic model in the training set, and the diagnostic efficacy of the model was verified through discrimination, calibration, clinical benefit, and clinical applicability evaluation. Results A total of 929 patients with ovarian tumors were included, including 318 cases of malignant ovarian tumors and 611 cases of benign ovarian tumors. The patients were randomly divided into a training set of 658 cases and a validation set of 271 cases. A diagnostic model was constructed using logistic regression in the training set, containing 5 factors namely age, percentage of neutrophil (NEU%), fibrinogen to albumin ratio (FAR), carbohydrate antigen 125 (CA125), and human epididymis protein 4 (HE4): modelUAM=−3.211+0.667×age+2.966×CA125+0.792×FAR+1.637×HE4+0.533×NEU%, with a Hosmer-Lemeshow test P-value of 0.21. The area under the receiver operating characteristic (ROC) curve measured in the training set was 0.927 [95% confidence interval (0.903, 0.951)], the sensitivity was 0.947, and the specificity was 0.780. The area under the ROC curve of the validation set was 0.888 [95% confidence interval (0.840, 0.930)], the sensitivity was 0.744, and the specificity was 0.901. Conclusion A new quantitative tool based on age, NEU%, FAR, CA125 and HE4 can be used for the clinical diagnosis of ovarian malignant tumors, and it is helpful to improve the diagnostic efficiency and is worth popularizing.
Abstract: Objective To investigate the method of improving effect, by investigating and analyzing the possible risk factors affecting shortterm outcome after total correction of tetralogy of Fallot (TOF). Methods Data of 219 patients who received total correction of TOF were divided into two groups according to the length of postoperative stay in hospital and recovery of heart function in the near future. Group A(n=110): patients had good recovery of heart function classified as gradeⅠorⅡ（NYHA classification）, and could smoothly be discharged from the hospital within two weeks without serious complications. The left ventricular ejection fraction (LVEF) had to exceed to 0.50 during 6 months followup visit. Group B(n=109): patients had worse recovery of heart function classified as grade Ⅱ or Ⅲ, and could not be discharged within two weeks with severe complications. LVEF was less than 0.50 during 6 months followup visit. The clinical data of two groups were compared, and risk factors affecting shortterm outcome after total correction of TOF operation were analyzed by logistic regression and model selection. Results There were good recovery of heart function classified as gradeⅠorⅡ(NYHA classification）in discharge, no death, and LVEF all exceeded to 0.50 in group A; there were 8 deaths in group B (7.34 %), and recovery of heart function was worse classified as grade Ⅱ or Ⅲ, with LVEF being less than 0.50（Plt;0.01）. Amount of postoperative daily thoracic drainage, assisted respiration time, time of inotropic agent stabilizing circulation, and the average length of postoperative stay in group A were all less or short than those in group B（Plt;0.01）. But the bypass and clamping time of group B were exceeded group A. The ratio of patching astride annulus in group B was greater than that in group A, and Nakata index was less than that in group A(Plt;0.01). The results of logistic regression and model selection indicate: age at repair (OR=0.69), oxygen saturation(OR=0.98), haematocrit before operation (OR=0.94), and patching astride annulus (OR=46.86), Nakata index (OR=16.90), amount of postoperative daily thoracic drainage (OR=0.84), presence of arrhythmia(OR=0.87), and wound infection(OR=63.57) have significant effect with shortterm outcome after total correction of TOF operation. Conclusions The probable methods to improving effect of shortterm outcome after total correction of TOF are an earlier age at repair, decreasing haematocrit, rising oxygen saturation before surgery, performing a palliative operation facilitating development of arteriae pulmonalis in earlier time, improving the surgical technique, and strengthening the perioperative care.
Objective To investigate the feasibility of diagnosis of potential chronic obstructive pulmonary disease (COPD) patients who cannot finish the pulmonary function test via biphasic CT scan. Methods Sixty-seven male individuals aged 43 to 74 (57.0±5.9) years were divided into a COPD group (n=26) and a control group (n=41). All individuals underwent biphasic quantitative CT scan for calculating the proportion of emphysema, functional small airway disease, and normal component of the whole lung and each lobe. Results Based on principle component analysis, two principal components “imaging feature function 1 and imaging feature function 2” were calculated and analyzed by logistic regression, which found that imaging feature function 1 was an independent risk factor of COPD (odds ratio=8.749, P<0.001), and imaging features function 1 could be used to assist the diagnosis of COPD (area under receiver operating characteristic curve=0.843, P<0.001). Conclusion Imaging features function 1 is an independent risk factor for COPD and can assist the diagnosis of COPD.
Erythemato-squamous diseases are a general designation of six common skin diseases, of which the differential diagnosis is a difficult problem in dermatology. This paper presents a new method based on virtual coding for qualitative variables and multinomial logistic regression penalized via elastic net. Considering the attributes of variables, a virtual coding is applied and contributes to avoid the irrationality of calculating nominal values directly. Multinomial logistic regression model penalized via elastic net is thence used to fit the correlation between the features and classification of diseases. At last, parameter estimations can be attained through coordinate descent. This method reached accuracy rate of 98.34%±0.0027% using 10-fold cross validation in the experiments. Our method attained equivalent accuracy rate compared to the results of other methods, but steps are simpler and stability is higher.