Kernel Partial Least Squares Feature Selection Based on Maximum Weight Minimum Redundancy.

Feature selection refers to a vital function in machine learning and data mining. The maximum weight minimum redundancy feature selection method not only considers the importance of features but also reduces the redundancy among features. However, the characteristics of various datasets are not identical, and thus the feature selection method should have different feature evaluation criteria for all datasets. Additionally, high-dimensional data analysis poses a challenge to enhancing the classification performance of the different feature selection methods. This study presents a kernel partial least squares feature selection method on the basis of the enhanced maximum weight minimum redundancy algorithm to simplify the calculation and improve the classification accuracy of high-dimensional datasets. By introducing a weight factor, the correlation between the maximum weight and the minimum redundancy in the evaluation criterion can be adjusted to develop an improved maximum weight minimum redundancy method. In this study, the proposed KPLS feature selection method considers the redundancy between the features and the feature weighting between any feature and a class label in different datasets. Moreover, the feature selection method proposed in this study has been tested regarding its classification accuracy on data containing noise and several datasets. The experimental findings achieved using different datasets explore the feasibility and effectiveness of the proposed method which can select an optimal feature subset and obtain great classification performance based on three different metrics when compared with other feature selection methods.

Mesenchymal Stem Cell Therapy for Acetaminophen-related Liver Injury: A Systematic Review and Meta-analysis of Experimental Studies In Vivo.

OBJECTIVE: The efficacy of mesenchymal stem cell (MSC) therapy in acetaminophen-induced liver injury has been investigated in animal experiments, but individual studies with a small sample size cannot be used to draw a clear conclusion. Therefore, we conducted a systematic review and meta-analysis of preclinical studies to explore the potential of using MSCs in acetaminophen- induced liver injury. METHODS: Eight databases were searched for studies reporting the effects of MSCs on acetaminophen hepatoxicity. The Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) guidelines were used. SYRCLE's risk of bias tool for animal studies was applied to assess the methodological quality. A meta-analysis was performed by using RevMan 5.4 and STATA/ SE 16.0 software. RESULTS: Eleven studies involving 159 animals were included according to PRISMA statement guidelines. Significant associations were found for MSCs with the levels of alanine transaminase (ALT) (standardized mean difference (SMD) - 2.58, p < 0.0001), aspartate aminotransferase (AST) (SMD - 1.75, p = 0.001), glutathione (GSH) (SMD 3.7, p < 0.0001), superoxide dismutase (SOD) (SMD 1.86, p = 0.022), interleukin 10 (IL-10) (SMD 5.14, p = 0.0002) and tumor necrosis factor-α (TNF-α) (SMD - 4.48, p = 0.011) compared with those in the control group. The subgroup analysis showed that the tissue source of MSCs significantly affected the therapeutic efficacy (p < 0.05). CONCLUSION: Our meta-analysis results demonstrate that MSCs could be a potential treatment for acetaminophen- related liver injury. The protocol for this meta-analysis was prospectively registered in PROSPERO (Number: CRD42020212677).

Relative Density-Based Intuitionistic Fuzzy SVM for Class Imbalance Learning.

The support vector machine (SVM) has been combined with the intuitionistic fuzzy set to suppress the negative impact of noises and outliers in classification. However, it has some inherent defects, resulting in the inaccurate prior distribution estimation for datasets, especially the imbalanced datasets with non-normally distributed data, further reducing the performance of the classification model for imbalance learning. To solve these problems, we propose a novel relative density-based intuitionistic fuzzy support vector machine (RIFSVM) algorithm for imbalanced learning in the presence of noise and outliers. In our proposed algorithm, the relative density, which is estimated by adopting the k-nearest-neighbor distances, is used to calculate the intuitionistic fuzzy numbers. The fuzzy values of the majority class instances are designed by multiplying the score function of the intuitionistic fuzzy number by the imbalance ratio, and the fuzzy values of minority class instances are assigned the intuitionistic fuzzy membership degree. With the help of the strong capture ability of the relative density to prior information and the strong recognition ability of the intuitionistic fuzzy score function to noises and outliers, the proposed RIFSVM not only reduces the influence of class imbalance but also suppresses the impact of noises and outliers, and further improves the classification performance. Experiments on the synthetic and public imbalanced datasets show that our approach has better performance in terms of G-Means, F-Measures, and AUC than the other class imbalance classification algorithms.

Effectiveness and safety of electroacupuncture for insomnia: A protocol for an overview of systematic reviews and meta-analysis.

BACKGROUND: Insomnia is a common disease characterized by difficulty falling and/or staying asleep, and accompanied by irritability or fatigue during wakefulness. It is widely reported that insomnia is one of the most extensive mental disorders which the incidence rate is estimated to be about 10%. Insomnia can have serious influences on patients health and quality of life. Electro acupuncture (EA) is reported to be efficacious and widely used for the treatment of insomnia in China. This overview aims to summarize the available evidence from current systematic reviews for the efficacy of electroacupuncture therapy for insomnia. METHODS: We will make a comprehensive retrieval in 7 databases as following:The time is limited from the construction of the library to August 2020. We will use the Assessment of Multiple Systematic Reviews-2 (AMSTAR-2) tool to evaluate methodological quality. Preferred Reporting Items for Systematic Reviews and Meta-analysis Protocols (PRISMA-P) will be used in the report checklist to assess the quality of reports in the study. The Grading of the Classification of Recommendations, Evaluation, Development and Evaluation (GRADE) will be used to evaluate the included SRs and meta-analysis. Our reviewers will conduct systematic reviews, qualification evaluation, data extraction, methodological quality and evidence quality screening in pairs. The outcomes of interest include: The Pittsburgh Sleep Quality Index (PSQI), The Insomnia Severity Index (ISI), Athens Insomnia Scale, Sleep parameters measured by either subjective or objective approaches, such as actigraphy, polysomnogram, and electroencephalogram. Or any other scale used to assess the level of illness. The evidence will be synthesized where appropriate based on patient subgroups and outcomes. RESULTS: The results will be published in a peer-reviewed journal. TRIAL REGISTRATION NUMBER: INPLASY202080087. CONCLUSION: This overview will provide comprehensive evidence of EA for patients with insomnia.

Utility of MELD scoring system for assessing the prognosis of acute fatty liver of pregnancy.

OBJECTIVE: To evaluate the value of Model for end-stage liver disease (MELD) in assessing the prognosis of acute fatty liver of pregnancy (AFLP). STUDY DESIGN: This was a retrospective study. From January 2010 to July 2018, data of 53 women diagnosed with AFLP in the third affiliated hospital of Sun Yat-Sen University were collected. Blood samples were collected on admission and MELD score was calculated. The MELD score was calculated by using the original MELD formula as shown: 9.57 log (creatinine) + 3.78 log (bilirubin) + 11.20 log (international normalized ratio, INR) + 6.43. The perinatal outcomes were documented. RESULTS: Nine women were excluded as they were transfered to our hospital after delivery in other hospitals. The remaining 44 women had average age of 28.8 ±â€¯5.2 years. The MELD score showed good performance in predicting most of the perinatal complications of AFLP with all the area under the receiver operating characteristic (ROC) curves (AUC) > 0.8, including ascites (AUC: 0.91, 95% CI: 0.78-0.98), wound seroma (AUC: 0.91, 95% CI: 0.78-0.93), hepatic encephalopathy (AUC: 0.93, 95% CI: 0.82-0.99), DIC (AUC: 0.87, 95% CI: 0.74-0.95), sepsis (AUC: 0.93, 95% CI: 0.82-0.99), renal insufficiency (AUC: 0.94, 95% CI: 0.82-0.99) and stillbirth (AUC: 0.85, 95% CI: 0.71-0.94). Nearly all the maternal complications were more frequently happened in MELD score ≥30 group (P < 0.05). CONCLUSION: MELD scoring system may be a suitable method for assessing the prognosis of AFLP.

First-trimester fasting plasma glucose as a predictor of gestational diabetes mellitus and the association with adverse pregnancy outcomes.

OBJECTIVE: To evaluate the usefulness of a fasting plasma glucose (FPG) at the first trimester in predicting gestational diabetes mellitus (GDM) and the association between FPG and adverse pregnancy outcomes. METHODS: The levels of FPG in women with singleton pregnancies were measured at 9-13+6 weeks. A two hour 75-g oral glucose tolerance test (OGTT) was completed at 24-28 weeks and the International Association of Diabetes and Pregnancy Study Groups (IADPSG) criteria was used. Adverse pregnancy outcomes were assessed and recorded. RESULTS: Among 2112 pregnant women enrolled in the study, 224 (10.6%) subjects were diagnosed with GDM. The AUC for FPG in predicting GDM was 0.63 (95% CI 0.61- 0.65) and the optimal cutoff value was 4.5 mmol/L (sensitivity 64.29% and specificity 56.45%). Higher first-trimester FPG increased the prevalence of GDM, large for gestational age (LGA) and assisted vaginal delivery and/or cesarean section (all P < 0.05). CONCLUSION: FPG at first trimester could be used to predict GDM and higher first-trimester FPG was associated with adverse pregnancy outcomes.

Effect of mildly elevated thyroid-stimulating hormone during the first trimester on adverse pregnancy outcomes.

BACKGROUND: To investigate the effect of a mildly elevated thyroid-stimulating hormone (TSH) concentration between 2.5 and 4.0 mIU/L during the first trimester on pregnancy outcomes in thyroid peroxydase antibody (TPOAb)-negative pregnant women. METHODS: A total of 1858 pregnant women who were TPOAb-negative before 13+ 6 gestational weeks, received regular prenatal services, and delivered in the third affiliated hospital of Sun Yat-Sen University were recruited from June 2016 to June 2017. Measurements of thyroid function (TSH, free T4 [FT4] and TPOAb) and adverse pregnancy outcomes were assessed and recorded. RESULTS: Among the 1858 study participants, the 97.5th percentile for TSH was 3.76 mIU/L, and 142 women (7.6%) had mildly elevated TSH levels between 2.5 and 4.0 mIU/L. No differences in the incidence of adverse pregnancy outcomes were observed between patients with a mildly elevated TSH level and those with a normal TSH level (< 2.5 mIU/L). CONCLUSION: A mildly elevated TSH concentration (2.5-4.0 mIU/L) during the first trimester of pregnancy in TPOAb-negative women was not associated with adverse pregnancy outcomes in our study population. Accordingly, it may be possible to raise the upper limit of the healthy TSH reference range for pregnant women.

First Trimester Neck Circumference as a Predictor for the Development of Gestational Diabetes Mellitus.

BACKGROUNDS: This study aimed to evaluate the relationship between neck circumference (NC) and gestational diabetes mellitus (GDM), and the efficacy of NC in predicting GDM by comparing with pregestational body mass index (preBMI) in southern Chinese woman. MARERIALS AND METHODS: A total of 371 pregnant women (97 GDM and 274 normal pregnant women) were recruited from the third affiliated hospital of Sun Yat-Sen University, Guangzhou, China. NC was measured at 11-13+6 gestational weeks. GDM was diagnosed through a 75-g oral glucose tolerance test at 24-28 gestational weeks. Using the receiver-operator characteristic (ROC) curve analysis, we evaluated the association between NC and GDM. RESULTS: The area under the receiver operator characteristic curves were 0.65 (95% CI: 0.60-0.70) for NC and 0.64 (95% CI: 0.59-0.69) for preBMI in diagnosing GDM and no difference was found between them (P = 0.66). NC ≥ 33.8cm was determined to be the best cut-off level for identifying subjects with GDM (sensitivity 68.04% and specificity 59.12%). Multivariate logistic regression analysis showed that a large NC in the first trimester was an independent risk factor for the development of GDM (odds ratio [OR] = 1.29, 95% CI: 1.72-7.45). CONCLUSIONS: NC, as well as preBMI, might be a novel anthropometric index for GDM screening. The increase of NC could be an independent risk factor for GDM in first trimester pregnancy.

Proteomic identification of candidate plasma biomarkers for preeclampsia in women with pregnancy-induced hypertension.

Preeclampsia (PE), a complication of pregnancy, is the leading cause of maternal and perinatal morbidity and mortality and seriously impacts maternal and child health. This study aimed to characterize biomarkers for the early diagnosis of PE. We performed a comparative proteomic analysis on the plasma obtained from PE and healthy pregnant women. We analyzed the plasma samples using two-dimensional differential gel electrophoresis (2D-DIGE) coupled with Ultraflex III, a MALDI-TOF-TOF (matrix-assisted laser desorption/ionization-time-of-flight) mass spectrometer and identified differentially expressed proteins (DEPs). We analyzed the abundance levels of these DEPs by enzyme-linked immunosorbent assay (ELISA) to further confirm their role as putative PE biomarkers. We identified a total of 56 DEPs, of which 48 were down-regulated and 8 were up-regulated in women with PE. The identities of 8 of these DEPs were characterized by mass spectrum analysis, including LG3BP (lectin, galactoside-binding, soluble, 3 binding protein), APOA1 (apolipoprotein A-I), FETUA (alpha-2-HS-glycoprotein), CFAI (complement factor I), CD5L (CD5 antigen-like), K2C6A (keratin, type II cytoskeletal 6A), PON1 (paraoxonase/arylesterase 1) and HP1 (haptoglobin). Finally, the differential expression of these 8 proteins was verified by ELISA. In summary, we applied the 2D-DIGE and Ultraflex III-TOF/TOF platform to identify potential plasma biomarkers of PE. Of these, plasma LG3BP, APOA1, FETUA, CFAI, CD5L, K2C6A, PON1 and HP1 were promising candidates for predicting PE.

Utility of Pregestational Body Mass Index and Initial Fasting Plasma Glucose in Predicting Gestational Diabetes Mellitus.

OBJECTIVE: The present study aimed to evaluate the pregestational body mass index (preBMI) and initial fasting plasma glucose (FPG) in predicting gestational diabetes mellitus (GDM) in southern Chinese women. STUDY DESIGN: A total of 327 pregnant women were recruited from the third affiliated hospital of Sun Yat-Sen University, Guangzhou, China. The preBMI and initial FPG at 16-18 weeks' gestation were measured. Oral glucose tolerance test was performed at 24-28 weeks' gestation. The sensitivity and specificity of preBMI and initial FPG as predictors for GDM were evaluated by receiver-operator characteristic curve analysis. RESULTS: Both preBMI and initial FPG correlated with the 0-hour, 1-hour and 2-hour plasma glucose during oral glucose tolerance test (P < 0.05). The area under receiver-operator characteristic curve was 0.63 (95% CI: 0.57-0.68) for preBMI and 0.68 (95% CI: 0.61-0.72) for initial FPG in diagnosing GDM. The optimal cutoff for preBMI was 21.5 kg/m(2) (sensitivity 52.1% and specificity 69.2%) and 4.6 mmol/L (sensitivity 64.6% and specificity 65.2%) for initial FPG. Interestingly, the initial FPG had a better sensitivity compared to preBMI when the specificity was the same. Multivariate logistic regression analysis showed that initial FPG but not preBMI was the independent risk factor for the later development of GDM. After adjustment for the preBMI and the maternal age, the odds ratios of initial FPG and parity were 3.57 (95% CI: 1.72-7.45) and 2.11 (95% CI: 1.20-3.72). CONCLUSIONS: Although both preBMI and initial FPG could be used as indicators for GDM, the initial FPG may be more suitable for predicting GDM in southern Chinese women.

Sparse LSSVM in Primal Using Cholesky Factorization for Large-Scale Problems.

For support vector machine (SVM) learning, least squares SVM (LSSVM), derived by duality LSSVM (D-LSSVM), is a widely used model, because it has an explicit solution. One obvious limitation of the model is that the solution lacks sparseness, which limits it from training large-scale problems efficiently. In this paper, we derive an equivalent LSSVM model in primal space LSSVM (P-LSSVM) by the representer theorem and prove that P-LSSVM can be solved exactly at some sparse solutions for problems with low-rank kernel matrices. Two algorithms are proposed for finding the sparse (approximate) solution of P-LSSVM by Cholesky factorization. One is based on the decomposition of the kernel matrix K as P P(T) with the best low-rank matrix P approximately by pivoting Cholesky factorization. The other is based on solving P-LSSVM by approximating the Cholesky factorization of the Hessian matrix with rank-one update scheme. For linear learning problems, theoretical analysis and experimental results support that P-LSSVM can give the sparsest solutions in all SVM learners. Experimental results on some large-scale nonlinear training problems show that our algorithms, based on P-LSSVM, can converge to acceptable test accuracies at very sparse solutions with a sparsity level <1%, and even as little as 0.01%. Hence, our algorithms are a better choice for large-scale training problems.

Development of strategies for screening, predicting, and diagnosing intrauterine HBV infection in infants born to HBsAg positive mothers.

This study aimed at developing strategies for screening, predicting, and diagnosing intrauterine HBV infection in infants born to HBsAg positive mothers. A total of 1,360 infants born to 1,355 HBsAg positive mothers were followed for 1 year. All newborn infants received active and passive immunization within 24 hr after birth. Maternal and infant blood samples were collected and tested for the status of serum HBsAg, HBeAg, and HBV DNA positivity. The accuracy of infant HBsAg positivity, HBV DNA positivity, HBsAg and HBV DNA double positivity, and HBsAg and/or HBV DNA positivity at birth in the diagnosis of intrauterine HBV infection was evaluated by receiver operating characteristic curve analysis. Of 1,360 infants, 145 tested positive for HBsAg and/or HBV DNA at birth. Twenty-one (1.5%) infants, who were diagnosed with intrauterine HBV infection, showed HBsAg positivity from birth to 7 and 12 months of age. Infant HBsAg positivity at birth had the highest sensitivity in predicting intrauterine HBV infection, while neonatal HBsAg and HBV DNA double positivity had the highest specificity. These findings suggest that infants, who were born to HBsAg positive mothers and were positive for both HBsAg and HBV DNA at birth, may be at a higher risk for intrauterine HBV infection. HBsAg positivity at birth may be a good marker for screening intrauterine HBV infection. Infant HBsAg positivity both at birth and 7 months of age may be used as a diagnostic criterion to simplify diagnostic procedures and improve diagnostic efficiency.

Clinical characteristics of fulminant hepatitis in pregnancy.

AIM: To investigate the clinical characteristics of fulminant hepatitis in pregnancy. METHODS: We compared and analyzed the etiology, clinical characteristics, and laboratory examinations of 25 cases of fulminant hepatitis in pregnancy and 30 cases of fulminant hepatitis not in pregnancy. RESULTS: HBV infection and chronic fulminant hepatitis were most common both in the pregnant and in the non-pregnant groups. Jaundice, digestive tract symptoms, increase of bilirubin and thrombinogen activity were the main manifestations. The incidence of hepatic encephalopathy (HE) and hepato-renal syndrome (HRS) was significantly different between the two groups. The incidence of preterm labor, dead fetus and neonatal asphyxia was high. CONCLUSION: Fulminant hepatitis is likely to occur in late pregnancy with more severe complications, which significantly influences maternity, perinatal fetus, and newborn.

Analyses of prognostic indices of chronic liver failure caused by hepatitis virus.

AIM: To analyze the related indices about the prognoses of chronic liver failure caused by hepatitis virus. METHODS: Retrospectively reviewed 320 cases of chronic liver failure caused by hepatitis viruses. An improved group and an ineffective group (IG) were made to compare and analyze their clinical manifestations, laboratory examination indices and complications. Logistic regression was also carried out. RESULTS: There were significant differences (P<0.05) between the improved group and the IG upon such indices as age, bilirubin, prothrombin time, albumin, alpha fetoprotein, the size of liver and complications (P<0.05). The regression formula was as follows: P = 1/(1+e(-y)) (y = 1.7262-0.0948X(1)+2.9846X(2)+0.6992X(3)+1.6019X(4)+ 2.0398X(5)). (Note: X(1)-Prothrombin activity; X(2)-digestive tract hemorrhage; X(3)-hepatic encephalopathy; X(4)-hepatorenal syndrome; X(5)-pulmonary infection.). CONCLUSION: Laboratory examination such as bilirubin, prothrombin time and alpha fetoprotein can be regarded as indices of the prognoses of chronic liver failure caused by hepatitis. Moreover, the regression equation can evaluate prognoses more comprehensively and direct our treatments.

[Relations of pre-pregnant weight and weight gain during pregnancy with pregnancy-induced hypertension and birth weight].

OBJECTIVE: To determine the influence of pre-pregnant body mass index (BMI) and weight gain during pregnancy on the occurrence of pregnancy-induced hypertension (PIH) and birth weight. METHODS: Pre-pregnant BMI and pregnancy weight gain of 769 mothers giving full-term birth to a single baby for the first time were measured and the pregnancy outcomes were followed up. RESULTS: (1) The incidence of PIH and fetal macrosomia was significantly higher in the overweight group than in the normal weight and underweight groups (P<0.01 and P<0.05, respectively), but differed little between the latter two groups (P>0.05). Underweight mothers were more likely to give birth to babies with low birth weight than the normal and overweight mothers (P<0.01), but the likelihood was similar between the latter two groups (P>0.05). (2) Irrespective of the pre-pregnant BMI, PIH and fetal macrosomia occurred at higher rates with the mothers with pregnancy weight gain no less than 18 kg (P<0.01), whereas low birth weight was significantly more likely with mothers with pregnancy weight gain less than 9 kg (P<0.01). (3) A weight gain during pregnancy over 18 kg gave rise to higher risk of PIH in normal and underweight mothers, but in overweight group, PIH occurred at a significantly higher rates when a weight gain more than 9 kg was recorded (P<0.05). The incidence of fetal macrosomia was significantly higher when the maternal weight gain exceeded 18 kg in the normal weight group (P<0.01), and low birth weight occurred more frequently in relation to a maternal weight gain less than 9 kg in the normal and underweight groups (P<0.01). CONCLUSION: Pre-pregnant BMI and weight gain during pregnancy can be important factors influencing the occurrence of PIH and the neonates' birth weight.

[Clinical analysis and treatment of hypospadias accompanied by associated anomalies in urogenital system].

OBJECTIVES: To study the occurrence of different anomalies associated with hypospadias and to instruct relevant treatment in clinical practice. METHODS: Three hundred and forty-one cases of hypospadias were investigated, all treated respectively corresponding to their specific anomalies. RESULTS: The morbidity of associated anomalies in cases of hypospadias was as high as 21.1%. Most of the anomaly cases were undescended testes and inguinal hernia, and the incidence of associated anomalies was related to the degree of hypospadias. CONCLUSIONS: Hypospadias is not just a local dysmorphic problem but rather a local manifestation of a systemic disease. It is necessary to take those associated anomalies as a systemic whole and attach enough importance to their clinical treatment.

[Papillary cystadenoma of the epididymis accompanied by testicular atrophy: one case report].

Papillary cystadenoma of the epididymis is a rare benign tumor, accounting for only 4 per cent of all epididymal tumors. Histologically, it can be confused with metastatic renal cell carcinoma. This extremely rare lesion may occur sporadically or as a manifestation of von Hippel-Lindau(VHL) disease. The present paper reported a case of papillary cystadenoma accompanied by testicular atrophy with no signs of VHL syndrome or infertility. To date, no similar case was reported in the literature. The tumor measured 5.0 cm x 4.0 cm x 4.0 cm and was located in the right epididymis. Histopathologic examination of a surgically removed specimen indicated a primary papillary cystadenoma. Histomorphologically, these tumors are characterized by cysts with colloid-like contents and papillary formations of light epithelium. Since metastatic renal cell carcinoma may be histologically similar to papillary cystadenoma, the importance of long-term urologic follow-up for possible presentation of renal cell carcinoma is discussed.