Objective This study aimed to investigate whether cesarean delivery (CD) is associated with the occurrence of neurodevelopmental disorders (NDDs) at the age of 8 years. Methods A total of 19 142 children were included from the Taiwan Birth Cohort Study (TBCS) database. Associations between modes of delivery or modalities of CD and NDDs were evaluated before and after controlling for gestational age (GA) and clinical condition at birth, children's characteristics, maternal socioeconomic status and maternal clinical condition at childbirth. Results The odds ratio (OR) of occurrence of NDDs in children born via CD was 1.15 and the 95% confidence interval (CI) was 1.00-1.32. Emergency CD had a higher occurrence of NDDs (OR: 1.38; 95% CI: 1.16-1.65) compared with vaginal delivery. These associations were attenuated after controlling for children's and maternal characteristics and GA at birth. GA at birth had a significant reverse dose-effect on the occurrence of NDDs in children born via vaginal delivery and CD. Conclusion Modes of delivery and GA could influence the occurrence of NDDs in childhood. However, association of risk of NDDs and modes of delivery or modalities of CD might be modified by males, lower socioeconomic status and mothers with gestational diabetes mellitus.

Interstitial cystitis/bladder pain syndrome (IC/BPS) is characterized by bladder pain accompanied by irritative urinary symptoms, and typical cystoscopic and histological features. In this pilot study, we assessed the impact of lesion-targeted bladder injection therapy using a biocellular regenerative medicine on patients with refractory IC/BPS. The medicine, which was an autologous emulsified fat (Nanofat) and platelet-rich plasma (PRP) combination, was prepared intraoperatively. Six patients (aged 40-54 years), who completed a standard protocol of four consecutive treatments at 3-month intervals, were followed up at 6 months postoperatively. All patients (100%) reported marked (+3; +3 ~ -3) improvement of their overall bladder conditions. Mean bladder pain (from 8.2 to 1.7; range: 0 ~ 10), IC-related symptoms (from 18.5 to 5.7; range: 0 ~ 20), and bother (from 14.8 to 3.8; range: 0 ~ 16) improved significantly (p < 0.01). The normalization of bladder mucosal morphology with treatments was remarkable under cystoscopic examination, and no significant adverse events were found. The cultured mesenchymal stem cells from Nanofat samples of the six patients were verified in vitro. Our preliminary results suggest novel intravesical therapy with autologous Nanofat plus PRP grafting is safe and effective for refractory IC/BPS. Surgical efficacy might be attributed to an in vivo tissue engineering process.

Previous studies on CKD patients have mostly been retrospective, cross-sectional studies. Few studies have assessed the longitudinal assessment of patients over an extended period. In consideration of the heterogeneity of CKD progression. It's critical to develop a longitudinal diagnosis and prognosis for CKD patients. We proposed an auto Machine Learning (ML) scheme in this study. It consists of four main parts: classification pipeline, cross-validation (CV), Taguchi method and improve strategies. This study includes datasets from 50,174 patients, data were collected from 32 chain clinics and three special physical examination centers, between 2015 and 2019. The proposed auto-ML scheme can auto-select the level of each strategy to associate with a classifier which finally shows an acceptable testing accuracy of 86.17%, balanced accuracy of 84.08%, sensitivity of 90.90% and specificity of 77.26%, precision of 88.27%, and F1 score of 89.57%. In addition, the experimental results showed that age, creatinine, high blood pressure, smoking are important risk factors, and has been proven in previous studies. Our auto-ML scheme light on the possibility of evaluation for the effectiveness of one or a combination of those risk factors. This methodology may provide essential information and longitudinal change for personalized treatment in the future.

Developing effective risk prediction models is a cost-effective approach to predicting complications of chronic kidney disease (CKD) and mortality rates; however, there is inadequate evidence to support screening for CKD. In this study, four data mining algorithms, including a classification and regression tree, a C4.5 decision tree, a linear discriminant analysis, and an extreme learning machine, are used to predict early CKD. The study includes datasets from 19,270 patients, provided by an adult health examination program from 32 chain clinics and three special physical examination centers, between 2015 and 2019. There were 11 independent variables, and the glomerular filtration rate (GFR) was used as the predictive variable. The C4.5 decision tree algorithm outperformed the three comparison models for predicting early CKD based on accuracy, sensitivity, specificity, and area under the curve metrics. It is, therefore, a promising method for early CKD prediction. The experimental results showed that Urine protein and creatinine ratio (UPCR), Proteinuria (PRO), Red blood cells (RBC), Glucose Fasting (GLU), Triglycerides (TG), Total Cholesterol (T-CHO), age, and gender are important risk factors. CKD care is closely related to primary care level and is recognized as a healthcare priority in national strategy. The proposed risk prediction models can support the important influence of personality and health examination representations in predicting early CKD.

Objective: To examine changes in the number and causes of maternal deaths after the introduction of pregnancy checkbox on the death certificate in January 2014 in Taiwan. Materials and methods: We first used the cause-of-death (COD) mortality data for years 2010 through 2017 to examine the number of deaths by item of pregnancy checkbox. We then compared the distribution of the causes of maternal deaths before and after the introduction of pregnancy checkbox. Results: Between 2014 and 2017, 111 women died, for whom the certifiers indicated the following in the pregnancy checkbox items: 2 (pregnant at the time of death; n = 10), 3 (died within 42 days after the termination of pregnancy; n = 64), and 4 (died between 43 days and 1 year after the termination of pregnancy; n = 37). However, in only 61 of the 111 deaths, the certifiers reported pregnancy or delivery-related diagnosis in the COD section of the death certificate-5 each for items 2 and 4 and 51 for item 3. The number of maternal deaths was 55 in 2010-2013; this number increased to 82 in 2014-2017. A decline in the percentage of maternal deaths from obstetric hemorrhage was noted from 38% (21/55) in 2010-2013 to 21% (17/82) in 2014-2017. Conclusion: The number of maternal deaths increased, and the distribution of causes of maternal deaths changed after the introduction of pregnancy checkbox. Additional studies are required to examine the possible misclassification of pregnancy-associated deaths indicated in the pregnancy checkbox. (C) 2019 Taiwan Association of Obstetrics & Gynecology. Publishing services by Elsevier B.V.

Objective: Intravesical hyaluronic acid (HA) therapy is one of acceptable methods to treat bladder pain and storage symptoms (i.e., urgency, frequency and nocturia) of interstitial cystitis/bladder pain syndrome (IC/BPS). We aim to assess the impacts of intravesical HA on bladder pain and storage symptoms, respectively, and to investigate their associated factors in patients with IC/BPS. Materials and methods: In this prospective, multicenter study, 103 women with refractory IC/BPS undergoing a standard protocol of intravesical HA therapy were enrolled. A pain Visual Analog Scale (VAS) and the Interstitial Cystitis Symptom and Problem Index (ICSI & ICPI) were used to assess symptoms and bother associated with IC/BPS. The Scaled Global Response Assessment (GRA) was used to evaluate patients' perception of overall changes in bladder pain and storage symptoms, respectively, after treatment. Results: Mean age of participants was 43.6 +/- 11.8 years. The average duration of symptoms was 5.1 +/- 5.0 years. Significant improvements in pain VAS, ICSI and ICPI scores were observed after treatment. However, patients reported significantly different rates of moderate/marked improvement in bladder pain and storage symptoms (73.8% vs. 47.6%; P < 0.001) on the GRA, respectively. "Lower pain VAS score" and "reduced functional bladder capacity" were found to be the factors that adversely affected the treatment responses of bladder pain and storage symptoms, respectively, after repeated statistical analyses. Conclusion: Bladder instillation of HA seemed more efficient in improving bladder pain than storage symptoms associated with IC/BPS. The persistence of bladder storage symptoms after treatment might result from a reduced functional bladder capacity. (C) 2019 Taiwan Association of Obstetrics & Gynecology. Publishing services by Elsevier B.V.

OBJECTIVE:To evaluate the short-term effect of routine early postpartum electromyographic biofeedback assisted pelvic floor muscle training on sexual function and lower urinary tract symptoms.MATERIALS AND METHODS:From December 2016 to November 2017, primiparous women with vaginal delivery, who experienced non-extended second-degree perineal laceration were invited to participate. Seventy-five participants were assigned into a pelvic floor muscle training (PFMT) group or control group. Women in the PFMT group received supervised biofeedback-assisted pelvic floor muscle training at the 1st week and 4th week postpartum. Exercises were performed at home with the same protocol until 6 weeks postpartum. The Pelvic Organ Prolapse Urinary Incontinence Sexual Questionnaire (PISQ-12) and the Urinary Distress Inventory short form questionnaire (UDI-6) were used to evaluate sexual function and lower urinary tract symptoms respectively at immediate postpartum, 6 weeks, 3 months, and 6 months postpartum.RESULTS:Forty-five women (23 in PFMT group,22 in control group) completed all questionnaires at 6 months postpartum. For overall sexual function and the three sexual functional domains, no statistically significant difference was found in PISQ scores from baseline to 6 weeks, 3 months, and 6 months postpartum between the PFMT and control groups. For postpartum lower urinary tract symptoms, all symptoms gradually improved over time for both groups without a statistically significant difference between groups.CONCLUSION:Our study showed that supervised biofeedback-assisted pelvic floor muscle training started routinely at one week postpartum did not provide additional improvement in postpartum sexual function and lower urinary tract symptoms.

In this paper, a computational method based on machine learning technique for identifying Alzheimer's disease genes is proposed. Compared with most existing machine learning based methods, existing methods predict Alzheimer's disease genes by using structural magnetic resonance imaging (MRI) technique. Most methods have attained acceptable results, but the cost is expensive and time consuming. Thus, we proposed a computational method for identifying Alzheimer disease genes by use of the sequence information of proteins, and classify the feature vectors by random forest. In the proposed method, the gene protein information is extracted by adaptive k-skip-n-gram features. The proposed method can attain the accuracy to 85.5% on the selected UniProt dataset, which has been demonstrated by the experimental results.

Alzheimer’s disease (AD) is considered to one of 10 key diseases leading to death in humans. AD is considered the main cause of brain degeneration, and will lead to dementia. It is beneficial for affected patients to be diagnosed with the disease at an early stage so that efforts to manage the patient can begin as soon as possible. Most existing protocols diagnose AD by way of magnetic resonance imaging (MRI). However, because the size of the images produced is large, existing techniques that employ MRI technology are expensive and time-consuming to perform. With this in mind, in the current study, AD is predicted instead by the use of a support vector machine (SVM) method based on gene-coding protein sequence information. In our proposed method, the frequency of two consecutive amino acids is used to describe the sequence information. The accuracy of the proposed method for identifying AD is 85.7%, which is demonstrated by the obtained experimental results. The experimental results also show that the sequence information of gene-coding proteins can be used to predict AD.

ObjectivesWhether birth by caesarean section (CS) increases the occurrence of neurodevelopmental disorders, asthma or obesity in childhood is controversial. We tried to demonstrate the association between children born by CS and the occurrence of the above three diseases at the age of 5.5 years.MethodsThe database of the Taiwan Birth Cohort Study which was designed to assess the developmental trajectories of 24 200 children born in 2005 was used in this study. Associations between children born by CS and these three diseases were evaluated before and after controlling for gestational age (GA) at birth, children’s characteristics and disease-related predisposing factors.ResultsChildren born by CS had significant increases in neurodevelopmental disorders (20%), asthma (14%) and obesity (18%) compared with children born by vaginal delivery. The association between neurodevelopmental disorders and CS was attenuated after controlling for GA at birth (OR 1.15; 95% CI 0.98 to 1.34). Occurrence of neurodevelopmental disorders steadily declined with increasing GA up to ≤40–42 weeks. CS and childhood asthma were not significantly associated after controlling for parental history of asthma and GA at birth. Obesity in childhood remained significantly associated with CS (OR 1.13; 95% CI 1.04 to 1.24) after controlling for GA and disease-related factors.ConclusionsOur results implied that the association between CS birth and children’s neurodevelopmental disorders was significantly influenced by GA. CS birth was weakly associated with childhood asthma since parental asthma and preterm births are stronger predisposing factors. The association between CS birth and childhood obesity was robust after controlling for disease-related factors.

Ovarian cancer is the second leading cause of deaths among gynecologic cancers in the world. Approximately 90% of women with ovarian cancer reported having symptoms long before a diagnosis was made. Literature shows that recurrence should be predicted with regard to their personal risk factors and the clinical symptoms of this devastating cancer. In this study, ensemble learning and five data mining approaches, including support vector machine (SVM), C5.0, extreme learning machine (ELM), multivariate adaptive regression splines (MARS), and random forest (RF), were integrated to rank the importance of risk factors and diagnose the recurrence of ovarian cancer. The medical records and pathologic status were extracted from the Chung Shan Medical University Hospital Tumor Registry. Experimental results illustrated that the integrated C5.0 model is a superior approach in predicting the recurrence of ovarian cancer. Moreover, the classification accuracies of C5.0, ELM, MARS, RF, and SVM indeed increased after using the selected important risk factors as predictors. Our findings suggest that The International Federation of Gynecology and Obstetrics (FIGO), Pathologic M, Age, and Pathologic T were the four most critical risk factors for ovarian cancer recurrence. In summary, the above information can support the important influence of personality and clinical symptom representations on all phases of guide interventions, with the complexities of multiple symptoms associated with ovarian cancer in all phases of the recurrent trajectory.

BACKGROUND/PURPOSE:Mesh-augmented vaginal surgery for treatment of pelvic organ prolapse (POP) does not meet patients' needs. This study aims to test the hypothesis that fascia tissue engineering using adipose-derived stem cells (ADSCs) might be a potential therapeutic strategy for reconstructing the pelvic floor. METHODS:Human ADSCs were isolated, differentiated, and characterized in vitro. Both ADSCs and fibroblastic-differentiated ADSCs were used to fabricate tissue-engineered fascia equivalents, which were then transplanted under the back skin of experimental nude mice. RESULTS:ADSCs prepared in our laboratory were characterized as a group of mesenchymal stem cells. In vitro fibroblastic differentiation of ADSCs showed significantly increased gene expression of cellular collagen type I and elastin (p < 0.05) concomitantly with morphological changes. By contrast, ADSCs cultured in control medium did not demonstrate these changes. Both of the engrafted fascia equivalents could be traced up to 12 weeks after transplantation in the subsequent animal study. Furthermore, the histological outcomes differed with a thin (111.0 ± 19.8 μm) lamellar connective tissue or a thick (414.3 ± 114.9 μm) adhesive fibrous tissue formation between the transplantation of ADSCs and fibroblastic-differentiated ADSCs, respectively. Nonetheless, the implantation of a scaffold without cell seeding (the control group) resulted in a thin (102.0 ± 17.1 μm) fibrotic band and tissue contracture. CONCLUSION:Our results suggest the ADSC-seeded implant is better than the implant alone in enhancing tissue regeneration after transplantation. ADSCs with or without fibroblastic differentiation might have a potential but different role in fascia tissue engineering to repair POP in the future.

This study applied advanced machine learning techniques, widely considered as the most successful method to produce objective to an inferential problem of recurrent cervical cancer. Traditionally, clinical diagnosis of recurrent cervical cancer was based on physician’s clinical experience with various risk factors. Since the risk factors are broad categories, years of clinical study and experience have tried to identify key risk factors for recurrence. In this study, three machine learning approaches including support vector machine, C5.0 and extreme learning machine were considered to find important risk factors to predict the recurrence-proneness for cervical cancer. The medical records and pathology were accessible by the Chung Shan Medical University Hospital Tumor Registry. Experimental results illustrate that C5.0 model is the most useful approach to the discovery of recurrence-proneness factors. Our findings suggest that four most important recurrence-proneness factors were Pathologic Stage, Pathologic T, Cell Type and RT Target Summary. In particular, Pathologic Stage and Pathologic T were important and independent prognostic factor. To study the benefit of adjuvant therapy, clinical trials should randomize patients stratified by these prognostic factors, and to improve surveillance after treatment might lead to earlier detection of relapse, and precise assessment of recurrent status could improve outcome.