Abstract:Various methods can be applied to build predictive models for the clinical data with binary outcome variables.This research aims to compare and explore the process of constructing common predictive models. Models based on an artificial neural network (the multilayer perceptron) and binary logistic regression were applied and compared in their ability to classifying disease-free subjects and those with diabetes mellitus(DM) diagnosed by glucose level. Demographic, enthropometric and clinical data were collected based on a total of 460 participants aged over 30 years from six villages in Bangladesh that were identified as mainly dependent on wells contaminated with arsenic. Out of 460 participants 133 (28.91%) suffered from DM, 116 (25.27%) had impaired glucose tolerance (IGT) and the remainder 211 (45.86%) were disease free. Among other factors, family history of diabetes and arsenic exposure were found as significant risk factors for developing diabetes mellitus (DM), with a higher value of odds ratio. This study shows that, binary logistic regression correctly classified 73.79% of cases with IGT or DM in the training datasets, 70.96% in testing datasets and 70.4% of all subjects. On the other hand, the sensitivities of artificial neural network architecture for training and testing datasets and for all subjects were 83.4%, 82.25% and 84.33% respectively, indicate better performance than binary logistic regression model.
Background: Partograph is a simple, of low cost but most important tool for record of progress of labour In the developing country like ours, where both pregnancy and maternal mortality rate is so high, the use of this inexpensive partograph is essential. Objective: To assess the importance of partographic control of labour in preventing prolongs labour and its consequences, thereby decreasing maternal morbidity and mortality and improvement of neonatal outcome. Method: This study was done in the Obstetrics and Gynaecology department of Institute of Child and Mother Health, Matuail, Dhaka. Total 196 patients were included in this study. Data were collected by predesigned data collection sheet. Data were analyzed by using Statistical Package for Social Science (SPSS) version 14. Result: 74% of these patients had spontaneous vaginal delivery, 7.14% required assisted delivery (forceps or ventouse) and 18.9% needed caesarean section. Caesarean section was done in 18.9% patients because of fetal distress (32.4%) and prolonged labour (67.6%) due to malrotation and cephalopelvic disproportion. Patients with non-engaged head in labour required more intervention than who had engaged head. With the use of partograph, unnecessary interventions were reduced. It was found that 66.7% of the patients were delivered within 7 hours and all patients were delivered within 10 hours from active phase of labour. Thus prolonged labour and its consequences, such as obstructed labour and ruptured uterus, can be avoided by using partograph. In 100% of the patients, crossing the action line in partograph required interference, but 92.5% within alert line of partograph delivered vaginally spontaneously and 7.5% required assisted delivery (forceps or ventouse). When IDR was 1 cm/hr 85.1% women delivered spontaneously. When IDR was <0.4 cm/hr, 100% of patients required some kind of interference. Thus, the maintenance of partograph in labour enables the obstetricians to recognize very early dystocic labour and act accordingly. Conclusion: With the help of a partogram, time of delivery can be estimated and if the progress is slow, an appropriate interference at the right time can be instituted before the labour becomes dangerously protracted. IDR very helpful in making early decisions about the prognosis for the type of labour. With the use of partogram and its scientific application, the result showed that operative interventions were reduced, duration of labour was within normal limit and there was no obstructed labour and no maternal or perinatal mortality.
Prophylactic drainage of wounds is aimed to reduce the wound complications and thereby morbidity. Obese patients are at more risk. Wound management is a basic practice in surgery, especially after an elective abdominal surgery. Our task after surgery is to avoid and thereby to reduce the adverse effects of wound complications. Objective: To determine whether subcutaneous drainage can reduce such complications in patients undergoing elective and emergency abdominal surgery. Materials and Methods: It is a prospective open comparative study carried out Department of obstetrics and gynecology, in two hospitals Al-Hera Hospital, Mawna, Chowrasta, Sreepur, Gazipur and Shaheed Tajuddin Ahmad Medical College Hospital, Gazipur, Bangladesh over a period of six (6) months August 2021 to January 2022. Patients were randomized before surgery and divided into two groups by systemic random sampling. Total sample size 150 with 75 in each group. All patients will receive same preparations. Results: Wound complications observed in 2 patients with subcutaneous drain which forms 8% of the total patients with subcutaneous drain. Wound complications observed in 25 patients without subcutaneous drain which forms 33.3% of the total patients without subcutaneous drain. Comparing these two data found to be statistically significant with P value < 0.05. Thus the incidence of wound complication is low in those with subcutaneous drain than those without drain. Conclusion: Subcutaneous drain when kept in obese individuals with more subcutaneous fat thickness who undergo elective abdominal surgeries had lesser incidence of local wound complications and lesser hospital stay when compared to those patients without subcutaneous drain.
processors controllers implemented in hardware for applications such as robots, (iii) as data analytic methods 2 . Artificial intelligence has been proposed as a reasoning tool to support clinical decision-making since the earliest days of computing 3-7 . Artificial neural networks are a computer modeling technique based on the observed behaviours of biological neurons 8 . This is a non-parametric pattern recognition method which can recognize hidden patterns between independent and dependent variables 9 .
Introduction: Gestational diabetes mellitus (GDM) is a transitory form of diabetes (glucose intolerance) with onset or first recognition during pregnancy. It is a major and growing public health problem in most parts of the world, with a global prevalence of between 2% and 6% (and as high as 20% in high-risk populations). Gestational Diabetes Mellitus (GDM) is a metabolic disorder defined as glucose intolerance with onset or first recognition during pregnancy. These women are at increased risk of adverse maternal and fetal outcome. Therefore, it’s early diagnosis and management is essential for better fetomaternal outcome. Objective: To assess the prevalence, risk factors and its outcome of gestational diabetes mellitus. Materials and Methods: A Prospective hospital based study was carried out at Dept. of Obstetrics & Gynecology, Al Hera Hospital (Private Clinic), Mawna Chowrasta, Sreepur, Gazipur, Bangladesh from June to December 2021. They were given 75gm glucose irrespective of meals and after 2 hours plasma glucose was estimated. GDM was diagnosed when after 2hours plasma glucose was>140mg/dl. All patients with GDM were followed up and treated with diet and /or insulin therapy till delivery. Maternal and fetal risks factors and outcome were evaluated. Results: Prevalence of GDM was 8.2% in my study. Many of the cases diagnosed as GDM had previous history of large baby, still birth or spontaneous abortion. Maternal complications observed were PIH (40%), polyhydramnious (37.7%), while 66.6% had to undergo caesarean section. Preterm labour occurred in 4 case each (8.8%). No complications were observed in 8 cases (17.7%). 28.8% babies had birth weight of >3.5kg and 17.7% were below 2.5 kg. Conclusion: Women with GDM showed an increased risk of obstetrical and fetal complications. Estimation of plasma glucose level using DIPSI criteria is a single step and cost -effective test to screen large number of cases and to diagnose and manage GDM to prevent maternal and fetal complications.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.