Prediction of Stable Angina for Coronary Artery Diseases using Boosting Algorithm

Narrowed arteries block the blood flow to the heart muscle and other parts of the body, which can cause chest pain. Coronary arteries disease (CAD) can weaken the heart muscle causing heart failure, in which the heart cannot pump blood. A person with underlying diseases is more prone to get highly affected by COVID-19 because of the decreased immunity. Cardiovascular disease and coronary heart disease have been associated with worsened outcomes of COVID-19 patients. Thus, detecting CAD at a proper stage is crucial to avoid any further serious issues. This paper is an empirical analysis to predict stable angina for CAD using Histogram gradient boosting (HGB) and Adaboost (ADB) classifier algorithm and compared the performance with traditional Naïve Bayes (NB) algorithm. © 2023 IEEE.

Rare Case of Immune-Mediated Necrotizing Myopathy With Isolated Dysphagia as Presenting Symptom

Introduction: Immune mediated necrotizing myopathy (IMNM) is a rare, but progressive disease that accounts for about 19% of all inflammatory myopathies. Dysphagia occurs in 20-30% of IMNM patients. It often follows proximal muscle weakness and ensues in the later stages of the disease. We report a rare case of IMNM, presenting with dysphagia as the initial symptom, followed by proximal muscle weakness. Case Description/Methods: A 74-year-old male with a past medical history of coronary artery disease, hypertension, and hyperlipidemia presented to the ED with 2-3 weeks of intractable nausea, vomiting, and dysphagia for solids and liquids. Vital signs were stable, and initial labs displayed an AST of 188 U/L and ALT of 64 U/L with a normal bilirubin. Computed tomogram of the chest, abdomen, and pelvis were negative. An esophagram showed moderate to severe tertiary contraction, no mass or stricture, and a 13 mm barium tablet passed without difficulty. Esophagogastroduodenoscopy exhibited a spastic lower esophageal sphincter. Botox injections provided no significant relief. He then developed symmetrical proximal motor weakness and repeat labs demonstrated an elevated creatine kinase (CK) level of 6,357 U/L and aldolase of 43.4 U/L. Serology revealed positive PL-7 autoxantibodies, but negative JO-1, PL-12, KU, MI-2, EJ, SRP, anti-smooth muscle, and anti-mitochondrial antibodies. Muscle biopsy did not unveil endomysial inflammation or MHC-1 sarcolemmal upregulation. The diagnosis of IMNM was suspected. A percutaneous endoscopic gastrostomy feeding tube was placed as a mean of an alternative route of nutrition. He was started on steroids and recommended to follow up with outpatient rheumatology. He expired a month later after complications from an unrelated COVID-19 infection. Discussion(s): The typical presentation of IMNM includes painful proximal muscle weakness, elevated CK, presence of myositis-associated autoantibodies, and necrotic muscle fibers without mononuclear cell infiltrates on histology. Dysphagia occurs due to immune-mediated inflammation occurring in the skeletal muscle of the esophagus, resulting in incoordination of swallowing. Immunotherapy and intravenous immunoglobulin are often the mainstay of treatment. Our patient was unique in presentation with dysphagia as an initial presenting symptom of IMNM, as well as elevated enzymes from muscle breakdown. It is critical as clinicians to have a high degree of suspicion for IMNM due to the aggressive nature of the disease and refractoriness to treatment.

Benign and Malignant Skin Lesion Detection from Melanoma Skin Cancer Images

Skin cancer is the most dangerous and lethal cancer that affects millions of people each year. The accurate identification of skin cancers can not be accomplished without expert dermatologists. However, specific research studies of WHO in Canada, US and Australia, show that in the year 1960s to 1980s, the cases of skin cancer has noted more than two times increased in comparison with the previous years. The identification of skin cancer in its early stage is an expensive and difficult task because it doesn't cause too much bad in the initial phase. Whereas, the growth of skin cancer requires biopsy and many other treatments each time which is quite costly as per the statistics of India. This challenge makes it a necessary step to identify the existence of skin cancer in the early stages to increase immortality. With the evolution and progression in technology, there are various methods which have participated in and solved medical issues including covid19, pneumonia and many others. Similarly, machine learning(ML) and deep learning(DL) models are applicable to diagnosing skin cancer in its early stages. In this work, the support vector machine (SVM), naive bayes (NB), K-nearest neighbour (KNN) and neural networks(NN) have been used for classifying benign and malignant lesions. Furthermore, for the feature extraction from the dataset, a pre-trained SqueezeNet model has been used. The classification results of KNN, SVM, NB and NN have been shown in the accuracy, recall, F1-Measure, precision, AUC and ROC. The comparison of the models has resulted that the NN model outperforms all other models when applied with the SqueezeNet feature extractor with the highest accuracy, F1-Measure, recall, precision and AUC as 88.2%, 0.882, 0.882, 0.882 and 0.957, respectively. Lastly, the performance metrics analogies results of each model have been illustrated for the classification of benign and malignant lesions. © 2023 IEEE.

Classification of Chest X-Ray Images for COVID-19 Positive Patients Using Transfer Learning

The Coronavirus pandemic COVID-19 which has been declared as a pandemic by the World Health Organization has infected more than 212,165,567 and fatality figure of 4,436,957 as of 22nd August 2021. This infection develops into pneumonia which causes breathing problem;this can be detected using chest x-rays or CT scan. This work aims to produce an automated way of detecting the presence of COVID-19 infection using chest X-rays as a part of transfer learning strategy to extract numerical features out of an image using pre trained models as feature extractors. Then construct a secondary data set out of these features, and use these features which are simple numerical vectors represented in tabular form as an input to simple machine learning classifiers that work well with numerical data in tabular form such as SVM, KNN, Logistic regression and Naive Bayes. This work also aims to extract features using texture-based techniques such as GLCM and use the GLCM to obtain 2nd order statistical features and construct another secondary data set based on texture-based feature extraction techniques on images. These features are again fed into simple machine learning classifiers mentioned above. A comparison is done, between deep learning feature extraction strategies and texture-based feature extraction strategies and the results are compared and analyzed. Considering the deep learning strategies Mobile Net with SVM perform the best with 0.98 test accuracy, followed by logistic regression, KNN and Naive Bayes algorithm. With respect to GLCM feature extraction strategy, KNN with test accuracy with 0.96 performed the best, followed by logistic regression, SVM and naive Bayes. Overall performance wise deep learning strategies proved to be effective but in terms of calculation time and number of features, texture-based strategy of GLCM proved effective. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Changes of atmospheric metal(loid) deposition from 2017 to 2021 at Mount Emei under China's air pollution control strategy

Acid deposition and particulate matter (PM) pollution have declined considerably in China. Although metal(loid) and acid deposition and PM have many common sources, the changes of metal(loid) deposition in China in the recent decade have not been well explored by using long-term monitoring. Therefore, we analyzed the dry and wet deposition of eleven metal(loid)s (including Al, As, Ba, Cd, Cu, Cr, Fe, Mn, Pb, Sr, and Zn) from 2017 to 2021 at Mount Emei, which is adjacent to the most economic-developed region in western China (Sichuan Basin (SCB)). Anthropogenic emissions contributed to over 80% of the annual wet deposition fluxes of metal(loid)s and acids (SO4 2-, NO3 -, and NH4 +) at Mount Emei, and the major source regions were the SCB, the Yunnan-Guizhou Plateau, and Gansu Province. Metal(loid) and acid deposition had similar seasonal variations with higher wet deposition fluxes in summer but higher wet deposition concentrations and dry fluxes in winter. The seasonal variations were partially associated with higher precipitation but lower pH in summer (968 mm and 5.52, respectively) than in winter (47 mm and 4.73, respectively). From 2017 to 2021, metal(loid) deposition did not decline as substantially as acid deposition (5.6%-30.4%). Both the annual total deposition fluxes and concentrations of Cr, Cu, Sr, Ba, and Pb were even higher in 2020-2021 than in 2017-2018. The inter-annual and seasonal changes implied the responses of metal(loid) deposition to anthropogenic emission changes were buffered (e.g., transformation, dilution, and degradation) by precipitation rates, acidity, natural emissions, and chemical reactions in the atmosphere, among others.Copyright © 2023 Elsevier Ltd

COVID-19 Detection in the Images of Chest CT Scan Using K-NN in Comparison with NB Classifier to Improve the Accuracy

This chapter is about the improvisation in the accuracy in COVID-19 detection using chest CT-scan images through K-Nearest Neighbour (K-NN) compared with Naive-Bayes (NB) classifier. The sample size considered for this detection is 20, for group 1 and 2, where G-power is 0.8. The value of alpha and beta was 0.05 and 0.2 along with a confidence interval at 95%. The K-NN classifier has achieved 95.297% of higher accuracy rate when compared with Naive Bayes classifier 92.087%. The results obtained were considered to be error-free since it was having the significance value of 0.036 (p < 0.05). Therefore, in this work K-Nearest Neighbor has performed significantly better than Naive Bayes algorithm in detection of COVID-19. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

A Novel Classification Technique for Safety Measures on Covid-19 Using Featured-Based Sentimental Analysis

Covid-19 is a term that has frightened the globe because it has broken beyond socioeconomic barriers in which people literally forgot the word social help because of this deadliest virus.The main goal of this study is to create a model that forecasts Covid-19 reviews based on coronavirus ratings from Kaggle repository. The World Health Organization(WHO) declared a pandemic of the coronavirus infection when it first appeared in 2019. People are worrying and concerned about their health as the number of instances rises throughout the world. People's physical and emotional health is inversely proportional to the pandemic scenario. As a result, in this case, a categorization model based on numerous metrics is required to rescue nations by analyzing facts and information about the outbreak. In this article to organise the reviews or opinions provided by people worldwide, we performed emotional or opinion classification using a Novel classifier. Then, the accuracy of the proposed model is compared with existing base classifiers like NB(Naive-Bayes) and Support Vector Machine(SVM), where Novel classifier gave the best accuracy compared to the other two classifiers, i.e., 95 © 2022 IEEE.

Duodenal Stricture as a Rare, Possible Complication of Eosinophilic Gastrointestinal Disease (Egid)

EGID is a recently described condition with an unknown etiology and pathogenesis. There are three case reports of duodenal stricture associated with EGID: one in an adult requiring pancreaticoduodenectomy due to the suspicion of malignancy and 2 cases in a child and a young adult, who responded to oral steroids. We report the case of a 10-year-old who presented to A&E with a 9-month history of epigastric abdominal pain and 1 episode of haematemesis, on a background of asthma. He was treated for Helicobacter pylori, based on a positive stool antigen. Abdominal pain and vomiting persisted, therefore an oesophago-gastro-duodenoscopy (OGD) was performed. This identified widespread white plaques throughout the oesophagus, erythema and nodularity of the gastric antrum and white nodules in the first part of the duodenum. Histology revealed changes of EGID and eosinophilic oesophagitis (EOE) and patient was commenced on Montelukast, oral viscous Budesonide (OVB), Cetirizine and continued proton pump inhibitor (PPI). After the allergy workup identified house dust mites, cat sensitisation and fish allergy, a 6-food elimination diet was initiated. During the next 2 years, symptoms subsided, and endoscopy changes improved, with only mild signs of active EOE while on OVB, PPI and diary/egg/fish free diet. However, the patient relapsed due to poor compliance to treatment. He became more unwell during the Covid pandemic with recurrent vomiting and static weight. A trial of dupilumab was considered, however his reassessment OGD had to be delayed due to restricted access to theatre. He was treated empirically with a reducing course of oral prednisolone, with temporary response. The endoscopic assessment performed subsequently showed erythema, erosions and white plaques in the distal oesophagus and gastric antrum with narrowing between the first and the second part of the duodenum (D2), that could not be entered. Histology identified mild upper oesophagitis (4 eosinophils (eos)/HPF), active middle and lower oesophagitis (20 eos/HPF and 12 eos/HPF, respectively), chronic gastritis (80 eos/HPF) and nonspecific reactive changes of the proximal duodenum. A barium meal confirmed a duodenal stricture. At this stage, we recommended a sloppy diet and a second weaning course of oral prednisolone, along with Montelukast. He was subsequently commenced on azathioprine for maintenance of remission. A repeat barium study and small bowel MRI performed post course of steroids and on azathioprine revealed stable appearances of the proximal duodenal stricture, excluding the presence of further strictures. While the patient has responded to the course of oral steroids and azathioprine, a repeat upper GI endoscopy is currently planned to dilate the duodenal stricture. The challenges posed by this case were the rarity of the condition, limited treatment options and access to endoscopy during the Covid pandemic and the fact that unlike previous case reports a sustained remission could not be obtained on steroids, and a maintenance immunosuppressive medication was required. We can conclude that this subgroup of patients should be monitored closely for signs of bowel obstruction and will require more intense treatment, including immunomodulators, endoscopic dilatation and or surgery.

Local Naïve Bayes for Predicting Evolution of COVID-19 Patients on Self Organizing Maps

The most recent Clinical Decision Support Systems use the potential of Machine Learning techniques to target clinical problems, avoiding the use of explicit rules. In this paper, a model to monitor and predict the risk of unfavourable evolution (UE) during hospitalization of COVID-19 patients is proposed. It combines Self Organizing Maps and local Naïve Bayes (NB) classifiers because of interpretation purposes. We used the results of six blood tests (leukocytes, D-dimer, among others) provided by a Spanish hospital group. The probabilistic approach allows us to get the daily risk of UE for each patient in an interpretable way. Several variants of the NB classifiers family have been explored, mainly weighting and likelihood estimation (parametric and nonparametric). Despite the over-simplified assumptions of the NB classifiers, they provided good predictive results in terms of sensitivity and specificity. The model with nonparametric likelihood estimation provided the best risk prediction over time even when designed with a limited number of samples. Specifically, the median value and interquartil range for the risk prediction were quite reliable even 10 days before the event day for patients hospitalized longer than 7 days. The risk median values also agree with the gold-standard for patients with a hospital stay shorter than 7 days, though the interquartil range can be too wide (probably because of the variability in the inpatient days - sometimes, just 2 days). Though a deepest analysis considering more patients and features would be convenient, our results show the potential of the proposed approach, both from a technical and clinical viewpoint. © 2022 IEEE.

Analysis of Depression, Anxiety, and Stress Chaos Among Children and Adolescents Using Machine Learning Algorithms

In recent times, the pandemic seems to have a serious impact on the mental health of people around the world across all age groups. This has been manifested in the form of unstable mental conditions, depression, anxiety, stress, and many other similar mental illnesses among individuals. In this study, we explore the use of machine learning classification algorithms to detect and classify children and adolescents with unstable mental conditions such as depression, stress, and anxiety through the Covid-19 period based on demographic information and characteristics using the DASS-21 Scale. Using a dataset of 2050 Chinese participants, an attempt has been made to classify their depression, stress, and anxiety behavior into different levels (Normal, Moderate, and Severe). The classification algorithms considered are Support Vector Machines, KNN, Naive Bayes, and Decision Trees. It is observed that the Support Vector Machine is the most effective method for the classification of mental depression, anxiety, and stress conditions. The goal of the study is to build a classification model for accurate categorization of unknown samples into appropriate psychological chaos levels. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Detection of COVID-19 Infection from Clinical Findings Using Machine Learning Algorithm

COVID-19 infection is a transmissible virus causing acute respiratory syndrome spreading worldwide. The number of patients infected by this deadly virus increases steadily, causing a high mortality rate. Hence, it is crucial to diagnose and identify the COVID-19 infection for earlier treatment of the patients. This study has applied four algorithms, namely, Logistic Regression (LR), Nu-Support Vector Machine (Nu-SVM), Multi-layer perceptron (MLP) and Naive Bayes (NB) to identify COVID-19 infection. The clinical laboratory findings of 600 individuals were taken from Hospital Isrelita Albert Einstein, Sao Paulo, Brazil, used in this study. We have selected significant features using Random forest-based recursive feature elimination for predicting the infection. Experiments are conducted with 90% training and 10% testing data. The performance result shows that the Nu-SVM algorithm obtained the prediction accuracy of 95% with 100% sensitivity and 94.23% specificity in predicting the infection. To our knowledge, the result achieved by Nu-SVM is the highest in the literature. Hence, the model can be used as a tool for the initial prediction of COVID-19 disease. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Design and Implementation of Remote Health Monitoring System and Application for Priority Recognition Using Machine Learning

This work demonstrates a remote health monitoring system that provides a holistic perspective of cases and their health conditions. Remote Patient Monitoring (RPM) systems will play a conspicuous role in the millennium of medical management. In this paper, to monitor covid patients during their quarantine days to keep track of chronic circumstances. For that, the model of a non-reactive preference grading independently in a single device to collect the essential parameters like blood Oxygen level, temperature and pulse rate. To predict and conduct the priority division using supervised machine learning algorithm for the received medical packets and relay them according to their priorities. This hitch results in transmitting advanced significance data packets of high importance in an advanced average waiting time. In this design, to acknowledge a vital criterion distinguishing the priority of health-info carried by a file and other low-ranking digital data parcels of different cases. The stored data then given for the supervised machine learning classification algorithms. In that the better accuracy of priority classification of 93.5% obtained from support vector machine (SVM) algorithm outperforms than the other machine learning classifiers and are 91%, 88%, 89% with respect to Multilayer Perception(MLP), Baysian Network (BN) and Logisitic Regression(LR). © 2022 IEEE.

Sentiment Analysis on MySejahtera Application during COVID-19 Pandemic

MySejahtera is an application developed by the Malaysian government to assist and monitor the Covid-19 flare-up that happened in Malaysia by allowing users to assess their health risk in the event of an outbreak. In MySejahtera, the public obtains significant information about the affected areas and other health-related conditions. The use of MySejahtera became mandatory during the pandemic to reduce the Covid-19 spread. This paper reports the public sentiment towards MySejahtera using the supervised Machine Learning (ML) method. The total number of feedback scraped from Twitter, Google Play Store, and App Store was 33 376, and the modelling was trained using 20 647 feedbacks based on the timeline during the launch of the application;26th March 2020 until 25th November 2021. The corpus was used to determine the feedback label, either positive or negative. The tested ML algorithms are Support Vector Machine (SVM) and Naïve Bayes (NB) through evaluation metrics that are accuracy, precision, recall/sensitivity, and specificity. The result of modelling shows that the SVM classifier with 90:10 percentage split, using Vader extraction technique, has the highest accuracy of 89.93% and recall/sensitivity of 90.55%. The results of this sentiment analysis are visualized for better understanding. It is preferable to utilize a Malay Language corpus and to have more records from Twitter for future work. © 2022 IEEE.

Bio-monitoring of atmospheric heavy metal pollution of major emergency events using moss bags:a case study in Xichang

In order to trace and monitor the atmospheric heavy metal pollution in Xichang City, an investigation activity was carried out with a sort of moss (Taxiphyllum taxirameum) (packed in moss bags) as a biological indicator for monitoring heavy metal pollution. The investigation was conducted from the period from April 2019 to April 2020, during which two grave emergency events occurred during spring monitoring period from January 15 to April 15, 2020, i.e., COVID-19 and "3.30"severe forest fire in Xichang, which inevitably affected the atmospheric quality. Based on the concentration analysis of 12 kinds of heavy metal, including Al, Cr, Fe, Cu, Ni, Pb, Mn, Hg, Zn, V, As and Ba contained in the moss and the local meteorological data, comparing those informative data before and after the time when the emergency events toke place, the paper made an analysis on the impacts of two enormous emergency events on the air pollution of heavy metal in Xichang. The results showed that total amount of enrichment of above-mentioned 12 heavy metals in spring (January 15 to April 15, 2020) is (12.85 +or- 1.57) mg/g, which was significantly higher than in the other three seasons (p < 0.01), but no significant discrepancies about the total enrichment amount in the other three seasons (p > 0.05). Primarily because of COVID-19 pandemic, the level of motor vehicles emissions cut down, and the decrease of the tourism in the related areas perhaps causing the decline of pollution of Pb. In addition, the decrease of unbalanced emission of pollutants led to a noted increase of atmospheric oxidation in urban area, thus boosting the formation of secondary particulate matter, and the particulate matter from surrounding industrial sources was transported into the urban area;as a result, remarkable increases of Hg concentration of moss within the moss bags were detected downwind the industrial area located in the urban fringe. Consequently, the investigation showed that the moss-bag method is an effective biological tool for monitoring air heavy metal pollution, which could reflect the impacts of major pollution events on air quality.

Public Sentiments in User Generated Content amid COVID-19 Pandemic in Ghana

Towards post COVID-19 pandemic, a natural language processing (NLP) technique was leveraged to understand the sentiments of Ghanaians through their public discourse in tweets during the lockdown period in Ghana. With NLP resources, feature words were extracted from the tweets and fed into three machine learning algorithms to track public sentiments in the tweets. The algorithms, support vector machines (SVM), naïve-bayes (NB) and artificial neural network (ANN) were evaluated to ascertain their efficacies. Frequently occurring words used by Ghanaians during the lockdown period were extracted to provide more insight into public sentiments. The study revealed that negative sentiments prevailed throughout the COVID-19 lockdown among Ghanaians. However, positive sentiments were surprisingly high at some points during the lockdown period. The result of evaluating the machine learning classifier yielded SVM as the best performing classifier though the other classifiers performed beyond the acceptable threshold. With these findings, it is envisioned that this study will be adopted by policymakers, as a guide, towards public management of public sentiments in pandemics. © 2022 IST-Africa Institute and Authors.

Prediction of Happiness Score of Countries by Considering Maximum Infection Rate of People by COVID-19 using Random Forest Algorithm

In this paper, the relationship between COVID-19 Maximum Infection Rate (MIR) and the happiness indicators has been investigated for the prediction of Happiness Score of Countries using Random Forest (RF) algorithm. The per-formance of the proposed algorithm is also compared against five other algorithms such as Linear Regression (LR), Ada Boost Classifier (ABC), K-Nearest Neighbor (KNN), Gaussian Naive Bayes (NB) and Logistic Regression. The comparison of performance includes parameters like training accuracy, testing accuracy and computation time. It is clear from the observation that the proposed approach is superior to others. Then the parameters like MAE, MSE, RMSE, R2 Score, Adjusted R2 Score is calculated. This proposed algorithm can be used for other classification and regression work involving large amount of data with missing values like COVID- 19 datasets. © 2022 IEEE.

Inclusive Study of Fake News Detection for COVID-19 with New Dataset using Supervised Learning Algorithms

Covid-19 imposes many bans and restrictions on news, individuals and teams, and thus social networks have become one of the most used platforms for sharing and destroying news, which can be either fake or true. Therefore, detecting fake news has become imperative and thus has drawn the attention of researchers to develop approaches for understanding and classifying news content. The focus was on the Twitter platform because it is one of the most used platforms for sharing and disseminating information among many organizations, personalities, news agencies, and satellite stations. In this research, we attempt to improve the detection process of fake news by employing supervised machine learning techniques on our newly developed dataset. Specifically, the proposed system categorizes fake news related to COVID-19 extracted from the Twitter platform using four machine learning-based models, including decision tree (DT), Naïve Bayes (NB), artificial neural network (ANN), and k-nearest neighbors (KNN) classifiers. Besides, the developed detection models were evaluated on our new dataset, which we extracted from Twitter in a real-time process using standard evaluation metrics such as detection accuracy (ACC), F1-score (FSC), the under the curve (AUC), and Matthew's correlation coefficient (MCC). In the first set of experiments which employ the full dataset (i.e., 14,000 tweets), our experimental evaluation reported that DT based detection model had achieved the highest detection performance scoring 99.0%, 96.0%, 98.0%, and 90.0% in ACC, FSC, AUC, and MCC, respectively. The second set of experiments employs the small dataset (i.e., 700 tweets);our experimental evaluation reported that DT based detection model had achieved the highest detection performance scoring 89.5%, 89.5%, 93.0%, and 80.0% in ACC, FSC, AUC, and MCC, respectively. The results obtained for all experiments have been generated for the best-selected features. © 2022, International Journal of Advanced Computer Science and Applications. All rights reserved.

LAPAROSCOPIC CERCLAGE SACROHYSTEROPEXY: ANATOMICAL AND SUBJECTIVE POST-OPERATIVE OUTCOMES AT 6 WEEKS

Introduction: Our group first described a novel approach for hysteropexy in 2017. This procedure utilized a combined laparoscopic and vaginal approach to place a polypropylene mesh sling around the cervicouterine junction as a cerclage and attach this mesh to the sacrum. Previous outcomes comparing this technique to laparoscopic hysterectomy and sacrocervicopexy showed equivalent anatomical and subjective outcomes with decreased suturing and intraoperative time compared to traditional sacrocervicopexy at 6 weeks, 6 months and 12 months. The procedure was refined in 2019 when vaginal attachment of the mesh was replaced with a novel laparoscopic mesh attachment technique, now referred to as total laparoscopic cerclage sacrohysteropexy (TLCSH). Objective: To assess postoperative outcomes of the novel, modified TLCSH. Methods: This was a retrospective study of patients who underwent TLCSH from February 2019 to October 2021. Chart review was performed to obtain patient demographics, baseline pelvic organ prolapse quantification (POP-Q) scores and 6- week outcome data. Anatomical success was a composite of anterior, posterior and apical success. We defined anterior and posterior compartment success as Ba and Bp ≤0, respectively. Apical success was defined as C ≤ half the total vaginal length (TVL). As a more conservative measure, we also defined success as C < -4 and C ≤ -2/3 TVL. Subjective outcomes, including patient-reported pelvic organ prolapse distress inventory (POPDI-6), patient global impression of improvement (PGI-I) and satisfaction, were also assessed at 6 weeks. Data are reported as median (interquartile range) and were compared with the Wilcoxon signed rank test. Results: A total of 117 patients underwent TLCSH and 107 (91%) had a 6- week post-operative visit at a median time of 2 months (1-2). Of patients who had a 6-week visit, 9 had a telehealth visit due to COVID-19 and did not have a POP-Q assessment, and 1 patient only had point C documented and therefore was only included in the point C analysis. Pre-operative characteristics are in Table 1. Post-operative changes for points C, Ba, Bp, and GH were significantly improved (P < 0.001 for all;Table 2). Most patients (93%) had surgical success as defined by C ≤ half TVL. Using the more restrictive definitions of apical success there was 94% success with C < -4 and 35% with C ≤ -2/3 TVL. At 6 weeks, 31% of patients were stage 0, 54% stage I, and 15% stage II. There were no mesh exposures. Subjective outcomes were available for 50 (47%) patients. While only available for a portion of patients, median POPDI-6 scores improved significantly from 30 (21-50) to 4 (0-21), P < 0.001. Most patients (85%) reported that they were “very satisfied,” 12% reported “satisfied,” 2% reported “neutral;” none reported “unsatisfied” or “very unsatisfied.” The median PGI-I score was 1 (1-2), with 1 and 2 corresponding to “very much better” and “much better,” respectively. Conclusions: TLCSH results in anatomical success, in addition to decreased POPDI-6 scores and high PGI-I scores at 6 weeks. Given this novel technique, additional follow-up time with further analysis is necessary to assess whether this procedure is a durable repair for long-term prolapse reduction and patient satisfaction. (Table Presented).

Bilious Emesis and Failure to Pass Meconium in the Nursery

Introduction: In this case we review important newborn nursery management strategies and unique surgical diagnostic measures in a severe case of intestinal obstruction due to small left colon syndrome (SLCS) - illustrating an impressive relationship between intestinal dysmotility and meconium plug formation that increases risk of intestinal perforation in the newborn. Case Description: We present a case of an infant born to a mother with symptomatic COVID-19, who at 24 hours of life was treated for failure to pass meconium with a glycerin suppository and went on to develop bilious emesis and severe abdominal distention as feeding continued over the next several hours. After a normal upper GI, a barium enema identified a distal obstruction and the pediatric surgical team used rectal irrigation to remove a large meconium plug which mimicked the appearance of the descending colon on plain film, ultimately leading to the diagnosis of SLCS. The infant went on to stool normally after removal, however due to the severity of his initial clinical picture, a multi-disciplinary team was consulted, and concluded that given the severity of the meconium plug, a workup for cystic fibrosis was indicated, but deferred a rectal biopsy for Hirschprung disease due to normal return of bowel function upon removal of the obstruction. Discussion: Meconium plug syndrome is a transient distal GI obstruction in the lower colon or rectum with thick meconium and is thought to be due to poor intestinal motility. A contrast enema is typically diagnostic, showing a decrease in bowel caliber distal to the plug, and therapeutic, as the plug is often passed during the procedure. A sharp transition zone at the splenic flexure followed by a narrow descending colon on imaging is consistent with SLCS with a meconium plug at the transition zone. Infants presenting with both meconium plug syndrome and SLCS may require an evaluation for an underlying diagnosis of cystic fibrosis or Hirschprung disease. Delayed meconium passage is present in 11.9% of infants diagnosed with cystic fibrosis, while 15% of infants with meconium plugs have an aganglionic segment on rectal biopsy, indicative of Hirschprung disease. The decision to perform additional tests in an infant with SLCS should be guided by the patient's clinical course and in conjunction with a pediatric surgical team. Conclusion: Although intestinal obstruction in the newborn is rather rare, it is imperative that it is promptly diagnosed and treated to avoid negative outcomes. Despite being considered a mild form of obstruction due to its transient nature, meconium plug syndrome can lead to an impressive clinical illness and urgent consultation with a surgical team is vital due to the risk of intestinal perforation if the obstruction is not relieved.

Review of ML techniques for analyzing Novel Corona Virus

Currently, the demand of machine learning is increasing in healthcare field for disease diagnosis. The various kinds of machine learning algorithms are helping the medical field for prognosis of diseases with accuracy and therefore serving the humankind in timely classification and detection of diseases. This study emphasizes on using different machine learning techniques for analysis of Covid-19 disease prediction. This paper presents the review of several machine learning classifiers such as SVM, Ensemble learning, Multilayered Perceptron, Naive Bayes, KNN and ANN, and analyze their classification accuracies in Novel Corona Virus prediction. The authorized datasets have been considered to perform this analysis. This analysis may serve as good indicator for analysts and medical professionals in selection of efficient classifier for the datasets that may save the time and prediction cost. © 2022 IEEE.