Cardiovascular Diseases (CVDs) pose a significant global health challenge, necessitating accurate risk prediction for effective preventive measures. This comprehensive comparative study explores the performance of tra...Cardiovascular Diseases (CVDs) pose a significant global health challenge, necessitating accurate risk prediction for effective preventive measures. This comprehensive comparative study explores the performance of traditional Machine Learning (ML) and Deep Learning (DL) models in predicting CVD risk, utilizing a meticulously curated dataset derived from health records. Rigorous preprocessing, including normalization and outlier removal, enhances model robustness. Diverse ML models (Logistic Regression, Random Forest, Support Vector Machine, K-Nearest Neighbor, Decision Tree, and Gradient Boosting) are compared with a Long Short-Term Memory (LSTM) neural network for DL. Evaluation metrics include accuracy, ROC AUC, computation time, and memory usage. Results identify the Gradient Boosting Classifier and LSTM as top performers, demonstrating high accuracy and ROC AUC scores. Comparative analyses highlight model strengths and limitations, contributing valuable insights for optimizing predictive strategies. This study advances predictive analytics for cardiovascular health, with implications for personalized medicine. The findings underscore the versatility of intelligent systems in addressing health challenges, emphasizing the broader applications of ML and DL in disease identification beyond cardiovascular health.展开更多
Background: The emergence of multidrug resistant tuberculosis (MDR-TB) and extensively drug- resistant tuberculosis (XDR-TB) has highlighted the need for early accurate detection and drug susceptibility. Objective: Th...Background: The emergence of multidrug resistant tuberculosis (MDR-TB) and extensively drug- resistant tuberculosis (XDR-TB) has highlighted the need for early accurate detection and drug susceptibility. Objective: The purpose of the present study was to evaluate the accuracy of GeneX-pert MTB/RIF assay for the detection of Mycobacterium tuberculosis and rifampicin resistance. Methodology: This cross sectional study was done in the Department of Microbiology at Sir Salimullah Medical College, Dhaka and National Institute of Chest Disease & Hospital (NIDCH), Dhaka during the period of January 2014 to December 2014 for a period of 1 (one) year. Sputum samples from suspected MDR-TB patients were collected by purposive sampling technique from OPD of Sir Salimullah Medical College (SSMC) and NIDCH. Microscopy, liquid culture in liquid MGIT 960 media and GeneXpert MTB/RIF were done for MTB diagnosis and detection of rifampicin resistance. MGIT 960 media were also used for determination of drug resistance. Result: Liquid culture yielded higher growth (68%) from 100 samples while GeneXpert MTB assay showed similar result (67% positive and 33% negative). Drug susceptibility test in MGIT 960 media showed that out of 68 positive cases Rifampicin resistant cases were 15 (22.05%) whereas GeneXpert MTB assay detected 14 (20.89%) were Rifampicin resistant out of 67 MTB positive samples. When compared to liquid culture the calculated sensitivity, specificity, negative predictive value (NPV), positive predictive value (PPV) and accuracy of GeneXpert MTB were 98.52%, 100%, 96.96%, 100% and 99%. Conclusion: GeneXpert MTB/RIF assay is high detection rate of pulmonary tuberculosis and multidrug resistant tuberculosis.展开更多
Background: Infertility is a global health issue, and it is a multidimensional problem with social, economic, and cultural influences. Objectives: The study aimed to determine types of infertility and their contributi...Background: Infertility is a global health issue, and it is a multidimensional problem with social, economic, and cultural influences. Objectives: The study aimed to determine types of infertility and their contributing factors among the respondent infertile women. Methods: This prospective cross-sectional study was conducted among infertile women visiting Sir Salimullah Medical College and Hospital, Dhaka. From January to December 2020, 111 infertile women were included and evaluated for infertility types and their contributing factors. Data were collected by face-to-face interviewing, and data were analyzed statistically. Results: Primary infertility was found among 90 (81%) and secondary infertility among 21 (18.9%). Among the direct risk factors of female infertility, ovulation failure was the majority of the cases, 74 (35.1%), and its mainly observed in primarily infertile women 58 (33.9%). These observations were statistically significant. Conclusions: Infertility should be treated as a public health problem, government and non-government organizations should develop a basic policy to create effective fertility centers.展开更多
Background: The pandemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection has greatly challenged public health worldwide. A growing number of studies have reported gastrointestinal (GI)...Background: The pandemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection has greatly challenged public health worldwide. A growing number of studies have reported gastrointestinal (GI) symptoms. The study aimed to estimate the various digestive symptoms frequently reported in Covid-19 patients among the adult population of Bangladesh. Methods: In this descriptive, cross-sectional study, we enrolled confirmed patients with COVID-19 who were admitted to the COVID unit of Shaheed Suhrawardy Medical college hospital, Dhaka from July 2020 to December 2020. All patients were COVID confirmed by real-time polymerase chain reaction (RT-PCR) and were analyzed for clinical characteristics, laboratory findings and imaging study. Results: The study population consisted of 121 COVID-19-positive patients, among them, 57.85% were male and 42.15% female. The majority (43%) of the study population were in the age group of 31 - 40 years. The male to female ratio was 1.4:1. Nearly 94.2% of the sample population were married, among them 92.9% were male and 96.1% were female. Out of 121 Covid-19 patients, 30.65% had a contact history, 17.4% had a history of traveling or residing in an area reporting COVID-19 and 11.6% of family members were affected by Covid-19. Most of the patients had a fever (95%), cough (88.4%) and dyspnoea (43.8%), pneumonia (37.4%) and severe pneumonia (36.4%). In this study, 40% patients reported a digestive symptom including diarrhea 47.9%, vomiting 55.5%, loss of appetite 16.5%, abdominal pain 29.8%, abdominal bloating 24.8%, reflux 0%, jaundice 3.3%. Regarding co-morbidities, the majority had bronchial asthma (50%) followed by hypertension 46%, diabetes 38%, obesity 23%, and CKD 14% and heart disease 3%. Among 121 COVID-19 patients, 98% had recovered from the disease and 2% of patients expired. Conclusion: Gastrointestinal symptoms are common among patients with COVID-19 and this group of patients had a long time of hospital stay from onset to admission, and higher liver enzyme levels. During the management of COVID-19 patients, clinicians need to be alert regarding suspicion of the GI features among COVID-19, so that they can diagnose early and treat effectively and immediately.展开更多
文摘Cardiovascular Diseases (CVDs) pose a significant global health challenge, necessitating accurate risk prediction for effective preventive measures. This comprehensive comparative study explores the performance of traditional Machine Learning (ML) and Deep Learning (DL) models in predicting CVD risk, utilizing a meticulously curated dataset derived from health records. Rigorous preprocessing, including normalization and outlier removal, enhances model robustness. Diverse ML models (Logistic Regression, Random Forest, Support Vector Machine, K-Nearest Neighbor, Decision Tree, and Gradient Boosting) are compared with a Long Short-Term Memory (LSTM) neural network for DL. Evaluation metrics include accuracy, ROC AUC, computation time, and memory usage. Results identify the Gradient Boosting Classifier and LSTM as top performers, demonstrating high accuracy and ROC AUC scores. Comparative analyses highlight model strengths and limitations, contributing valuable insights for optimizing predictive strategies. This study advances predictive analytics for cardiovascular health, with implications for personalized medicine. The findings underscore the versatility of intelligent systems in addressing health challenges, emphasizing the broader applications of ML and DL in disease identification beyond cardiovascular health.
文摘Background: The emergence of multidrug resistant tuberculosis (MDR-TB) and extensively drug- resistant tuberculosis (XDR-TB) has highlighted the need for early accurate detection and drug susceptibility. Objective: The purpose of the present study was to evaluate the accuracy of GeneX-pert MTB/RIF assay for the detection of Mycobacterium tuberculosis and rifampicin resistance. Methodology: This cross sectional study was done in the Department of Microbiology at Sir Salimullah Medical College, Dhaka and National Institute of Chest Disease & Hospital (NIDCH), Dhaka during the period of January 2014 to December 2014 for a period of 1 (one) year. Sputum samples from suspected MDR-TB patients were collected by purposive sampling technique from OPD of Sir Salimullah Medical College (SSMC) and NIDCH. Microscopy, liquid culture in liquid MGIT 960 media and GeneXpert MTB/RIF were done for MTB diagnosis and detection of rifampicin resistance. MGIT 960 media were also used for determination of drug resistance. Result: Liquid culture yielded higher growth (68%) from 100 samples while GeneXpert MTB assay showed similar result (67% positive and 33% negative). Drug susceptibility test in MGIT 960 media showed that out of 68 positive cases Rifampicin resistant cases were 15 (22.05%) whereas GeneXpert MTB assay detected 14 (20.89%) were Rifampicin resistant out of 67 MTB positive samples. When compared to liquid culture the calculated sensitivity, specificity, negative predictive value (NPV), positive predictive value (PPV) and accuracy of GeneXpert MTB were 98.52%, 100%, 96.96%, 100% and 99%. Conclusion: GeneXpert MTB/RIF assay is high detection rate of pulmonary tuberculosis and multidrug resistant tuberculosis.
文摘Background: Infertility is a global health issue, and it is a multidimensional problem with social, economic, and cultural influences. Objectives: The study aimed to determine types of infertility and their contributing factors among the respondent infertile women. Methods: This prospective cross-sectional study was conducted among infertile women visiting Sir Salimullah Medical College and Hospital, Dhaka. From January to December 2020, 111 infertile women were included and evaluated for infertility types and their contributing factors. Data were collected by face-to-face interviewing, and data were analyzed statistically. Results: Primary infertility was found among 90 (81%) and secondary infertility among 21 (18.9%). Among the direct risk factors of female infertility, ovulation failure was the majority of the cases, 74 (35.1%), and its mainly observed in primarily infertile women 58 (33.9%). These observations were statistically significant. Conclusions: Infertility should be treated as a public health problem, government and non-government organizations should develop a basic policy to create effective fertility centers.
文摘Background: The pandemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection has greatly challenged public health worldwide. A growing number of studies have reported gastrointestinal (GI) symptoms. The study aimed to estimate the various digestive symptoms frequently reported in Covid-19 patients among the adult population of Bangladesh. Methods: In this descriptive, cross-sectional study, we enrolled confirmed patients with COVID-19 who were admitted to the COVID unit of Shaheed Suhrawardy Medical college hospital, Dhaka from July 2020 to December 2020. All patients were COVID confirmed by real-time polymerase chain reaction (RT-PCR) and were analyzed for clinical characteristics, laboratory findings and imaging study. Results: The study population consisted of 121 COVID-19-positive patients, among them, 57.85% were male and 42.15% female. The majority (43%) of the study population were in the age group of 31 - 40 years. The male to female ratio was 1.4:1. Nearly 94.2% of the sample population were married, among them 92.9% were male and 96.1% were female. Out of 121 Covid-19 patients, 30.65% had a contact history, 17.4% had a history of traveling or residing in an area reporting COVID-19 and 11.6% of family members were affected by Covid-19. Most of the patients had a fever (95%), cough (88.4%) and dyspnoea (43.8%), pneumonia (37.4%) and severe pneumonia (36.4%). In this study, 40% patients reported a digestive symptom including diarrhea 47.9%, vomiting 55.5%, loss of appetite 16.5%, abdominal pain 29.8%, abdominal bloating 24.8%, reflux 0%, jaundice 3.3%. Regarding co-morbidities, the majority had bronchial asthma (50%) followed by hypertension 46%, diabetes 38%, obesity 23%, and CKD 14% and heart disease 3%. Among 121 COVID-19 patients, 98% had recovered from the disease and 2% of patients expired. Conclusion: Gastrointestinal symptoms are common among patients with COVID-19 and this group of patients had a long time of hospital stay from onset to admission, and higher liver enzyme levels. During the management of COVID-19 patients, clinicians need to be alert regarding suspicion of the GI features among COVID-19, so that they can diagnose early and treat effectively and immediately.
