Identification and analysis of accident black spots using Geographic Information System (GIS): A study on Kushtia-Jhenaidah national highway (N704), Bangladesh.

Road accidents, mostly on national highways, pose a significant public health and economic burden in Bangladesh, requiring in-depth analysis for road safety measures. This study comprehensively analyzes accident trends, characteristics, causes, and consequences by identifying the accident black spots on the Kushtia-Jhenaidah National Highway (N704). Accident records from 2017 to 2021 were collected from nearby police stations. Additionally, using a cluster random sampling approach, a questionnaire survey with 100 respondents (50% drivers and 50% general road users) was also conducted to capture diverse perceptions and behaviors. The study utilizes descriptive methods, such as trends analysis and frequency distributions, alongside spatial analysis techniques, including severity index, Kernel Density Estimation, and hotspot analysis. Findings indicate a decrease in accidents from 2018 to 2021, yet a concerning rise in fatalities in 2021. Trucks (47.9%) emerge as the primary contributor among 169 vehicles involved in accidents. Head-on collisions (36%) are prevalent, attributed to both human and environmental factors, including driver inexperience (56%), mobile phone use while driving (78%), lack of proper training (12%), overspeeding (28.3%), and nighttime driving (54%) influenced by seasons and land use. Mostly, victims aged from 20 to 40, where men are more affected by fatalities (70.7%) and women by injuries (86.3%). Out of 35 identified accident spots, including Battail, Bittipara Bazar, Laxmipur Bazar, Modhupur Bazar, IU Main Gate, Sheikhpara Bazar, and DM College Front, are designated as blackspot zones based on the frequency of accidents, deaths, and injuries. The study concludes by recommending targeted interventions, driver training, infrastructure improvements, regulatory measures, and victim assistance in collaboration with local and national agencies to enhance road safety and mitigate accident risks.

Prediction of suicidal ideation with associated risk factors among university students in the southern part of Bangladesh: Machine learning approach.

BACKGROUND: The prevalence of suicidal ideation has become an urgent issue, particularly among adolescents. The primary objective of this research is to determine the prevalence of suicidal ideation among students in the southern region of Bangladesh and to predict this phenomenon using machine learning (ML) models. METHODS: The data collection process involved using a simple random sampling technique to gather information from university students located in the southern region of Bangladesh during the period spreading from April 2022 to June 2022. Upon accounting for missing values and non-response rates, the ultimate sample size was determined to be 584, with 51.5 % of participants identifying as male and 48.5 % female. RESULTS: A significant proportion of students, precisely 19.9 %, reported experiencing suicidal ideation. Most participants were female (77 %) and unmarried (78 %). Within the machine learning (ML) framework, KNN exhibited the highest accuracy score of 91.45 %. In addition, the Random Forest (RF), and Categorical Boosting (CatBoost) algorithms exhibited comparable levels of accuracy, achieving scores of 90.60 and 90.59 respectively. LIMITATIONS: Using a cross-sectional design in research limits the ability to establish causal relationships. CONCLUSION: Mental health practitioners can employ the KNN model alongside patients' medical histories to detect those who may be at a higher risk of attempting suicide. This approach enables healthcare professionals to take appropriate measures, such as counselling, encouraging regular sleep patterns, and addressing depression and anxiety, to prevent suicide attempts.

Complete genome sequence analysis of the multidrug resistant Aeromonas veronii isolated for the first time from stinging catfish (Shing fish) in Bangladesh.

Objective: Whole genome sequencing (WGS) of Aeromonas veronii Alim_AV_1000 isolated from ulcerative lesions of Shing fish (stringing catfish; Heteropneustes fossilis) was performed during the outbreak year 2021. Materials and Methods: Using next-generation sequencing (Illumina) technology, WGS was accomplished, resulting in the sequencing, assembly, and analysis of the entire genome of the A. veronii strain. Moreover, the genomic features, virulence factors, antimicrobial resistome, and phylogenetic analysis for the molecular evolution of this strain were also examined. Results: The genome size of the A. veronii Alim_AV_1000 strain was 4,494,515 bp, with an average G+C content of 58.87%. Annotation revealed the known transporters and genes linked to virulence, drug targets, and antimicrobial resistance. Conclusion: The findings of the phylogenetic analysis revealed that the strain of the present study has a close relationship with the China strain TH0426 and strain B56. This study provides novel information on A. veronii isolated from Shing fish in Bangladesh.

A comparative study of machine learning algorithms for predicting domestic violence vulnerability in Liberian women.

Domestic violence against women is a prevalent in Liberia, with nearly half of women reporting physical violence. However, research on the biosocial factors contributing to this issue remains limited. This study aims to predict women's vulnerability to domestic violence using a machine learning approach, leveraging data from the Liberian Demographic and Health Survey (LDHS) conducted in 2019-2020. We employed seven machine learning algorithms to achieve this goal, including ANN, KNN, RF, DT, XGBoost, LightGBM, and CatBoost. Our analysis revealed that the LightGBM and RF models achieved the highest accuracy in predicting women's vulnerability to domestic violence in Liberia, with 81% and 82% accuracy rates, respectively. One of the key features identified across multiple algorithms was the number of people who had experienced emotional violence. These findings offer important insights into the underlying characteristics and risk factors associated with domestic violence against women in Liberia. By utilizing machine learning techniques, we can better predict and understand this complex issue, ultimately contributing to the development of more effective prevention and intervention strategies.

Knowledge, attitude, perceived effectiveness and self-practice of complementary and alternative medicine: a cross-sectional comparison between medical and non-medical students of Bangladesh.

BACKGROUND: Bangladesh's population commonly utilizes Complementary and alternative medicine (CAM) to treat their health issues. Despite the increasing interest in CAM, it has been excluded from conventional medical training in Bangladesh for many years. Therefore, this study assessed and compared the knowledge level, attitude, perceived effectiveness, and self-practice of CAM among undergraduate students of Bangladesh. METHODS: This cross-sectional group comparison study was conducted among undergraduate (both medical and non-medical) students of Bangladesh between November and December 2021. Data was collected using a self-reported pretested semi-structured online questionnaire. The questionnaire contained questions regarding background information, knowledge regarding CAM, source of CAM knowledge, attitude towards CAM, interest in attaining CAM knowledge, perceived effectiveness of CAM, perceived adverse effects of CAM, self-practice of CAM, and whether would they refer CAM to others. A total of 576 students responded and the data gathered allowed for the following: (1) an overview of the study groups, (2) respondents' general perception and knowledge regarding CAM, and (3) a comparison of respondents' CAM knowledge, general perception, and usage by area of study. Data were analyzed using STATA (v.16) and descriptive statistics, Pearson's chi-square test, and Mann-Whitney U test were performed. RESULTS: A total of 329 medical students and 247 non-medical students participated in the study. The mean age of the participants was 21.57 ± 1.8 years and 56.2% of them were male. The most known CAM among medical (M) students was homeopathy (44.6%) and among non-medical (NM) students were herbal medicine (45.7%). Non-medical students had significantly better knowledge about nine out of twelve CAM modalities included in the study, and no significant differences were present for the rest of the modalities. Medical (81.1%) and non-medical students (86.2%) perceived traditional Chinese medicine and homeopathy to be the most effective respectively. "Incorporating CAM with conventional medicine would result in increased patient satisfaction" showed the most statistically significant (p = 0.0002) difference among both groups. Yoga was the most often practiced modality among medical students and homeopathy among non-medical students. CONCLUSION: Medical students have a lacking of knowledge and a positive attitude towards CAM, despite its very common practice among the people of Bangladesh. Therefore, emphasis should be put on the inclusion of CAM modules in medical training.