Machine learning-based prognostic model for 30-day mortality prediction in Sepsis-3.

BACKGROUND: Sepsis poses a critical threat to hospitalized patients, particularly those in the Intensive Care Unit (ICU). Rapid identification of Sepsis is crucial for improving survival rates. Machine learning techniques offer advantages over traditional methods for predicting outcomes. This study aimed to develop a prognostic model using a Stacking-based Meta-Classifier to predict 30-day mortality risks in Sepsis-3 patients from the MIMIC-III database. METHODS: A cohort of 4,240 Sepsis-3 patients was analyzed, with 783 experiencing 30-day mortality and 3,457 surviving. Fifteen biomarkers were selected using feature ranking methods, including Extreme Gradient Boosting (XGBoost), Random Forest, and Extra Tree, and the Logistic Regression (LR) model was used to assess their individual predictability with a fivefold cross-validation approach for the validation of the prediction. The dataset was balanced using the SMOTE-TOMEK LINK technique, and a stacking-based meta-classifier was used for 30-day mortality prediction. The SHapley Additive explanations analysis was performed to explain the model's prediction. RESULTS: Using the LR classifier, the model achieved an area under the curve or AUC score of 0.99. A nomogram provided clinical insights into the biomarkers' significance. The stacked meta-learner, LR classifier exhibited the best performance with 95.52% accuracy, 95.79% precision, 95.52% recall, 93.65% specificity, and a 95.60% F1-score. CONCLUSIONS: In conjunction with the nomogram, the proposed stacking classifier model effectively predicted 30-day mortality in Sepsis patients. This approach holds promise for early intervention and improved outcomes in treating Sepsis cases.

PPG2RespNet: a deep learning model for respirational signal synthesis and monitoring from photoplethysmography (PPG) signal.

Breathing conditions affect a wide range of people, including those with respiratory issues like asthma and sleep apnea. Smartwatches with photoplethysmogram (PPG) sensors can monitor breathing. However, current methods have limitations due to manual parameter tuning and pre-defined features. To address this challenge, we propose the PPG2RespNet deep-learning framework. It draws inspiration from the UNet and UNet + + models. It uses three publicly available PPG datasets (VORTAL, BIDMC, Capnobase) to autonomously and efficiently extract respiratory signals. The datasets contain PPG data from different groups, such as intensive care unit patients, pediatric patients, and healthy subjects. Unlike conventional U-Net architectures, PPG2RespNet introduces layered skip connections, establishing hierarchical and dense connections for robust signal extraction. The bottleneck layer of the model is also modified to enhance the extraction of latent features. To evaluate PPG2RespNet's performance, we assessed its ability to reconstruct respiratory signals and estimate respiration rates. The model outperformed other models in signal-to-signal synthesis, achieving exceptional Pearson correlation coefficients (PCCs) with ground truth respiratory signals: 0.94 for BIDMC, 0.95 for VORTAL, and 0.96 for Capnobase. With mean absolute errors (MAE) of 0.69, 0.58, and 0.11 for the respective datasets, the model exhibited remarkable precision in estimating respiration rates. We used regression and Bland-Altman plots to analyze the predictions of the model in comparison to the ground truth. PPG2RespNet can thus obtain high-quality respiratory signals non-invasively, making it a valuable tool for calculating respiration rates.

Hypospadias Reconstruction Training: Development of an Ex-Vivo Model for Objective Evaluation of Surgical Skills.

OBJECTIVES: To objectively evaluate technical skill acquisition in hypospadias repair procedures during surgical training using non-invasive wearable sensor technology. METHODS: We combined subjective video evaluations with objective electromyography (EMG) measurements in a hands-on hypospadias training course. Surgeons wore wireless EMG and accelerometer sensors on their dominant hand while performing tasks on ex-vivo cadaveric calf penises. The study focused on four skills: urethral mobilization, dorsal inlay graft harvest/implantation, meatal-based flap urethroplasty, and dorsal plication. Machine learning techniques analyzed muscle activation patterns and attributes for assessing surgical precision. RESULTS: The course included 18 participants (10 female, 8 males; average age 40.18 ± 8.46 years) categorized as novice (n=10, <3 years' experience), intermediate (n=5, 3-5 years), and expert (n=3, >5 years). Video evaluations did not reveal significant differences due to short-term training. However, EMG measurements showed significant reductions in average EMG power, total time, dominant frequency, and cumulative muscle workload after training. Additionally, the mean power spectral density of the EMG signal decreased notably post-training. CONCLUSIONS: This study presents a structured approach for hypospadias training and highlights the effectiveness of wearable sensor technology for objective skill assessment. While video evaluations did not detect significant changes, EMG data provided measurable differences in skill acquisition, suggesting that wearable sensors could enhance objective evaluations of surgical proficiency in residency programs.

Effects of extreme climate events and child mortality on total fertility rate in Bangladesh.

Floods, storms, and temperature extremes are examples of extreme weather events that have a substantial influence on a country's demographic dynamics, including migration, fertility, and mortality. Changes in population size, composition, and distribution may result from these occurrences. This study, which spans the years 1966-2018, looks at how Bangladesh's total fertility rate (TFR) is affected by extreme weather events and child mortality, including neonatal, infant, male infant, and under-five mortality. We use data from secondary publicly accessible sources, such as the World Bank and The Emergency Events Database (EM-DAT), and we investigate the correlations using the autoregressive integrated moving average model (ARIMA), complemented by bivariate and multivariable analyses. Our findings from the univariate analysis are noteworthy. Total extreme climate events (ß = -0.345, 95 % CI: 0.510, -0.180), as well as individual extreme climate events, such as extreme temperatures (ß = -1.176, 95 % CI: 1.88, -0.47), floods (ß = -0.644, 95 % CI: 1.0729, -0.216), and storms (ß = -0.351, 95 % CI: 0.63159, -0.07154), exhibited negative associations with the TFR. Additionally, factors such as contraceptive prevalence rate (CPR) (ß = -0.085, 95 % CI: 0.09072, -0.07954) and gross national income (GNI) per capita (ß = -0.003, 95 % CI: 0.0041123, -0.0024234) were negatively correlated with the TFR. Conversely, various categories of child mortality, namely, infants (ß = 0.041, 95 % CI: 0.040474, 0.042748), males (ß = 0.038, 95 % CI:0.037719, 0.039891), and under-five (ß = 0.026, 95 % CI:0.025684, 0.026979) - are positively associated with TFR. Controlling for two pivotal confounding factors, time and GNI per capita, yielded consistent results in the multivariate analysis. These findings provide insight on the dual impact of extreme weather events, which can reduce TFR while also raising it through infant mortality. This phenomena may be due to the increased vulnerability of younger children in climate-event-prone areas, prompting parents to seek additional children as both a replacement for lost offspring and an insurance mechanism against future child loss.

Institution of a difficult airway response team for emergency department patients with anticipated or encountered difficult airways: Descriptive analysis of a 5-year experience at an academic teaching hospital.

Objectives: This study aimed to describe characteristics and outcomes associated with difficult airway response team (DART) encounters in the emergency department (ED). Methods: We performed a descriptive analysis of a prospective, single-center database of DART encounters in the ED from April 1, 2016 to March 31, 2021 cross-referenced with retrospective chart review. Adult ED patients ≥18 years old for whom a DART was activated were eligible. We prospectively collected activation characteristics, intubation indications, operator characteristics, and intubation methods used for DART encounters. Retrospective chart review was conducted to obtain patient demographics and outcome variables. Descriptive analyses were computed for all outcomes. Results: We analyzed 89 DART encounters. No intubation attempts were made prior to DART activation in 52 cases (58.4%). The most common indications for intubation were angioedema (n = 17, 19.1%) or other airway obstruction (n = 15, 16.9%). A definitive airway was established by anesthesiology (n = 46, 51.7%), emergency medicine (n = 25, 28.1%), trauma surgery (n = 9, 10.1%), and ENT (n = 5, 5.6%). The most common method of intubation used to establish a definitive airway was video laryngoscopy with a bougie or D-blade (n = 29, 32.6%) followed by flexible fiberoptic intubation (n = 19, 21.3%). A surgical airway was required in eight encounters (cricothyrotomy [n = 4, 4.5%]; tracheostomy [n = 4, 4.5%]). Cases were managed in the ED (n = 73, 82%), operating room (OR) (n = 10, 11.2%), and intensive care unit (ICU) (n = 1, 1.1%). All patients requiring intubation had an endotracheal or surgical airway established. Conclusion: Our findings provide important insights regarding ED DART utilization and have implications when considering institution of a DART in the ED.

Improved pediatric ICU mortality prediction for respiratory diseases: machine learning and data subdivision insights.

The growing concern of pediatric mortality demands heightened preparedness in clinical settings, especially within intensive care units (ICUs). As respiratory-related admissions account for a substantial portion of pediatric illnesses, there is a pressing need to predict ICU mortality in these cases. This study based on data from 1188 patients, addresses this imperative using machine learning techniques and investigating different class balancing methods for pediatric ICU mortality prediction. This study employs the publicly accessible "Paediatric Intensive Care database" to train, validate, and test a machine learning model for predicting pediatric patient mortality. Features were ranked using three machine learning feature selection techniques, namely Random Forest, Extra Trees, and XGBoost, resulting in the selection of 16 critical features from a total of 105 features. Ten machine learning models and ensemble techniques are used to make accurate mortality predictions. To tackle the inherent class imbalance in the dataset, we applied a unique data partitioning technique to enhance the model's alignment with the data distribution. The CatBoost machine learning model achieved an area under the curve (AUC) of 72.22%, while the stacking ensemble model yielded an AUC of 60.59% for mortality prediction. The proposed subdivision technique, on the other hand, provides a significant improvement in performance metrics, with an AUC of 85.2% and an accuracy of 89.32%. These findings emphasize the potential of machine learning in enhancing pediatric mortality prediction and inform strategies for improved ICU readiness.

ECG waveform generation from radar signals: A deep learning perspective.

Cardiovascular diagnostics relies heavily on the ECG (ECG), which reveals significant information about heart rhythm and function. Despite their significance, traditional ECG measures employing electrodes have limitations. As a result of extended electrode attachments, patients may experience skin irritation or pain, and motion artifacts may interfere with signal accuracy. Additionally, ECG monitoring usually requires highly trained professionals and specialized equipment, which increases the treatment's complexity and cost. In critical care scenarios, such as continuous monitoring of hospitalized patients, wearable sensors for collecting ECG data may be difficult to use. Although there are issues with ECG, it remains a valuable tool for diagnosing and monitoring cardiac disorders due to its non-invasive nature and the detailed information it provides about the heart. The goal of this study is to present an innovative method for generating continuous ECG waveforms from non-contact radar data by using Deep Learning. The method can eliminate the need for invasive or wearable biosensors and expensive equipment to collect ECGs. In this paper, we propose the MultiResLinkNet, a one-dimensional convolutional neural network (1D CNN) model for generating ECG signals from radar waveforms. With the help of a publicly accessible radar benchmark dataset, an end-to-end DL architecture is trained and assessed. There are six ports of raw radar data in this dataset, along with ground truth physiological signals collected from 30 participants in five distinct scenarios: Resting, Valsalva, Apnea, Tilt-up, and Tilt-down. By using strong temporal and spectral measurements, we assessed our proposed framework's ability to convert ECG data from Radar signals in three distinct scenarios, namely Resting, Valsalva, and Apnea (RVA). ECG segmentation performed better by MultiResLinkNet than by state-of-the-art networks in both combined and individual cases. As a result of the simulations, the resting, valsalva, and RVA scenarios showed the highest average temporal values, respectively: 66.09523 ± 19.33, 60.13625 ± 21.92, and 61.86265 ± 21.37. In addition, it exhibited the highest spectral correlation values (82.4388 ± 18.42 (Resting), 77.05186 ± 23.26 (Valsalva), 74.65785 ± 23.17 (Apnea), and 79.96201 ± 20.82 (RVA)), along with minimal temporal and spectral errors in almost every case. The qualitative evaluation revealed strong similarities between generated and actual ECG waveforms. As a result of our method of forecasting ECG patterns from remote radar data, we can monitor high-risk patients, especially those undergoing surgery.

An Interdisciplinary Protocol for Ventriculoperitoneal Shunt Patient Selection in Normal Pressure Hydrocephalus.

BACKGROUND: Normal pressure hydrocephalus can be treated with ventriculoperitoneal shunt (VPS) placement, but no broadly implemented indication for VPS exists. METHODS: Our protocol consists of physical therapy and occupational therapy practitioners administering validated tests of gait, balance, and cognition before and after lumbar drain placement. Specific tests include: Timed "Up & Go", Tinetti Gait and Balance Assessment, Berg Balance Scale, Mini Mental Status Exam, Trail Making Test Part B, and the Rey Auditory and Visual Learning Test. Minimal clinically important difference values for each test were determined from literature review. A retrospective review of patients treated under this protocol was performed. The primary outcomes were candidacy for VPS based on the protocol and patient-reported symptomatic improvement after VPS placement. RESULTS: A total of 48/75 (64%) patients received VPS. A total of 43/48 (89.6%) of those shunted reported improved symptoms at 6-week follow-up. However, 10/22 (45.5%) reported worsening symptoms at 1-year follow-up. The mean Tinetti score significantly increased after lumbar drain in patients who improved with VPS compared to the no shunt group (4.27 vs. -0.48, P < 0.001). A total of 6/33 (18%) patients with postoperative imaging had a subdural fluid collection identified and 3/49 (6%) had other complications, including 1 seizure, 1 intracerebral hemorrhage, and 1 stroke. CONCLUSIONS: Standardized assessment of gait, balance, and cognition before and after temporary cerebrospinal fluid diversion identifies patients with normal pressure hydrocephalus likely to benefit from VPS placement with a low complication rate. One year after VPS, approximately one half of patients had symptoms recurrence.

User Experience of Access to Sexual Assault Nurse Examiner and Emergency Contraception in Emergency Departments in the United States: A National Survey.

Background: Despite the prevalence of sexual assault presentations to emergency departments (ED) in the United States, current access to sexual assault nurse examiners (SANE) and emergency contraception (EC) in EDs is unknown. Methods: In this study we employed a "secret shopper," cross-sectional telephonic survey. A team attempted phone contact with a representative sample of EDs and asked respondents about the availability of SANEs and EC in their ED. Reported availability was correlated with variables including region, urban/rural status, hospital size, faith affiliation, academic affiliation, and existence of legislative requirements to offer EC. Results: Over a two-month period in 2019, 1,046 calls to hospitals were attempted and 960 were completed (91.7% response rate). Of the 4,360 eligible hospitals listed in a federal database, 960 (22.0%) were contacted. Access to SANEs and EC were reported to be available in 48.9% (95% confidence interval [CI] 45.5-52.0) and 42.5% (95% CI 39.4-45.7) of hospitals, respectively. Access to EC was positively correlated with SANE availability. The EDs reporting SANE and EC availability were more likely to be large, rural, and affiliated with an academic institution. Those reporting access to EC were more likely to be in the Northeast and in states with legislative requirements to offer EC. Conclusion: Our results suggest that perceived access to sexual assault services and emergency contraception in EDs in the United States remains poor with regional and legislative disparities. Results suggest disparities in perceived access to EC and SANE in the ED, which have implications for improving ED practices regarding care of sexual assault victims.

Academic accomplishments of Black neurosurgeons in the United States.

OBJECTIVE: Neurosurgery has remained relatively homogeneous in terms of racial and gender diversity, trailing behind national demographics. Less than 5% of practicing neurosurgeons in the United States identify as Black/African American (AA). Research and academic productivity are highly emphasized within the field and are crucial for career advancement at academic institutions. They also serve as important avenues for mentorship and recruitment of diverse trainees and medical students. This study aimed to summarize the academic accomplishments of AA neurosurgeons by assessing publication quantity, h-index, and federal grant funding. METHODS: One hundred thirteen neurosurgery residency training programs accredited by the Accreditation Council for Graduate Medical Education in 2022 were included in this study. The American Society of Black Neurosurgeons registry was reviewed to analyze the academic metrics of self-identified Black or AA academic neurosurgeons. Data on the academic rank, leadership position, publication quantity, h-index, and race of neurosurgical faculty in the US were obtained from publicly available information and program websites. RESULTS: Fifty-five AA and 1393 non-AA neurosurgeons were identified. Sixty percent of AA neurosurgeons were fewer than 10 years out from residency training, compared to 37.4% of non-AA neurosurgeons (p = 0.001). AA neurosurgeons had a median 32 (IQR 9, 85) publications compared to 52 (IQR 22, 122) for non-AA neurosurgeons (p = 0.019). AA neurosurgeons had a median h-index of 12 (IQR 5, 24) compared to 16 (IQR 9, 31) for non-AA colleagues (p = 0.02). Following stratification by academic rank, these trends did not persist. No statistically significant differences in the median amounts of awarded National Institutes of Health funding (p = 0.194) or level of professorship attained (p = 0.07) were observed between the two cohorts. CONCLUSIONS: Racial disparities between AA and non-AA neurosurgeons exist in publication quantity and h-index overall but not when these groups are stratified by academic rank. Given that AA neurosurgeons comprise more junior faculty, it is expected that their academic accomplishments will increase as more enter academic practice and current neurosurgeons advance into more senior positions.

Assessment of mental wellbeing of university students in Bangladesh using Goldberg's GHQ-12: A cross-sectional study.

Background and Aims: The mental well-being of university students is a primary public health concern worldwide, including in Bangladesh. The objective of this study was to determine the prevalence of the overall mental health status among Bangladeshi university students. The study used larger and more diverse sample compared to previous studies, and also explored factors associated with the mental health well-being of those students. Methods: Data were collected through an online questionnaire, utilizing the proportional allocation method, from students in various universities across Bangladesh. The sample included 2036 participants. The study applied Goldberg's General Health Questionnaire (GHQ-12) using the GHQ2+ threshold (i.e., having more than two symptoms). A binary outcome variable was created with two levels: "good mental health" and "poor mental health," to assess the mental health status of the university students. The explanatory variables were age, gender, academic year, type of university, and sources of personal expenses. Exploratory data analysis, association tests, and binary logistic regression models were used to identify factors influencing the outcome variable. Results: A total of 55.9% of students (male: 52.6% and female: 62.8%) exhibited poor mental health status. Female students' mental health was found to be worse (odds ratio [OR]: 1.49, 95% confidence interval [CI]: 1.23-1.81) compared to that of males. Similarly, public university students displayed a worse mental health condition than their counterparts in private universities (OR: 1.29, 95% CI: 1.03-1.61). Conclusion: The overall mental health of university students in Bangladesh is concerning. There is a pressing need for effective mental health policies and interventions to bolster the mental well-being of university students, with a specific focus on students from public universities and females.

Prevalence of unqualified sources of antimalarial drug prescription for children under the age of five: A study in 19 low- and middle-income countries.

BACKGROUND: Antimalarial drug resistance poses a severe danger to global health. In Low- and Middle-Income Countries (LMICs), there is a lack of reliable information on antimalarial prescriptions for recent malarial fever in children under five. Our study aims to determine the prevalence of unqualified sources of antimalarial drug prescription for children under the age of five in 19 low- and middle-income countries. METHODS: We performed a cross-sectional study of the Malaria Indicator Survey (MIS) datasets (n = 106265) across 19 LMICs. The recent MIS datasets were used, and the study only included children under five who had taken an antimalarial drug for a recent malarial fever. The outcome variable was classified into two distinct categories: those who had taken antimalarial drugs for malarial fever from qualified sources and those who did not. FINDINGS: Among LMICs, we found that 87.1% of children under five received an antimalarial prescription from unqualified sources who had recently experienced malarial fever. In several LMICs (Tanzania, Nigeria, and Ghana), a substantial portion of recent antimalarial prescriptions for malaria was taken from unqualified sources (about 60%). Some LMICs (Guinea (31.8%), Mali (31.3%), Nigeria (20.4%), Kenya (2.6%), and Senegal (2.7%)) had low rates of antimalarial drug consumption even though children under five received a high percentage of antimalarial prescriptions from qualified sources for a recent malarial fever. Living in rural areas, having mothers with higher education, and having parents with more wealth were frequently taken antimalarial from qualified sources for recent malarial fever in children under five across the LMICs. INTERPRETATION: The study draws attention to the importance of national and local level preventative strategies across the LMICs to restrict antimalarial drug consumption. This is because antimalarial prescriptions from unqualified sources for recent malarial fever in children under five were shockingly high in most LMICs and had high rates of unqualified prescriptions in certain other LMICs.

Availability of basic infection control items and personal protection equipment in 7948 health facilities in eight low- and middle-income countries: Evidence from national health system surveys.

Background: Hundreds of millions of people become infected globally every year while seeking care in health facilities that lack basic needs like infection control measures and personal protective equipment (PPE). We aimed to evaluate the availability of infection control items and PPE in eight low- and middle-income countries and identify disparities in the availability of those items. Methods: In this study, we combined publicly available nationally representative cross-sectional health system surveys (Service Provision Assessments by the Demographic and Health Survey Programme) conducted in eight countries between 2013 and 2018: Afghanistan, Bangladesh, the Democratic Republic of the Congo, Haiti, Malawi, Nepal, Senegal, and Tanzania. The availability of infection control items was evaluated using a list of six items (a waste receptacle, a sharps container, disinfectant, single-use disposable or auto-disposable syringes, soap and running water, or an alcohol-based hand rub, and guidelines for standard precautions). PPE includes four items: gloves, medical masks, gowns, and eye protection. We considered these items available in a facility if they were observed in general outpatient areas or any service-specific area (i.e. delivery room). Results: We analysed data from 7948 health facilities (694 hospitals and 7254 health centres/clinics). Overall, among the infection control items and PPE, most surveyed facilities had high availability of single-use disposable or auto-disposable syringes (91.40%) and latex gloves (92.56%). Of infection control measures, guidelines for infection control were the least available during the survey, with the lowest (6.15%) in Nepal and the highest (68.18%) in Malawi. Of the PPE items, eye protection was the least available during the survey, with the lowest (5.4% in Senegal) and the highest (28.17%) in Haiti. Only 1567 (19.71%) facilities looked to have all the basic infection control materials, and 1023 (12.87%) of the analysed facilities possessed all of the PPE. Within the same country, the availability of items varied more between hospitals and health centres/clinics than between them. Conclusions: All eight of our study countries experience shortages of the most fundamental standard precaution items to avert infection. Steps must be taken in each of these countries to reduce inadequacies and disparities and enhance efficiency in the conversion of health-system inputs into the facility's availability of standard precaution items for infection control - to curb the risk of infectious disease transmission.

FPGA Implementation of Complex-Valued Neural Network for Polar-Represented Image Classification.

This proposed research explores a novel approach to image classification by deploying a complex-valued neural network (CVNN) on a Field-Programmable Gate Array (FPGA), specifically for classifying 2D images transformed into polar form. The aim of this research is to address the limitations of existing neural network models in terms of energy and resource efficiency, by exploring the potential of FPGA-based hardware acceleration in conjunction with advanced neural network architectures like CVNNs. The methodological innovation of this research lies in the Cartesian to polar transformation of 2D images, effectively reducing the input data volume required for neural network processing. Subsequent efforts focused on constructing a CVNN model optimized for FPGA implementation, emphasizing the enhancement of computational efficiency and overall performance. The experimental findings provide empirical evidence supporting the efficacy of the image classification system developed in this study. One of the developed models, CVNN_128, achieves an accuracy of 88.3% with an inference time of just 1.6 ms and a power consumption of 4.66 mW for the classification of the MNIST test dataset, which consists of 10,000 frames. While there is a slight concession in accuracy compared to recent FPGA implementations that achieve 94.43%, our model significantly excels in classification speed and power efficiency-surpassing existing models by more than a factor of 100. In conclusion, this paper demonstrates the substantial advantages of the FPGA implementation of CVNNs for image classification tasks, particularly in scenarios where speed, resource, and power consumption are critical.

Two decades of endemic dengue in Bangladesh (2000-2022): trends, seasonality, and impact of temperature and rainfall patterns on transmission dynamics.

The objectives of this study were to compare dengue virus (DENV) cases, deaths, case-fatality ratio [CFR], and meteorological parameters between the first and the recent decades of this century (2000-2010 vs. 2011-2022) and to describe the trends, seasonality, and impact of change of temperature and rainfall patterns on transmission dynamics of dengue in Bangladesh. For the period 2000-2022, dengue cases and death data from Bangladesh's Ministry of Health and Family Welfare's website, and meteorological data from the Bangladesh Meteorological Department were analyzed. A Poisson regression model was performed to identify the impact of meteorological parameters on the monthly dengue cases. A forecast of dengue cases was performed using an autoregressive integrated moving average model. Over the past 23 yr, a total of 244,246 dengue cases were reported including 849 deaths (CFR = 0.35%). The mean annual number of dengue cases increased 8 times during the second decade, with 2,216 cases during 2000-2010 vs. 18,321 cases during 2011-2022. The mean annual number of deaths doubled (21 vs. 46), but the overall CFR has decreased by one-third (0.69% vs. 0.23%). Concurrently, the annual mean temperature increased by 0.49 °C, and rainfall decreased by 314 mm with altered precipitation seasonality. Monthly mean temperature (Incidence risk ratio [IRR]: 1.26), first-lagged rainfall (IRR: 1.08), and second-lagged rainfall (IRR: 1.17) were significantly associated with monthly dengue cases. The increased local temperature and changes in rainfall seasonality might have contributed to the increased dengue cases in Bangladesh.

Urologist validation of an artificial intelligence-based tool for automated estimation of penile curvature.

INTRODUCTION: Severity of penile curvature (PC) is commonly used to select the optimal surgical intervention for hypospadias, either alone or in conjunction with other phenotypic characteristics. Despite this, current literature on the accuracy and precision of different PC measurement techniques in hypospadias patients remains limited. PURPOSE: Assess the feasibility and validity of an artificial intelligence (AI)-based model for automatic measurement of PC. MATERIAL AND METHODS: Seven 3D-printed penile models with variable degrees of ventral PC were used to evaluate and compare interobserver agreement in estimation of penile curvatures using various measurement techniques (including visual inspection, goniometer, manual estimation via a mobile application, and an AI-based angle estimation app. In addition, each participant was required to complete a questionnaire about their background and experience. RESULTS: Thirty-five clinical practitioners participated in the study, including pediatric urologists, pediatric surgeons, and urologists. For each PC assessment method, time required, mean absolute error (MAE), and inter-rater agreement were assessed. For goniometer-based measurement, the lowest MAE achieved was derived from a model featuring 86° PC. When using either UVI (unaid visual inspection), mobile apps, or AI-based measurement, MAE was lowest when assessing a model with 88° PC, indicating that high-grade cases can be quantified more reliably. Indeed, MAE was highest when PC angle ranged between 40° and 58° for all the investigated measurement tools. In fact, among these methodologies, AI-based assessment achieved the lowest MAE and highest level of inter-class correlation, with an average measurement time of only 22 s. CONCLUSION: AI-based PC measurement models are more practical and consistent than the alternative curvature assessment tools already available. The AI method described in this study could help surgeons and hypospadiology researchers to measure PC more accurately.

Quantification of vesicoureteral reflux using machine learning.

INTRODUCTION: The radiographic grading of voiding cystourethrogram (VCUG) images is often used to determine the clinical course and appropriate treatment in patients with vesicoureteral reflux (VUR). However, image-based evaluation of VUR remains highly subjective, so we developed a supervised machine learning model to automatically and objectively grade VCUG data. STUDY DESIGN: A total of 113 VCUG images were gathered from public sources to compile the dataset for this study. For each image, VUR severity was graded by four pediatric radiologists and three pediatric urologists (low severity scored 1-3; high severity 4-5). Ground truth for each image was assigned based on the grade diagnosed by a majority of the expert assessors. Nine features were extracted from each VCUG image, then six machine learning models were trained, validated, and tested using 'leave-one-out' cross-validation. All features were compared and contrasted, with the highest-ranked then being used to train the final models. RESULTS: F1-score is a metric that is often used to indicate performance accuracy of machine learning models. When using the highest-ranked VCUG image features, F1-scores for the support vector machine (SVM) and multi-layer perceptron (MLP) classifiers were 90.27 % and 91.14 %, respectively, indicating a high level of accuracy. When using all features combined, F1 scores were 89.37 % for SVM and 90.27 % for MLP. DISCUSSION: These findings indicate that a distorted pattern of renal calyces is an accurate predictor of high-grade VUR. Machine learning protocols can be enhanced in future to improve objective grading of VUR.

GCDN-Net: Garbage classifier deep neural network for recyclable urban waste management.

The escalating waste volume due to urbanization and population growth has underscored the need for advanced waste sorting and recycling methods to ensure sustainable waste management. Deep learning models, adept at image recognition tasks, offer potential solutions for waste sorting applications. These models, trained on extensive waste image datasets, possess the ability to discern unique features of diverse waste types. Automating waste sorting hinges on robust deep learning models capable of accurately categorizing a wide range of waste types. In this study, a multi-stage machine learning approach is proposed to classify different waste categories using the "Garbage In, Garbage Out" (GIGO) dataset of 25,000 images. The novel Garbage Classifier Deep Neural Network (GCDN-Net) is introduced as a comprehensive solution, adept in both single-label and multi-label classification tasks. Single-label classification distinguishes between garbage and non-garbage images, while multi-label classification identifies distinct garbage categories within single or multiple images. The performance of GCDN-Net is rigorously evaluated and compared against state-of-the-art waste classification methods. Results demonstrate GCDN-Net's excellence, achieving 95.77% accuracy, 95.78% precision, 95.77% recall, 95.77% F1-score, and 95.54% specificity when classifying waste images, outperforming existing models in single-label classification. In multi-label classification, GCDN-Net attains an overall Mean Average Precision (mAP) of 0.69 and an F1-score of 75.01%. The reliability of network performance is affirmed through saliency map-based visualization generated by Score-CAM (class activation mapping). In conclusion, deep learning-based models exhibit efficacy in categorizing diverse waste types, paving the way for automated waste sorting and recycling systems that can mitigate costs and processing times.

Examining the disparities of anti-malarial drug consumption among children under the age of five: a study of 5 malaria-endemic countries.

BACKGROUND: Malaria is one of the most prominent illnesses affecting children, ranking as one of the key development concerns for many low- and middle-income countries (LMICs). There is not much information available on the use of anti-malarial drugs in LMICs in children under five. The study aimed to investigate disparities in anti-malarial drug consumption for malaria among children under the age of five in LMICs. METHODS: This study used recent available cross-sectional data from the Malaria Indicator Survey (MIS) datasets across five LMICs (Guinea, Kenya, Mali, Nigeria, and Sierra Leone), which covered a portion of sub-Saharan Africa. The study was carried out between January 2, 2023, and April 15, 2023, and included children under the age of five who had taken an anti-malarial drug for malaria 2 weeks before the survey date. The outcome variable was anti-malarial drug consumption, which was classified into two groups: those who had taken anti-malarial drugs and those who had not. RESULTS: In the study of LMICs, 32,397 children under five were observed, and among them, 44.1% had received anti-malarial drugs. Of the five LMICs, Kenya had the lowest (9.2%) and Mali had the highest (70.5%) percentages of anti-malarial drug consumption. Children under five with malaria are more likely to receive anti-malarial drugs if they are over 1 year old, live in rural areas, have mothers with higher education levels, and come from wealthier families. CONCLUSION: The study emphasizes the importance of developing universal coverage strategies for anti-malarial drug consumption at both the national and local levels. The study also recommends that improving availability and access to anti-malarial drugs may be necessary, as the consumption of these drugs for treating malaria in children under the age of five is shockingly low in some LMICs.