Search

Background: Malnutrition in childhood has been linked with inappropriate and ineffective complementary feeding practices especially during the first two year of life. Complementary feeding involves the introduction of other forms of foods and or liquids from six months of age when breast milk only can no longer meet the dietary requirements of infants. The study aimed to assess the prevalence of optimal complementary feeding practices and associated factors among mothers of children 6-23 months in Jijiga town of Somali Region of Ethiopia. Methods: A community based cross-sectional design conducted among 227 mothers of children aged 6–23 months using multi-stage sampling technique. Data was collected using a structured questionnaire analysed using SPSS version 23. Logistic regression analysis was done to determine factors associated between optimal complementary feeding practices. Results: The prevalence of optimal complementary feeding practice was 49.4%, however 57% of the respondents introduced complementary feeding between 6-8 months. Minimal meal frequency and minimal dietary diversity among the respondents was 52% and 45% respectively. Optimal complementary feeding practice was significantly associated with mother’s level of education [AOR=3.4; 95% CI: 2.26-6.14], being employed [AOR=3.94; 95% CI: 1.08-6.57],parity [AOR=5.60; 95% CI: 2.17-8.67], Antenatal Care (ANC) attendance [AOR=7.23; 95% CI: 2.76-11.91), health facility delivery [AOR=4.20;95% CI: 1.06-7.55] and family size [AOR=3.65; 95% CI: 1.80-7.17) Conclusion: Nutrition education and counselling being provided by health workers to mothers should focus on promoting not only timely initiation of complementary feeding but adequate in quantity, appropriate frequency and consistency using variety of foods combination to accommodate the nutritional needs of the growing child while continuing breastfeeding.

Objective: To determine the frequency and etiology of Early Return Visits within 3 days of discharge to the Emergency Department. Study Design: Prospective longitudinal study. Place and Duration of Study: Emergency Department of Combined Military Hospital, Rawalpindi Pakistan, from Jan to Jun 2022. Methodology: All patients visiting the Emergency Department within the defined 6-month period were included in this study, which came to 101’113. To determine overall incidence of Early Return Visits, total number of patients revisiting within 72 hours of Emergency Department discharge was used. To find out the possible factors responsible for ERVs, a sample size of 80 patients revisiting the Emergency Department was calculated through World Health Organization calculator and selected through random sampling technique. Factors responsible for unscheduled Early Return Visits were divided into three broad categories: Doctor-associated, Disease-associated, and Patient-associated. Results: The total number of patients revisiting Emergency Department within 72 hours was 2,880 (2.9%). Out of these 52.5% patients reported back to the Emergency Department due to disease-associated reasons, 27.5% due to doctor-related reasons, and 20% revisited for patient-related reasons. Conclusion: Two-point nine percent patients made ERVs to the Emergency Department within 72 hours. The most common causes of Early Return Visits in this study are disease-related issues followed by doctor-related issues.

The rapid advancement in self-driving and autonomous vehicles (AVs) integrated with artificial intelligence (AI) technology demands not only precision but also output transparency. In this paper, we propose a novel hybrid explainable AI (XAI) framework that combines local interpretable model-agnostic explanations (LIME) and Shapley additive explanations (SHAP). Our framework combines the precision and globality of SHAP and low computational requirements of LIME, creating a balanced approach for onboard deployment with enhanced transparency. We evaluate the proposed framework on three different state-of-the-art models: ResNet-18, ResNet-50, and SegNet-50 on the KITTI dataset. The results demonstrate that our hybrid approach consistently outperforms traditional approaches by achieving a fidelity rate of more than 85%, interpretability factor of more than 80%, and consistency of more than 70%, surpassing the conventional methods. Furthermore, the inference time of our proposed framework with ResNet-18 was 0.28 s; for ResNet-50, it was 0.571 s; and that for SegNet was 3.889 s with XAI layers. This is optimal for onboard computations and deployment. This research establishes a strong foundation for the deployment of XAI in safety-critical AV with balanced tradeoffs for real-time decision-making.

This study presents an advanced framework integrating LLAMA_V2, a large language model, into Open Radio Access Network (O-RAN) systems. The focus is on efficient network slicing for various services. Sensors in IoT devices generate continuous data streams, enabling resource allocation through O-RAN’s dynamic slicing and LLAMA_V2’s optimization. LLAMA_V2 was selected for its superior ability to capture complex network dynamics, surpassing traditional AI/ML models. The proposed method combines sophisticated mathematical models with optimization and interfacing techniques to address challenges in resource allocation and slicing. LLAMA_V2 enhances decision making by offering explanations for policy decisions within the O-RAN framework and forecasting future network conditions using a lightweight LSTM model. It outperforms baseline models in key metrics such as latency reduction, throughput improvement, and packet loss mitigation, making it a significant solution for 5G network applications in advanced industries.

Abstract Background Community Based Health Insurance (CBHI) is a type of health insurance program that provides financial protection against the cost of illness and improving access to health care services for communities engaged in the informal sector. In Ethiopia, the coverage of CBHI enrolment varies across regions and decision of household enrolment is affected by different factors. There are pocket studies on CBHI scheme with different coverage in Ethiopia and there is no pooled study on CBHI enrolment coverage in Ethiopia for better understanding the scheme and decision making. The aim of this systematic review and meta-analysis was to identify the pooled coverage of CBHI enrolment in Ethiopia to understand its policy implications. Methods The systematic review and meta-analysis was done by adhering the PRISMA guideline with exhaustive search in PubMed/Medline, HINARI, SCOPUS and Google scholar complemented by manual search. Two authors independently selected studies, extracted data, and assessed quality of studies. The I2 test statistic was used to test heterogeneity among studies. The overall coverage of CBHI scheme was estimated by using random-effects model. Result Among 269 identified, 17 studies were included in this meta-analysis and the overall coverage of CBHI scheme was 45% (95% CI 35%, 55%) in Ethiopia. The sub-group analysis shows higher enrolment rate 55.97 (95%CI: 41.68, 69.77) in earlier (2016–2017) studies than recent 37.33 (95%CI: 24.82, 50.77) studies (2018–2020). Conclusion The pooled coverage of CBHI enrolment is low in Ethiopia compared the national target of 80% set for 2020. It is also concentrated in only major regions of the country. The finding of the study helps national decision making for CBHI scheme service improvement. Due attention to be given to improving geographic expansion of CBHI and to the declining coverages with in the CBHI implementing regions by addressing the main bottlenecks restraining coverages. Trial registration The protocol of this systematic review and meta-analysis was published in PROSPERO with registration number: CRD42021252762 .

Abstract Malnutrition remains prevalent and existing health problem globally. Particularly Undernutrition is a major public health issue in developing countries. Globally the causes of severe acute undernutrition varies across context. The aim of this study was to identify the determinants of severe acute malnutrition to uncover contextual factors based on UNICEF conceptual framework, as there was no study done in a similar context in Ethiopia. Health facility based (health post) un-matched case control study with Key informant interview was conducted to identify determinant factors of severe acute malnutrition (SAM) among children between 6 and 36 months. 246 children (82 cases and 164) with their mothers or care takers participated the study which was conducted between December 20, 2019 to January 20, 2020 in Kalafo district in Shebele River. Odds ratio with 95% confidence interval was calculated to identify the determinants of SAM among children aged 6–36 months using multivariate logistic regression. The odds of severe acute malnutrition was 2.28 (1.22, 4.26); 4.68 (2.29, 9.58); 2.85 (1.26, 6.45); 2.39 (1.16, 4.96) and 3.262 (1.46, 7.31) and 3.237 (1.45, 7.23); respectively for mothers with three or more under five children, Children with inadequate dietary diversity, experienced diarrhea in past 2 weeks, their mothers had not nutrition counselling during pregnancy and younger (6–11 and 12–17 months) children as compared to controls. The finding of this study reveals the main determinants of severe acute malnutrition in riverine context are multi-level. In addition to this, poor childcare and polygamy identified in qualitative finding. Decisive and multi-sectoral approach is required to addressing SAM in the riverine area.

Background Diet monitoring has been linked with improved eating habits and positive health outcomes such as prevention of obesity. However, this is often unsustainable as traditional methods place a high burden on both participants and researchers through pen and paper recordings and manual nutrient coding respectively. The digitisation of dietary monitoring has greatly reduced these barriers. This paper proposes a diet application with a novel food recognition feature with a usability study conducted in the real world. Methods This study describes the development of a mobile diet application (MyDietCam) targeted at healthy Malaysian adults. Focus group discussions (FGD) were carried out among dietitians and potential users to determine ideal features in a diet application. Thirty participants were recruited from a local university to log their meals through MyDietCam for six days and submit the Malay mHealth Application Usability Questionnaire (M-MAUQ) at the end of the study. Results The findings from the FGD led to the implementation of the main features: individualised recommendations, food logging through food recognition to reduce steps for data entry and provide detailed nutrient analyses through visuals. An average overall usability score of 5.13 out of a maximum of seven was reported from the M-MAUQ which is considered acceptable. Conclusion The development of a local (Malaysian) mobile diet application with acceptable usability may be helpful in sustaining the diet monitoring habit to improve health outcomes. Future work should focus on improving the issues raised before testing the effectiveness of the application for improving health outcomes.

Background: Autoimmune encephalitis (AIE) has been ranked as the third most common cause of encephalitis after viral encephalitis and acute disseminated encephalomyelitis. The estimated incidence is 5-8 cases per 100,000 population. The objective of this study was to develop a costeffective test for detection of anti NMDA R antibodies by using in house prepared rodent brain tissue sections which could facilitate timely diagnosis and management of anti NMDA R Encephalitis, which if left undiagnosed may prove fatal. Methods: A total of 500 samples sent for autoimmune encephalitis related antibody testing were included in this cross-sectional study from April 2019 to March 2021 at department of Immunology, Shifa International Hospital (SIH), Islamabad. Rodent brain was dissected to prepare tissue sections on which samples were tested by Indirect Immunofluorescence. Simultaneously samples were tested on cell-based assay (CBA) which is gold standard for testing anti NMDA R antibodies. Sensitivity, specificity, positive and negative predictive values were calculated. Results: Median age of patients who tested positive for anti NMDA encephalitis was 19 years (range: 1 to 57). Out these 76% were female and 24% males. 5% patients tested positive for anti NMDA antibodies out of those suspected to be suffering from autoimmune encephalitis. The sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of rodent brain IF for anti-NMDR antibodies taking CBA as gold standard was 92.6%, 98.5%, 78.1% and 99.6% respectively. The accuracy of the procedure was 98.2%. Conclusion: Indirect immunofluorescence (IF) on rodent brain tissue sections can be useful as a cost-effective alternate for resource constrained laboratories for timely detection of anti NMDA R antibodies facilitating timely diagnosis and management of anti-NMDA receptor encephalitis patients. [ABSTRACT FROM AUTHOR]

Recently, food recognition has received more research attention for mHealth applications that use automated visual-based methods to assess dietary intake. The goal is to improve the food diaries by addressing the challenges faced by existing methodologies. In addition to the classical challenge of the absence of rigid food structure and intra-class variations, food diaries employing deep networks trained with pristine images are susceptible to quality variations in real-world conditions of image acquisition and transmission. Similarly, existing progressive classifiers that use visual features via a convolutional neural network (CNN) classify food categories and cannot detect food ingredients. We aim to provide a system that selects the optimal subset of features from quality resilient CNNs and subsequently incorporates the parallel type of classification to tackle such challenges. The first progressive classifier recognizes food categories, and its multilabel extension detects food ingredients. Following this idea, after extracting features from the quality resilient category and ingredient CNN models by fine-tuning it on synthetic images generated using the novel online data augmentation method random iterative mixup. Our feature selection strategy uses the Shapley additive explanation (SHAP) values from the gradient explainer to select the best features. Then, novel progressive kernel extreme learning machine (PKELM) is exploited to cater to domain variations due to quality distortions, intra-class variations, and so forth, by remodeling the network structure based on activity value with the nodes. PKELM extension for multilabel classification detects ingredients by employing a bipolar step function to process test output and then selecting the column labels of the resulting matrix with a value of one. Moreover, during online learning, the PKELM novelty detection mechanism can label unlabeled instances and detect noisy samples. Experimental results showed superior performance on an integrated set of measures for seven publicly available food datasets.