Statistical Significance Tests Research Articles

Acute Kidney Injury Among Admitted COVID-19 Patients in Addis Ababa, Ethiopia.

Although diffuse alveolar damage and respiratory failure are the most common symptoms of coronavirus disease 2019, other organ involvement, such as the kidney, has been reported. The incidence of acute kidney injury in COVID-19 patients has been reported to vary greatly. In this study, we look at the magnitude and risk factors for acute kidney injury in COVID-19 patients in Ethiopia, a developing country. A hospital-based retrospective cross-sectional study design was conducted among admitted COVID-19 patients at Eka Kotebe general hospital and Saint Peter COVID-19 treatment center by reviewing data from September 2020 to September 2021. A random sampling technique with proportional size allocation was used to select a total sample of 402 patients (225 from Eka Kotebe and 177 from St. Peter). Secondary data was collected from patient medical records using a standard, pre-tested data collection checklist using the Kobo toolbox, which was then exported to SPSS version 25.0 for analysis. The association between dependent and independent variables was analyzed using binary logistic regression. A statistical significance test was declared at a p value of<=0.05 with a 95% confidence interval. A total of 402 patient charts were reviewed, and the proportion of patients with acute kidney injury was found to be 18.9%. After adjusting for potential confounders, age<=35 years (AOR = 0.23, 95% CI = 0.07-0.72), female gender (AOR = 0.51, 95% CI = 0.28-0.94), and isolation type ICU (AOR = 5.11, 95% CI = 1.44-18.06) were significantly associated with acute kidney injury. Acute kidney injury is a common complication in hospitalized COVID-19 patients. The prevalence of acute kidney injury in this study was 18.9%. Age, gender, and type of isolation were the factors that had a significant association with acute kidney injury. Clinicians and other concerned parties should provide more care to ICU patients and COVID-19 patients who are older.

Ophthalmic services utilisation and associated factors in the Ashanti region, Ghana.

This survey determined the utilisation of eye care services and associated factors among adults in the Ashanti region of Ghana. A population-based cross-sectional descriptive study. Data for this study was collected from 1615 randomly selected individuals in the Ashanti region of Ghana, using a structured, pretested interviewer-guided questionnaire. Information regarding the accessibility and determinants of, and barriers to, eye care services was based on self-reports, using the WHO Eye Care Services Assessment Questionnaire. Inferential analyses were performed using the chi-square test for statistical significance, set at p=0.05. Ashanti Region, Ghana. One thousand six hundred and fifteen randomly selected adults. Public eye care facilities were used by 58.2% of the participants for their last eye exam. Of the participants, 47.0% had travelled less than five kilometres for their last eye exam. Waiting time and service cost were participants' most frequently cited challenges in seeking care. No need felt (40.1%), self-medication (37.7%) and cost (22.2%) were the most frequently mentioned barriers to seeking ophthalmic services. The major challenges encountered in seeking eye care services were waiting time and cost of service. Major barriers to ophthalmic services utilisation were no need felt, self-medication and cost. Factors such as cost, lack of felt need and self-medication, which serve as barriers to utilising eye care services, should be addressed by stake-holders through eye health education and promotion. None declared.

BUS-Set: A benchmark for quantitative evaluation of breast ultrasound segmentation networks with public datasets.

BUS-Set is a reproducible benchmark for breast ultrasound (BUS) lesion segmentation, comprising of publicly available images with the aim of improving future comparisons between machine learning models within the field ofBUS. Four publicly available datasets were compiled creating an overall set of 1154 BUS images, from five different scanner types. Full dataset details have been provided, which include clinical labels and detailed annotations. Furthermore, nine state-of-the-art deep learning architectures were selected to form the initial benchmark segmentation result, tested using five-fold cross-validation and MANOVA/ANOVA with Tukey statistical significance test with a threshold of 0.01. Additional evaluation of these architectures was conducted, exploring possible training bias, and lesion size and typeeffects. Of the nine state-of-the-art benchmarked architectures, Mask R-CNN obtained the highest overall results, with the following mean metric scores: Dice score of 0.851, intersection over union of 0.786 and pixel accuracy of 0.975. MANOVA/ANOVA and Tukey test results showed Mask R-CNN to be statistically significant better compared to all other benchmarked models with a p-value>0.01. Moreover, Mask R-CNN achieved the highest mean Dice score of 0.839 on an additional 16 image dataset, that contained multiple lesions per image. Further analysis on regions of interest was conducted, assessing Hamming distance, depth-to-width ratio (DWR), circularity, and elongation, which showed that the Mask R-CNN's segmentations maintained the most morphological features with correlation coefficients of 0.888, 0.532, 0.876 for DWR, circularity, and elongation, respectively. Based on the correlation coefficients, statistical test indicated that Mask R-CNN was only significantly different toSk-U-Net. BUS-Set is a fully reproducible benchmark for BUS lesion segmentation obtained through the use of public datasets and GitHub. Of the state-of-the-art convolution neural network (CNN)-based architectures, Mask R-CNN achieved the highest performance overall, further analysis indicated that a training bias may have occurred due to the lesion size variation in the dataset. All dataset and architecture details are available at GitHub: https://github.com/corcor27/BUS-Set, which allows for a fully reproduciblebenchmark.

Promoting generic drug usage in Japan: correlation between generic drug usage and monthly personal income

BackgroundTo reduce pharmacy-related medical expenses, it is necessary to cut drug costs, potentially by increasing generic drug usage. This study analyzes the correlation between generic drug usage and monthly personal income by examining prescriptions for individual drugs.MethodsWe conducted a cross-sectional study based on the data set from the National Database of Health Insurance Claims and Specific Health Checkups of Japan Open Data Japan and the Basic Survey on Wage Structure. We calculated the correlation coefficient between the usage rate of generic drugs in each prefecture of Japan and monthly personal incomes. We then analyzed the correlation coefficients based on the therapeutic categories of medicinal drugs; the contingency table was visualized as a mosaic plot. To compare the proportions between multiple categories, the chi-squared test was applied as a statistical significance test that was used in the analysis of n × m contingency tables. We worked with the null hypothesis that there were no differences between classes in the population.ResultsRegarding the correlation coefficient between the usage rate of generic drugs and monthly personal incomes, the proportion of negative correlation coefficients for outpatient out-of-hospital and outpatient in-hospital prescriptions was over 70%, while that for inpatient prescriptions was 46.9%. The proportion of medicinal drugs exhibiting a negative correlation between the rates of generic drug usage and monthly personal incomes for outpatient out-of-hospital prescriptions and outpatient in-hospital prescriptions was higher than that of inpatient prescriptions. The proportion of statistically correlated medicinal drugs among inpatient prescriptions was lower than that among outpatient out-of-hospital and outpatient in-hospital prescriptions. The proportions of significant negative correlations for outpatient out-of-hospital, outpatient in-hospital, and inpatient prescriptions were 30.6%, 22.7%, and 3.5%, respectively. It was also observed that the rate of generic prescription usage for outpatient out-of-hospital and in-hospital prescriptions increased as monthly personal incomes decreased. In outpatients, the therapeutic categories with strong negative correlations were vasodilators and hyperlipidemia drugs.ConclusionsOur results may help to increase the usage rate of generic drugs in different prefectures by providing useful information for promoting them throughout Japan.

Use of menopausal hormone therapy and ovarian cancer risk in a French cohort study.

Epidemiological studies have found that menopausal hormone therapy (MHT) use is associated with an increased ovarian cancer risk. However, whether different MHT types confer the same level of risk is unclear. We estimated the associations between different MHT types and the risk of ovarian cancer in a prospective cohort. The study population included 75 606 postmenopausal women from the E3N cohort. Exposure to MHT was identified from self-reports in biennial questionnaires between 1992 and 2004 and from drug claim data matched to the cohort between 2004 and 2014. Hazard ratios and 95% confidence intervals (CIs) of ovarian cancer were estimated using multivariable Cox proportional hazards models with MHT as a time-varying exposure. Tests of statistical significance were 2-sided. Over an average 15.3 years follow-up, 416 ovarian cancers were diagnosed. Hazard ratios of ovarian cancer associated with ever use of estrogens combined with progesterone or dydrogesterone and ever use of estrogens combined with other progestagen were equal to 1.28 (95% CI = 1.04 to 1.57) and 0.81 (95% CI = 0.65 to 1.00), respectively (Phomogeneity = .003), compared with never use. The hazard ratio for unopposed estrogen use was 1.09 (95% CI = 0.82 to 1.46). We found no trend according to duration of use or time since last use except for estrogens combined with progesterone or dydrogesterone, which showed decreasing risk with increasing time since last use. Different MHT types may impact ovarian cancer risk differentially. The possibility that MHT containing progestagens other than progesterone or dydrogesterone may confer some protection should be evaluated in other epidemiological studies.

Prognostic Value of the Intermediate-risk Feature in Men with Favorable Intermediate-risk Prostate Cancer: Implications for Active Surveillance

BackgroundGuidelines suggest that active surveillance (AS) may be considered for select patients with favorable intermediate-risk (fIR) prostate cancer. ObjectiveTo compare the outcomes between fIR prostate cancer patients included by Gleason score (GS) or prostate-specific antigen (PSA). Most patients are classified with fIR disease due to either a 3 + 4 = 7 GS (fIR-GS) or a PSA level of 10–20 ng/ml (fIR-PSA). Previous research suggests that inclusion by GS 7 may be associated with worse outcomes. Design, setting, and participantsWe conducted a retrospective cohort study of US veterans diagnosed with fIR prostate cancer from 2001 to 2015. Outcome measurements and statistical analysisWe compared the incidence of metastatic disease, prostate cancer–specific mortality (PCSM), all-cause mortality (ACM), and receipt of definitive treatment between fIR-PSA and fIR-GS patients managed with AS. Outcomes were compared with those of a previously published cohort of patients with unfavorable intermediate-risk disease using cumulative incidence function and Gray’s test for statistical significance. Results and limitationsThe cohort included 663 men; 404 had fIR-GS (61%) and 249 fIR-PSA (39%). There was no evidence of difference in the incidence of metastatic disease (8.6% vs 5.8%, p = 0.77), receipt of definitive treatment (77.6% vs 81.5%, p = 0.43), PCSM (5.7% vs 2.5%, p = 0.274), and ACM (16.8% vs 19.1%, p = 0.14) between the fIR-PSA and fIR-GS groups at 10 yr. On multivariate regression, unfavorable intermediate-risk disease was associated with higher rates of metastatic disease, PCSM, and ACM. Limitations included varying surveillance protocols. ConclusionsThere is no evidence of difference in oncological and survival outcomes between men with fIR-PSA and fIR-GS prostate cancer undergoing AS. Thus, presence of GS 7 disease alone should not exclude patients from consideration of AS. Shared decision-making should be utilized to optimize management for each patient. Patient summaryIn this report, we compared the outcomes of men with favorable intermediate-risk prostate cancer in the Veterans Health Administration. We found no significant difference between survival and oncological outcomes.

An ACO-based Hyper-heuristic for Sequencing Many-objective Evolutionary Algorithms that Consider Different Ways to Incorporate the DM's Preferences

Many-objective optimization is an area of interest common to researchers, professionals, and practitioners because of its real-world implications. Preference incorporation into Multi-Objective Evolutionary Algorithms (MOEAs) is one of the current approaches to treat Many-Objective Optimization Problems (MaOPs). Some recent studies have focused on the advantages of embedding preference models based on interval outranking into MOEAs; several models have been proposed to achieve it. Since there are many factors influencing the choice of the best outranking model, there is no clear notion of which is the best model to incorporate the preferences of the decision maker into a particular problem. This paper proposes a hyper-heuristic algorithm—named HyperACO—that searches for the best combination of several interval outranking models embedded into MOEAs to solve MaOPs. HyperACO is able not only to select the most appropriate model but also to combine the already existing models to solve a specific MaOP correctly. The results obtained on the DTLZ and WFG test suites corroborate that HyperACO can hybridize MOEAs with a combined preference model that is suitable to the problem being solved. Performance comparisons with other state-of-the-art MOEAs and tests for statistical significance validate this conclusion.

On the Statistical Significance Test for the Procedure of Polarity Classification by Types of Acoustic Emission Sources

On the Statistical Significance Test for the Procedure of Polarity Classification by Types of Acoustic Emission Sources

Dynamic Candidate Solution Boosted Beluga Whale Optimization Algorithm for Biomedical Classification

In many fields, complicated issues can now be solved with the help of Artificial Intelligence (AI) and Machine Learning (ML). One of the more modern Metaheuristic (MH) algorithms used to tackle numerous issues in various fields is the Beluga Whale Optimization (BWO) method. However, BWO has a lack of diversity, which could lead to being trapped in local optimaand premature convergence. This study presents two stages for enhancing the fundamental BWO algorithm. The initial stage of BWO’s Opposition-Based Learning (OBL), also known as OBWO, helps to expedite the search process and enhance the learning methodology to choose a better generation of candidate solutions for the fundamental BWO. The second step, referred to as OBWOD, combines the Dynamic Candidate Solution (DCS) and OBWO based on the k-Nearest Neighbor (kNN) classifier to boost variety and improve the consistency of the selected solution by giving potential candidates a chance to solve the given problem with a high fitness value. A comparison study with present optimization algorithms for single-objective bound-constraint optimization problems was conducted to evaluate the performance of the OBWOD algorithm on issues from the 2022 IEEE Congress on Evolutionary Computation (CEC’22) benchmark test suite with a range of dimension sizes. The results of the statistical significance test confirmed that the proposed algorithm is competitive with the optimization algorithms. In addition, the OBWOD algorithm surpassed the performance of seven other algorithms with an overall classification accuracy of 85.17% for classifying 10 medical datasets with different dimension sizes according to the performance evaluation matrix.

Screening of Mild Cognitive Impairment Through Conversations With Humanoid Robots: Exploratory Pilot Study.

The rising number of patients with dementia has become a serious social problem worldwide. To help detect dementia at an early stage, many studies have been conducted to detect signs of cognitive decline by prosodic and acoustic features. However, many of these methods are not suitable for everyday use as they focus on cognitive function or conversational speech during the examinations. In contrast, conversational humanoid robots are expected to be used in the care of older people to help reduce the work of care and monitoring through interaction. This study focuses on early detection of mild cognitive impairment (MCI) through conversations between patients and humanoid robots without a specific examination, such as neuropsychological examination. This was an exploratory study involving patients with MCI and cognitively normal (CN) older people. We collected the conversation data during neuropsychological examination (Mini-Mental State Examination [MMSE]) and everyday conversation between a humanoid robot and 94 participants (n=47, 50%, patients with MCI and n=47, 50%, CN older people). We extracted 17 types of prosodic and acoustic features, such as the duration of response time and jitter, from these conversations. We conducted a statistical significance test for each feature to clarify the speech features that are useful when classifying people into CN people and patients with MCI. Furthermore, we conducted an automatic classification experiment using a support vector machine (SVM) to verify whether it is possible to automatically classify these 2 groups by the features identified in the statistical significance test. We obtained significant differences in 5 (29%) of 17 types of features obtained from the MMSE conversational speech. The duration of response time, the duration of silent periods, and the proportion of silent periods showed a significant difference (P<.001) and met the reference value r=0.1 (small) of the effect size. Additionally, filler periods (P<.01) and the proportion of fillers (P=.02) showed a significant difference; however, these did not meet the reference value of the effect size. In contrast, we obtained significant differences in 16 (94%) of 17 types of features obtained from the everyday conversations with the humanoid robot. The duration of response time, the duration of speech periods, jitter (local, relative average perturbation [rap], 5-point period perturbation quotient [ppq5], difference of difference of periods [ddp]), shimmer (local, amplitude perturbation quotient [apq]3, apq5, apq11, average absolute differences between the amplitudes of consecutive periods [dda]), and F0cov (coefficient of variation of the fundamental frequency) showed a significant difference (P<.001). In addition, the duration of response time, the duration of silent periods, the filler period, and the proportion of fillers showed significant differences (P<.05). However, only jitter (local) met the reference value r=0.1 (small) of the effect size. In the automatic classification experiment for the classification of participants into CN and MCI groups, the results showed 66.0% accuracy in the MMSE conversational speech and 68.1% accuracy in everyday conversations with the humanoid robot. This study shows the possibility of early and simple screening for patients with MCI using prosodic and acoustic features from everyday conversations with a humanoid robot with the same level of accuracy as the MMSE.

Kidney transplant from HCV viremic donors to HCV-negative recipients and risk for de novo donor specific antibodies and acute rejection.

Kidney transplantation from HCV-viremic donors into uninfected recipients is associated with excellent short-term outcomes. However, concerns regarding an increased risk for the development of de novo donor specific antibodies (DSA) and acute rejection have been raised in single center reports. A retrospective study of HCV-negative kidney-only transplant recipients between 2018 and 2020. Patients were grouped based on the donor HCV status into group 1; HCV-viremic donors, and group 2; HCV-negative donors. Inverse probability of treatment weighting (IPTW), with weights derived from the propensity score, were used to estimate the effect of donors' HCV-viremia on the recipients. The primary objective was to compare the 1-year incidence of de novo DSA. Secondary outcomes included group comparison of the incidence of biopsy proven acute rejection (BPAR), 1-year patient and allograft survival, and 1-year renal allograft function. A total of 71 patients were included in the HCV NAT+ group, and 440 in the HCV- negative group. One-year incidence of de novo DSA was higher in the HCV NAT+ group in the IPTW weighted analysis (19%vs. 9%, p=.02). In the unweighted analysis, BPAR occurred in 7% of recipients in the HCV NAT+ group, compared to 3% in the control group (p=.06). However, due to the low event rate in the in the IPTW weighted groups, a statistical significance test could not be performed. Average estimated GFR was higher in the HCV-viremic group at 3 months (61vs. 53ml/min/1.73m2 p=.002), but comparable at 6 (59vs. 56ml/min/1.73m2 , p=.31) and 12 months (60vs. 55ml/min/1.73m2 , p=.07). Patient and allograft survival were comparable between the two groups. Kidney transplant from HCV-viremic donors was associated with an increased risk for the development of post-transplant de novo DSA in the first year after transplantation, but no difference in patient and graft survival.

Frailty status improvement after kidney transplantation.

Frailty is a clinical syndrome characterized by a decrease in strength, resistance and body physiological condition, making the individual more vulnerable, and increasing his/her risk of dependence and death. Kidney transplant (KT) is currently the best end-stage renal disease therapeutic alternative for certain individuals. Frailty status occurs in approximately 20% of KT patients. Thus, it was evaluated if there would be any change in frailty status level in a population of adult patients on chronic HD after receiving KT. A cross-sectional study was conducted on a population of adult hemodialysis patients (n: 57), with the objective of evaluating if there was a significant change in their clinical frailty score (CFS) after 6months of KT. For the statistical analysis, the Student's t-test, and the test of statistical significance between two proportions were applied. Mean CFS before KT was 4 (vulnerable), and after KT was 3 (robust). CFS value was significantly lower after KT (p value < 0.01). A significant improvement was found between pre- and post-transplant clinical frailty scores in hemodialysis adult patients.

The effects of chronic intraperitoneal monosodium glutamate in social interaction and on rotating rod in adult Swiss albino mice

Background: Short-term use of monosodium glutamate (MSG) induces anxiety in animals. Due to the lack of stringent regulations for food supplements and increase in the use of MSG in the past decade, the long-term effects of MSG need to be evaluated. There is a scarcity of the literature on the chronic effects of MSG on anxiety, hence the present study. Since anxiety models require an intact motor function, motor function was also evaluated. Aims and Objectives: The aim of the study was to evaluate the long-term effects of intraperitoneal (i.p.) MSG on mice models of anxiety (social interaction) and motor function (accelerating rota rod). Materials and Methods: The present prospective interventional study was conducted on 40 adult male Swiss albino mice. Mice were randomly divided into four equal groups to receive, distilled water, and MSG at doses of 40, 60, and 80 mg/kg/day for 3 months. Parameters were assessed at baseline, 1 month, 2 months, and 3 months of daily MSG administration. Statistical tests of significance were the Wilcoxon signed-rank test and Friedman test (within group) and Kruskal–Wallis Test (between groups), P &lt; 0.05 was considered statistically significant. Results: Social interaction time was reduced in all the MSG-treated groups (P &lt; 0.05) without any change in motor function (P &gt; 0.05). Anxiety was evident from 40 mg/kg/day MSG from the 1st month till 3 months compared to baseline and controls. Duration-dependent change in social interaction was observed with MSG at doses of 40 mg/kg/day and 60 mg/kg/day. Dose-dependent change in social interaction was not observed among treatment groups. Conclusion: Long-term administration of MSG produced anxiogenic effects at doses of 40 mg/kg, 60 mg/kg, and 80 mg/kg without impairing the motor functions in the mice.

Speed and Power Indices of tests and items

A simple index is proposed to measure speed or power components of a test. The index is independent of position of the items and provides necessary and sufficient condition for pure speed test and pure power test and enables testing of statistical hypothesis to infer that the test can be taken as a speed test or a power test. Similar index of an item is also proposed to reflect whether the item is a speed item or a power item. The proposed index C is a ratio such that C = 0 ⟺Pure power test and C = 1⟺Pure speed test facilitating computation of similar index of each item and statistical test of significance. Properties of the index discussed. Operational method outlined to modify a test to speed or power test. Items can be ranked with respect to such item-wise index. Identification of power items and speed items help to modify the test to a speed or power test by deleting items in stages, if speediness (or power) is not intended. Relationship between index for the test and item-wise indices derived.

Prevalence, pattern and factors associated with undernutrition among Primary school aged children in Rivers State Nigeria

Background: Undernutrition among children contributes to the high diseases burden in Nigeria and other developing countries undergoing nutritional transition. It presents as underweight, stunting and thinness/wasting. &#x0D; Objective: This study looked at the pattern of undernutrition among primary school aged children in Rivers State.&#x0D; Materials and Methods: This is a cross-sectional descriptive study among primary school-aged children in Rivers State Nigeria recruited through a multistage sampling method. Information on socio-demography, dietary habit and physical activity of the pupils were obtained from parents who gave informed consent while weight and height measurements were carried out directly on assenting pupils. Data was analyzed using IBM SPSS Statistics version 23 and WHO Anthroplus software. Results were presented in frequency table. Test of statistical significance was done at P &lt; 0.05&#x0D; Results: A total of 465 pupils aged 5 – 13 years participated in the study. Mean age was 8.64 ± 0.113 years. Twenty-nine (6.2%) of the pupils were stunted, 8 (1.7%) were severely stunted; 19 (4.1%) were thin/wasted and 18 (3.9%) were severely thin/wasted; 12 (3.1%) were under-weight and 4 (1.0%) were severely underweight. Stunting and underweight were associated with type of school, place of residence, class of pupils, occupation and level of education of parents (P &lt; 0.05); thinness/wasting was associated with only birth order (P &lt; 0.05). Undernutrition was not associated with physical activity and dietary habit. &#x0D; Conclusion: Stunting was the commonest pattern of undernutrition among primary school age children in Rivers State Nigeria followed by underweight and thinness/wasting.

Prevalence of Sleep Problems among Children in Saudi Arabia

Background: Sleep is a vital aspect of a child\&amp;apos;s development, impacting physical health, emotional well-being, and academic performance. This study delves into the prevalence of sleep problems among children, their association with demographic factors and sleep-related habits, and the potential influence on academic performance. Methods: A cross-sectional study involving 198 boys and girls between the ages of 2 and 16 was conducted in Riyadh, the Western and Eastern Provinces. An online questionnaire, divided into six parts focusing on personal data, the quality of sleep, the relationship between trouble sleeping or resisting normal sleeping and the regularity of sleeping, sleeping and resting hours during weekdays and weekends, and the educational level, was administered. The data were analyzed using SPSS, with statistical significance tests used for data analysis. Results: The findings revealed that bedtime resistance was the most prevalent sleep issue, affecting over half of the participants, followed by sleep-onset delay and bedtime fears. Notably, a significant percentage of children reported not getting enough sleep and experiencing daytime fatigue, indicating potential sleep-related challenges within the cohort. Factors such as interrupted sleep, sleep talking, and difficulty waking up on weekdays and weekends exhibited significant age-related differences. Co-sleeping with parents was most common among the youngest children.. The study found that children who reported sleeping a lot due to various sleep-related issues tended to have lower academic performance. Sleep duration on both weekdays and weekends also correlated with academic outcomes. Conclusion: The study highlights the prevalence of sleep problems among children and their potential consequences for academic performance. The findings emphasize the importance of addressing these sleep-related challenges to support better educational outcomes in this demographic.

Morphological classification of Radio Galaxies using Semi-Supervised Group Equivariant CNNs

Out of the estimated few trillion galaxies, only around a million have been detected through radio frequencies, and only a tiny fraction, approximately a thousand, have been manually classified. We have addressed this disparity between labeled and unlabeled images of radio galaxies by employing a semi-supervised learning approach to classify them into the known Fanaroff-Riley Type I (FRI) and Type II (FRII) categories. A Group Equivariant Convolutional Neural Network (G-CNN) was used as an encoder of the state-of-the-art self-supervised methods SimCLR (A Simple Framework for Contrastive Learning of Visual Representations) and BYOL (Bootstrap Your Own Latent). The G-CNN preserves the equivariance for the Euclidean Group E(2), enabling it to effectively learn the representation of globally oriented feature maps. After representation learning, we trained a fully-connected classifier and fine-tuned the trained encoder with labeled data. Our findings demonstrate that our semi-supervised approach outperforms existing state-of-the-art methods across several metrics, including cluster quality, convergence rate, accuracy, precision, recall, and the F1-score. Moreover, statistical significance testing via a t-test revealed that our method surpasses the performance of a fully supervised G-CNN. This study emphasizes the importance of semi-supervised learning in radio galaxy classification, where labeled data are still scarce, but the prospects for discovery are immense.

Detection of Diabetic Retinopathy Using Collaborative Model of CNN with IoMT

The cause of blindness that primarily affects middle-aged adults is diabetic retinopathy (DR), due to excessive blood sugar levels. Internet of Medical Things (IoMT) is capable to collect Diabetic Retinopathy-related information remotely using CAD (Computer-aided diagnostic) systems and provide patients with convincing information. Therefore, the primary goal of this study is to identify and categorize the severity of DR fundus images to prevent a diabetic sufferer from going blind. Thus, this paper developed a unique Diabetic Retinopathy Segmentation (DRS) system by fusing the Deep Learning model with optimization techniques. The preprocessing phase of this system is considered to remove noise from the edges. Next, the usable region from the images is extracted using the increasing region segmentation through K-mean clustering. The characteristics of the Area of Interest (AOI) are then extracted and classified into four severity levels using the suggested Hybrid Genetic and Ant Colony Optimization (HGACO) algorithm with the help of a pertained CNN model, Residual Neural Network (RESnet). Additionally, the test of statistical significance evaluates the DRS system’s Segmentation accuracy. The suggested Diabetic Retinopathy System achieves improved categorization outcomes, with sensitivity, accuracy, and specificity numbers.

The adoption of mobile financial services in Tanzania: The application of logit model

The adoption of mobile technology has received much attention in recent studies in Africa. Several previous studies have assessed mobile financial service adoption using classification choice models, the assessment being primarily a test of statistical significance, but little is known about the performance of choice models, including logistic regression. Using the World Bank Demographic Health Survey (TDHS, 2015/16) dataset for Tanzania, a logistic regression model was fitted to determine the extent to which men use mobile phones for financial transactions. The results demonstrate the statistical significance of a logit model. The variables such as financial institution, region, place of residence, education level, marital status, age of head of household, literacy level and newspaper reading are better predictors of the likelihood that men will use mobile financial services. Regarding the classification models, the results show that the 8-predictor stepwise logit model fits the data well, with approximately 82.01% of the males being correctly classified. However, the results showed that the sensitivity of the model was (85.1 percent) and its specificity (77.94 percent). In terms of AIC and BIC, the reduced model is better because the statistical metrics of AIC and BIC are smaller than those of the full model. The results mean that the statistically significant filtered predictors explain well the motives for the adoption of mobile financial services. These results suggest that the logit model fits the data well, and can therefore be used to assess mobile financial service adoption and other related studies.

The correlation between obesity and other cardiovascular disease risk factors among adult patients attending a specialist clinic in Kumasi. Ghana

&lt;abstract&gt;&lt;sec&gt; &lt;title&gt;Background&lt;/title&gt; &lt;p&gt;Obesity is a complex and multifactorial disease marker, which has become a major threat to cardiovascular health. We sought to assess the correlation of obesity and other cardio-metabolic risk factors in patients seen at the outpatient specialist clinic in Ghana.&lt;/p&gt; &lt;/sec&gt;&lt;sec&gt; &lt;title&gt;Methods&lt;/title&gt; &lt;p&gt;A prospective cross-sectional study was conducted on 395 patients at Precise Specialist Clinic in Kumasi, Ghana. A standardized questionnaire was used to obtain demographic, anthropometric and clinical data of patients. Fisher's exact test for statistical significance at a 95% confidence interval was used to evaluate associations between categorical variables. The associations between obesity indices and cardiovascular disease risk factors were analyzed by Pearson's correlation.&lt;/p&gt; &lt;/sec&gt;&lt;sec&gt; &lt;title&gt;Results&lt;/title&gt; &lt;p&gt;Of the 395 participants, 187 were males and 208 were females. The mean (± standard deviation) age of study participants was 59.29 (± 13.93); more than half of the participants were between 50 and 69 years. The mean BMI of male participants was significantly lower than the mean BMI of female participants (28.18 kg/m&lt;sup&gt;2&lt;/sup&gt; vs 31.16 kg/m&lt;sup&gt;2&lt;/sup&gt;, &lt;italic&gt;P-value&lt;/italic&gt; &amp;lt; 0.0001). Gender was significantly associated with the weight categories (&lt;italic&gt;P&lt;/italic&gt; = 0.0144). Obesity was seen more in females (49.0%) than in males (35.8%). The Pearson correlation analysis also showed a significant positive correlation between obesity, increasing systolic blood pressure (&lt;italic&gt;r&lt;/italic&gt; = 0.1568, &lt;italic&gt;P-value&lt;/italic&gt; = 0.0018) and increasing diastolic blood pressure (&lt;italic&gt;r&lt;/italic&gt; = 0.2570, &lt;italic&gt;P-value&lt;/italic&gt; &amp;lt; 0.0001).&lt;/p&gt; &lt;/sec&gt;&lt;sec&gt; &lt;title&gt;Conclusions&lt;/title&gt; &lt;p&gt;Obesity was found to be significantly associated with female gender, increasing age, increasing systolic blood pressure, and increasing diastolic blood pressure. Efforts to step-up preventive measures to reduce the increasing prevalence of obesity in Ghana are highly recommended.&lt;/p&gt; &lt;/sec&gt;&lt;/abstract&gt;