Empirical exploration of whale optimisation algorithm for heart disease prediction

Heart Diseases have the highest mortality worldwide, necessitating precise predictive models for early risk assessment. Much existing research has focused on improving model accuracy with single datasets, often neglecting the need for comprehensive evaluation metrics and utilization of different datasets in the same domain (heart disease). This research introduces a heart disease risk prediction approach by harnessing the whale optimization algorithm (WOA) for feature selection and implementing a comprehensive evaluation framework. The study leverages five distinct datasets, including the combined dataset comprising the Cleveland, Long Beach VA, Switzerland, and Hungarian heart disease datasets. The others are the Z-AlizadehSani, Framingham, South African, and Cleveland heart datasets. The WOA-guided feature selection identifies optimal features, subsequently integrated into ten classification models. Comprehensive model evaluation reveals significant improvements across critical performance metrics, including accuracy, precision, recall, F1 score, and the area under the receiver operating characteristic curve. These enhancements consistently outperform state-of-the-art methods using the same dataset, validating the effectiveness of our methodology. The comprehensive evaluation framework provides a robust assessment of the model's adaptability, underscoring the WOA's effectiveness in identifying optimal features in multiple datasets in the same domain.

Platelet-rich plasma for treating dry eye disease - A systematic review and meta-analysis

PURPOSE

Dry eye disease has public health and economic significance. Platelet-rich plasma is rich in anti-inflammatory agents and growth factors, both beneficial for ocular surface repair. This study aimed to conduct a systematic review and meta-analysis to summarize the benefits of platelet-rich plasma for treating dry eye disease and its adverse effects.

METHODS

Prospective comparative studies using platelet-rich plasma as monotherapy for dry eye disease were included for efficacy assessment. Before-after studies were included for adverse events assessment. Data sources included PubMed, Google Scholar, Web of Science, and Scopus. A systematic review and meta-analysis protocol was pre-registered on PROSPERO (CRD42022347982). PRISMA guidelines were followed. The National Health Institute (NIH) quality assessment tool for before-after studies, the Cochrane risk of bias tool (RoB2), and the methodological index for non-randomized studies were used to assess the risk of bias. Heterogeneity was assessed using the I2 statistic.

RESULTS

19 studies (10 comparative and 9 before-after) were included in the systematic review and meta-analysis. The occurrence rate of adverse effects was 2.6 % (95 % CI: 0.5 - 4.7). The pooled standardized mean difference (SMD) for dry eye symptoms was 0.81 (95 % CI: 0.25 - 1.37; I2 = 82 %; p < 0.00001; Z = 2.84, p = 0.004); tear quality was 0.44 (95 % CI: 0.06 - 0.81; I2 = 67 %; p = 0.003; Z = 2.26, p = 0.02); tear quantity was 0.45 (95 % CI: 0.03 - 0.88; I2 = 74 %; p = 0.0003; Z = 2.10, p = 0.04); and corneal staining 0.72 (95 % CI: 0.14 - 1.30; I2 = 85 %; p < 0.00001; Z = 2.43, p = 0.02).

CONCLUSION

The current study shows that platelet-rich plasma is efficacious in managing dry eye disease, significantly reducing dry eye signs and symptoms. Such significant improvements could translate to improved quality of life.

Trace metal load of two urban wetlands with varied catchment activities in Ghana

This study compared Lead (Pb), Chromium (Cr), Copper (Cu), Zinc (Zn), Mercury (Hg), Arsenic (As) and Cadmium (Cd) concentrations in sediment, water, and biota at Vaughan Dam which receives limited sewage effluent discharge from residential areas, and Korle Lagoon which receives industrial effluents, electronic waste, garages-spill oil and a host of others in addition to residential sewage effluent discharge. Samples were analyzed with Atomic Absorption Spectrometer. The results showed that concentrations of trace metals were generally higher in the sediment, water, and plants from the Korle Lagoon but only Cu in the sediment of Korle Lagoon showed a significantly high concentration. The similarities in the rank orders of the metal concentrations together with the dominance of Zn and Pb in most compartments of the wetlands indicated major differences did not exist in the contaminant input to the two wetlands except electronic waste recycling and disposal that resulted in significantly high copper concentrations in the sediment of Korle Lagoon. No evidence of biomagnification was determined along the food chains of the Vaughan Dam and the Korle Lagoon for all the metals studied.The Tilapia zilli from Vaughan Dam, the only biota that is regularly consumed from the wetlands, had Cr, Cu, Pb, Cd, Hg, and As concentrations above FAO/WHO permissible limits and therefore pose a health risk to consumers.

A Deep Learning Approach for Loan Default Prediction Using Imbalanced Dataset

Lending institutions face key challenges in making accurate predictions of loan defaults. Large sums of money given as loans are defaulted and this causes a substantial loss in business. This study addresses loan default in online peer-to-peer lending activities. Data for the study was obtained from the online lending club on the Kaggle platform. The loan status was chosen as the dependent variable and was classified discretely into “default” and “fully paid” loans. The dataset is preprocessed to eliminate all irrelevant instances. Due to the imbalanced nature of the dataset, the adaptive synthetic (ADASYN) oversampling algorithm is used to balance the data by oversampling the minority class with synthetic data instances. Deep neural network (DNN) is used for prediction. A prediction accuracy of 94.1% is realized and this emerged as the highest score from several trials with variations in batch sizes and epochs. The result of the study clearly shows that the proposed procedure is very promising.

Association between Dyslipidemia and Meibomian Gland Dysfunction: A Systematic Review and Meta-Analysis

PURPOSE

This study aimed to use meta-analysis to estimate the association between dyslipidemia and meibomian gland dysfunction.

METHODS

The following databases were searched: PubMed, Google Scholar, and Scopus. Case-control and cohort studies assessing the association between dyslipidemia and meibomian gland dysfunction were included. The association was assessed using odds ratios. Heterogeneity between studies was assessed with the χ2 statistic and degree of inconsistency. The quality of studies was assessed using the Newcastle-Ottawa Scale. The systematic review was registered on PROSPERO (ID: CRD42022347982).

RESULTS

The systematic review included three case-control and two cohort studies. The odds of hypercholesterolemia and hypertriglyceridemia in meibomian gland dysfunction were 5.45 (95% confidence interval [CI], 1.65 to 17.95) and 3.28 (95% CI, 1.25 to 8.62), respectively. The odds of elevated serum low-density lipoprotein and reduced high-density lipoprotein in meibomian gland dysfunction were 2.72 (95% CI, 1.24 to 5.98) and 1.15 (95% CI, 0.74 to 1.79), respectively. The current study's limitation is that the effects of sex, age, and meibomian gland dysfunction severity on the association between dyslipidemia and meibomian gland dysfunction were not assessed.

CONCLUSIONS

The current study suggests a significant association between dyslipidemia and meibomian gland dysfunction. This finding suggests that meibomian gland dysfunction diagnosis may call for dyslipidemia screening.

Estimating Overhead Performance of Supervised Machine Learning Algorithms for Intrusion Detection

Estimating the energy and memory consumption of machine learning(ML) models for intrusion detection ensures efficient allocation of system resources. This study investigates the impact of supervised ML algorithms on the energy and memory consumption of intrusion detection systems. Experiments are conducted with seven ML algorithms and a proposed ensemble model, utilizing two intrusion detection datasets. Pearson correlation coefficient(PCC) and Spearman correlation coefficient are employed for the selection of optimum features. Regarding energy consumption, the findings reveal that the PCC with the UNSW-NB15 dataset uses the least amount of DRAM and CPU power. For ML methods, SVM utilizes the highest energy for both feature selection methods and datasets. Concerning memory consumption, the results show that decision tree uses the most current memory with PCC on the UNSW-NB15. The proposed ensemble model demonstrates the highest performance. These findings offer practical guidelines to ML experts when choosing the optimum model with the most efficient utilization of energy and memory.

Strabismus and amblyopia in Africa - a systematic review and meta-analysis

The objective of this review was to estimate the prevalence of strabismus and amblyopia in Africa. A systematic online literature search was conducted for articles on strabismus and amblyopia in Africa. Meta-analysis was performed, using the Freeman-Tukey double arcsine transformation, to estimate the prevalence of strabismus and amblyopia in Africa. Subgroup analyses were conducted according to age, gender, study year, and type of amblyopia. Meta-regression was used to evaluate the influence of predetermined factors on the prevalence of amblyopia. 8 (1 population-based & 7 school-based) and 21 (3 population-based & 18 school-based) studies on strabismus and amblyopia with sample sizes of 22,355 and 46,841, respectively, were included in the review. Overall prevalence of strabismus in Africa was estimated to be 0.8% (95% CI: 0.4% - 1.4%); exotropia was 0.2% (95% CI: 0.1% - 0.5%) and esotropia was 0.5% (95% CI: 0.1% - 1.2%). Overall prevalence of amblyopia was estimated to be 0.6% (95% CI: 0.3% - 0.9%); refractive and strabismic amblyopia were 1.1% (95% CI: 0.2% - 2.5%) and 0.4% (95% CI: 0.2% - 0.6%), respectively. Prevalence estimate of amblyopia in males was 1.8% (95% CI: 0.7% - 3.3%) and in females was 1.3% (95% CI: 0.4% - 2.6%). There was a significant association between the prevalence of amblyopia and the type of amblyopia (p = .007) and the study year (p = .006). Although there appears to be a relatively low prevalence of strabismus and amblyopia in Africa, there is a dearth of well-designed population-based studies on strabismus and amblyopia in Africa, resulting in the lack of epidemiological information on strabismus and amblyopia within the general African population. Information about the prevalence of strabismus and amblyopia across Africa can inform policy making and design and implementation of public health intervention program.

Evaluation of organizational climate factors on tax administration enterprise resource planning (ERP) system

Tax collection is an essential activity to boost the economy of all countries. Larger businesses and governments are increasingly relying on Enterprise Resource Planning (ERP) systems, which are designed to enhance the collection of revenues among other things. However, the implementation of an ERP system often affects the organizational climate by changing the manner businesses are conducted from the past both internally and externally. These changes have the tendency to impact the actions of workers throughout the transition process. Nevertheless, organization climate which is an essential variable to measure the success of ERPs is mostly underutilized. Thus in this study, we proposed an information system (IS) success model that integrates organizational climate variables namely, role clarity, teamwork and support, and, training and learning into the DeLone and McLean model to evaluate the success of a tax ERP system. The proposed model was based on a quantitative and a mixed-method case study (MM-CS). Data was gathered from a top company with many branches in Ghana through interviews, observation, focus groups, and questionnaires. Partial least squares structural equation modeling was used to examine the 555 data collected from the questionnaire. The result of the study shows that the organizational climate variables (training & learning, teamwork & support, and role clarity) were statistically significant in determining the success of a tax ERP system. Training & learning and teamwork & support also had a positive impact on service quality, user satisfaction, and individual impact.

Robust facial expression recognition system in higher poses

Facial expression recognition (FER) has numerous applications in computer security, neuroscience, psychology, and engineering. Owing to its non-intrusiveness, it is considered a useful technology for combating crime. However, FER is plagued with several challenges, the most serious of which is its poor prediction accuracy in severe head poses. The aim of this study, therefore, is to improve the recognition accuracy in severe head poses by proposing a robust 3D head-tracking algorithm based on an ellipsoidal model, advanced ensemble of AdaBoost, and saturated vector machine (SVM). The FER features are tracked from one frame to the next using the ellipsoidal tracking model, and the visible expressive facial key points are extracted using Gabor filters. The ensemble algorithm (Ada-AdaSVM) is then used for feature selection and classification. The proposed technique is evaluated using the Bosphorus, BU-3DFE, MMI, CK + , and BP4D-Spontaneous facial expression databases. The overall performance is outstanding.

Primary Mobile Image Analysis of Human Intestinal Worm Detection

One among a lot of public health concerns in rural and tropical areas is the human intestinal parasite. Traditionally, diagnosis of these parasites is by visual analysis of stool specimens, which is usually tedious and time-consuming. In this study, the authors combine techniques in the Laplacian pyramid, Gabor filter, and wavelet to build a feature vector for the discrimination of intestinal worm in a low-resolution image captured with mobile devices. The dimension of the feature vector is reduced using principal component analysis, and the resultant vector is considered as input to the SVM classifier. The proposed framework was applied to the Makerere intestinal dataset. At its preliminary stage, the results demonstrate satisfactory classification with an accuracy rate of 65.22% with possible extension in future work.

Overcoming the Challenges of Enterprise Resource Planning (ERP)

The study presents the results of a comprehensive review conducted between 2005-2020 to identify Enterprise Resource Planning (ERP) challenges, discover the divisions in which these challenges can be clustered, and provide general strategies to resolve these challenges. The study also found 25 categories that can be classified into ERP challenges. 65 ERP challenges were identified based on the reviewed literature, of which 18 were not provided with adequate solutions as to how to resolve them, and the related solutions as mentioned in the reviewed literature are presented in-depth. The result will help both academics and practitioners involved with how to resolve ERP system challenges.

Assessing the Impact of System Quality, Information Quality, and Service Quality on Enterprise Resource Planning (ERP) Systems

Globally, governments are taking steps to help them increase their income generation margin by implementing tax administrative ERP systems. However, the impacts on the internal system users of these ERP system quality features have not drawn the attention needed. This study, therefore, examines the relationship between the information systems' (IS) quality and individual impact using the theoretical foundation of the DeLone and McLean IS success model and, secondly, addresses the interrelationships between the quality constructs of information systems (IS). The authors also used the structural equation modeling technique of partial least squares to evaluate and analyze the data. The results show that system quality, the information quality, and the service quality characteristics of the tax administrative ERP system have a strong positive impact on the success of the IS at the individual level. There is also a positive relationship between the information systems' (IS) quality construction. The results provide additional empirical observations and consequences for management.

PREVALENCE OF MEIBOMIAN GLAND DYSFUNCTION IN AFRICA: A SYSTEMATIC REVIEW AND META-ANALYSIS OF OBSERVATIONAL STUDIES

PURPOSE

To review and summarize information on meibomian gland dysfunction (MGD) epidemiology in Africa.

METHODS

A systematic search of online databases was conducted for literature/studies on MGD in Africa. Meta-analysis was conducted to estimate the prevalence of MGD in Africa. Meta-regression was used to explore sources of heterogeneity.

RESULTS

Twelve studies conducted in five countries were included in the review. All studies were hospital-based studies. Nine studies were included in the meta-analysis; the total sample size was 4963 and participants' age range was 17-96 years. The overall prevalence estimate of MGD in Africa was 45.9% (95% CI: 27.6-64.1%). Prevalence of MGD among males and females were each pooled from three studies and in urban and rural setting from 6 and 3 studies, respectively. Prevalence of MGD among males and females were 56.0% (95% CI: 22.4-89.5%) and 58.9% (95% CI: 28.5-89.4%) respectively; in urban and rural settings were 42.8% (95% CI: 21.1-64.5%) and 65.7% (95% CI: 25.7-95.7%), respectively. There was no association of MGD with sex (p = .872) and with study setting (p = .231).

CONCLUSION

There is a paucity of evidence on MGD prevalence in Africa, emphasizing the need for epidemiological studies to enhance our understanding of region-specific differences in MGD in Africa. The pooled estimate from hospital-based studies, however, suggests a substantial MGD burden in Africa. Epidemiological studies are needed to assess if this translates to a high disease burden within the general African population.

Construction of an Ensemble Scheme for Stock Price Prediction Using Deep Learning Techniques

This study proposes a deep learning approach for stock price prediction by bridging the long short-term memory with gated recurrent unit. In its evaluation, the mean absolute error and mean square error were used. The model proposed is an extension of the study of Hossain et al. established in 2018 with an MSE of 0.00098 as its lowest error. The current proposed model is a mix of the bidirectional LSTM and bidirectional GRU resulting in 0.00000008 MSE as the lowest error recorded. The LSTM model recorded 0.00000025 MSE, the GRU model recorded 0.00000077 MSE, and the LSTM + GRU model recorded 0.00000023 MSE. Other combinations of the existing models such as the bi-directional LSTM model recorded 0.00000019 MSE, bi-directional GRU recorded 0.00000011 MSE, bidirectional LSTM + GRU recorded 0.00000027 MSE, LSTM and bi-directional GRU recorded 0.00000020 MSE.

The effect of vinegar and drying (Solar and Open Sun) on the microbiological quality of ginger (ZINGIBER OFFICINALE ROSCOE) rhizomes

This study evaluated the influence of 10% vinegar and solar drying using two solar dryers and open-sun drying on the microbiological quality of ginger (Zingiber officinale Roscoe) rhizome. The rhizomes were analyzed for bacterial, mold, and Salmonella populations in the raw state, which were water-washed and soaked in 10% vinegar, and in dried form. The fungal population was isolated and identified. Fresh and dried ginger rhizome contained both bacterial and fungal population in the range of 3.0 x 102 ± 1.14 x 102 to 2,180 x 109 ± 70.7 x 109 CFU/g. The stainless steel solar dryer had fewer fungal loads among the drying methods. Aspergillus and Penicillium species of mycotoxin-producing potential were identified. The 10% vinegar as pretreatment showed no significant difference (p ≤ .05) in the bacterial population reduction but in the fungal population reduction. Growth of fungi in fresh and dried ginger extracts was lower compared with growth in Potato Dextrose Broth.

Career aspirations and factors influencing career choices of optometry students in Ghana

Optometry students in clinical years are usually faced with the challenges of making a career choice in or outside optometry. This cross sectional study was conducted to investigate the career aspirations of optometry students in Ghana. All students in their fourth to sixth year who consented to participate in the study responded to a questionnaire which explored: demographic characteristics, career aspirations, and factors influencing their choices. Descriptive statistics was used to present data as frequencies, proportions and percentages. Chi-square test and logistic regression analysis were used to evaluate relationships between variables. Two hundred and nine students from the two optometry training institutions in Ghana; Kwame Nkrumah University of Science and Technology (49.8%) and University of Cape Coast (51.2%) responded to the questionnaire. The mean (SD) age of students was 23.6 (1.9) years (males = 65.6%). On seeking admission into the university, optometry (65.6%) and human biology/medicine (28.2%) were the leading first choice programmes among participants. Participants largely aspire to be in clinical practice (64.6%) or Academia/Research (28.2%). The major factors which influenced career choices were interest in career field (64.1%) and potential good income (38.3%). Females were twice more likely to practice optometry and pursue an interest in paediatric optometry than males. Institution of study (p = .028) and information on career opportunities (p = .018) were significant predictors of students' decision to pursue a career in academia/research. Optometry students in Ghana largely aspire to be in clinical practice, a finding which is useful for optometry training institutions and relevant stakeholders in developing the optometry programme and projecting its future in Ghana.

Surveillance of surgical site infection in a teaching hospital in Ghana: a prospective cohort study

BACKGROUND

Surveillance systems for surgical site infections (SSIs), as a measure of patient safety, help health institutions devise strategies to reduce or prevent them. No surveillance systems exist to monitor SSIs in Ghana.

AIM

To establish a system for monitoring trends and detecting outbreaks in order to create awareness of and control SSIs.

METHODS

An active 30-day surveillance was undertaken at the general surgical unit of the Korle Bu Teaching Hospital, from July 1^st, 2017 to December 31^st, 2018 to identify SSI. It involved a daily inpatient surveillance of patients who had had a surgical procedure, followed by post-discharge surveillance by means of a healthcare personnel-based survey and a patient-based telephone survey. We supplied quarterly feedback of results to surgeons.

FINDINGS

Among the 3267 patients included, 331 were identified with an SSI, a 10% incidence risk. Patients who acquired an SSI experienced increased morbidity including nine extra days in hospital and an adjusted relative mortality risk of 2.3 (95% confidence interval: 1.3 - 4.1; P=0.006) compared to patients without SSI. Forty-nine per cent (161/331) of SSIs were diagnosed post discharge using the healthcare personnel-based survey. The patient-based telephone survey contributed 12 additional cases. SSI incidence risk decreased from 12.8% to 7.5% during the study period.

CONCLUSION

Post-discharge surveillance is feasible using existing healthcare personnel, and the results highlight the high risk and burden of SSIs in Ghana. A surveillance system with feedback for monitoring SSIs may contribute to reducing SSIs; however, firm conclusions regarding the impact need longer observation time.

Review of gunshot fatalities in the Northern part of Ghana; a 6 year forensic autopsy based study

Studies on firearm fatalities in some parts of Ghana have been reported. However, the incidence and pattern of firearm fatalities in the Northern sector of Ghana have fled the spotlight. This study aimed at reporting the incidence and pattern of gunshot fatalities autopsied within 2008 and 2013 year. There were 82(91.1%) male and 8(8.9%) female victims of gunshot deaths during the study period with an average of 15 cases annually. Where 60(66.7%) of the victims aged within 21-40; years resembling the pattern observed in several parts of the world. A significant number 28(31.1%) of the victims died of multiple shots or dispersed pellets affecting several parts of the body, followed by a single shot to the chest 18(20.0%), abdomen 17(18.9%), head 14(15.6%). Collectively, entry sites like the neck and upper limb among others accounted for 13(14.4%). Robbery accounted for 44(48.9%) followed by homicides 14(15.6%) cases. Recovered pellets, nature and legal status of firearm involved were also examined, and like in several developing countries, country-made guns played a substantial role in the firearm fatalities with calls to strengthen laws governing gun acquisition and use in the country.

Findings from a buruli ulcer mouse model study

SUMMARY INTRODUCTION

Buruli ulcer disease is endemic in many developing countries in Africa. It is caused by Mycobacterium ulcerans, a toxin-producing bacterium with predilection for the skin and its deeper tissues. The exact mode of transmission is unclear and the pathogenesis is also not well understood, necessitating further elucidation through animal studies.

OBJECTIVE

The study assessed the infectivity of a Ghanaian Mycobacterium ulcerans isolate and the dose-response pattern in BALB/c mice.

METHOD

Ten standardized bacterial suspensions of different concentrations were prepared from the M. ulcerans isolate and inoculated into the foot-pads of the mice. Thereafter they were observed for clinical signs of Buruli ulcer, upon which they were serially euthanised and evaluated for pathological and microbiological changes.

RESULTS

Irrespective of the inoculum dose, all the experimentally infected mice developed similar clinical lesions, from erythema to foot ulceration (3.1 to 6.7 weeks after inoculation). However, the higher the inoculum dose the earlier the onset of the lesions. After the development of foot ulceration, mice that had received between 1 to 4 doses developed gangrene (5.7 to 7.2 weeks after inoculation) and died within a week, while those that had received 5 to 10 doses lost their limbs spontaneously (5.6 to 6.1 weeks after inoculation), followed by sudden clinical recovery. Eight weeks after the spontaneous amputation the amputees relapsed with concomitant metastasis, anasarca and death. Acid-fast bacilli (AFBs) were detected in inoculated and non-inoculated limbs, tails, visceral organs, faecal pellets and caecal contents of the mice. The AFBs detected in the caecal samples were innumerable and unusually long. Though AFBs were consistently detected in lymph nodes they were never detected in blood samples.

CONCLUSION

The findings suggest that the progression and final outcome of an M. ulcerans infection maybe dose related. The unequivocal absence of AFBs in the blood, but their consistent presence in lymph nodes located in the lower limbs right up to the neck, suggests that the microbes are disseminated through the lymphatic system rather than through the blood.