MyMedR

Displaying publications 341 - 360 of 934 in total

Abstract:

Sort:

Fulltext Effectiveness of Problem-Based Learning versus Traditional Teaching Methods in Improving Acquisition of Radiographic Interpretation Skills among Dental Students-A Systematic Review and Meta-Analysis

Luke AM, Mathew S, Kuriadom ST, George JM, Karobari MI, Marya A, et al.

Biomed Res Int, 2021;2021:9630285.
PMID: 34608440 DOI: 10.1155/2021/9630285

Problem-based learning is an experiential and student-centred learning method to practice important skills like querying, critical thinking, and collaboration through pair and group work. The study is aimed at comparing the effectiveness of problem-based learning (PBL) and traditional teaching (TT) methods in improving acquisition of radiographic interpretation skills among dental students. Clinical trials (randomized and nonrandomized) were conducted with the help of dental students studying oral radiology using PBL and TT methods and assessing radiographic interpretation skills, knowledge scores, and satisfaction level as outcomes. Articles published from PubMed/MEDLINE, DOAJ, Cochrane Central Register of Controlled Trials, and Web of Science were searched. The quality of the studies was evaluated using the Cochrane Collaboration Tool, the MINORS Checklist, and the Risk of Bias in Nonrandomized Studies of Interventions (ROBIN-I) tool. Meta-analysis was done using Review Manager 5.3. There were twenty-four articles for qualitative synthesis and 13 for meta-analysis. The cumulative mean difference was found to be 0.54 (0.18, 0.90), 4.15 (-0.35, 8.65), and -0.14 (-0.36, 0.08) for radiographic interpretation skills, knowledge scores, and satisfaction level, respectively, showing significant difference favouring PBL as compared to TT except for satisfaction level which favoured the TT group. To understand the long-term effectiveness of PBL over TT methods in oral radiology among dental students, well-designed long-term randomized controlled trials are needed.

Matched MeSH terms: Problem-Based Learning*
Fulltext Comparing flipped classroom and conventional live demonstration for teaching orthodontic wire-bending skill

Lau MN, Kamarudin Y, Zakaria NN, Sivarajan S, Mohd Tahir NNZ, Bahar AD, et al.

PLoS One, 2021;16(7):e0254478.
PMID: 34243187 DOI: 10.1371/journal.pone.0254478

Flipped classroom may overcome weaknesses of live demonstration in teaching orthodontic wire-bending. This study aims to compare the effectiveness between flipped classroom and live demonstration in transferring skills for fabricating Adams clasp. Forty third-year undergraduate dental students were assigned to two groups. The students in group LD (n = 20) attended a live demonstration while students in group FC (n = 20) attended a flipped classroom. Both groups were taught on skills to fabricate Adams clasp in a standardised way. Each student from both groups were asked to submit an Adams clasp for a blinded quality assessment by two trained and calibrated assessors using a 18-item rubric, followed by validated students' satisfaction questionnaires to evaluate their perceived satisfaction on the teaching method received. A crossover study was then conducted three weeks later where LD attended a flipped classroom while FC attended a live demonstration. Students' satisfaction questionnaires were again collected from each student for blinded analysis. Mean scores for the quality of Adams clasp were 9.775 and 9.125 for LD and FC, respectively. No significant difference was detected between the two groups. Statistically significant association was found for one statement on the questionnaire, "I found the classroom arrangements conducive for the wire-bending activity" (p = 0.010). No significant differences were found between the two groups for other statements (p > 0.05). In conclusion, within the limitations of the study, flipped classroom is equally effective as conventional live demonstration in transferring orthodontic wire-bending skills for fabrication of Adams clasp. However, students perceived the classroom arrangements during the flipped classroom significantly more conducive for teaching orthodontic wire-bending.

Matched MeSH terms: Problem-Based Learning/methods
Use of WhatsApp in assisting psychiatry learning

Loo JL, Koh EB, Pang NT, Nor Hadi NM

Med Educ, 2016 Nov;50(11):1165.
PMID: 27762032 DOI: 10.1111/medu.13195
Matched MeSH terms: Learning*
Fulltext Listening while reading promotes word learning from stories

Valentini A, Ricketts J, Pye RE, Houston-Price C

J Exp Child Psychol, 2018 03;167:10-31.
PMID: 29154028 DOI: 10.1016/j.jecp.2017.09.022

Reading and listening to stories fosters vocabulary development. Studies of single word learning suggest that new words are more likely to be learned when both their oral and written forms are provided, compared with when only one form is given. This study explored children's learning of phonological, orthographic, and semantic information about words encountered in a story context. A total of 71 children (8- and 9-year-olds) were exposed to a story containing novel words in one of three conditions: (a) listening, (b) reading, or (c) simultaneous listening and reading ("combined" condition). Half of the novel words were presented with a definition, and half were presented without a definition. Both phonological and orthographic learning were assessed through recognition tasks. Semantic learning was measured using three tasks assessing recognition of each word's category, subcategory, and definition. Phonological learning was observed in all conditions, showing that phonological recoding supported the acquisition of phonological forms when children were not exposed to phonology (the reading condition). In contrast, children showed orthographic learning of the novel words only when they were exposed to orthographic forms, indicating that exposure to phonological forms alone did not prompt the establishment of orthographic representations. Semantic learning was greater in the combined condition than in the listening and reading conditions. The presence of the definition was associated with better performance on the semantic subcategory and definition posttests but not on the phonological, orthographic, or category posttests. Findings are discussed in relation to the lexical quality hypothesis and the availability of attentional resources.

Matched MeSH terms: Learning*
Automated diagnosis of focal liver lesions using bidirectional empirical mode decomposition features

Acharya UR, Koh JEW, Hagiwara Y, Tan JH, Gertych A, Vijayananthan A, et al.

Comput Biol Med, 2018 03 01;94:11-18.
PMID: 29353161 DOI: 10.1016/j.compbiomed.2017.12.024

Liver is the heaviest internal organ of the human body and performs many vital functions. Prolonged cirrhosis and fatty liver disease may lead to the formation of benign or malignant lesions in this organ, and an early and reliable evaluation of these conditions can improve treatment outcomes. Ultrasound imaging is a safe, non-invasive, and cost-effective way of diagnosing liver lesions. However, this technique has limited performance in determining the nature of the lesions. This study initiates a computer-aided diagnosis (CAD) system to aid radiologists in an objective and more reliable interpretation of ultrasound images of liver lesions. In this work, we have employed radon transform and bi-directional empirical mode decomposition (BEMD) to extract features from the focal liver lesions. After which, the extracted features were subjected to particle swarm optimization (PSO) technique for the selection of a set of optimized features for classification. Our automated CAD system can differentiate normal, malignant, and benign liver lesions using machine learning algorithms. It was trained using 78 normal, 26 benign and 36 malignant focal lesions of the liver. The accuracy, sensitivity, and specificity of lesion classification were 92.95%, 90.80%, and 97.44%, respectively. The proposed CAD system is fully automatic as no segmentation of region-of-interest (ROI) is required.

Matched MeSH terms: Machine Learning*
Analysing the accuracy of machine learning techniques to develop an integrated influent time series model: case study of a sewage treatment plant, Malaysia

Ansari M, Othman F, Abunama T, El-Shafie A

Environ Sci Pollut Res Int, 2018 Apr;25(12):12139-12149.
PMID: 29455350 DOI: 10.1007/s11356-018-1438-z

The function of a sewage treatment plant is to treat the sewage to acceptable standards before being discharged into the receiving waters. To design and operate such plants, it is necessary to measure and predict the influent flow rate. In this research, the influent flow rate of a sewage treatment plant (STP) was modelled and predicted by autoregressive integrated moving average (ARIMA), nonlinear autoregressive network (NAR) and support vector machine (SVM) regression time series algorithms. To evaluate the models' accuracy, the root mean square error (RMSE) and coefficient of determination (R2) were calculated as initial assessment measures, while relative error (RE), peak flow criterion (PFC) and low flow criterion (LFC) were calculated as final evaluation measures to demonstrate the detailed accuracy of the selected models. An integrated model was developed based on the individual models' prediction ability for low, average and peak flow. An initial assessment of the results showed that the ARIMA model was the least accurate and the NAR model was the most accurate. The RE results also prove that the SVM model's frequency of errors above 10% or below - 10% was greater than the NAR model's. The influent was also forecasted up to 44 weeks ahead by both models. The graphical results indicate that the NAR model made better predictions than the SVM model. The final evaluation of NAR and SVM demonstrated that SVM made better predictions at peak flow and NAR fit well for low and average inflow ranges. The integrated model developed includes the NAR model for low and average influent and the SVM model for peak inflow.

Matched MeSH terms: Machine Learning*
Parent-Reported Health-Related Quality of Life Outcomes and Impact on Family of Congenital Diaphragmatic Hernia Survivors After Repair: A Cross-Sectional Comparison to Healthy Controls

Rajasegaran S, Nooraziz AN, Abdullah A, Sanmugam A, Singaravel S, Gan CS, et al.

J Pediatr Surg, 2024 Apr;59(4):577-582.
PMID: 38160184 DOI: 10.1016/j.jpedsurg.2023.12.007

BACKGROUND: Congenital diaphragmatic hernia (CDH) survivors often experience long-term CDH-associated morbidities, including musculoskeletal, gastrointestinal and respiratory issues. This study evaluates parent-reported health-related quality of life (HRQOL) and family impact of the disease.
METHODS: Electronic medical records (EMR) were reviewed and phone surveys performed with parents of CDH survivors who underwent repair at our institution from 2010 to 2019. They completed the following Pediatric Quality of Life Inventory™ (PedsQL™) questionnaires: Generic Core Scales 4.0 (parent-proxy report) and Family Impact (FI) Module 2.0. Age-matched and gender-matched healthy controls from an existing database were used for comparison. Subgroup analysis of CDH patients alone was also performed. Appropriate statistical analysis was used with p

Matched MeSH terms: Learning Disorders*
Dietary menhaden fish oil supplementation suppresses lipopolysaccharide-induced neuroinflammation and cognitive impairment in diabetic rats

Titisari N, Fauzi A, Abdul Razak IS, Mohd Noor MH, Samsulrizal N, Ahmad H

Pharm Biol, 2024 Dec;62(1):447-455.
PMID: 38753370 DOI: 10.1080/13880209.2024.2351933

CONTEXT: Menhaden fish oil (FO) is widely recognized for inhibiting neuroinflammatory responses and preserving brain function. Nevertheless, the mechanisms of FO influencing brain cognitive function in diabetic states remain unclear.
OBJECTIVE: This study examines the potential role of FO in suppressing LPS-induced neuroinflammation and cognitive impairment in diabetic animals (DA).
MATERIALS AND METHODS: Thirty male Wistar rats were divided into 5 groups: i) DA received LPS induction (DA-LPS); ii) DA received LPS induction and 1 g/kg FO (DA-LPS-1FO); iii) DA received LPS induction and 3 g/kg FO (DA-LPS-3FO); iv) animals received normal saline and 3 g/kg FO (NS-3FO) and v) control animals received normal saline (CTRL). Y-maze test was used to measure cognitive performance, while brain samples were collected for inflammatory markers and morphological analysis.
RESULTS: DA received LPS induction, and 1 or 3 g/kg FO significantly inhibited hyperglycaemia and brain inflammation, as evidenced by lowered levels of pro-inflammatory mediators. Additionally, both DA-LPS-1FO and DA-LPS-3FO groups exhibited a notable reduction in neuronal damage and glial cell migration compared to the other groups. These results were correlated with the increasing number of entries and time spent in the novel arm of the Y-maze test.
DISCUSSION AND CONCLUSION: This study indicates that supplementation of menhaden FO inhibits the LPS signaling pathway and protects against neuroinflammation, consequently maintaining cognitive performance in diabetic animals. Thus, the current study suggested that fish oil may be effective as a supporting therapy option for diabetes to avoid diabetes-cognitive impairment.

Matched MeSH terms: Maze Learning/drug effects
Fulltext How Socio-economic Inequalities Cluster People with Diabetes in Malaysia: Geographic Evaluation of Area Disparities Using a Non-parameterized Unsupervised Learning Method

Ganasegeran K, Abdul Manaf MR, Safian N, Waller LA, Mustapha FI, Abdul Maulud KN, et al.

J Epidemiol Glob Health, 2024 Mar;14(1):169-183.
PMID: 38315406 DOI: 10.1007/s44197-023-00185-2

Accurate assessments of epidemiological associations between health outcomes and routinely observed proximal and distal determinants of health are fundamental for the execution of effective public health interventions and policies. Methods to couple big public health data with modern statistical techniques offer greater granularity for describing and understanding data quality, disease distributions, and potential predictive connections between population-level indicators with areal-based health outcomes. This study applied clustering techniques to explore patterns of diabetes burden correlated with local socio-economic inequalities in Malaysia, with a goal of better understanding the factors influencing the collation of these clusters. Through multi-modal secondary data sources, district-wise diabetes crude rates from 271,553 individuals with diabetes sampled from 914 primary care clinics throughout Malaysia were computed. Unsupervised machine learning methods using hierarchical clustering to a set of 144 administrative districts was applied. Differences in characteristics of the areas were evaluated using multivariate non-parametric test statistics. Five statistically significant clusters were identified, each reflecting different levels of diabetes burden at the local level, each with contrasting patterns observed under the influence of population-level characteristics. The hierarchical clustering analysis that grouped local diabetes areas with varying socio-economic, demographic, and geographic characteristics offer opportunities to local public health to implement targeted interventions in an attempt to control the local diabetes burden.

Matched MeSH terms: Unsupervised Machine Learning*
Fulltext Arrangements of Resting State Electroencephalography as the Input to Convolutional Neural Network for Biometric Identification

Lai CQ, Ibrahim H, Abdullah MZ, Abdullah JM, Suandi SA, Azman A

Comput Intell Neurosci, 2019;2019:7895924.
PMID: 31281339 DOI: 10.1155/2019/7895924

Biometric is an important field that enables identification of an individual to access their sensitive information and asset. In recent years, electroencephalography- (EEG-) based biometrics have been popularly explored by researchers because EEG is able to distinct between two individuals. The literature reviews have shown that convolutional neural network (CNN) is one of the classification approaches that can avoid the complex stages of preprocessing, feature extraction, and feature selection. Therefore, CNN is suggested to be one of the efficient classifiers for biometric identification. Conventionally, input to CNN can be in image or matrix form. The objective of this paper is to explore the arrangement of EEG for CNN input to investigate the most suitable input arrangement of EEG towards the performance of EEG-based identification. EEG datasets that are used in this paper are resting state eyes open (REO) and resting state eyes close (REC) EEG. Six types of data arrangement are compared in this paper. They are matrix of amplitude versus time, matrix of energy versus time, matrix of amplitude versus time for rearranged channels, image of amplitude versus time, image of energy versus time, and image of amplitude versus time for rearranged channels. It was found that the matrix of amplitude versus time for each rearranged channels using the combination of REC and REO performed the best for biometric identification, achieving validation accuracy and test accuracy of 83.21% and 79.08%, respectively.

Matched MeSH terms: Machine Learning*
Fulltext Machine learning techniques for diabetic macular edema (DME) classification on SD-OCT images

Alsaih K, Lemaitre G, Rastgoo M, Massich J, Sidibé D, Meriaudeau F

Biomed Eng Online, 2017 Jun 07;16(1):68.
PMID: 28592309 DOI: 10.1186/s12938-017-0352-9

BACKGROUND: Spectral domain optical coherence tomography (OCT) (SD-OCT) is most widely imaging equipment used in ophthalmology to detect diabetic macular edema (DME). Indeed, it offers an accurate visualization of the morphology of the retina as well as the retina layers.
METHODS: The dataset used in this study has been acquired by the Singapore Eye Research Institute (SERI), using CIRRUS TM (Carl Zeiss Meditec, Inc., Dublin, CA, USA) SD-OCT device. The dataset consists of 32 OCT volumes (16 DME and 16 normal cases). Each volume contains 128 B-scans with resolution of 1024 px × 512 px, resulting in more than 3800 images being processed. All SD-OCT volumes are read and assessed by trained graders and identified as normal or DME cases based on evaluation of retinal thickening, hard exudates, intraretinal cystoid space formation, and subretinal fluid. Within the DME sub-set, a large number of lesions has been selected to create a rather complete and diverse DME dataset. This paper presents an automatic classification framework for SD-OCT volumes in order to identify DME versus normal volumes. In this regard, a generic pipeline including pre-processing, feature detection, feature representation, and classification was investigated. More precisely, extraction of histogram of oriented gradients and local binary pattern (LBP) features within a multiresolution approach is used as well as principal component analysis (PCA) and bag of words (BoW) representations.
RESULTS AND CONCLUSION: Besides comparing individual and combined features, different representation approaches and different classifiers are evaluated. The best results are obtained for LBP[Formula: see text] vectors while represented and classified using PCA and a linear-support vector machine (SVM), leading to a sensitivity(SE) and specificity (SP) of 87.5 and 87.5%, respectively.

Matched MeSH terms: Machine Learning*
Fulltext Optimised genetic algorithm-extreme learning machine approach for automatic COVID-19 detection

Albadr MAA, Tiun S, Ayob M, Al-Dhief FT, Omar K, Hamzah FA

PLoS One, 2020;15(12):e0242899.
PMID: 33320858 DOI: 10.1371/journal.pone.0242899

The coronavirus disease (COVID-19), is an ongoing global pandemic caused by severe acute respiratory syndrome. Chest Computed Tomography (CT) is an effective method for detecting lung illnesses, including COVID-19. However, the CT scan is expensive and time-consuming. Therefore, this work focus on detecting COVID-19 using chest X-ray images because it is widely available, faster, and cheaper than CT scan. Many machine learning approaches such as Deep Learning, Neural Network, and Support Vector Machine; have used X-ray for detecting the COVID-19. Although the performance of those approaches is acceptable in terms of accuracy, however, they require high computational time and more memory space. Therefore, this work employs an Optimised Genetic Algorithm-Extreme Learning Machine (OGA-ELM) with three selection criteria (i.e., random, K-tournament, and roulette wheel) to detect COVID-19 using X-ray images. The most crucial strength factors of the Extreme Learning Machine (ELM) are: (i) high capability of the ELM in avoiding overfitting; (ii) its usability on binary and multi-type classifiers; and (iii) ELM could work as a kernel-based support vector machine with a structure of a neural network. These advantages make the ELM efficient in achieving an excellent learning performance. ELMs have successfully been applied in many domains, including medical domains such as breast cancer detection, pathological brain detection, and ductal carcinoma in situ detection, but not yet tested on detecting COVID-19. Hence, this work aims to identify the effectiveness of employing OGA-ELM in detecting COVID-19 using chest X-ray images. In order to reduce the dimensionality of a histogram oriented gradient features, we use principal component analysis. The performance of OGA-ELM is evaluated on a benchmark dataset containing 188 chest X-ray images with two classes: a healthy and a COVID-19 infected. The experimental result shows that the OGA-ELM achieves 100.00% accuracy with fast computation time. This demonstrates that OGA-ELM is an efficient method for COVID-19 detecting using chest X-ray images.

Matched MeSH terms: Machine Learning*
Fulltext Exploring the effectiveness of technology-based learning on the educational outcomes of undergraduate healthcare students: an overview of systematic reviews protocol

Romli MH, Cheema MS, Mehat MZ, Md Hashim NF, Abdul Hamid H

BMJ Open, 2020 Nov 23;10(11):e041153.
PMID: 33234650 DOI: 10.1136/bmjopen-2020-041153

INTRODUCTION: Rapid technology development due to the introduction of Industrial Revolution 4.0 and Internet of Things has created a demand and gradual transition from traditional teaching and learning to technology-based learning in higher education, including healthcare education. The COVID-19 pandemic has accelerated this process, with educators now required to quickly adapt to and adopt such changes. The abundance of available systematic reviews has made the effectiveness of such approaches ambiguous especially in healthcare education. Therefore, a protocol of the overview of systematic reviews (OoSR) is planned to extrapolate the effectiveness of technology-based learning in undergraduate healthcare education.
METHODS AND ANALYSIS: Scopus, CINAHL, Academic Search Complete, Cochrane Library, MEDLINE and Psychology and Behavioral Sciences Collection databases were selected. Screening was conducted independently by at least two authors and the decision for inclusion was done through discussion or involvement of an arbiter against a predetermined criteria. Included articles will be evaluated for quality using A MeaSurement Tool to Assess systematic Reviews and Risk of Bias in Systematic Review tools, while primary systematic review articles will be cross-checked and reported for any overlapping using the 'corrected covered area' method. Only narrative synthesis will be employed according to the predefined themes into two major dimensions-theory and knowledge generation (focusing on cognitive taxonomy due to its ability to be generalised across disciplines), and clinical-based competence (focusing on psychomotor and affective taxonomies due to discipline-specific influence). The type of technology used will be identified and extracted.
ETHICS AND DISSEMINATION: The OoSR involves analysis of secondary data from published literature, thus ethical approval is not required. The findings will provide a valuable insight for policymakers, stakeholders, and researchers in terms of technology-based learning implementation and gaps identification. The findings will be published in several reports due to the extensiveness of the topic and will be disseminated through peer-reviewed publications and conferences.
PROSPERO REGISTRATION NUMBER: CRD4202017974.

Matched MeSH terms: Learning*
Fulltext EEG-Based Emotion Recognition: A State-of-the-Art Review of Current Trends and Opportunities

Suhaimi NS, Mountstephens J, Teo J

Comput Intell Neurosci, 2020;2020:8875426.
PMID: 33014031 DOI: 10.1155/2020/8875426

Emotions are fundamental for human beings and play an important role in human cognition. Emotion is commonly associated with logical decision making, perception, human interaction, and to a certain extent, human intelligence itself. With the growing interest of the research community towards establishing some meaningful "emotional" interactions between humans and computers, the need for reliable and deployable solutions for the identification of human emotional states is required. Recent developments in using electroencephalography (EEG) for emotion recognition have garnered strong interest from the research community as the latest developments in consumer-grade wearable EEG solutions can provide a cheap, portable, and simple solution for identifying emotions. Since the last comprehensive review was conducted back from the years 2009 to 2016, this paper will update on the current progress of emotion recognition using EEG signals from 2016 to 2019. The focus on this state-of-the-art review focuses on the elements of emotion stimuli type and presentation approach, study size, EEG hardware, machine learning classifiers, and classification approach. From this state-of-the-art review, we suggest several future research opportunities including proposing a different approach in presenting the stimuli in the form of virtual reality (VR). To this end, an additional section devoted specifically to reviewing only VR studies within this research domain is presented as the motivation for this proposed new approach using VR as the stimuli presentation device. This review paper is intended to be useful for the research community working on emotion recognition using EEG signals as well as for those who are venturing into this field of research.

Matched MeSH terms: Machine Learning/trends*
Fulltext Observational Application Comparing Problem-Based Learning with the Conventional Teaching Method for Clinical Acupuncture Education

Kim YJ

Evid Based Complement Alternat Med, 2019;2019:2102304.
PMID: 31011356 DOI: 10.1155/2019/2102304

Aim: Although the problem-based learning (PBL) teaching method was introduced in 1969, its rapid and widespread application in Malaysia started in 1979. This study aimed to evaluate satisfaction with PBL compared to that of conventional learning, using satisfaction surveys and the Rosenberg Self-Esteem scores, of students learning clinical acupuncture at the School of Traditional Chinese Medicine (TCM), Xiamen University Malaysia.
Method: The participants of this study (N=36) were registered for a bachelor's degree program in TCM in 2016 and enrolled in the Science of Acupuncture and Moxibustion course beginning in September 2018. The students were randomly allocated into two groups: PBL group and conventional group. A self-administered learning satisfaction survey and the Rosenberg Self-Esteem scores were used for data collection. An independent sample t-test was used to compare the results between the two groups. A p-value <0.05 was considered significant.
Results: The results of the learning satisfaction survey and Rosenberg Self-Esteem scores were significantly better in the PBL group than in the conventional group (p<0.05).
Conclusions: PBL appears to be more effective for clinical acupuncture education than the conventional teaching method. However, further studies are needed to identify the mechanisms by which PBL excels in clinical acupuncture education, as well as other related TCM fields.

Matched MeSH terms: Learning; Problem-Based Learning
Fulltext Functional data geometric morphometrics with machine learning for craniodental shape classification in shrews

Pillay AB, Pathmanathan D, Dabo-Niang S, Abu A, Omar H

Sci Rep, 2024 Jul 06;14(1):15579.
PMID: 38971911 DOI: 10.1038/s41598-024-66246-z

This work proposes a functional data analysis approach for morphometrics in classifying three shrew species (S. murinus, C. monticola, and C. malayana) from Peninsular Malaysia. Functional data geometric morphometrics (FDGM) for 2D landmark data is introduced and its performance is compared with classical geometric morphometrics (GM). The FDGM approach converts 2D landmark data into continuous curves, which are then represented as linear combinations of basis functions. The landmark data was obtained from 89 crania of shrew specimens based on three craniodental views (dorsal, jaw, and lateral). Principal component analysis and linear discriminant analysis were applied to both GM and FDGM methods to classify the three shrew species. This study also compared four machine learning approaches (naïve Bayes, support vector machine, random forest, and generalised linear model) using predicted PC scores obtained from both methods (a combination of all three craniodental views and individual views). The analyses favoured FDGM and the dorsal view was the best view for distinguishing the three species.

Matched MeSH terms: Machine Learning*
Fulltext Ensemble machine learning for predicting in-hospital mortality in Asian women with ST-elevation myocardial infarction (STEMI)

Kasim S, Amir Rudin PNF, Malek S, Ibrahim KS, Wan Ahmad WA, Fong AYY, et al.

Sci Rep, 2024 May 29;14(1):12378.
PMID: 38811643 DOI: 10.1038/s41598-024-61151-x

The accurate prediction of in-hospital mortality in Asian women after ST-Elevation Myocardial Infarction (STEMI) remains a crucial issue in medical research. Existing models frequently neglect this demographic's particular attributes, resulting in poor treatment outcomes. This study aims to improve the prediction of in-hospital mortality in multi-ethnic Asian women with STEMI by employing both base and ensemble machine learning (ML) models. We centred on the development of demographic-specific models using data from the Malaysian National Cardiovascular Disease Database spanning 2006 to 2016. Through a careful iterative feature selection approach that included feature importance and sequential backward elimination, significant variables such as systolic blood pressure, Killip class, fasting blood glucose, beta-blockers, angiotensin-converting enzyme inhibitors (ACE), and oral hypoglycemic medications were identified. The findings of our study revealed that ML models with selected features outperformed the conventional Thrombolysis in Myocardial Infarction (TIMI) Risk score, with area under the curve (AUC) ranging from 0.60 to 0.93 versus TIMI's AUC of 0.81. Remarkably, our best-performing ensemble ML model was surpassed by the base ML model, support vector machine (SVM) Linear with SVM selected features (AUC: 0.93, CI: 0.89-0.98 versus AUC: 0.91, CI: 0.87-0.96). Furthermore, the women-specific model outperformed a non-gender-specific STEMI model (AUC: 0.92, CI: 0.87-0.97). Our findings demonstrate the value of women-specific ML models over standard approaches, emphasizing the importance of continued testing and validation to improve clinical care for women with STEMI.

Matched MeSH terms: Machine Learning*
Fulltext Bengali-Sign: A Machine Learning-Based Bengali Sign Language Interpretation for Deaf and Non-Verbal People

Raihan MJ, Labib MI, Jim AAJ, Tiang JJ, Biswas U, Nahid AA

Sensors (Basel), 2024 Aug 19;24(16).
PMID: 39205045 DOI: 10.3390/s24165351

Sign language is undoubtedly a common way of communication among deaf and non-verbal people. But it is not common among hearing people to use sign language to express feelings or share information in everyday life. Therefore, a significant communication gap exists between deaf and hearing individuals, despite both groups experiencing similar emotions and sentiments. In this paper, we developed a convolutional neural network-squeeze excitation network to predict the sign language signs and developed a smartphone application to provide access to the ML model to use it. The SE block provides attention to the channel of the image, thus improving the performance of the model. On the other hand, the smartphone application brings the ML model close to people so that everyone can benefit from it. In addition, we used the Shapley additive explanation to interpret the black box nature of the ML model and understand the models working from within. Using our ML model, we achieved an accuracy of 99.86% on the KU-BdSL dataset. The SHAP analysis shows that the model primarily relies on hand-related visual cues to predict sign language signs, aligning with human communication patterns.

Matched MeSH terms: Machine Learning*
Fulltext Development and validation of a higher-order thinking skills (HOTS) scale for major students in the interior design discipline for blended learning

Li D, Fan X, Meng L

Sci Rep, 2024 Aug 31;14(1):20287.
PMID: 39217173 DOI: 10.1038/s41598-024-70908-3

Assessing and cultivating students' HOTS are crucial for interior design education in a blended learning environment. However, current research has focused primarily on the impact of blended learning instructional strategies, learning tasks, and activities on the development of HOTS, whereas few studies have specifically addressed the assessment of these skills through dedicated scales in the context of blended learning. This study aimed to develop a comprehensive scale for assessing HOTS in interior design major students within the context of blended learning. Employing a mixed methods design, the research involved in-depth interviews with 10 education stakeholders to gather qualitative data, which informed the development of a 66-item soft skills assessment scale. The scale was administered to a purposive sample of 359 undergraduate students enrolled in an interior design program at a university in China. Exploratory and confirmatory factor analyses were also conducted to evaluate the underlying factor structure of the scale. The findings revealed a robust four-factor model encompassing critical thinking skills, problem-solving skills, teamwork skills, and practical innovation skills. The scale demonstrated high internal consistency (Cronbach's alpha = 0.948-0.966) and satisfactory convergent and discriminant validity. This scale provides a valuable instrument for assessing and cultivating HOTS among interior design major students in blended learning environments. Future research can utilize a scale to examine the factors influencing the development of these skills and inform instructional practices in the field.

Matched MeSH terms: Learning*
Leveraging machine learning algorithms in dynamic modeling of urban expansion, surface heat islands, and carbon storage for sustainable environmental management in coastal ecosystems

Kafy AA, Dey NN, Saha M, Altuwaijri HA, Fattah MA, Rahaman ZA, et al.

J Environ Manage, 2024 Nov;370:122427.
PMID: 39305877 DOI: 10.1016/j.jenvman.2024.122427

Climate change and rapid urbanization are dramatically altering coastal ecosystems worldwide, with significant implications for land surface temperatures (LST) and carbon stock concentration (CSC). This study investigates the impacts of day and night time LST dynamics on CSC in Cox's Bazar, Bangladesh, from 1996 to 2021, with future projections to 2041. Using Landsat and MODIS imagery, we found that mean daytime LST increased by 3.57 °C over the 25-year period, while nighttime LST showed a slight decrease of 0.05 °C. Concurrently, areas with no carbon storage increased by 355.78%, while high and very high CSC zones declined by 14.15% and 47.78%, respectively. The Integrated Valuation of Ecosystem Services and Tradeoffs (InVEST) model estimated a 28.64 km2 reduction in high CSC areas from 1996 to 2021. Statistical analysis revealed strong negative correlations between LST and vegetation indices (R2 = -0.795 to -0.842, p 32 °C, while areas with LST <24 °C may decrease to 1.68%. These observations underscore the pressing necessity for sustainable strategies in urban planning and conservation in swiftly evolving coastal areas, especially considering the challenges posed by climate change and population growth.

Matched MeSH terms: Machine Learning*

Filters

Please provide feedback to Administrator ([email protected])

External Links