METHODS: Dental therapists from two major public dental organisations in the East-Peninsular Malaysia (n = 26) were invited to participate in an audiotaped semi-structured interview using a pre-tested topic-guide informed by workforce policy and research literature. The qualitative data were transcribed and analysed using Framework Analysis.
RESULTS: The research conducted with dental therapists (n = 26) identified four motivation domains namely 'altruism', 'personal and academic inspiration', 'profession characteristics' and 'career advising and social influences' as key factors motivating their choice of a professional career as dental therapists, influenced by work-life balance and financial stability. They were also aware of the new dental act and its potential implications, particularly regarding their future career expectations. The majority felt the necessity 'to improve their skills and knowledge' within the first 5 years as part of their short-term career plans. A few participants expressed a desire to 'pursue a higher level of education' and 'wished to join the private sector' in the long-term. They perceived the possibility of 'working in the private sector' to increase their income and believed that they did not require any additional training for such a transition.
CONCLUSION: Malaysian dental therapists welcomed the changes in the new act, which allow them to work across sectors. Many perceived themselves as adequately motivated and equipped to transition to different work settings without requiring additional training.
OBJECTIVE: This study aims to conduct a comprehensive analysis of machine learning (ML) methods for MRI-based biomarker selection and classification to investigate early cognitive decline in AD. The focus to discriminate between classifying healthy control (HC) participants who remained stable and those who developed mild cognitive impairment (MCI) within five years (unstable HC or uHC).
METHODS: 3-Tesla (3T) MRI data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and Open Access Series of Imaging Studies 3 (OASIS-3) were used, focusing on HC and uHC groups. Freesurfer's recon-all and other tools were used to extract anatomical biomarkers from subcortical and cortical brain regions. ML techniques were applied for feature selection and classification, using the MATLAB Classification Learner (MCL) app for initial analysis, followed by advanced methods such as nested cross-validation and Bayesian optimization, which were evaluated within a Monte Carlo replication analysis as implemented in our customized pipeline. Additionally, polynomial regression-based data harmonization techniques were used to enhance ML and statistical analysis. In our study, ML classifiers were evaluated using performance metrics such as Accuracy (Acc), area under the receiver operating characteristic curve (AROC), F1-score, and a normalized Matthew's correlation coefficient (MCC').
RESULTS: Feature selection consistently identified biomarkers across ADNI and OASIS-3, with the entorhinal, hippocampus, lateral ventricle, and lateral orbitofrontal regions being the most affected. Classification results varied between balanced and imbalanced datasets and between ADNI and OASIS-3. For ADNI balanced datasets, the naíve Bayes model using z-score harmonization and ReliefF feature selection performed best (Acc = 69.17%, AROC = 77.73%, F1 = 69.21%, MCC' = 69.28%). For OASIS-3 balanced datasets, SVM with zscore-corrected data outperformed others (Acc = 66.58%, AROC = 72.01%, MCC' = 66.78%), while logistic regression had the best F1-score (66.68%). In imbalanced data, RUSBoost showed the strongest overall performance on ADNI (F1 = 50.60%, AROC = 81.54%) and OASIS-3 (MCC' = 63.31%). Support vector machine (SVM) excelled on ADNI in terms of Acc (82.93%) and MCC' (70.21%), while naïve Bayes performed best on OASIS-3 by F1 (42.54%) and AROC (70.33%).
CONCLUSION: Data harmonization significantly improved the consistency and performance of feature selection and ML classification, with z-score harmonization yielding the best results. This study also highlights the importance of nested cross-validation (CV) to control overfitting and the potential of a semi-automatic pipeline for early AD detection using MRI, with future applications integrating other neuroimaging data to enhance prediction.
METHODS: We used pre-COVID-19 pulmonary tuberculosis (PTB) data (2007-2018) to fit SARIMA, Prophet, and LSTM models, assessing their ability to predict PTB incidence trends. These models were then applied to compare the predicted PTB incidence patterns with actual reported cases during the COVID-19 pandemic (2020-2023), using deviations between predicted and actual values to reflect the impact of COVID-19 countermeasures on PTB incidence.
RESULTS: Prior to the COVID-19 outbreak, PTB incidence in China exhibited a steady decline with strong seasonal fluctuations, characterized by two annual peaks-one in March and another in December. These seasonal trends persisted until 2019. During the COVID-19 pandemic, there was a significant reduction in PTB cases, with actual reported cases falling below the predicted values. The disruption in PTB incidence appears to be temporary, as 2023 data indicate a gradual return to pre-pandemic trends, though the incidence rate remains slightly lower than pre-COVID levels. Additionally, we compared the fitting and forecasting performance of the SARIMA, Prophet, and LSTM models using RMSE (root mean squared error), MAE (mean absolute error), and MAPE (mean absolute percentage error) indexes prior to the COVID-19 outbreak. We found that the Prophet model had the lowest values for all three indexes, demonstrating the best fitting and prediction performance.
CONCLUSIONS: The COVID-19 pandemic has had a temporary but significant impact on PTB incidence in China, leading to a reduction in reported cases during the pandemic. However, as pandemic control measures relax and the healthcare system stabilizes, PTB incidence patterns are expected to return to pre-COVID-19 levels. The Prophet model demonstrated the best predictive performance and proves to be a valuable tool for analyzing PTB trends and guiding public health planning in the post-pandemic era.
DESIGN: A search was conducted in five databases: PubMed, Scopus, ProQuest, Web of Science, and SPORT Discus, from January 2000 to June 2023.
METHOD: This search followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines.
RESULTS: The results of the search identified a total of twenty-six articles. Improvements were primarily demonstrated in the three main areas of fundamental motor skills: locomotor skills (n = 17), balance skills (n = 10), and object control skills (n = 2).
CONCLUSIONS: The results suggest that functional training programs can improve children's fundamental motor skills. Existing evidence also concludes that functional training significantly impacts locomotor and balance skills, whereas further research is required to confirm its positive effects on object control skills.