MATERIAL AND METHODS: This cluster randomised controlled trial (RCT) will involve 207 Arab students (14-18 years old) from 12 Arabic schools in the Klang Valley. The schools will be assigned randomly to an intervention (online life skills programme) or control group at a 1:1 ratio. The researcher will deliver eight one-hour sessions to the intervention group weekly. The control group will receive the intervention at the evaluation end. Both groups will complete assessments at baseline, and immediately and three months after the intervention. The primary outcome is anxiety, depression, and stress [Depression Anxiety and Stress Scale-21 (DASS-21)]. The secondary outcomes are self-efficacy (General Self-Efficacy Scale) and coping skills (Brief COPE Inventory). Data analysis will involve the Generalised Estimation Equation with a 95% confidence interval. P < .05 will indicate significant inter- and intra-group differences.
DISCUSSION: This will be the first cluster RCT of an online life skills education programme involving Arab adolescent migrants in Malaysia. The results could support programme effectiveness for improving the participants' mental health problems (depression, anxiety, stress), increasing their self-efficacy, and enhancing their coping skills. The evidence could transform approaches for ameliorating migrant children and adolescents' mental well-being.
TRIAL REGISTRATION: The study is registered with the Clinical Trial Registry (Identifier: NCT05370443).
OBJECTIVE: To employ machine learning (ML) and stacked ensemble learning (EL) methods in predicting short- and long-term mortality in Asian patients diagnosed with NSTEMI/UA and to identify the associated features, subsequently evaluating these findings against established risk scores.
METHODS: We analyzed data from the National Cardiovascular Disease Database for Malaysia (2006-2019), representing a diverse NSTEMI/UA Asian cohort. Algorithm development utilized in-hospital records of 9,518 patients, 30-day data from 7,133 patients, and 1-year data from 7,031 patients. This study utilized 39 features, including demographic, cardiovascular risk, medication, and clinical features. In the development of the stacked EL model, four base learner algorithms were employed: eXtreme Gradient Boosting (XGB), Support Vector Machine (SVM), Naive Bayes (NB), and Random Forest (RF), with the Generalized Linear Model (GLM) serving as the meta learner. Significant features were chosen and ranked using ML feature importance with backward elimination. The predictive performance of the algorithms was assessed using the area under the curve (AUC) as a metric. Validation of the algorithms was conducted against the TIMI for NSTEMI/UA using a separate validation dataset, and the net reclassification index (NRI) was subsequently determined.
RESULTS: Using both complete and reduced features, the algorithm performance achieved an AUC ranging from 0.73 to 0.89. The top-performing ML algorithm consistently surpassed the TIMI risk score for in-hospital, 30-day, and 1-year predictions (with AUC values of 0.88, 0.88, and 0.81, respectively, all p < 0.001), while the TIMI scores registered significantly lower at 0.55, 0.54, and 0.61. This suggests the TIMI score tends to underestimate patient mortality risk. The net reclassification index (NRI) of the best ML algorithm for NSTEMI/UA patients across these periods yielded an NRI between 40-60% (p < 0.001) relative to the TIMI NSTEMI/UA risk score. Key features identified for both short- and long-term mortality included age, Killip class, heart rate, and Low-Molecular-Weight Heparin (LMWH) administration.
CONCLUSIONS: In a broad multi-ethnic population, ML approaches outperformed conventional TIMI scoring in classifying patients with NSTEMI and UA. ML allows for the precise identification of unique characteristics within individual Asian populations, improving the accuracy of mortality predictions. Continuous development, testing, and validation of these ML algorithms holds the promise of enhanced risk stratification, thereby revolutionizing future management strategies and patient outcomes.
METHODS: Data for the years 2016 through 2018 were gathered retrospectively from several sources. These were existing Ministry of Health (MOH) influenza sentinel sites data, two teaching hospitals, and two private medical institutions in the Klang Valley, Malaysia. Expert consensus determined the final estimates of burden for laboratory-confirmed influenza-like illness (ILI) and severe acute respiratory infection (SARI). Economic burden was estimated separately using secondary data supplemented by MOH casemix costing.
RESULTS: Altogether, data for 11,652 cases of ILI and 5,764 cases of SARI were extracted. The influenza B subtype was found to be predominant in 2016, while influenza A was more prevalent in 2017 and 2018. The distribution timeline revealed that the highest frequency of cases occurred in March and April of all three years. The costs of influenza amounted to MYR 310.9 million over the full three-year period.
CONCLUSIONS: The study provides valuable insights into the dynamic landscape of influenza in Malaysia. The findings reveal a consistent year-round presence of influenza with irregular seasonal peaks, including a notable influenza A epidemic in 2017 and consistent surges in influenza B incidence during March across three years. These findings underscore the significance of continuous monitoring influenza subtypes for informed healthcare strategies as well as advocate for the integration of influenza vaccination into Malaysia's national immunization program, enhancing overall pandemic preparedness.
METHODS AND ANALYSIS: NPC patients will be required to complete a risk factor questionnaire after obtaining their informed consent. The risk factor questionnaire will be used to collect potential risk factors for malnutrition. Univariate and multivariate logistic regression analyses will be used to identify risk factors for malnutrition. A new nutritional assessment tool will be developed based on risk factors. The new tool's performance will be assessed by calibration and discrimination. The bootstrapping will be used for internal validation of the new tool. In addition, external validation will be performed by recruiting NPC patients from another hospital.
DISCUSSION: If the new tool is validated to be effective, it will potentially save medical staff time in assessing malnutrition and improve their work efficiency. Additionally, it may reduce the incidence of malnutrition and its adverse consequences.
STRENGTHS AND LIMITATIONS OF THIS STUDY: The study will comprehensively analyze demographic data, disease status, physical examination, and blood sampling to identify risk factors for malnutrition. Furthermore, the new tool will be systematically evaluated, and validated to determine their effectiveness. However, the restricted geographical range may limit the generalizability of the results to other ethnicities. Additionally, the study does not analyze subjective indicators such as psychology.
ETHICS AND DISSEMINATION: The ethical approval was granted by the Ethical Committee of the First Affiliated Hospital of Guangxi Medical University (NO. 2022-KT-GUI WEI-005) and the Second Affiliated Hospital of Guangxi Medical University (NO. 2022-KY-0752).
CLINICAL TRIAL REGISTRATION NUMBER: ChiCTR2300071550.
METHOD: A systematic search was conducted in MEDLINE, SCOPUS, WEB OF SCIENCE. (Jan 2000 to April 2022). Included studies for HSUV estimates were from outpatient setting, regardless of treatment types, complication stages, regions and HRQoL instruments. Health Related Quality of Life (HRQoL) outcomes was to be presented as HSUV decrement values, adjusted according to social demographics and comorbidities. Adjusted HSUV decrements were extracted and compiled according to individual complications. After which, subsequently grouped into mild or severe category for comparison.
RESULTS: Searches identified 35 studies. The size of the study population ranged from 160 to 14,826. The HSUV decrement range was widest for cerebrovascular disease (stroke): -0.0060 to -0.0780 for mild stroke and -0.035 to -0.266 for severe stroke; retinopathy: mild (-0.005 to -0.0862), moderate (-0.0030 to -0.1845) and severe retinopathy (-0.023 to -0.2434); amputation: (-0.1050 to -0.2880). Different nature of complication severity defined in studies could be categorized into: those with acute nature, chronic with lasting effects, those with symptoms at early stage or those with repetitive frequency or episodes.
DISCUSSION: Overview of HSUV decrement ranges across different stages of each T2DM diabetes-related complications shows that chronic complications with lasting impact such as amputation, severe stroke with sequelae and severe retinopathy with blindness were generally associated with larger HSUV decrement range. Considerable heterogeneities exist across the studies. Promoting standardized complication definitions and identifying the most influential health state stages on HSUV decrements may assist researchers for future cost-effectiveness studies.