Methods: Data from 160 hypertensive patients from a tertiary hospital in Kuala Lumpur, Malaysia, were used in this study. Variables were ranked based on their significance to adherence levels using the RF variable importance method. The backward elimination method was then performed using RF to obtain the variables significantly associated with the patients' adherence levels. RF, SVR and ANN models were developed to predict adherence using the identified significant variables. Visualizations of the relationships between hypertensive patients' adherence levels and variables were generated using SOM.
Result: Machine learning models constructed using the selected variables reported RMSE values of 1.42 for ANN, 1.53 for RF, and 1.55 for SVR. The accuracy of the dichotomised scores, calculated based on a percentage of correctly identified adherence values, was used as an additional model performance measure, resulting in accuracies of 65% (ANN), 78% (RF) and 79% (SVR), respectively. The Wilcoxon signed ranked test reported that there was no significant difference between the predictions of the machine learning models and the actual scores. The significant variables identified from the RF variable importance method were educational level, marital status, General Overuse, monthly income, and Specific Concern.
Conclusion: This study suggests an effective alternative to conventional methods in identifying the key variables to understand hypertensive patients' adherence levels. This can be used as a tool to educate patients on the importance of medication in managing hypertension.
METHODS: A cross-sectional study was conducted among 370 Yemeni women in Selangor and Kuala Lumpur, Malaysia. Data on the awareness of symptoms/signs, risk factors, and screening programme were collected using Cervical Cancer Awareness Measurement (Cervical CAM) questionnaire.
RESULTS: More than 74% of the study participants were unable to recall any warning symptoms/signs, and 73% were unable to recall any risk factors. The factors associated with the awareness of symptoms and risk factors were age (95% CI 4.22-5.22, p = 0.039), marital status (95% CI 4.05-7.87, p = 0.021), employment (95% CI 3.89-5.77, p = 0.046) and the number of children (95% CI 5.33-6.54, p = 0.041).
CONCLUSION: The findings underline the need for public awareness campaigns to improve public awareness of cancer symptoms and risk factors among underserved communities.
SUBJECTS/METHODS: A total of 177 female vegetarians were recruited from a Buddhist and Hindu organization in Selangor, Malaysia. The participants completed a self-administered questionnaire, which analyzed their sociodemographic characteristics, physical activity level, sleep quality, depression, anxiety, and stress. The body weight, height, waist circumference, and body fat percentage of the participants were also measured. A 3-day dietary recall was conducted to assess their dietary intake. Blood samples (3 ml) were withdrawn by a nurse from each participant to determine the hemoglobin (Hb) level.
RESULTS: The findings revealed 28.2% of the participants to be anemic. The age group (AOR = 2.46, 95% CI = 1.19-5.05), marital status (AOR = 2.69, 95% CI = 1.27-5.71), and percentage of energy from protein (AOR = 5.52, 95% CI = 1.41-21.65) were the significant predictors of anemia.
CONCLUSIONS: Anemia is a public health problem among female vegetarians in this study. Health promotion programs that target female adult vegetarians should be conducted to manage and prevent anemia, particularly among those who are married, aged 50 and below, and with an inadequate protein intake.