Methods: A cross-sectional study was performed among residents residing around Klang and Petaling district in Selangor, Malaysia from November 2015 to January 2017. Multivariable logistic regression models were used to assess the predictors of mobile device and health apps usage and examine the association between apps use and intention to change behavior with sociodemographic predictors.
Results: A total of 4,504 respondents participated in our survey. Most respondents reported that they owned a mobile or smartphone, which was commonly used to make calls and deliver text messages. However, only one-fifth (20.4%) of respondents were familiar with the term m-health or had used a health related application, with millennial (individuals aged ≤39 years) generally more aware of the term m-health and were more likely to use m-health as a tool for health management. The most commonly used application were for promoting adherence as well as self-efficacy (e.g., lifestyle advice). Other factors associated with higher levels of m-health use were individuals with higher level of education and individuals taking multiple medications.
Conclusions: While most Malaysian were not familiar with m-health, they reported to have a positive attitude towards m-health. Malaysians were willing to use m-health to manage their health conditions but expressed that they required further education and training. As m-health is still at its infancy in Malaysia, there is potential to further develop m-health as an innovative solution to manage the population health.
METHODS: This study analysed all traumatic brain injury cases for children ages 0-19 included in the 2010 NTrD report.
RESULTS: A total of 5,836 paediatric patients were admitted to emergency departments (ED) of reporting hospitals for trauma. Of these, 742 patients (12.7 %) suffered from brain injuries. Among those with brain injuries, the mortality rate was 11.9 and 71.2 % were aged between 15 and 19. Traffic accidents were the most common mode of injury (95.4 %). Out of the total for traffic accidents, 80.2 % of brain injuries were incurred in motorcycle accidents. Severity of injury was higher among males and patients who were transferred or referred to the reporting centres from other clinics. Glasgow Coma Scale (GCS) total score and type of admission were found to be statistically significant, χ (2) (5, N = 178) = 66.53, p
RESULTS: Our models learned several syntactic, lexical, and n-gram linguistic biomarkers to distinguish the probable AD group from the healthy group. In contrast to the healthy group, we found that the probable AD patients had significantly less usage of syntactic components and significantly higher usage of lexical components in their language. Also, we observed a significant difference in the use of n-grams as the healthy group were able to identify and make sense of more objects in their n-grams than the probable AD group. As such, our best diagnostic model significantly distinguished the probable AD group from the healthy elderly group with a better Area Under the Receiving Operating Characteristics Curve (AUC) using the Support Vector Machines (SVM).
CONCLUSIONS: Experimental and statistical evaluations suggest that using ML algorithms for learning linguistic biomarkers from the verbal utterances of elderly individuals could help the clinical diagnosis of probable AD. We emphasise that the best ML model for predicting the disease group combines significant syntactic, lexical and top n-gram features. However, there is a need to train the diagnostic models on larger datasets, which could lead to a better AUC and clinical diagnosis of probable AD.
MATERIALS AND METHODS: This was a retrospective descriptive study. We identified 1041 patients (810 Chinese, 139 Malays, 92 Indians) without previous history of cardiovascular disease who underwent cardiac computed tomography for atypical chest pain evaluation. A cardiologist, who was blinded to the patients' clinical demographics, reviewed all scans. We retrospectively analysed all their case records.
RESULTS: Overall, Malays were most likely to be active smokers (P = 0.02), Indians had the highest prevalence of diabetes mellitus (P = 0.01) and Chinese had the highest mean age (P <0.0001). The overall prevalence of patients with non-calcified plaques as the only manifestation of sub-clinical coronary artery disease was 2.1%. There was no significant difference in the prevalence of CAC, mean CAC score or prevalence of non-calcified plaques among the 3 ethnic groups. Active smoking, age and hypertension were independent predictors of CAC. Non-calcified plaques were positively associated with male gender, age, dyslipidaemia and diabetes mellitus.
CONCLUSION: The higher MI rates in Malays and Indians in Singapore cannot be explained by any difference in CAC or non-calcified plaque. More research with prospective follow-up of larger patient populations is necessary to establish if ethnic-specific calibration of CAC measures is needed to adjust for differences among ethnic groups.