AIMS AND OBJECTIVES: In order to improve predictive model performance, this paper proposed a predictive model by classifying the disease predictions into different categories. To achieve this model performance, this paper uses traumatic brain injury (TBI) datasets. TBI is one of the serious diseases worldwide and needs more attention due to its seriousness and serious impacts on human life.
CONCLUSION: The proposed predictive model improves the predictive performance of TBI. The TBI data set is developed and approved by neurologists to set its features. The experiment results show that the proposed model has achieved significant results including accuracy, sensitivity, and specificity.
METHODS: We used a cross-sectional study with data from the Malaysian TB Information System (TBIS) recorded from 1 January 2014 to 31 December 2017. All children aged 0-14 years who were registered in the TBIS with at least one household contact of TB cases were included in the study. Multiple logistic regression analysis was performed to calculate the adjusted odds ratio (adj. OR) and for adjusting the confounding factors.
RESULTS: A total of 2793 children were included in the study. The prevalence of active TB was 1.5% (95% confidence interval [CI]: 1.31, 1.77%). Children aged 6 weeks [adj. OR 7.48 (95% CI: 2.88, 19.43), p
METHODS: A cross-sectional study of patients requiring ICU admissions in a teaching hospital in Malaysia from 2013 to 2015 was conducted. The cost at the ICU was estimated using the step down approach. Factors that determined the cost and LOS at the ICU were also explored by using multivariate regression analysis.
RESULTS: Each day of stay cost $427 (USD) at the pediatric intensive care unit and $1324 at the general intensive care unit. The mean LOS at the ICU was 5.7 days (standard deviation [SD]: 8.4) with a median of 4 days (95% confidence interval [CI] 1-16.7 days). Average cost of care at the ICU per episode of care was $5473 (SD $6499), and the median was $3463. ICU patients spent 29.3% of the total stay and 47.2% of the cost at ICU units. Upon multivariate regression analysis, severity, case base-group, and type of ICU that the patient was admitted to were associated with the cost and LOS at ICU.
CONCLUSIONS: Compared with critical care practices in hospitals from more developed nations, a Malaysian teaching hospital required a longer length of ICU stay. Hence, implementations of strategies that can reduce the length of stay and hospital costs without compromising healthcare quality are required.