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.
Patients and methods: An observational study was conducted at four different intensive care units of an academic medical institution. Demographic characteristics, disease-management casemix information, cost and outcome of the high costing decile, and the rest of the cases were compared.
Results: A total of 3,220 discharges were included in the study. The high-cost group contributed 35.4% of the ICU stays and 38.8% of the total ICU expenditure. Diseases of the central nervous system had higher odds to be in the top decile of costly patients whereas the cardiovascular system was more likely to be in the non-high cost category. The high-cost patients were more likely to have death as an outcome (19.2% vs 9.3%; p<0.001). The most common conditions that were in the high-cost groups were craniotomy, other ear, nose, mouth, and throat operations, simple respiratory system operations, complex intestinal operations, and septicemia. These five diagnostic groups made up 43% of the high-cost decile.
Conclusion: High-cost patients utilized almost 40% of the ICU cost although they were only 10% of the ICU patients. The chances of admission to the ICU increased with older age and severity level of the disease. Central nervous system diseases were the major problem of patients aged 46-69 years old. In addition to cost reduction strategies at the treatment level, detailed analysis of these cases was needed to explore and identify pre-event stage prevention strategies.
METHODS: This has been achieved by the participation of a prospective cohort involving a total of 90 moderate to severe psoriasis patients, which has been conducted at 5 public hospitals in Malaysia. The main outcome measures have been evaluated via cost and effectiveness psoriasis area severity index (PASI)-75 and/or body surface area (BSA) <5 and/or dermatology life quality index (DLQI) ≤5), estimated from the societal perspective over a 6-months duration. All costs are based on 2015's recorded Malaysian Ringgit (RM) currency.
RESULTS: Consequently, TS has been found to be the most cost-effective treatment with the lowest cost/PASI-75/and/or BSA <5 and/or DLQI ≤5, valued at RM9034.56 (US$2582.55). This is followed by TP, which is valued at RM28 080.71 (US$8026.93) and TB, valued at RM54 287.02 (US$15 518.06). Furthermore, one-way sensitivity analysis has highlighted the cost of medication as the most sensitive parameter.
CONCLUSION: Thus, the input from this study is helpful for policy-makers in determining the first line treatment for moderate to severe psoriasis with consideration of the costs and its effectiveness in Malaysia. This will consequently allow hospitals to justify and provide the essential resources for further research and development, as well as the adoption of better treatment options.
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.