METHODS: Accident-related autopsy reports were obtained from one of the largest hospital in Kuala Lumpur. These reports belong to nine different accident-related causes of death. Master feature vector was prepared by extracting features from the collected autopsy reports by using unigram with lexical categorization. This master feature vector was used to detect cause of death [according to internal classification of disease version 10 (ICD-10) classification system] through five automated feature selection schemes, proposed expert-driven approach, five subset sizes of features, and five machine learning classifiers. Model performance was evaluated using precisionM, recallM, F-measureM, accuracy, and area under ROC curve. Four baselines were used to compare the results with the proposed system.
RESULTS: Random forest and J48 decision models parameterized using expert-driven feature selection yielded the highest evaluation measure approaching (85% to 90%) for most metrics by using a feature subset size of 30. The proposed system also showed approximately 14% to 16% improvement in the overall accuracy compared with the existing techniques and four baselines.
CONCLUSION: The proposed system is feasible and practical to use for automatic classification of ICD-10-related cause of death from autopsy reports. The proposed system assists pathologists to accurately and rapidly determine underlying cause of death based on autopsy findings. Furthermore, the proposed expert-driven feature selection approach and the findings are generally applicable to other kinds of plaintext clinical reports.
METHODS: This validation study involves retrospective review of available hospital discharge records and hand-search medical records for years 2010 and 2013. We randomly selected 3219 hospital discharge records coded with dengue and non-dengue infections as their discharge diagnoses from the national hospital discharge database. We then randomly sampled 216 and 144 records for patients with and without codes for dengue respectively, in keeping with their relative frequency in the MOH database, for chart review. The ICD codes for dengue were validated against lab-based diagnostic standard (NS1 or IgM).
RESULTS: The ICD-10-CM codes for dengue had a sensitivity of 94%, modest specificity of 83%, positive predictive value of 87% and negative predictive value 92%. These results were stable between 2010 and 2013. However, its specificity decreased substantially when patients manifested with bleeding or low platelet count.
CONCLUSION: The diagnostic performance of the ICD codes for dengue in the MOH's hospital discharge database is adequate for use in health services research on dengue.
METHODS: An observational study of children aged between 0-18 years receiving palliative care at 13 hospitals between 1st January and 31st December 2014 was carried out.
RESULTS: There were 315 patients analysed, 90 (28.6%) and 46 (14.6%) were neonates and adolescents respectively. The main ICD-10 diagnostic categories for all patients were identified to be 'Congenital malformations, deformations and chromosomal abnormalities' 117 (37.1%), 'Diseases of nervous system' 76 (24.1%) and 'Neoplasms' 60 (19.0%). At referral 156 (50%) patients had holistic needs assessments. Patients with 'Diseases of nervous system' were assessed to have significantly more physical needs than the other two diagnostic categories. Majority of patients who knew of their diagnosis and prognosis were those with malignancy. Over a fifth of referrals were at their terminal admission. Of 144 who died, 111 (77.1%) had advanced care plans. There was bereavement follow-up in 98 (68.1%) patients.
CONCLUSION: Patients referred for palliative care have varied diagnoses and needs. To ensure all paediatricians are competent to deliver quality care to all children, further education and training initiatives is imperative.
Design: This study was a retrospective cohort study. The national hospital admissions database was reviewed and children who had died who had life-limiting illnesses were identified.
Setting: This study was conducted at Ministry of Health hospitals, Malaysia.
Patients: Children aged 18 years and below who had died between January 1, 2012 and December 31, 2014.
Main Outcome Measures: Life-limiting diagnoses based on Hain et al.'s directory of LLI or the ACT/RCPCH categories of life-limiting disease trajectories.
Results: There were 8907 deaths and 3958 (44.4%) were that of children with LLI. The majority, 2531 (63.9%) of children with LLI were neonates, and the most common diagnosis was extreme prematurity <28 weeks with 676 children (26.7%). For the nonneonatal age group, the median age at admission was 42 months (1-216 months). A majority, 456 (32.0%) had diagnoses from the ICD-10 chapter "Neoplasms" followed by 360 (25.3%) who had a diagnoses from "Congenital malformations, deformations, and chromosomal abnormalities" and 139 (9.7%) with diagnoses from "Disease of the nervous system." While a majority of the terminal admissions were to the general ward, there were children from the nonneonatal age group, 202 (14.2%) who died in nonpediatric wards.
Conclusion: Understanding the characteristics of children with LLI who die in hospitals could contribute toward a more efficient pediatric palliative care (PPC) service development. PPC service should include perinatal and neonatal palliative care. Palliative care education needs to extend to nonpediatric healthcare providers who also have to manage children with LLI.
AIMS: This paper aims to describe the profiles of diabetes mellitus type 2 in tertiary setting and to identify the risk factors for high level of HbA1c among the study population. The findings will give a glimpse on current status of diabetes in our country and may reflect the achievement of the country in combating this disease.
SETTINGS AND DESIGN: A cross-sectional study was conducted in UKM Medical Centre.
METHODS AND MATERIAL: Medical records of patient with E11 ICD-10 code were collected using Case Report Form.
STATISTICAL ANALYSIS USED: Descriptive analysis done of mean and median while test of association were done using Spearman correlation and logistic regression.
RESULTS: The results showed that majority of inpatients of DMT2 showed mean age of 58.8 + 12.6 years and most were males (56.7%) with secondary level of education (41.7%). Median duration of disease was 12.0 + 11.0 years with median HbA1c level of 8.9 ± 4.4%. Only small proportion of patients achieved the desired level of HbA1c <6.5% (21.3%) and significant association was found with tertiary level of education [AOR = 0.10, 95%CI = 0.01-0.96] and with type of anti-diabetic therapy [AOR = 15.90, 95%CI=1;2.03-124.30].
CONCLUSIONS: In conclusion, diabetes mellitus type 2 inpatients still showed unsatisfactory glycemic control and holistic approach using health education should be advocated continuously in the future in view of education being one of the predictors for the good HbA1c outcome.
Settings and Design: This was a cross-sectional study conducted in a Neurological Centre at Hospital Tengku Ampuan Afzan, Kuantan, Pahang, Malaysia, from January 2016 to December 2016.
Subjects and Methods: A total of 209 patients; 133 males and 76 females, in the age range of 16-84 years, were randomly recruited for this study. All the selected patients were subjected to the checklist for diagnosis of PCS as per International Statistical Classification of Diseases and Related Health Problems 10th edition classification at a 2-week interval.
Statistical Analysis Used: Descriptive statistic and Multivariable Logistic Regression Model were used for frequency and percentage analyses of categorical variables, using SPSS version 23.0.
Results: Only 20 patients were identified with PCS. There were more female (70%) patients with PCS than the male (30%) patients. The prevalence of PCS for 2 weeks, 3 and 6 months since injuries were 9.6%, 8.1%, and 8.1% respectively. Majority (80%) of the patients were found to have PCS due to road traffic accidents, while the remaining were attributed to assault (15%), and falls (5%). Among the sample population, 25% were smokers, while 10% of them had either skull fracture or premorbidity.
Conclusion: Less than 10% of patients with MTBI had PCS after 6 months' following trauma. None of the variables tested were significant factors for the development of PCS symptoms.
MATERIALS AND METHODS: This is a multicentre, cross-sectional study involving 5 Health Clinics conducted by Family Medicine Specialists in Malaysia. Convenience sampling of 100 respondents with DM were selected. The International Classifi cation of Functioning, Disability and Health (ICF) based measures were collected using the Comprehensive Core Set for DM. SF-36 and self-administered forms and comorbidity questionnaire (SCQ) were also used.
RESULTS: Ninety-seven percent had Type 2 DM and 3% had Type 1 DM. The mean period of having DM was 6 years. Body functions related to physical health including exercise tolerance (b455), general physical endurance (b4550), aerobic capacity (b4551) and fatiguability (b4552) were the most affected. For body structures, the structure of pancreas (s550) was the most affected. In the ICF component of activities and participation, limitation in sports (d9201) was the highest most affected followed by driving (d475), intimate relationships (d770), handling stress and other psychological demands (d240) and moving around (d455). Only 7% (e355 and e450) in the environmental category were documented as being a relevant factor by more than 90% of the patients.
CONCLUSION: The content validity of the comprehensive ICF Core set DM for Malaysian population were identified and the results show that physical and mental functioning were impaired in contrast to what the respondents perceived as leading healthy lifestyles.
METHODS: Various databases were used to search relevant articles since 1995. Studies included were cohort and cross-sectional studies, all patients with dengue infection and must report the number of death or case fatality rate. The Joanna Briggs Institute appraisal checklist was used to evaluate the risk of bias of the full-texts. The studies were grouped according to the classification adopted: WHO 1997 and WHO 2009. Meta-regression was employed using a logistic transformation (log-odds) of the case fatality rate. The result of the meta-regression was the adjusted case fatality rate and odds ratio on the explanatory variables.
RESULTS: A total of 77 studies were included in the meta-regression analysis. The case fatality rate for all studies combined was 1.14% with 95% confidence interval (CI) of 0.82-1.58%. The combined (unadjusted) case fatality rate for 69 studies which adopted WHO 1997 dengue case classification was 1.09% with 95% CI of 0.77-1.55%; and for eight studies with WHO 2009 was 1.62% with 95% CI of 0.64-4.02%. The unadjusted and adjusted odds ratio of case fatality using WHO 2009 dengue case classification was 1.49 (95% CI: 0.52, 4.24) and 0.83 (95% CI: 0.26, 2.63) respectively, compared to WHO 1997 dengue case classification. There was an apparent increase in trend of case fatality rate from the year 1992-2016. Neither was statistically significant.
CONCLUSIONS: The WHO 2009 dengue case classification might have no effect towards the case fatality rate although the adjusted results indicated a lower case fatality rate. Future studies are required for an update in the meta-regression analysis to confirm the findings.