MATERIALS & METHODS: This was a cross-sectional study involving 101 subjects recruited from the National Institute of Forensic Medicine (IPFN) Hospital Kuala Lumpur (HKL) over a period of 15 months, from December 2012 until April 2014. PMCT CS of the coronary arteries was calculated using Agatston-Janowitz score. Histological presence of calcification was observed and the degree of stenosis was calculated using an image analysis technique.
RESULTS: PMCT CS increased with increasing severity of stenosis (p<0.001). PMCT CS showed a positive correlation with the presence of calcification (r=-0.82, p<0.001).
CONCLUSION: Calcium score is strongly associated with coronary artery calcification and the degree of luminal stenosis in post mortem subjects. Thus, PMCT may be useful as a non-invasive tool in diagnosing CAD in the event that an autopsy is not possible.
METHODS: This is a retrospective study of post mortem cases at Hospital Kuala Lumpur from 2014 to 2016. Deaths from RTC were included while decomposed and homicide cases were excluded. We performed Spearman Correlation statistical test to relate RTC and positive DoA results.
RESULTS: A total of 523 RTC cases were identified in which either blood or urine or both samples were taken for toxicology. 93 cases were positive for both DoA and therapeutic drugs. A total of 37 cases were positive for DoA. Alcohol was present in 5 out of 37 DoA positive cases. Most of the cases seen among 16 to 45 years old (69%) and predominantly in males (93.1%). 29 out of 37 were motorcyclist and the rest were pillion rider and pedestrian. Spearman Correlation statistical test showed a negative relationship between RTC and positive DoA results.
DISCUSSION AND CONCLUSION: Majority of the DoA cases in RTC were identified in the younger age group and among the motorcyclist. Spearman Correlation statistical test showed that more cases of DoA died in natural or suicidal manner compared to RTC. However, this doesn't reflect the true association of DoA in RTC. This is because of mainly two factors which the delayed effect of DoA that gives negative toxicology test and also the influence of other road users on DoA.
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.