MATERIAL & METHOD: 61 road traffic accidental death cases underwent both PMCT and conventional autopsy. The imaging findings were compared to the conventional autopsy findings.
RESULT: The sensitivity, specificity, PPV and NPV for liver injuries in PMCT was 71%, 82%, 68% and 85% while that of splenic injuries was 73%, 80%, 55% and 90% respectively. The accuracy of PMCT scan was 79% for both liver and splenic injuries. There is strong association between lower left ribs fracture and splenic injury (p=0.005) and significant association between positive liver and splenic PMCT finding and intraabdominal fatal injury (p=0.037).
CONCLUSION: In conclusion PMCT has high specificity and NPV for liver and splenic injuries; however the sensitivity and PPV are low. The overall accuracy is not high enough to enable PMCT to be used as a replacement for conventional autopsy; however it is a useful complementary examination and has potential to be used as decision making tool for selective internal autopsy.
METHODS: For experiments, the autopsy reports belonging to eight different causes of death were collected, preprocessed and converted into 43 master feature vectors using various schemes for feature extraction, representation, and reduction. The six different text classification techniques were applied on these 43 master feature vectors to construct a classification model that can predict the cause of death. Finally, classification model performance was evaluated using four performance measures i.e. overall accuracy, macro precision, macro-F-measure, and macro recall.
RESULTS: From experiments, it was found that that unigram features obtained the highest performance compared to bigram, trigram, and hybrid-gram features. Furthermore, in feature representation schemes, term frequency, and term frequency with inverse document frequency obtained similar and better results when compared with binary frequency, and normalized term frequency with inverse document frequency. Furthermore, the chi-square feature reduction approach outperformed Pearson correlation, and information gain approaches. Finally, in text classification algorithms, support vector machine classifier outperforms random forest, Naive Bayes, k-nearest neighbor, decision tree, and ensemble-voted classifier.
CONCLUSION: Our results and comparisons hold practical importance and serve as references for future works. Moreover, the comparison outputs will act as state-of-art techniques to compare future proposals with existing automated text classification techniques.
METHODS: We sourced articles from Scopus, Ovid and PubMed databases for journal publications related to post-mortem diagnostic imaging. We highlight the most relevant full articles in English that explain the type of modality that was utilised and the added value it provided for diagnosing the cause of death.
RESULTS: Minimally invasive autopsies assisted by imaging modalities added a great benefit to forensic medicine, and supported conventional autopsy. In particular the role of post mortem computed tomography (PMCT), post mortem computed tomography angiography (PMMR) and positron emission tomography computed tomography (PMCTA) that have incremental benefits in diagnosing traumatic death, fractures, tissue injuries, as well as the assessment of body height or weight for corpse identification.
CONCLUSION: PMCT and PMMR, with particular emphasis on PMCTA, can provide higher accuracy than the other modalities. They can be regarded as indispensable methods that should be applied to the routine autopsy protocol, thus improving the findings and accuracy of diagnosing the cause of death.