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: This is a retrospective non-randomized study of outcomes and tumor recurrence of all patients diagnosed with mandibular ameloblastoma from August 1997 until August 2017 (20 years) requiring free fibula osteocutaneous flap reconstruction at a single institution. The patients were identified through an electronic operative database; subsequently, their medical records and photo documentation were retrieved.
RESULTS: Twenty-seven patients were included in this study. Eighteen patients were male, while nine were female. The majority of the patients (48.1%) were in their third decade of life when they were diagnosed with ameloblastoma. All of them underwent radical resection of the tumor with a surgical margin of 2 cm (hemimandibulectomy in cases with a large tumor) and immediate mandibular reconstruction with a free fibula osteocutaneous flap. Two patients required revision of a vascular anastomosis due to venous thrombosis postoperatively, while one patient developed a flap recipient site infection. The flap success rate was 100%. There was no tumor recurrence during a mean follow-up period of 5.6 years.
CONCLUSIONS: Mandibular ameloblastoma should be treated with segmental mandibulectomy (with a surgical margin of 2 cm) to reduce the risk of recurrence. Subsequent mandibular and adjacent soft tissue defects should be reconstructed immediately with a free fibula osteocutaneous flap.
METHODS: This is a nationwide retrospective audit on the documentation of Dabigatran Prescribing and Dispensing Checklist for a period of two years from January 2013 till December 2014. Data from these Dabigatran Checklists (indication, dose, duration, renal function and adverse drug reactions encountered) were extracted by the pharmacist at MOH healthcare facilities.
RESULTS: A total of 52 out of 56 (92.9%) of MOH facilities complied to usage of checklist at their centres involving a total of 582 patients of which 569 (97.7%) patients were initiated on dabigatran for the approved indications. The recommended dose of dabigatran was used correctly in 501 (99.6%) of patients. Reason for switching to DOACs use was only documented in 76.7% (131/171) of patients. The most common reason for switching from warfarin was poor INR control (n=39), history of bleeding/overwarfarinisation (n=22) and unable to attend regular INR clinic (n=21). There were 75 cases of adverse events reported. The most common adverse event reported were abdominal discomfort (n=10) followed by gum bleeding (n=9) and dizziness (n=5).
CONCLUSIONS: Compliance to the dabigatran check list was high with 70% of patients prescribed the appropriate dosing.