MATERIALS AND METHODS: The questionnaire was distributed in eight major cities in West Malaysia during the World Health Digestive Day (WDHD) campaign. Two thousand four hundred and eight respondents participated in this survey.
RESULTS: Generally, awareness of colorectal cancer was found to be relatively good. Symptoms such as change in bowel habit, blood in the stool, weight loss and abdominal pain were well recognized by 86.6%, 86.9%, 83.4% and 85.6% of the respondents, respectively. However, common risk factors such as positive family history, obesity and old age were acknowledged only by less than 70% of the respondents. Almost 80% of the respondents are willing to take the screening test even without any apparent symptoms. Colonoscopy is the preferred screening method, but only 37.5% were willing to pay from their own pocket to get early colonoscopy.
CONCLUSIONS: Continous cancer education should be promoted with more involvement from healthcare providers in order to make future colorectal cancer screening programs successful.
METHOD: A total of 2247 PET/CT patients with normal glucose level underwent 18F-FDG-whole body imaging procedures. The 18F-FDG dose of 3.7MBq per kg of patient weight administered via intravenous infusion. For CT parameters, kilovoltage of 140keV and current of 40 mAs were used for all studies. All the acquired images collected retrospectively and the effective dose was calculated for each patient using algorithm adapted from ICRP Publication 106, modified for patient weight and patient blood volume. The estimated effective doses were evaluated for patients' body weight and BMI.
RESULTS: The mean of total effective dose and standard deviation is approximately 15.08(4.52) mSv using ICRP algorithm. 56% of total patient has normal BMI and their average total effective dose is 13.6mSv. Underweight patients' effective dose can be as low as 9.6mSv even using diagnostic CT protocols.
CONCLUSION: The effective dose of PET/CT procedure in present study is one of the lowest although using diagnostic parameters for CT acquisition compared to published data worldwide. This is due to the improved sensitivity of PET and complex reconstruction technique that maintains the image quality. A significant association between body weight, BMI and effective dose is reported in present study. Therefore, it is suggested that attention must be given for underweight and ideal BMI patients while prescribing FDG activity and CT imaging parameters in order to minimize the effective dose. The effective dose reported in present study can be considered as an upper limit for effective dose in PET/CT patients with normal BMI. This upper limit can be treated as a standard limit when optimizing imaging parameters, developing algorithm for image reconstruction and prescribing activity for patients. This practice could fulfill ALARA principle that could reduce cancer risk.
RESULT: We tested Naive Bayes, Logistic Regression, KNN, J48, Random Forest, SVM, and Deep Neural Network algorithms to ASD screening dataset and compared the classifiers' based on significant parameters; sensitivity, specificity, accuracy, receiver operating characteristic, area under the curve, and runtime, in predicting ASD occurrences. We also found that most of previous studies focused on classifying health-related dataset while ignoring the missing values which may contribute to significant impacts to the classification result which in turn may impact the life of the patients. Thus, we addressed the missing values by implementing imputation method where they are replaced with the mean of the available records found in the dataset.
CONCLUSION: We found that J48 produced promising results as compared to other classifiers when tested in both circumstances, with and without missing values. Our findings also suggested that SVM does not necessarily perform well for small and simple datasets. The outcome is hoped to assist health practitioners in making accurate diagnosis of ASD occurrences in patients.