RESULTS: Prediction in two and three state classification systems with several thresholds are provided. Our prediction method achieved the accuracy level upto 90% for training and 88% for test data sets. Three state prediction results provide a maximum 65% accuracy for training and 63% for the test data. Applicability of neural networks for ASA prediction has been confirmed with a larger data set and wider range of state thresholds. Salient differences between a linear and exponential network for ASA prediction have been analysed.
AVAILABILITY: Online predictions are freely available at: http://www.netasa.org. Linux ix86 binaries of the program written for this work may be obtained by email from the corresponding author.
OBJECTIVES: This paper aims to identify requirements in developing a breast examination awareness mobile app based on the component of the Health Belief Model (HBM) for integration in health promotion strategy.
METHODS: A qualitative approach using semi-structured in-depth interview was utilized in this study. A purposive sampling method was conducted among public women attending hospital services, software and content experts in a tertiary teaching hospital in the East coast of Peninsular Malaysia. These interviews were recorded, transcribed and organized using NVIVO 11. The main themes were identified through thematic analysis of the interview transcripts. Results: A total of 37 participants recruited in this study. The themes that emerged from the analysis are vulnerability, forecasting, reactive, influence, outcome and obstacles. The sub-themes findings supported the HBM's component in terms of the requirement for are an infographic risk factor, video (symptoms, self-examination), info (metastasis, survival, screening, triple assessment, treatment, myth and facts, benefit of early treatment, support groups), features (screening reminder, sharing button, prompt) and mobile app's design.
CONCLUSION: The research findings could provide a guide for future app development from public women, content and software experts. The information will be used to develop a breast examination awareness mobile app integrated with health theories.
METHODS: The system typically consists of segmenting the calcium region from the CT scan into slices based on Hounsfield Unit-based threshold, and subsequently computing the summation of the calcium areas in each slice. However, when the carotid volume has intermittently higher concentration of contrast agent, a dependable approach is adapted to correct the calcium region using the neighboring slices, thereby estimating the correct volume. Furthermore, mitigation is provided following the regulatory constraints by changing the system to semi-automated criteria as a fall back solution. We evaluate the automated and semi-automated techniques using completely manual calcium volumes computed based on the manual tracings by the neuroradiologist.
RESULTS: A total of 64 patients with calcified plaque in the internal carotid artery were analyzed. Using the above algorithm, our automated and semi-automated system yields correlation coefficients (CC) of 0.89 and 0.96 against first manual readings and 0.90 and 0.96 against second manual readings, respectively. Using the t-test, there was no significant difference between the automated and semi-automated methods against manual. The intra-observer reliability was excellent with CC 0.98.
CONCLUSIONS: Compared to automated method, the semi-automated method for calcium volume is acceptable and closer to manual strategy for calcium volume. Further work evaluating and confirming the performance of our semi-automated protocol is now warranted.
PURPOSE: The purpose of this observational study was to measure the prevalence of the presence of the anterior loop and to estimate sex and ethnicity-related variations in anterior loop length in the Malaysian population.
MATERIAL AND METHODS: A total of 100 cone beam computed tomography (CBCT) Digital Imaging and Communications in Medicine (DICOM) files were selected from a pool of 810 ongoing or completed patients in 3 different ethnic groups: Malay (33), Indian (33), and Chinese (34). The DICOM data were imported into commercial software. The IAN was traced with software along with the anterior loop and part of the incisive nerve. The vertical length of the nerve was estimated from the canal to the opening of the mental foramen from the cross-sectional view and translated to the panoramic view. Measurement was made from this point to the most anterior point of the anterior loop by following the trajectory of the nerve and was repeated on the opposite side. A 2-way mixed analysis of variance (ANOVA) test was carried out to evaluate the sex- and ethnicity-related variations (α=.05).
RESULTS: The anterior loop was present in 94% of the 100 participants. Overall anterior loop length (AnLL) ranged between 0.73 and 7.99 mm with a mean length of 3.69 ±1.75 mm on the left side and 3.85 ±1.73 mm on the right side. Among all participants, no statistically significant differences were found between the left and right sides of the mandible (P=.379). Overall, no significant main effect of ethnicity (P=.869) or sex (P=.576) was found on AnLL measurements. Also, with multiple comparisons, no significant effect was found between each pair of ethnic groups. Men in all 3 ethnic groups had greater AnLL than women.
CONCLUSIONS: The anterior loop was present in 94% of the 100 participants among the 3 major ethnic groups of Malaysia. Overall AnLL ranged between 0.73 and 7.99 mm and mean lengths of 3.69 ±1.75 mm on the left side and 3.85 ±1.73 mm on the right side, with no significant ethnicity- or sex-related variations.