RESUMO
OBJECTIVE: The aim of this study was to employ artificial intelligence (AI) via convolutional neural network (CNN) for the separation of oral lichen planus (OLP) and non-OLP in biopsy-proven clinical cases of OLP and non-OLP. MATERIALS AND METHODS: Data comprised of clinical photographs of 609 OLP and 480 non-OLP which diagnosis has been confirmed histopathologically. Fifty-five photographs from the OLP and non-OLP groups were randomly selected for use as the test dataset, while the remaining were used as training and validation datasets. Data augmentation was performed on the training dataset to increase the number and variation of photographs. Performance metrics for the CNN model performance included accuracy, positive predictive value, negative predictive value, sensitivity, specificity, and F1-score. Gradient-weighted class activation mapping was also used to visualize the important regions associated with discriminative clinical features on which the model relies. RESULTS: All the selected CNN models were able to diagnose OLP and non-OLP lesions using photographs. The performance of the Xception model was significantly higher than that of the other models in terms of overall accuracy and F1-score. CONCLUSIONS: Our demonstration shows that CNN models can achieve an accuracy of 82 to 88%. Xception model performed the best in terms of both accuracy and F1-score.
RESUMO
Bus accidents are a serious issue, with high rates of injury and fatality in Thailand. However, no studies have been conducted on the factors affecting bus accident severity in Thailand. A cross-sectional study was conducted by the Department of Highways, Thailand over the 2010-2019 period. A multinomial logit model was used to evaluate the factors associated with bus accident severity. This model divided accidents into three categories: non-injury, injury, and fatality. The risk factors consisted of three major categories: the bus driver, characteristics of the crash, and environmental characteristics. The results showed that characteristics of the bus driver, the crash, and the environment where the crash occurred all increased the probability of bus accidents causing injury. These three main factors included driving on sloped roads (relative risk ratio [RRR] 3.03, 95% confidence level [CI] 1.73 to 5.30), drowsy driving (RRR 2.60, 95% CI 1.71 to 3.96), and driving in the wrong direction (RRR 2.37, 95% CI 1.77 to 3.19). Moreover, the factors that increased the probability of the accidents causing fatality were drowsy driving (RRR 3.40, 95% CI 2.07 to 5.57) and drivers not obeying or following traffic rules (RRR 3.02, 95% CI 1.95 to 4.67), especially in the northern part of Thailand (RRR 3.01, 95% CI 1.98 to 4.62). The results can provide a valuable resource to help road authorities in development targeting road safety programs at sloped roads in the northern part of Thailand. Stakeholders should increase road safety efforts and implement campaigns, such as raising public awareness of the risks of not obeying or following traffic rules and drowsy driving which could possibly reduce the risk of both injury and fatality.
