Potential risk of driving performance under combined conditions of taking second-generation antihistamines and attending calls using a hands-free function.

OBJECTIVE: Although second-generation antihistamines have reduced sedation-related side effects compared to first-generation antihistamines, sedation may still impair motor vehicle driving performance. Moreover, receiving/making phone calls using a hands-free function can negatively affect driving performance. Therefore, herein, driving performance was evaluated using a driving simulator to gain insights into the hazards of driving by combining second-generation antihistamines and a calling task, i.e., simulated calls using a hands-free function. METHODS: In this study, 20 subjects drove in a driving simulator in the absence or presence of a calling task while taking or not taking second-generation antihistamines. Driving performances for nonemergency and emergency events were determined, and a comparative analysis of intra-individual variability when taking and not taking second-generation antihistamines was conducted. RESULTS: First, when nonemergency and emergency were examined in the absence of a calling task, no significant difference in driving performance was observed between taking and not taking second-generation antihistamines. Next, when the nonemergency event was examined in the presence of a calling task, no significant difference in driving performance was observed between taking and not taking second-generation antihistamines. However, when the emergency event was examined in the presence of a calling task, a significant difference in driving performance was observed between taking and not taking second-generation antihistamines, thus resulting in reduced driving performance. CONCLUSIONS: The new system with added calling tasks allowed the extraction of the potential risks of driving performance of second-generation antihistamines that may have been previously overlooked. This study suggests that pharmacists and other healthcare professionals may need to instruct people taking any second-generation antihistamine to focus on driving and not on subtasks that require cognitive load such as talking while driving.

Learning and predicting the unknown class using evidential deep learning.

In practical deep-learning applications, such as medical image analysis, autonomous driving, and traffic simulation, the uncertainty of a classification model's output is critical. Evidential deep learning (EDL) can output this uncertainty for the prediction; however, its accuracy depends on a user-defined threshold, and it cannot handle training data with unknown classes that are unexpectedly contaminated or deliberately mixed for better classification of unknown class. To address these limitations, I propose a classification method called modified-EDL that extends classical EDL such that it outputs a prediction, i.e. an input belongs to a collective unknown class along with a probability. Although other methods handle unknown classes by creating new unknown classes and attempting to learn each class efficiently, the proposed m-EDL outputs, in a natural way, the "uncertainty of the prediction" of classical EDL and uses the output as the probability of an unknown class. Although classical EDL can also classify both known and unknown classes, experiments on three datasets from different domains demonstrated that m-EDL outperformed EDL on known classes when there were instances of unknown classes. Moreover, extensive experiments under different conditions established that m-EDL can predict unknown classes even when the unknown classes in the training and test data have different properties. If unknown class data are to be mixed intentionally during training to increase the discrimination accuracy of unknown classes, it is necessary to mix such data that the characteristics of the mixed data are as close as possible to those of known class data. This ability extends the range of practical applications that can benefit from deep learning-based classification and prediction models.