Driving Skills in HIV-Infected Patients Well Controlled with Antiretroviral Therapy

A study was made to determine whether HIV-infected patients with prolonged virological control suffer subclinical neurocognitive problems capable of interfering with driving skills, compared with the general population, and to explore the possible existence of differences between those treated with and without efavirenz. Material and Methods: We included 40 patients without history of neoplasm, psychiatric disorders or infections of the central nervous system associated or not to HIV, with stable and effective antiretroviral therapy during at least 48 months. Use was made of the ASDE DRIVER TEST N-845 standardized by the Spanish traffic authorities, and for which data corresponding to the Spanish general population were obtained from the manufacturer of the test battery. The Student t-test was used to compare the different variables with the population standards, and the comparison of proportions Z-statistic was used to determine the proportion of subjects above the accepted limit of normality cutoff point. These analyses were replicated for the two sub-samples (with or without efavirenz therapy), with a 95% confidence level. The SPSS version 15 statistical package and Epidat 3.1 program were used. Results: The scores obtained in the HIV group were significantly poorer in the anticipation speed tests and in one of the multiple reactions test, though better results were obtained in the bimanual visual-motor coordination test. There were no differences in the percentages of patients with scores below the recommended limits. On comparing the treatment subgroups (efavirenz versus protease inhibitor), no differences were recorded in any of the study variables, and the differences with respect to the general population were the same as those described for the global group. Conclusions: Little differences were observed in driving skills in HIV well controlled HIV patients of minor clinical significance, and no differences were found in driving skills between the patients administered Efavirenz and those receiving protease inhibitor treatments.

Driving skill classification in curve driving scenes using machine learning

Driver support and infotainment systems can be adapted to the specific needs of individual drivers by assessing driver skill and state. In this paper, we present a machine learning approach to classifying the skill at maneuvering by drivers using both longitudinal and lateral controls in a vehicle. Conceptually, a model of drivers is constructed on the basis of sensor data related to the driving environment, the drivers＇ behaviors, and the vehi- cles＇ responses to the environment and behavior together. Once the model is built, the driving skills of an unknown driver can be classified automatically from the driving data. In this paper, we demonstrate the feasibility of using the proposed method to assess driving skill from the results of a driving simulator. We experiment with curve driving scenes, using both full curve and segmented curve sce- narios. Six curves with different radii and angular changes were set up for the experiment. In the full curve driving scene, principal component analysis and a support vector machine-based method accurately classified drivers in 95.7 % of cases when using driving data about high- and low/average-skilled driver groups. In the cases with seg- mented curves, classification accuracy was 89 %.