ABSTRACT
The fatalities associated with driving while intoxicated (DWI) are on the rise, leading to a staggering twelve thousand people dying from it and nine lakh people getting arrested every year. DWIs are usually confirmed with the use of breathalyzers, which require the subject to blow into the machine. In light of the current pandemic caused by COVID-19, a susceptible individual may deny blowing into the machine. Thus, the need for a contactless method to detect if someone is drunk arises, so that suspects are prevented from taking advantage of the situation. This also assists law enforcement in the detection of DWI cases. The proposed study is the method to detect intoxication in a given suspect through Graph Neural Networks using facial landmarks. We also present a labeled dataset as a complementary dataset for intoxication detection. This dataset is the first graph-based data available for the detection of alcohol intoxication. Extensive experiments were carried out to validate this approach. © 2021 IEEE.
ABSTRACT
Background: Vaccination for severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) has already resulted in a reduction in new infection and mortality cases. Preliminary reports indicate variable and reduced antibody response in multiple sclerosis (MS) patients treated with different disease-modifying therapies (DMTs). Objective and Aim: To determine the effects of different DMT on the humoral response after COVID-19 vaccination in MS patients. Methods: A total of 154 MS patients were vaccinated with one of three available SARS-CoV-2 vaccines (BNT162b2, mRNA-1273, and Ad26.COV2.S). The humoral response was determined by measurement of either unspecific IgG antibodies or anti-spike IgG antibodies. The time between vaccination and serological testing and time from the last infusion date (if applicable) to testing were determined. Humoral response greater than 1.0 was considered as positive and suggestive of acquired immunity. Results: Overall, 89 out of 127 (70.1%) and 15 out of 27 (55.6%) MS patients had a positive anti-S1 test and unspecific IgG test, respectively. Excluded from the analysis were two patients who had only one dose of the mRNA vaccine with negative seroconversion and four patients with a history of SARS-CoV-2 PCRpositive test and positive seroconversion. In the remaining sample, there were no sex and age differences in seroconversion (both p>0.05). Based on DMT groups, seroconversion was seen in 22/26 (84.6%) patients treated with interferon-β, 18/19 (94.7%) on glatiramer acetate, 14/16 (87.5%) on natalizumab, 6/10 (60%) on teriflunomide, 3/8 (37.5%) on sphingosine-1-phosphate (S1P) modulators, 9/9 (100%) on dimethyl fumarate, 0/3 (0%) on cladribine (but all of these patients had prior ocrelizumab from 8 to 9 months prior), 4/28 (14.3%) on anti-CD20 depleters, and 3/5 (60%) on off-label medications. 87.5% (21/24) of non-treated MS patients had positive seroconversion. Seroconverted MS patients treated with anti-CD20 had numerically greater time from the last infusion to the first vaccination (162.3 vs. 80.9 days). Conclusion: MS patients treated with B-cell depleting medications and S1P modulators have significantly lower seroconversion after COVID-19 vaccination when compared to DMT-naive patients and other DMT groups. Future studies should determine the risk of severe clinical outcomes in vaccinated patients with no evidence of seroconversion.