Design and Evaluation of an In-Vehicle Real-Time Drunk Driving Detection System
- Conditions
- Impaired DrivingDrunk DrivingAlcohol Drinking
- Interventions
- Other: Driving under the influence of alcoholOther: Driving under the influence of a placebo
- Registration Number
- NCT05796609
- Lead Sponsor
- University of Bern
- Brief Summary
To analyze driving behavior of individuals under the influence of alcohol while driving in a real car. Based on the in-vehicle variables, the investigators aim at establishing algorithms capable of discriminating sober and drunk driving using machine learning.
- Detailed Description
Driving under the influence of alcohol (or "drunk driving") is one of the most significant causes of traffic accidents. Alcohol consumption impairs neurocognitive and psychomotor function and has been shown to be associated with an increased risk of driving accidents. However, autonomous driving (level 4 or 5) is likely to be broadly available only at a substantially later time point than previously thought due to increasing concerns of safety associated with this technology. Therefore, solutions bridging the upcoming time period by more rapidly and directly addressing the problem of drunk driving associated traffic incidents are urgently needed.
On the supposition that driving behavior differs significantly between sober state and drunk state, the investigators assume that different driving patterns of people under alcohol influence compared to sober states can be used to generate drunk driving detection models using machine learning algorithms. In this study, driving for data collection is initially performed at a sober baseline state (no alcohol) and then after alcohol administration (with a target of 0.15 mg/l and 0.35 mg/l breath alcohol concentration).
Recruitment & Eligibility
- Status
- COMPLETED
- Sex
- All
- Target Recruitment
- 55
- Informed consent as documented by signature.
- In possession of a definite Swiss or EU driving license.
- At least 21 years old
- Active driving in the last 6 months.
- No special equipment needed when driving.
- Drinks alcohol at least occasionally (moderate/social consumption).
- Fluent in (Swiss) German and no speech impairment.
- Health concerns that are incompatible with alcohol consumption.
- Any potential participant currently taking illegal drugs or medications that interact with alcohol.
- Women who are pregnant or breast feeding.
- Intention to become pregnant during the course of the study.
- Teetotallers (alcohol abstinent persons).
- Alcohol misuse (excessive alcohol consumption habits/risky drinking behaviour (according to WHO definition) and/or the biomarker PEth in capillary blood > 200 ng/mL at first visit.
- Known or suspected drug abuse within 4 weeks before the study (e.g., positive urine drug test at first visit).
- Non-compliance to alcohol abstinence within 24 hours before the study visits.
- Inability to follow the procedures of the study, e.g., due to language problems, psychological disorders, dementia, etc. of the participant.
- Participation in another study with investigational drug within the 30 days preceding and during the present study.
Study & Design
- Study Type
- INTERVENTIONAL
- Study Design
- PARALLEL
- Arm && Interventions
Group Intervention Description Treatment Group Driving under the influence of alcohol Driving under the influence of alcohol Aware of the possible induction of alcohol (purpose of the study), but blinded to the actual amount and target blood alcohol concentration Placebo Group Driving under the influence of a placebo Driving under the influence of a placebo Not informed (blinded)
- Primary Outcome Measures
Name Time Method Diagnostic accuracy of the drunk driving warning system (DRIVE) to detect states of alcohol influence while driving quantified as the Area Under the Receiver Operator Characteristics Curve (AUROC) 480 minutes The machine learning model is developed and evaluated based on in-vehicle data generated in different states of alcohol intoxication. Detection performance of alcohol influence is quantified as AUROC.
- Secondary Outcome Measures
Name Time Method Diagnostic accuracy of the drunk driving warning system using eye-tracking data to detect states of alcohol influence quantified as the AUROC 480 minutes The machine learning model is developed and evaluated based on eye-tracking data recorded in different states of alcohol intoxication. Detection performance of alcohol influence is quantified as AUROC.
Change of steer torque over the alcohol intoxication trajectory 480 minutes Steer torque is recorded based on the controller area network.
Diagnostic accuracy of the drunk driving warning system using physiological data to detect states of alcohol influence quantified as the Area Under the Receiver Operator Characteristics Curve (AUROC) 480 minutes The machine learning model is developed and evaluated based on physiological wearable data recorded in different states of alcohol intoxication. Detection performance of alcohol influence is quantified as AUROC.
Diagnostic accuracy of the drunk driving warning system using controller area network data of the study car to detect states of alcohol influence quantified as the AUROC 480 minutes The machine learning model is developed and evaluated based on controller area network data of the study car recorded in different states of alcohol intoxication. Detection performance of alcohol influence is quantified as AUROC.
Diagnostic accuracy of the drunk driving warning system using audio data to detect states of alcohol influence quantified as the AUROC 480 minutes The machine learning model is developed and evaluated based on audio data recorded in different states of alcohol intoxication. Detection performance of alcohol influence is quantified as AUROC.
Diagnostic accuracy of the drunk driving warning system using gas sensor data to detect states of alcohol influence quantified as the AUROC 480 minutes The machine learning model is developed and evaluated based on gas sensor data recorded in different states of alcohol intoxication. Detection performance of alcohol influence is quantified as AUROC.
Diagnostic accuracy of the drunk driving warning system using radar sensor data to detect states of alcohol influence quantified as the AUROC 480 minutes The machine learning model is developed and evaluated based on radar sensor data recorded in different states of alcohol intoxication. Detection performance of alcohol influence is quantified as AUROC.
Change of steering over the alcohol intoxication trajectory 480 minutes Steering is recorded based on the controller area network.
Change of steer speed over the alcohol intoxication trajectory 480 minutes Steer speed is recorded based on the controller area network.
Change of velocity over the alcohol intoxication trajectory 480 minutes Velocity is recorded based on the controller area network.
Change of acceleration over the alcohol intoxication trajectory 480 minutes Acceleration is recorded based on the controller area network.
Change of braking over the alcohol intoxication trajectory 480 minutes Braking is recorded based on the controller area network.
Change of gaze acceleration over the alcohol intoxication trajectory 480 minutes Gaze acceleration is recorded using an eye-tracker device.
Change of swerving over the alcohol intoxication trajectory 480 minutes Swerving is recorded based on the controller area network.
Change of spinning over the alcohol intoxication trajectory 480 minutes Spinning is recorded based on the controller area network.
Change of gaze position over the alcohol intoxication trajectory 480 minutes Gaze position is recorded using an eye-tracker device.
Change of gaze velocity over the alcohol intoxication trajectory 480 minutes Gaze velocity is recorded using an eye-tracker device.
Change of gaze regions of interest over the alcohol intoxication trajectory 480 minutes Gaze regions of interest (e.g., windshield, car dashboard, etc.) are recorded using an eye-tracker device.
Change of gaze events over the alcohol intoxication trajectory 480 minutes Gaze events (e.g., fixations, saccades, etc.) are recorded using an eye-tracker device.
Change of head pose over the alcohol intoxication trajectory 480 minutes Head pose (position/rotation) is recorded using an eye-tracker device.
Change of heart rate over the alcohol intoxication trajectory 480 minutes Heart rate is recorded using a heart rate monitoring device and wearables.
Change of heart rate variability over the alcohol intoxication trajectory 480 minutes Heart rate variability is recorded using a heart rate monitoring device and wearables.
Change of electrodermal activity over the alcohol intoxication trajectory 480 minutes Electrodermal activity is recorded using wearables.
Change of wrist accelerometer measurements over the alcohol intoxication trajectory 480 minutes Wrist accelerometer measurements are recorded using wearables.
Change of skin temperature over the alcohol intoxication trajectory 480 minutes Skin temperature is recorded using wearables.
Self-assessment of driving performance over the alcohol intoxication trajectory 480 minutes Participants rate their driving performance on a 7-point Likert Scale (lower value means poorer driving performance).
Self-estimation of alcohol concentrations over the alcohol intoxication trajectory 480 minutes Participants estimate their blood alcohol concentration.
Number of driving mishaps over the alcohol intoxication trajectory 480 minutes Any driving mishaps, accidents and interventions by the driving instructor will be documented.
Number of Adverse Events (AEs) 3 months, from screening to close out visit for each participant Adverse Events will be recorded at each study visit.
Number of Serious Adverse Events (SAEs) 3 months, from screening to close out visit for each participant. Serious Adverse Events will be recorded at each study visit.
Trial Locations
- Locations (1)
Institut für Rechtsmedizin
🇨ðŸ‡Bern, Switzerland