Decisions on driving after brain injury/disease: Feasibility and construct validity of a new simulator assessment tool

Samuelsson, Kersti; Wressle, Ewa

doi:10.1177/0308022620950986

Cited by 4 publications

(11 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ashendorf et al [29] investigated the average TMT scores among cognitively normal older adults and adults with mild cognitive impairment (MCI). In [30], patients with cognitive dysfunction took a driving test; their UFOV test scores were examined in the passing and failing groups.…”

Section: Trail Making Test (Tmt)mentioning

confidence: 99%

“…Therefore, we segment arterial road and intersection data further with various durations and extract features from each segmented road. We segment arterial data so that the average number of seconds for each segment are [All,60,30,15,10,5,3]. "All" means no division, i.e., whole arterial road (with an average of 355 s).…”

Section: Segmentation With Various Durationsmentioning

confidence: 99%

“…The TMT and MAZE scores are expressed in seconds, and the UFOV test scores are expressed in milliseconds. The red and black lines indicate the MCI and cognitively normal standards in[29] or passing the driving test in[30]. The average TMT (A), TMT (B), MAZE, and UFOV scores of the subjects were 34.1, 94.9, 26.3, and 151.4, respectively.…”

mentioning

confidence: 99%

“…Table 10 shows the relative proportion without normalization, and the right side shows that with normalization. The unnormalized importance of segments[All, 60,30,15,10,5,] …”

mentioning

confidence: 99%

See 3 more Smart Citations

Psychological Characteristics Estimation from On-Road Driving Data

Kimura,

Tanaka,

Yoshihara

et al. 2022

Social Computing and Social Media: Design, User Experience and Impact

View full text Add to dashboard Cite

Driving assistance systems that support drivers by adapting individual psychological characteristics can provide appropriate feedback and prevent traffic accidents. As a first step toward implementing such adaptive assistance systems, this research aims to develop a model to estimate drivers' psychological characteristics, such as cognitive function, psychological driving style, and workload sensitivity, from on-road driving behavioral data using machine learning and deep learning techniques. We also investigated the relationship between driving behavior and various cognitive functions including the Trail Making test and Useful Field of View test through regression modeling. The proposed method focuses on road type information and captures various durations of time-series data observed from driving behaviors. First, we segment the driving time-series data into two road types, namely, arterial roads and intersections, to consider driving situations. Second, we further segment data into many sequences of various durations. Third, statistics are calculated from each sequence. Finally, these statistics are used as input features of machine learning models to predict psychological characteristics. The experimental results show that our model can predict a driver's cognitive function, namely, the Trail Making Test version B and Useful Field of View test scores, with Pearson correlation coefficients r of 0.579 and 0.557, respectively. Some characteristics, such as psychological driving style and workload sensitivity, are predicted with high accuracy, but whether various duration segmentation improves accuracy depends on the characteristics, and it is not effective for all characteristics. Additionally, we reveal important sensor and road types for the estimation of cognitive function.

show abstract

Section: Trail Making Test (Tmt)mentioning

confidence: 99%

Section: Segmentation With Various Durationsmentioning

confidence: 99%

mentioning

confidence: 99%

“…Table 10 shows the relative proportion without normalization, and the right side shows that with normalization. The unnormalized importance of segments[All, 60,30,15,10,5,] …”

mentioning

confidence: 99%

See 2 more Smart Citations

Psychological Characteristics Estimation from On-Road Driving Data

Kimura,

Tanaka,

Yoshihara

et al. 2022

Social Computing and Social Media: Design, User Experience and Impact

View full text Add to dashboard Cite

show abstract

“…On-road driving is considered the golden standard regarding assessing driving capacity and driving behavior, since it has high face validity ( Mathias and Lucas, 2009 ; Samuelsson and Wressle, 2021 ). However, on-road assessments might be impractical, costly and have shown to be stressful to older drivers ( Lee et al, 2003 ).…”

Section: Introductionmentioning

confidence: 99%

Validation of a computerized driving simulator test of cognitive abilities for fitness-to-drive assessments

Gårdinger,

Johansson,

Lidestam

et al. 2024

Front. Psychol.

View full text Add to dashboard Cite

BackgroundDriving requires a series of cognitive abilities, many of which are affected by age and medical conditions. The psychosocial importance of continued driving ushers the need for valid measurements in fitness-to-drive assessments. A driving simulator test could prove useful in these assessments, having greater face validity than other off-road tests and being more cost-effective and safer than ordinary on-road testing. The aim of this study was to validate a driving simulator test for assessment of cognitive ability in fitness-to-drive assessments.MethodsThe study included 67 healthy participants. Internal consistency of the simulator subtests was estimated. A correlation analysis between results on the simulator and the cognitive tests Trail Making Test (TMT) A and B and the Useful field of View test (UFOV) and multiple regression analysis were conducted. Finally, a comparison of results between age groups (>65 years) and (<65 years) was done.ResultsResults showed good internal consistency. Significant and moderate correlations were found for all reaction time in the simulator’s subtests and UFOV 3, and all but two with TMT A. Lane positioning in the simulator showed significant and low to moderate correlations with UFOV 3 in all subtests. Reaction time and Double reaction time on subtest 3 were significantly correlated with UFOV 2 and UFOV 3 and TMT A, respectively. Test on Centerline (position) in subtest 3 as dependent variable was significantly correlated with UFOV 3. Significant means differences and large effect sizes between the age groups were found for all reaction time and lane positioning tests.ConclusionThe findings of concurrent validity, especially with TMT A and UFOV 3 and its sensitivity for age-related differences, indicate potential for the simulator to be used as a complement in fitness-to-drive assessments. However, a clinical study is necessary to further examine its usefulness for patients with cognitive deficits.

show abstract

Estimating Driver Personality Traits From On-Road Driving Data

Kimura,

Tanaka,

Yoshihara

et al. 2023

IEEE Access

View full text Add to dashboard Cite

This paper focuses on the estimation of a driver's psychological characteristics using driving data for driving assistance systems. Driving assistance systems that support drivers by adapting individual psychological characteristics can provide appropriate feedback and prevent traffic accidents. As a first step toward implementing such adaptive assistance systems, this research aims to develop a model to estimate drivers' psychological characteristics, such as cognitive function, psychological driving style, and workload sensitivity, from on-road driving behavioral data using machine learning and deep learning techniques. We also investigated the relationship between driving behavior and various cognitive functions, including the Trail Making Test (TMT) and Useful Field of View (UFOV) test, through regression modeling. The proposed method focuses on road type information and captures various durations of time-series data observed from driving behaviors. First, we segment the driving time-series data into two road types, namely, arterial roads and intersections, to consider driving situations. Second, we further segment data into many sequences of various durations. Third, statistics are calculated from each sequence. Finally, these statistics are used as input features of machine learning models to estimate psychological characteristics. The experimental results show that our model can estimate a driver's cognitive function, namely, the TMT (B) and UFOV test scores, with Pearson correlation coefficients r of 0.579 and 0.708, respectively. Some characteristics, such as psychological driving style and workload sensitivity, are estimated with high accuracy, but whether various duration segmentation improves accuracy depends on the characteristics, and it is not effective for all characteristics. Additionally, we reveal important sensor and road types for the estimation of cognitive function.

show abstract

Decisions on driving after brain injury/disease: Feasibility and construct validity of a new simulator assessment tool

Cited by 4 publications

References 21 publications

Psychological Characteristics Estimation from On-Road Driving Data

Psychological Characteristics Estimation from On-Road Driving Data

Validation of a computerized driving simulator test of cognitive abilities for fitness-to-drive assessments

Estimating Driver Personality Traits From On-Road Driving Data

Contact Info

Product

Resources

About