Car accidents in drivers with Parkinson's disease or multiple sclerosis: A Swedish nationwide study.

BACKGROUND AND PURPOSE: Parkinson's disease (PD) and multiple sclerosis (MS) can impair driving. However, we lack evidence on car accidents associated with these diseases. The aims of this study were to examine what types of car accident were associated with drivers with PD and MS, compared to individuals with ulcerative colitis (UC; the comparison group), and to evaluate the occurrence of car accidents in relation to years since diagnosis. METHODS: This retrospective nationwide, registry-based study included drivers involved in car accidents between 2010 and 2019, based on the Swedish Traffic Accident Data Acquisition database. Data on pre-existing diagnoses were retrieved retrospectively from the National Patient Registry. Data analyses included group comparisons, time-to-event analysis, and binary logistic regression. RESULTS: In total, 1491 drivers, including 199 with PD, 385 with MS, and 907 with UC, were registered to have been involved in a car accident. The mean time from diagnosis to the car accident was 5.6 years for PD, 8.0 years for MS, and 9.4 years for UC. Time to car accident since diagnosis differed significantly (p < 0.001) among groups (adjusted for age). Drivers with PD had more than twice the odds of a single-car accident than drivers with MS or UC, but no differences were observed between MS and UC. CONCLUSIONS: Drivers with PD were older and experienced the car accident within a shorter timeframe after disease diagnosis. Although several factors may cause a car accident, fitness to drive could be more thoroughly evaluated for patients with PD by physicians, even early after the diagnosis.

A qualitative study exploring the experiences and needs of people living with young onset dementia related to driving cessation: 'It's like you get your legs cut off'.

BACKGROUND: driving disruptions have significant impact on individuals living with dementia, their care partners and family members. Previous studies show that for older people with dementia, stopping driving is one of the hardest things that they cope with. To date, no studies exist that address the expressed needs and experiences of people living with young onset dementia (YOD) who are adjusting to life without driving, whose needs are not well understood and whose needs might be expected to differ from those of older people with dementia. METHODS: a multi-perspective, qualitative descriptive phenomenological approach was undertaken. A topic guide was developed in consultation with lived experience experts. In-depth interviews (n = 18) with 10 people with YOD and eight family caregivers were conducted, to elicit lived experiences in relation to changing and cessation of driving. Interviews were recorded and transcribed verbatim. Data were analysed using a hybrid approach, employing deductive and inductive coding. RESULTS: core findings reflected the impact and coping strategies employed by people with YOD and their care partners across four themes: (i) losses and burdens, (ii) the unique challenges of YOD, (iii) coping and adjustment and (iv) how to meet needs. CONCLUSIONS: driving disruptions often come at a time when people living with YOD are likely to have significant financial and family commitments, or they/their partners may be employed or raising a family, negatively impacting individual's roles and self-identities. Intervention to support emotional and practical adjustment and reduce social isolation is essential for coping.

Non-cognitive factors associated with driving cessation among older adults: An integrative review.

Exploring the factors that affect driving cessation is crucial, because sustained mobility plays an important role in successful aging. This study aimed to collect evidence on the non-cognitive factors associated with driving cessation among older adults. The method used in this study was an integrated review of published research on the factors affecting driving cessation. A comprehensive search was performed using electronic databases including PubMed, Web of Science, Scopus, CINHAL, ProQuest, EBSCO, and Google Scholar. The results revealed six main categories (physical health, psychological health, interpersonal influence, transportation support, policies, and sociodemographic characteristics) and 24 subcategories for driving cessation. Given the potentially serious consequences of driving cessation in the older adult population, exploring the predictors of driving cessation can be used to design interventions for optimizing drivers' health, rehabilitating the functional limitations that affect driving ability, creating a safer driving environment, and optimizing vehicles to meet the needs of older drivers.

Frequency and correlates of driving status among the oldest old: results from a large, representative sample.

BACKGROUND/AIMS: In the light of the restricted knowledge, our aim was to explore the frequency and correlates of driving status among the oldest old. METHODS: Data came from the representative "Survey on quality of life and subjective well-being of the very old in North Rhine-Westphalia (NRW80 +)" consisting of community-dwelling and institutionalized individuals ≥ 80 years residing in the most populous German state (North Rhine-Westphalia; n = 1,832 in the analytical sample, mean age: 86.5 years). The present driving status (no; yes, I drive myself; yes, as a passenger; yes, as driver and passenger) served as outcome measure. RESULTS: Overall, 43.62% (95% CI 40.98-46.29%) of the individuals did not drive, whereas 30.12% (95% CI 27.75-32.59%) of the individuals drove by themselves, 20.97% (95% CI 18.91-23.20%) of the individuals drove as a passenger, and 5.29% of the individuals drove both (by themselves and as a passenger) (95% CI 4.16-6.71%). Multinomial logistic regressions showed, e.g., that being male (RRR: 0.13, 95% CI 0.09-0.18), younger age (RRR: 0.88, 95% CI 0.84-0.91), being married and living together with spouse (RRR: 1.48, 95% CI 1.08-2.02), living in a private household (RRR: 0.04, 95% CI 0.01-0.35), better self-rated health (RRR: 1.26, 95% CI 1.02-1.56), and lower functional impairment (RRR: 19.82, 95% CI 12.83-30.62) were positively associated with 'Yes, I drive myself' (compared to not driving a car). DISCUSSION/CONCLUSIONS: A sizable proportion of the individuals aged 80 years and above still drove by themselves. Less than half of the oldest old individuals did not drive. Moreover, our current study identified some correlates of driving status among individuals in latest life.

Typologies of Canadian young adults who drive after cannabis use: A two-step cluster analysis.

Young adults that drive after cannabis use (DACU) may not share all the same characteristics. This study aimed to identify typologies of Canadians who engage in DACU. About 910 cannabis users with a driver's license (17-35 years old) who have engaged in DACU completed an online questionnaire. Two-step cluster analysis identified four subgroups, based on driving-related behaviors, cannabis use and related problems, and psychological distress. Complementary comparative analysis among the identified subgroups was performed as external validation. The identified subgroups were: (1) frequent cannabis users who regularly DACU; (2) individuals with generalized deviance with diverse risky road behaviors and high levels of psychological distress; (3) alcohol and drug-impaired drivers who were also heavy frequent drinkers; and (4) well-adjusted youths with mild depressive-anxious symptoms. Individuals who engaged in DACU were not a homogenous group. When required, prevention and treatment need to be tailored according to the different profiles.

Professional reasoning of occupational therapy driver rehabilitation interventions.

INTRODUCTION: Driver-trained occupational therapists are advanced practitioners who work with people to help maintain their independence and autonomy through driving. There is a lack of investigation of professional reasoning processes for why interventions are recommended by driver-trained occupational therapists. This research project sought to explore the reasoning of driver-trained occupational therapists when they plan, implement, and reflect on driver rehabilitation interventions. METHODS: In-depth semistructured interviews (n = 7) and one focus group (n = 5) were conducted with 12 experienced driver-trained occupational therapists, comprising a wide range of experience, client populations, and licensing jurisdictions. Data were analysed using a modified template analysis approach. RESULTS: Seven higher order modes that reflect professional reasoning theory and hierarchical models were evident in the work of the driver-trained occupational therapists, with no new modes of reasoning emerging. Ethical reasoning regarding the balance of safety versus client independence was an overarching shared framework, with therapists mostly using interactive and conditional reasoning in practice. Twenty-three second-level themes were identified that exemplify how the reasoning modes operate in practice. Therapists described assessment activity even when solely asked about intervention, indicating the importance of assessment to intervention design. The full hierarchy of reasoning was evident during the rehabilitation phase. CONCLUSION: These findings elucidate the application of professional reasoning in advanced occupational therapy practices and could support driver-trained occupational therapists in making driving rehabilitation recommendations if used in reflective practices.

Clinical predictors of driving simulator performance in drivers with multiple sclerosis.

BACKGROUND: Drivers with multiple sclerosis (MS) may experience visual-cognitive impairment that affects their fitness to drive. Due to limitations associated with the on-road assessment, an alternative assessment that measures driving performance is warranted. Whether clinical indicators of on-road outcomes can also predict driving performance outcomes on a driving simulator are not fully understood. OBJECTIVE: This study examined if deficits in immediate verbal/auditory recall (California Verbal Learning Test-Second Edition; CVLT2-IR) and/or slower divided attention (Useful Field of View™; UFOV2) predicted deficits in operational, tactical, or strategic maneuvers assessed on a driving simulator, in drivers with and without MS. METHODS: Participants completed the CVLT2-IR, UFOV2, and a driving simulator assessment of operational, tactical, and strategic maneuvers. RESULTS: Deficits in immediate verbal/auditory recall and slower divided attention predicted adjustment to stimuli errors, pertaining to tactical maneuvers only, in 36 drivers with MS (vs 20 drivers without MS; F(3, 51) = 6.1, p = 0.001, R2 = 0.3, Radj2=0.2). CONCLUSION: The CVLT2-IR and UFOV2 capture the visual and verbal/auditory recall, processing speed, and divided attention required to appropriately adjust to stimuli in a simulated driving environment. Clinicians may use the CVLT2-IR and UFOV2 as precursors to driving performance deficits in drivers with MS.

The Impact of HIV-Associated Neurocognitive Impairment on Driving Performance in Commercial Truck Drivers.

Driving ability can be diminished amongst people with HIV with associated neurocognitive impairment (NCI). We explore the relationship between HIV status, NCI and driving ability in professional truck drivers. Forty male professional drivers (20 HIV-positive; mean age = 39.20 ± 7.05) completed a neuropsychological test battery, two driving simulator tasks that assessed driving ability, and a driving history and habits questionnaire. A higher proportion of HIV-positive drivers exhibited impaired overall cognitive performance (p ≤ 0.001). Overall, drivers with NCI (defined as z ≤ 1.00) were more likely than those without NCI to crash (p = 0.002). There were no significant between-group (HIV-positive versus HIV-negative) differences with regard to self-reported on-road driving events. Professional drivers with NCI, as measured on a driving simulator, are at increased risk of making driving errors under high-risk conditions compared to their neurocognitively normal counterparts. These data should inform driver health management with regard to annual medical screening and surveillance.

RESUMEN: La capacidad de conducción puede verse disminuida entre las personas con VIH con deterioro neurocognitivo asociado (neurocognitive impairment, NCI). Exploramos la relación entre la situación frente al VIH, el NCI y la capacidad de conducción en conductores profesionales de camiones. Cuarenta conductores profesionales masculinos (20 seropositivos, edad media = 39.20 ± 7.05) completaron una batería de pruebas neuropsicológicas, dos tareas de simulador de conducción que evaluaron la capacidad de conducción y un cuestionario de hábitos y antecedentes de conducción. Una mayor proporción de conductores VIH positivos exhibió un desempeño cognitivo general deficiente (p ≤ 0.001). En general, los conductores con NCI (definido como z ≤ 1.00) tenían más probabilidades de chocar que aquellos sin NCI (p = 0.002). No hubo diferencias significativas entre los grupos (VIH positivo frente a VIH negativo) con respecto a los eventos autoinformados de conducción en carretera. Los conductores profesionales con NCI, según lo medido en un simulador de conducción, tienen un mayor riesgo de cometer errores de conducción en condiciones de alto riesgo en comparación con sus homólogos neurocognitivamente normales. Estos datos deberían informar a la gestión de la salud del conductor en lo que respecta a la vigilancia y los exámenes médicos anuales.

Tightening legal restrictions for drivers with epilepsy in Japan.

Epilepsy is a highly prevalent condition around the world, and many countries impose restrictions on drivers with epilepsy. After toughening the law in Japan, the number of refused driving license applications for patients with epilepsy increased markedly. However, the number of collisions caused by drivers with epilepsy did not decrease.

Return to Driving After Moderate-to-Severe Traumatic Brain Injury: A Traumatic Brain Injury Model System Study.

OBJECTIVE: Describe who is able to return to driving (RTD) after moderate-to-severe traumatic brain injury (TBI), when this occurs, who maintains that activity, and the association with outcome. DESIGN: Cross-sectional descriptive study. SETTING: Eight follow-up sites of the TBI Model Systems (TBIMS) program. PARTICIPANTS: 618 participants enrolled in the TBIMS and 88 caregivers (N=706). INTERVENTIONS: Not applicable. MAIN OUTCOME MEASURES: A survey was completed from 1-30 years postinjury focusing on RTD. Descriptors included demographic information, injury severity, and current employment status. Outcome was assessed at the time of the interview, including depression, quality of life, functional status, and community participation. RESULTS: Of 706 respondents, 78% (N = 552) RTD, but 14% (N = 77) of these did not maintain that activity. Of those who RTD, 43% (N = 192) did so within 6 months of the injury and 92% did so within 24 months postinjury. The percentage of people driving after TBI did not differ significantly based on age at time of injury or follow-up. There were significant differences between drivers and nondrivers with respect to severity of injury, seizures, race, education, employment, rural vs urban setting, marital status, and family income. We performed a multivariate logistic regression to examine the association between driving status and demographic variables, adjusting for other variables in the model. The strongest associations were with current employment, family income, race, seizures, and severity of injury. Driving was associated with greater community participation, better functional outcomes, fewer symptoms of depression, and greater life satisfaction. CONCLUSIONS: Over a span of 30 years, three-quarters of people experiencing moderate-to-severe TBI return to driving a personal vehicle, although not everyone maintains this activity. Employment, race, family income, and seizures are strongly associated with RTD.

Dialysis and driving: an anonymous survey of patients receiving dialysis for end-stage kidney disease.

BACKGROUND: Driving is a complex task requiring multiple cognitive domains and the musculoskeletal system. Cognitive dysfunction is associated with driving impairment. Dialysis patients are known to have a high prevalence of cognitive impairment and other comorbidities, and may be at risk of driving impairment. No Australian guidelines address driving safety in dialysis patients. AIMS: To estimate the proportion of dialysis patients who were driving and those at risk of driving impairment, and to investigate the agreement between objective and subjective markers of risk. METHODS: This single-centre study involved dialysis patients voluntarily completing two questionnaires relating to risk of driving impairment; the first questionnaire focussed on objective markers, and the second questionnaire focussed on subjective markers. Risk of driving impairment was established using pre-determined criteria, and the agreement between objective and subjective markers was estimated using Cohen kappa. RESULTS: A total of 44.8% (99/221) of patients participated; 76.8% (76/99) of participants were driving, and 76.3% (58/76) of drivers were at risk of driving impairment. Factors associated with at-risk driving included post dialysis dizziness, leg weakness or numbness, falling asleep while driving and hypoglycaemia. Sixteen patients reported collisions since commencing dialysis. The questionnaires displayed slight agreement (Cohen kappa = 0.20) between objective and subjective markers. CONCLUSIONS: Dialysis patients are at risk of driving impairment based on self-reported questionnaire responses. Discrepancies between patients' perceptions and objective markers were apparent. Further research into appropriate risk assessments, as well as development of guidelines to aid in determining driving safety in dialysis patients, is needed.

Driving status and health-related quality of life among the oldest old: a population-based examination using data from the AgeCoDe-AgeQualiDe prospective cohort study.

BACKGROUND: It is almost unknown whether the driving status is associated with HRQOL among individuals in highest age. AIMS: Based on a multicenter prospective cohort study, the objective of this study was to examine whether the driving status is associated with health-related quality of life (HRQOL) among the oldest old in Germany. METHODS: Cross-sectional data from follow-up wave 9 (n = 544) were derived from the "Study on Needs, health service use, costs and health-related quality of life in a large sample of oldest-old primary care patients (85+)" (AgeQualiDe). Average age was 90.3 years (± 2.7; 86 to 101 years). The current driver status (no; yes) was used in our analysis. The EuroQoL EQ-5D questionnaire was used to assess HRQOL in this study. RESULTS: Regression analysis showed that being a current driver was associated with the absence of problems in 'self-care' [OR 0.41 (95%-CI 0.17 to 0.98)], and 'usual activities' [OR 0.48 (0.26 to 0.90)], whereas it was not significantly associated with problems in 'pain/discomfort' [OR  0.82 (0.47 to 1.45)] and 'anxiety/depression' [OR  0.71 (0.36 to 1.39)]. Being a current driver was marginally significantly associated with the absence of problems in 'mobility' [OR 0.60 (0.34 to 1.06)]. While being a current driver was not associated with the EQ-VAS in the main model, it was positively associated with the driving status (ß = 5.00, p < .05) when functional impairment was removed from the main model. DISCUSSION: Our findings provide first evidence for an association between driving status and HRQOL among the oldest old. CONCLUSIONS: Future longitudinal studies are required to evaluate a possible causal relationship between driving status and HRQOL in very old individuals.

Fitness to drive practices among non-driver trained occupational therapists in an Australian community-based rehabilitation setting.

INTRODUCTION: Driving is a valued occupation given the independence and freedom it provides. Safe driving performance can be impacted by medical conditions, change in functional status and ageing processes. Occupational therapy driver assessors (OTDAs) provide invaluable driving recommendations; however, this requires specialist training for the therapist and is costly for clients. The number of OTDAs is not expected to meet the growing demand for expert services in this area, and little is known about the practices that non- OTDAs use to assist clients with returning to driving. The aims of this study were to investigate the practices of non-OTDAs in a community-based rehabilitation setting in Australia with respect to knowledge, confidence and skills in assessments, recommendations and outcomes for clients as part of the return to driving process. METHODS: A descriptive study including medical record audits between April and September 2019 and staff surveys were completed at a large metropolitan community-based rehabilitation facility. Descriptive statistics and thematic analysis were used to summarise data. RESULTS: A total of 102 client medical records were audited, and 13 clinician surveys were completed. Medical record audits identified that return to driving was not consistently addressed by occupational therapists. Clinician surveys outlined a lack of knowledge and confidence of return to driving processes and available assessment tools to guide this process. CONCLUSION: All occupational therapists have an ethical obligation to address driving as an activity of daily living; however, non-OTDAs report that they are not equipped for this role. This may negatively impact on driver safety, independence and overall health and well-being of clients in community-based rehabilitation. Further research is indicated to develop evidence-based driving resources to support best practice of non-OTDAs.

Test-retest reliability of touchscreen DriveSafe DriveAware.

INTRODUCTION: This prospective study examines the test-retest reliability of touchscreen DriveSafe DriveAware (DSDA). In a future study, the authors intend assessing the usefulness of DSDA to measure progress of patients undergoing treatment for neurological conditions. Evidence of test-retest reliability is required first. METHODS: Australian adults with current driver's licences (N = 39) aged 20 to 91 years (Mage  = 58) recruited from a convenience sample were assessed with DSDA. The assessment was repeated 6 weeks, 6 months, and 12 months later to match planned assessments of patients undergoing neurosurgical treatment in future research. DSDA classification, DriveSafe subtest score, and DriveAware subtest scores were analysed as a whole sample, and in three age groups. RESULTS: DSDA classification and DriveAware scores were consistent over repeated tests. DriveSafe scores increased between test 1 and 2 (p = .006), and thereafter no significant change from test 2 to 4. DriveSafe scores of older participants (70+ years) increased between test 1 and 2 more notably than younger participants' scores. No DriveSafe scores decreased over time. CONCLUSION: DSDA classification and DriveAware scores demonstrated test-retest reliability for all age groups. DriveSafe scores did not demonstrate test-retest reliability between test 1 and 2 for participants 70+ years. However, DriveSafe scores demonstrated test-retest reliability after test 2, possibly indicating an initial learning effect for the DriveSafe score only. The authors posit that this result may have been influenced by older adults' reduced familiarity with iPad technology at first assessment. Further longitudinal research is required to confirm whether these results are consistent in a sample population with diagnosed cognitive impairment. Future research will assess whether repeated assessment of DSDA may be useful for monitoring and screening cognitive fitness to drive in patients who have undergone neurosurgical treatment and whether declining scores may indicate cognitive changes in ability to drive.

The revision of competency standards for occupational therapy driver assessors in Australia: A mixed methods approach.

INTRODUCTION: Competency standards outline the knowledge, skills, and attributes that are required for competent practice. This study describes the process followed to revise and validate the competency standards for occupational therapy driver assessors in order to guide clinical practice in this area of advanced occupational therapy practice. METHODS: A mixed methods research approach was used in this study. In phase 1, three focus groups with driver assessors reviewed and suggested revisions to the competency standards for occupational therapy driver assessors. Phase 2 involved content validation with key stakeholders through a focus group with consumers, written feedback from Australian state, and territory driver licensing authorities, and a two-round Delphi process with Australian occupational therapy driver assessors. RESULTS: Forty-nine occupational therapy driver assessors participated in the phase 1 focus groups. Deductive content analysis of the transcripts provided data to revise the competency standards. Inductive analysis provided an in-depth understanding of the participants' views and was interpreted through six categories and their underlying subcategories: purposes and benefits; jurisdictional variations and practice diversity; language use; defining competent practice; challenging systems and processes; and competency standards content. Forty-eight occupational therapy driver assessors participated in the Delphi process. In Round 1, only 1 of the 164 competency standards and practice behaviours rated did not achieve the pre-determined 70% consensus rate. In Round 2, all statements achieved consensus, with the overall average consensus level obtained across the Round 2 statements at 96.8%. CONCLUSION: The revised Australian Competency Standards for Occupational Therapy Driver Assessors have been endorsed by Occupational Therapy Australia and released for clinical use. The methods described in this research provide a framework suitable for revision or development of competency standards in both other areas of occupational therapy practice and other health-care professions.

Components of driving competency measurement in the elderly: A scoping review.

Background: Iran will face the "aging Tsunami" phenomenon by the 2040s. Therefore, paying attention to the elderly's driving to maintain and promote their independence and quality of life on the one hand and paying attention to the dangers of driving by the elderly for road safety will be important. The purpose of this research was to determine the components of driving competency in the elderly. Methods: The research has employed a scoping review. To this end, searches of scientific databases were conducted using keywords between 1990 and 2019. The process of selecting the documentation was-based on the PRISMA chart. Results: In the first phase, 2769 records were found, and finally, 37 records met the inclusion criteria set for this study. The results indicated that 18 components were extracted that were classified into seven main categories including cognitive, sensory, motor, mental functions, and medications, diseases, and driving history. Conclusion: Sensory, motor, and cognitive abilities are the most important components of elderly safe driving. Therefore, as age increases, chronic disease, multiple drug use, and subsequent problems increase. This can affect the ability to drive safely and can cause traffic injuries. Therefore, it is recommended to use the results of this research to design a suitable tool and model for assessing driving competency in the elderly.

The Risk of Functional Limitations After Driving Cessation Among Older Japanese Adults: The JAGES Cohort Study.

BACKGROUND: Population ageing and stringent licensing policies will increase the number of older drivers who stop driving. Adverse health outcomes owing to driving cessation and their prevention are emerging concerns. Therefore, we longitudinally examined the impact of driving cessation and alternative transportation use after cessation on the risk of functional limitations in a cohort of community-dwelling people (65 years and older) in Japan. METHODS: Using cohort data of those who drove as of 2006/07, we compared the risk of functional limitations between 2,704 current drivers and 140 former drivers (who stopped driving by 2010). Of the former drivers, 77 did not use public transportation or bicycles after driving cessation (thus losing independent mobility). We calculated the hazard ratios (HRs) for the incidence of functional limitations with 95% confidence intervals (CIs) based on the Cox proportional hazards model with the covariates influencing the functional limitations. RESULTS: From 2010 through 2016, 645 people had functional limitations, which included 38, 82, and 119 per 1,000 person-years among current drivers, former drivers who used public transportation or bicycles, and former drivers who were only driven by others, respectively (HR 1.69; 95% CI, 1.15-2.49 and HR 2.16; 95% CI, 1.51-3.10, relative to current drivers). CONCLUSION: Driving cessation is associated with an increased risk of functional limitations among older adults, but this risk might be alleviated if they are able to maintain independent mobility using public transportation or bicycles after driving cessation.

Simulator Pre-Screening of Underprepared Drivers Prior to Licensing On-Road Examination: Clustering of Virtual Driving Test Time Series Data.

BACKGROUND: A large Midwestern state commissioned a virtual driving test (VDT) to assess driving skills preparedness before the on-road examination (ORE). Since July 2017, a pilot deployment of the VDT in state licensing centers (VDT pilot) has collected both VDT and ORE data from new license applicants with the aim of creating a scoring algorithm that could predict those who were underprepared. OBJECTIVE: Leveraging data collected from the VDT pilot, this study aimed to develop and conduct an initial evaluation of a novel machine learning (ML)-based classifier using limited domain knowledge and minimal feature engineering to reliably predict applicant pass/fail on the ORE. Such methods, if proven useful, could be applicable to the classification of other time series data collected within medical and other settings. METHODS: We analyzed an initial dataset that comprised 4308 drivers who completed both the VDT and the ORE, in which 1096 (25.4%) drivers went on to fail the ORE. We studied 2 different approaches to constructing feature sets to use as input to ML algorithms: the standard method of reducing the time series data to a set of manually defined variables that summarize driving behavior and a novel approach using time series clustering. We then fed these representations into different ML algorithms to compare their ability to predict a driver's ORE outcome (pass/fail). RESULTS: The new method using time series clustering performed similarly compared with the standard method in terms of overall accuracy for predicting pass or fail outcome (76.1% vs 76.2%) and area under the curve (0.656 vs 0.682). However, the time series clustering slightly outperformed the standard method in differentially predicting failure on the ORE. The novel clustering method yielded a risk ratio for failure of 3.07 (95% CI 2.75-3.43), whereas the standard variables method yielded a risk ratio for failure of 2.68 (95% CI 2.41-2.99). In addition, the time series clustering method with logistic regression produced the lowest ratio of false alarms (those who were predicted to fail but went on to pass the ORE; 27.2%). CONCLUSIONS: Our results provide initial evidence that the clustering method is useful for feature construction in classification tasks involving time series data when resources are limited to create multiple, domain-relevant variables.

Machine-learning approach to predict on-road driving ability in healthy older people.

AIM: In Japan, fatal traffic accidents due to older drivers are on the rise. Considering that approximately half the older drivers who have caused fatal accidents are cognitively normal healthy people, it has been required to detect older drivers who are cognitively normal but at high risk of having fatal traffic accidents. However, a standardized method for assessing the driving ability of older drivers has not yet been established. We thus aimed to identify a new sensing method for the evaluation of the on-road driving ability of healthy older people on the basis of vehicle behaviors. METHODS: We enrolled 33 healthy older individuals aged over 65 years and utilized a machine-learning approach to dissociate unsafe drivers from safe drivers based on cognitive assessments and a functional visual acuity test. RESULTS: The linear support vector machine classifier successfully dissociated unsafe drivers from safe drivers with accuracy of 84.8% (sensitivity of 66.7% and specificity of 95.2%). Five clinical parameters, namely age, the first trial of the Rey Auditory Verbal Learning Test immediate recall, the delayed recall of the Rey-Osterrieth Complex Figure Test, the result of the free-drawn Clock Drawing Test, and maximal visual acuity, were consistently selected as essential features for the best classification model. CONCLUSION: Our findings improve our understanding of clinical risk factors leading to unsafe driving and may provide insight into a new intervention that prevents fatal traffic accidents caused by healthy older people.

Beyond cognitive dysfunction: Relevance of ecological validity of neuropsychological tests in multiple sclerosis.

In neurological diseases such as multiple sclerosis (MS), a neuropsychological assessment is often requested to assist clinicians in evaluating the role of cognition in a patient's level of everyday functioning. To be effective in this charge, it is assumed that performance on neuropsychological tests is related to how a person may function in everyday life, and the question is often asked: "Are neuropsychological tests ecologically valid?" In this review, we synthesize the literature that examines the use of neuropsychological tests to assess functioning across a variety of everyday functioning domains in MS (i.e. driving, employment, instrumental activities of daily living (IADLs)). However, we critically examine the usefulness of asking this broad question regarding ecological validity, given the psychometric and conceptual pitfalls it may yield. While many neuropsychological tests may be generally considered "ecologically valid" in MS, it is much more helpful to specify for whom, under what circumstances, and to what degree.