Objective To evaluate potential mediators of weight loss in the Strong Hearts, Health Communities-2.0 (SHHC-2.0) trial. Design Community-randomized trial (intervention vs delayed intervention). Outcomes were evaluated at baseline and postintervention. Setting Eleven rural, medically-underserved communities Participants Women (n = 182), mean age 57.2 years, 97.6% White, non-Hispanic. Intervention Classes delivered 2 times/wk for 24 weeks, targeting diet and physical activity behaviors. Main Outcomes Measures Dependent variable: weight; mediators: diet and physical activity behaviors, and related psychosocial factors. Analysis Mixed linear regressions evaluated the effect of mediators on weight loss. Results Significant mediators included dietary behaviors (Rapid Eating Assessment for Participants-Short; 31.8%; P = 0.03), healthy eating attitudes (23.0%; P = 0.03), and dietary cognitive restraint (29.8%; P = 0.01). Physical activity did not mediate weight loss; however, a worsening in attitudes toward exercise was a mediator of weight loss (22.6%; P = 0.01). Social support for diet and physical activity was unchanged in the intervention group and did not mediate weight loss effects. Conclusions and implications Healthy eating attitudes and dietary cognitive restraint represent important targets for future behavioral interventions for weight loss. Hypothesized mediators found to be nonsignificant (i.e., social support) represent opportunities for future intervention optimization.

OBJECTIVE:This study aimed to conduct cost analysis (CA) and cost-effectiveness analysis (CEA) of Strong Hearts, Healthy Communities (SHHC) implemented in two randomized trials. METHODS:Women with obesity or women who were sedentary with overweight who were ≥ 40 years old from rural medically underserved towns were randomized to SHHC intervention or control. CA calculated total and per participant costs and opportunity costs. CEA compared incremental costs to incremental outcome changes. Quality-adjusted life year (QALY) CEA compared incremental costs and effectiveness of a national SHHC intervention for a hypothetical cohort of 2.2 million women. RESULTS:SHHC-1.0 resource cost was $775/participant and SHHC-2.0 was $747. The incremental cost-effectiveness ratio from the payer's perspective for SHHC-1.0 was $346/kg weight loss and $187 and $155 for SHHC-2.0 at 24 and 48 weeks, respectively. Over a 10-year horizon, to avert QALYs lost, SHHC-1.0 was estimated to cost $238,271 from the societal perspective and $62,646 from the health care sector perspective. For SHHC-2.0, the corresponding numbers were $214,257 and $67,747 at 24 weeks and $94,395 and $11,341 at 48 weeks. CONCLUSIONS:SHHC-2.0 compared favorably to SHHC-1.0 and could be cost-effective for longer-term effects. Results can help guide policy makers' decisions on larger-scale community-based obesity and cardiovascular disease prevention interventions. TRIAL REGISTRATION:ClinicalTrials.gov identifier NCT03059472.

ABSTRACTBackgroundAs the US population continues to age, depression and other mental health issues have become a significant challenge for healthy aging. Few studies, however, have examined the prevalence of depression in community‐dwelling older adults in the United States.MethodsBaseline data from the Longitudinal Research on Aging Drivers study were analyzed to examine the prevalence and correlates of depression in a multisite sample of community‐dwelling adults aged 65–79 years who were enrolled and assessed between July 2015 and March 2017. The Patient‐Reported Outcomes Measurement Information System (PROMIS) depression scale was used to determine the depression status.ResultsOf the 2990 study participants, 186 (6.2%) had depression at the time of assessment. Elevated prevalence of depression was found in those who were 65–69 years of age (7.9%); were women (7.2%); were not married (8.1%); had attained an education of high school or less (8.3%); or had annual household incomes less than $50,000 (10.7%). Older adults with a positive history of depression or chronic medical conditions (e.g., diabetes mellitus and anxiety) had a significantly higher prevalence of depression whereas those engaged in volunteering activities had a significantly lower prevalence of depression. With adjustment for demographic characteristics and comorbidities, volunteering was associated with a 43% reduction in the odds of depression (adjusted odds ratio: 0.57, 95% confidence interval 0.40–0.81).ConclusionsThe point prevalence of depression in this multisite sample of community‐dwelling older adults in the United States was 6.2%, which varied significantly with demographic characteristics and comorbid conditions. Engagement in volunteering activities might help older adults to reduce their risk of depression.

Diabetes mellitus (DM) can impair driving safety due to hypoglycemia, hyperglycemia, diabetic peripheral neuropathy, and diabetic eye diseases. However, few studies have examined the association between DM and driving safety in older adults based on naturalistic driving data. Data for this study came from a multisite naturalistic driving study of drivers aged 65–79 years at baseline. Driving data for the study participants were recorded by in-vehicle recording devices for up to 44 months. We used multivariable negative binomial modeling to estimate adjusted incidence rate ratios (aIRRs) and 95

Older adults aged 70 and older who drive have higher crash death rates per mile driven compared to middle aged (35-54 years) adults who drive in the US. Prior studies have found that depression and or antidepressant medication use in older adults are associated with an increase in the vehicular crash rate. Using data from the prospective multi-site AAA Longitudinal Research on Aging Drivers Study, this analysis examined the independent and interdependent associations of self-reported depression and antidepressant use with driving behaviors that can increase motor vehicle crash risk such as hard braking, speeding, and night-time driving in adults over age 65. Of the 2951 participants, 6.4% reported having depression and 21.9% were on an antidepressant medication. Correcting for age, race, gender, and education level, participants on an antidepressant had increased hard braking events (1.22 [1.10-1.34]) but self-reported depression alone was not associated with changes in driving behaviors.

Background Trajectories of health-related quality of life (HRQoL) after driving cessation (DC) are thought to decline steeply, but for some, HRQoL may improve after DC. Our objective is to examine trajectories of HRQoL for individuals before and after DC. We hypothesize that for urban drivers, volunteers and those who access alternative transportation participants’ health may remain unchanged or improve. Methods This study uses data from the AAA Longitudinal Research on Aging Drivers (LongROAD) study, a prospective cohort of 2,990 older drivers (ages 65–79 at enrollment). The LongROAD study is a five-year multisite study and data collection ended October 31, 2022. Participants were recruited using a convenience sample from the health centers roster. The number of participants approached were 40,806 with 7.3% enrolling in the study. Sixty-one participants stopped driving permanently by year five and had data before and after DC. The PROMIS®-29 Adult Profile was utilized and includes: 1) Depression, 2) Anxiety, 3) Ability to Participate in Social Roles and Activities, 4) Physical Function, 5) Fatigue, 6) Pain Interference, 7) Sleep Disturbance, and 8) Numeric Pain Rating Scale. Adjusted (age, education and gender) individual growth models with 2989 participants with up to six observations from baseline to year 5 in the models (ranging from n = 15,041 to 15,300) were utilized. Results Ability to participate in social roles and activities after DC improved overall. For those who volunteered, social roles and activities declined not supporting our hypothesis. For those who accessed alternative transportation, fatigue had an initial large increase immediately following DC thus not supporting our hypothesis. Urban residents had worse function and more symptoms after DC compared to rural residents (not supporting our hypothesis) except for social roles and activities that declined steeply (supporting our hypothesis). Conclusions Educating older adults that utilizing alternative transportation may cause initial fatigue after DC is recommended. Accessing alternative transportation to maintain social roles and activities is paramount for rural older adults after DC especially for older adults who like to volunteer.

Purpose: Human papillomavirus (HPV) vaccine uptake is lower in rural areas, particularly for boys. The purpose of the study was to demonstrate how a participatory approach to developing a series of videos about the HPV vaccine better meets the informational needs of rural parents. Methods: We recruited six rural parents to participate on a parent advisory board (PAB). The PAB met monthly spanning five months (n = 5 meetings) from February to May 2023. Each meeting focused on an element of video creation, including: 1) Providing feedback on existing HPV vaccine videos created by federal agencies and developing a tailored plan for local rural parents; 2) Providing feedback on the video plan so the study team could draft scripts; 3) Editing scripts; 4) Finalizing video concepts; and 5) Providing feedback to produced videos. Between meetings, parents completed tasks to facilitate the process, which also served as a way for parent input to be documented. We worked with a local, professional videographer to produce the videos. A local parent and a nurse practitioner were recruited as actors. Results: Six one-minute videos were produced on the following topics: What is HPV?; Does the vaccine prevent cancer?; How does the vaccine work?; Is the vaccine safe?; Who should get the vaccine?; and Where can you go to get the vaccine? The PAB was essential in clarifying source, message, channel and receiver throughout the video creation process. Conclusions: Engaging parents to co-create a series of one-minute videos supports HPV vaccine confidence efforts in rural areas.

Despite the growing number of older adult drivers, knowledge on factors influencing their driving safety from device-collected behavior data in naturalistic driving environment is limited. This study utilizes GPS tracked driving data of 1,200 older adults in the US to examine the link between home neighborhood environment, driving exposure, and driving safety behaviors. Structural equation model results show that urban older adults exhibited more frequent events of very high-speed driving (\>80 mile/h, 130 km/h), rapid decelerations, and higher right-to-left turn ratios than their suburban and rural counterparts. This is partially explained by differences in driving exposure (i.e., more trips on high-speed roads, during nighttime, and shorter distances). Notably, living in neighborhoods with higher auto-oriented road densities and more nighttime destinations contribute substantially to unsafe driving behaviors.

Abstract Background Dietary supplement (DS) use is common and increasing among older adults, though much data available on use frequencies are from surveys and performed cross-sectionally. This paper sought to assess the frequency and pattern of dietary supplement use among older adults over time. Methods A secondary analysis of data from the AAA LongROAD study, a longitudinal prospective cohort study of older adult drivers, using data from baseline and the first two years of follow up included a total of 2990 drivers aged 65–79 years recruited at five study sites across the US from July 2015 to March 2017. Participants underwent baseline and annual evaluations, which included a “brown bag” medication review. DS were identified and categorized according to type and key components. Prevalence and pattern of DS use over time and relationship to demographics were measured with frequency and Chi squared analyses. Results 84% of participants took at least one dietary supplement during the 2-year study period, and 55% of participants continually reported use. DS accounted for approximately 30% of the total pharmacologic-pill burden in all years. Participants who were White non-Hispanic, female, 75–79 years of age at baseline, and on more non-supplement medications took significantly more dietary supplements (P < 0.05). Vitamin D, multivitamins, calcium, and omega-3 formulations were the most common supplements, with stable use over time. Use of individual herbal supplements and cannabis products was uncommon (< 1% participants per year). Conclusions DS use among older adults is common and relatively stable over time and contributes to polypharmacy. In clinical settings, providers should consider the influence of DS formulations on polypharmacy, and the associated cost, risk of medication interactions, and effect on medication compliance.

Abstract Background Strong Hearts, Healthy Communities 2.0 (SHHC-2.0) was a 24-week cardiovascular disease prevention program that was effective in improving physical activity and nutrition behaviors and clinical outcomes among women in 11 rural New York, USA towns. This study evaluated the delivery of SHHC-2.0 to prepare the intervention for further dissemination. Methods This process evaluation was guided by the Medical Research Council recommendations and engaged program leaders and participants (i.e., women over age 40) using quantitative and qualitative methods. The quantitative evaluation included examination of enrollment and retention data, a participant survey, and a fidelity checklist completed after classes. Descriptive and comparative statistics were used to assess implementation measures: program reach, participant attendance, dose delivered, program length, perceived effectiveness, fidelity, and participant satisfaction. The qualitative evaluation included focus groups (n = 13) and interviews (n = 4) using semi-structured guides; audio was recorded and transcripts were deductively coded and analyzed using directed content analysis and iterative categorization approaches. Comparisons across towns and between intervention and waitlist control groups were explored. Results Average reach within towns was 7.5% of the eligible population (range 0.7-15.7%). Average attendance was 59.8% of sessions (range 42.0-77.4%). Average dose delivered by leaders was 86.4% of curriculum components (range 73.5-95.2%). Average session length was 51.8 ± 4.8 min across 48 sessions. Leaders’ perceived effectiveness rating averaged 4.1 ± 0.3 out of 5. Fidelity to curricular components was 81.8% (range 67.4-93.2%). Participants reported being “more than satisfied” with the overall program (88.8%) and the health benefits they obtained (72.9%). Qualitative analysis revealed that participants: (1) gained new knowledge and enjoyable experiences; (2) perceived improvements in their physical activity, nutrition, and/or health; (3) continued to face some barriers to physical activity and healthy eating, with those relating to social support being reduced; and (4) rated leaders and the group structure highly, with mixed opinions on the research elements. Conclusions SHHC-2.0 had broad reach, was largely delivered as intended, and participants expressed high levels of satisfaction with the program and its health benefits. Our findings expand on best practices for implementing cardiovascular disease prevention programs in rural communities. Clinical trials Registration www.clinicaltrials.gov #NCT03059472.

IntroductionFrailty and low physical performance are modifiable factors and, therefore, targets for interventions aimed at delaying driving cessation (DC). The objective was to determine the impact of frailty and physical performance on DC.MethodsMultisite prospective cohort of older drivers. The key inclusion criteria are as follows: active driver age 65–79 years, possessing a valid driver’s license, without significant cognitive impairment, and driving a 1996 car or a newer model car. Of the 2,990 enrolled participants, 2,986 (99.9%) had at least one frailty or Short Physical Performance Battery (SPPB) measure and were included in this study. In total, 42% of participants were aged 65–69 years, 86% were non-Hispanic white, 53% were female, 63% were married, and 41% had a high degree of education. The Fried Frailty Phenotype and the Expanded Short Physical Performance Battery (SPPB) from the National Health and Aging Trends Study were utilized. At each annual visit, DC was assessed by the participant notifying the study team or self-reporting after no driving activity for at least 30 days, verified via GPS. Cox proportional hazard models, including time-varying covariates, were used to examine the impact of the SPPB and frailty scores on time to DC. This assessment included examining interactions by sex.ResultsSeventy-three participants (2.4%) stopped driving by the end of year 5. Among women with a fair SPPB score, the adjusted hazard ratio (HR) of DC was 0.26 (95% confidence interval (CI) 0.10–0.65) compared to those with a poor SPPB score. For those with a good SPPB score, the adjusted HR of DC had a p-value of <0.001. Among men with a fair SPPB score, the adjusted hazard ratio (HR) of DC was 0.45 (95% CI 0.25–0.81) compared to those with a poor SPPB score. For men with a good SPPB score, the adjusted HR of DC was 0.19 (95% CI 0.10–0.36). Sex was not an effect modifier between frailty and DC. For those who were categorized into pre-frail or frail, the adjusted ratio of HR to DC was 6.1 (95% CI 2.7–13.8) compared to those who were not frail.Conclusion and relevanceFrailty and poor physical functioning are major risk factors for driving cessation. Staying physically active may help older adults to extend their driving life expectancy and mobility.

Background: Polypharmacy (i.e., simultaneous use of two or more medications) poses a serious safety concern for older drivers. This study assesses the association between polypharmacy and hard braking events in older adult drivers. Methods: Data for this study came from a naturalistic driving study of 2990 older adults. Information about medications was collected through the "brown-bag review" method. Primary vehicles of the study participants were instrumented with data recording devices for up to 44 months. Multivariable negative binomial model was used to estimate the adjusted incidence rate ratios (aIRRs) and 95 % confidence intervals (CIs) of hard-braking events (i.e., maneuvers with linear deceleration rates >= 0.4 g) associated with polypharmacy. Results: Of the 2990 participants, 2872 (96.1 %) were eligible for this analysis. At the time of enrollment, 157 (5.5 %) drivers were taking fewer than two medications, 904 (31.5 %) were taking 2-5 medications, 895 (31.2 %) were taking 6-9 medications, 571 (19.9 %) were taking 10-13 medications, and 345 (12.0 %) were taking 14 or more medications. Compared to drivers using fewer than two medications, the risk of hard-braking events increased 8 % (aIRR 1.08, 95 % CI 1.04, 1.13) for users of 2-5 medications, 12 % (aIRR 1.12, 95 % CI 1.08, 1.16) for users of 6-9 medications, 19 % (aIRR 1.19, 95 % CI 1.15, 1.24) for users of 10-13 medications, and 34 % (aIRR 1.34, 95 % CI 1.29, 1.40) for users of 14 or more medications. Conclusions: Polypharmacy in older adult drivers is associated with significantly increased incidence of hardbraking events in a dose-response fashion. Effective interventions to reduce polypharmacy use may help improve driving safety in older adults.

BackgroundMigraine headache is common in older adults, often causing symptoms that may affect driving safety. This study examined associations of migraine with motor vehicle crashes (MVCs) and driving habits in older drivers and assessed modification of associations by medication use.MethodsIn a multi-site, prospective cohort study of active drivers aged 65-79 (53% female), we assessed prevalent migraine (i.e., ever had migraine, reported at enrollment), incident migraine (diagnosis first reported at a follow-up visit), and medications typically used for migraine prophylaxis and treatment. During 2-year follow-up, we recorded self-reported MVCs and measured driving habits using in-vehicle GPS devices. Associations of prevalent migraine with driving outcomes were estimated in multivariable mixed models. Using a matched design, associations of incident migraine with MVCs in the subsequent year were estimated with conditional logistic regression. Interactions between migraine and medications were tested in all models.ResultsOf 2589 drivers, 324 (12.5%) reported prevalent migraine and 34 (1.3%) incident migraine. Interactions between migraine and medications were not statistically significant in any models. Prevalent migraine was not associated with MVCs in the subsequent 2 years (adjusted OR [aOR] = 0.98; 95% CI: 0.72, 1.35), whereas incident migraine significantly increased the odds of having an MVC within 1 year (aOR = 3.27; 1.21, 8.82). Prevalent migraine was associated with small reductions in driving days and trips per month and increases in hard braking events in adjusted models.ConclusionOur results suggest substantially increased likelihood of MVCs in the year after newly diagnosed migraine, indicating a potential need for driving safety interventions in these patients. We found little evidence for MVC risk or substantial changes in driving habits associated with prevalent migraine. Future research should examine timing, frequency, and severity of migraine diagnosis and symptoms, and use of medications specifically prescribed for migraine, in relation to driving outcomes.

BACKGROUNDPolypharmacy use among older adults is of increasing concern for driving safety. This study assesses the individual and joint effects of benzodiazepines and prescription opioids on the incidence of hard braking events in older drivers.METHODSData for this study came from the Longitudinal Research on Aging Drivers project-a multisite, prospective cohort study of 2990 drivers aged 65-79 years at enrollment (2015-2017). Adjusted incidence rate ratios (aIRRs) and 95% confidence intervals (CIs) of hard braking events (defined as maneuvers with deceleration rates ≥0.4 g and commonly known as near-crashes) were estimated through multivariable negative binominal modeling.RESULTSOf the 2929 drivers studied, 167 (5.7%) were taking benzodiazepines,  163 (5.6%) prescription opioids, and 23 (0.8%) both drugs at baseline. The incidence rates of hard braking events per 1000 miles driven were 1.14 (95% CI 1.10-1.18) for drivers using neither benzodiazepines nor prescription opioids, 1.25 (95% CI 1.07-1.43) for those using benzodiazepines only, 1.55 (95% CI 1.35-1.76) for those using prescription opioids only, and 1.63 (95% CI 1.11-2.16) for those using both medications. Multivariable modeling revealed that the use of prescription opioids was associated with a 19% increased risk of hard braking events (aIRR 1.19, 95% CI 1.03-1.36). There existed a positive interaction between the two drugs on the additive scale but not on the multiplicative scale.CONCLUSIONConcurrent use of benzodiazepines and prescription opioids by older drivers appears to affect driving safety through increased incidence of hard braking events.

BACKGROUND:Cardiovascular disease (CVD) prevalence has disproportionately risen among midlife and older female adults of rural communities, partly due to poor diet and diet-related behaviors and psychosocial factors that impede healthy eating. OBJECTIVES:This study aimed to evaluate the impact of Strong Hearts Healthy Communities 2.0 (SHHC-2.0) on secondary diet-related outcomes between intervention and control participants that align with the dietary goal and behavioral aims of the SHHC-2.0, a CVD risk reduction program. METHODS:A community-randomized controlled trial was conducted in rural, medically underserved communities. Participants were female adults ≥40 y who were classified as obese or both overweight and sedentary. Communities were randomized to SHHC-2.0 intervention (n = 5 communities; n = 87 participants) or control (with delayed intervention) (n = 6 communities; n = 95 participants). SHHC-2.0 consisted of 24 wk of twice-weekly experiential nutrition education and group-based physical activity classes led by local health educators. Changes between baseline and end point (24 wk) in dietary intake (24-h recalls), dietary behaviors (e.g., Rapid Eating Assessment for Participants-Short Version [REAP-S] scores) and diet-related psychosocial measures (e.g., Three Factor Eating questionnaire) between groups were analyzed using linear mixed-effects multilevel models. RESULTS:At 24 wk, participants from the 5 intervention communities, compared with controls, consumed fewer calories (mean difference [MD]= -211 kcal, 95% CI: -412, -110, P = 0.039), improved overall dietary patterns measured by REAP-S scores (MD: 3.9; 95% CI: 2.26, 5.6; P < 0.001), and improved psychosocial measures (healthy eating attitudes, uncontrolled eating, cognitive restraint, and emotional eating). CONCLUSIONS:SHHC-2.0 has strong potential to improve diet patterns and diet-related psychosocial wellbeing consistent with improved cardiovascular health. This trial was registered at www. CLINICALTRIALS:gov as NCT03059472.

Background Acute cannabis use is associated with a higher risk of motor vehicle crashes (MVC). This study aimed to determine if self-reported past-year cannabis use is associated with MVC or traffic stops among older drivers.Methods This cross-sectional analysis used data from a multi-center study enrolling active drivers aged 65-79 years. Data regarding cannabis use, MVC, and traffic stops (i.e., being pulled over by police, whether ticketed or not) within the previous 12 months were collected through participant interviews. Log-binomial regression models examined associations of past-year cannabis use with MVC and traffic stops, adjusting for site and sociodemographic and mental health characteristics.Results Of 2,095 participating older drivers, 186 (8.88%) used cannabis in the past year but only 10 (<0.5%) within an hour before driving in the last 30 days; 11.41% reported an MVC and 9.45% reported a traffic stop. Past-year cannabis users had a higher prevalence of MVC (adjusted prevalence ratio [aPR] = 1.38; 95%CI: 0.96, 2.00; p = 0.086) and traffic stops (aPR = 1.58; 1.06, 2.35; p = 0.024).Conclusions Past-year cannabis use was associated with increased traffic stops, which are correlated modestly with increased MVC in past studies and may indicate impaired driving performance. We did not find a statistically significant association of past-year cannabis use with MVC, which may indicate limited sustained effects on driving performance from periodic use among older adults, who report rarely driving immediately after use.

The National Clinical Care Commission (NCCC) was established by Congress to make recommendations to leverage federal policies and programs to more effectively prevent and treat diabetes and its complications. The NCCC developed a guiding framework that incorporated elements of the Socioecological and Chronic Care Models. It surveyed federal agencies and conducted follow-up meetings with representatives from 10 health-related and 11 non-health-related federal agencies. It held 12 public meetings, solicited public comments, met with numerous interested parties and key informants, and performed comprehensive literature reviews. The final report, transmitted to Congress in January 2022, contained 39 specific recommendations, including 3 foundational recommendations that addressed the necessity of an all-of-government approach to diabetes, health equity, and access to health care. At the general population level, the NCCC recommended that the federal government adopt a health-in-all-policies approach so that the activities of non-health-related federal agencies that address agriculture, food, housing, transportation, commerce, and the environment be coordinated with those of health-related federal agencies to affirmatively address the social and environmental conditions that contribute to diabetes and its complications. For individuals at risk for type 2 diabetes, including those with prediabetes, the NCCC recommended that federal policies and programs be strengthened to increase awareness of prediabetes and the availability of, referral to, and insurance coverage for intensive lifestyle interventions for diabetes prevention and that data be assembled to seek approval of metformin for diabetes prevention. For people with diabetes and its complications, the NCCC recommended that barriers to proven effective treatments for diabetes and its complications be removed, the size and competence of the workforce to treat diabetes and its complications be increased, and new payment models be implemented to support access to lifesaving medications and proven effective treatments for diabetes and its complications. The NCCC also outlined an ambitious research agenda. The NCCC strongly encourages the public to support these recommendations and Congress to take swift action.

Several recent studies indicate that atypical changes in driving behaviors appear to be early signs of mild cognitive impairment (MCI) and dementia. These studies, however, are limited by small sample sizes and short follow-up duration. This study aims to develop an interaction-based classification method building on a statistic named Influence Score (i.e., I-score) for prediction of MCI and dementia using naturalistic driving data collected from the Longitudinal Research on Aging Drivers (LongROAD) project. Naturalistic driving trajectories were collected through in-vehicle recording devices for up to 44 months from 2977 participants who were cognitively intact at the time of enrollment. These data were further processed and aggregated to generate 31 time-series driving variables. Because of high dimensional time-series features for driving variables, we used I-score for variable selection. I-score is a measure to evaluate variables’ ability to predict and is proven to be effective in differentiating between noisy and predictive variables in big data. It is introduced here to select influential variable modules or groups that account for compound interactions among explanatory variables. It is explainable regarding to what extent variables and their interactions contribute to the predictiveness of a classifier. In addition, I-score boosts the performance of classifiers over imbalanced datasets due to its association with the F1 score. Using predictive variables selected by I-score, interaction-based residual blocks are constructed over top I-score modules to generate predictors and ensemble learning aggregates these predictors to boost the prediction of the overall classifier. Experiments using naturalistic driving data show that our proposed classification method achieves the best accuracy (96%) for predicting MCI and dementia, followed by random forest (93%) and logistic regression (88%). In terms of F1 score and AUC, our proposed classifier achieves 98% and 87%, respectively, followed by random forest (with an F1 score of 96% and an AUC of 79%) and logistic regression (with an F1 score of 92% and an AUC of 77%). The results indicate that incorporating I-score into machine learning algorithms could considerably improve the model performance for predicting MCI and dementia in older drivers. We also performed the feature importance analysis and found that the right to left turn ratio and the number of hard braking events are the most important driving variables to predict MCI and dementia.

Importance:Symptoms of attention-deficit/hyperactivity disorder (ADHD), such as inattentiveness and impulsivity, could affect daily functioning and driving performance throughout the life span. Previous research on ADHD and driving safety is largely limited to adolescents and young adults.Objective:To examine the prevalence of ADHD and the association between ADHD and crash risk among older adult drivers.Design, Setting, and Participants:This prospective cohort study collected data from primary care clinics and residential communities in 5 US sites (Ann Arbor, Michigan; Baltimore, Maryland; Cooperstown, New York; Denver, Colorado; and San Diego, California) between July 6, 2015, and March 31, 2019. Participants were active drivers aged 65 to 79 years at baseline enrolled in the Longitudinal Research on Aging Drivers project who were studied for up to 44 months through in-vehicle data recording devices and annual assessments. The data analysis was performed between July 15, 2022, and August 14, 2023.Exposure:Lifetime ADHD based on an affirmative response to the question of whether the participant had ever had ADHD or had ever been told by a physician or other health professional that he or she had ADHD.Main Outcomes and Measures:The main outcomes were hard-braking events defined as maneuvers with deceleration rates of 0.4g or greater, self-reported traffic ticket events, and self-reported vehicular crashes. Multivariable negative binomial modeling was used to estimate adjusted incidence rate ratios (aIRRs) and 95% CIs of outcomes according to exposure status.Results:Of the 2832 drivers studied, 1500 (53.0%) were women and 1332 (47.0%) were men with a mean (SD) age of 71 (4) years. The lifetime prevalence of ADHD in the study sample was 2.6%. Older adult drivers with ADHD had significantly higher incidence rates of hard-braking events per 1000 miles than those without ADHD (1.35 [95% CI, 1.30-1.41] vs 1.15 [95% CI, 1.14-1.16]), as well as self-reported traffic ticket events per 1 million miles (22.47 [95% CI, 16.06-31.45] vs 9.74 [95% CI, 8.99-10.55]) and self-reported vehicular crashes per 1 million miles (27.10 [95% CI, 19.95-36.80] vs 13.50 [95% CI, 12.61-14.46]). With adjustment for baseline characteristics, ADHD was associated with a significant 7% increased risk of hard-braking events (aIRR, 1.07; 95% CI, 1.02-1.12), a 102% increased risk of self-reported traffic ticket events (aIRR, 2.02; 95% CI, 1.42-2.88), and a 74% increased risk of self-reported vehicular crashes (aIRR, 1.74; 95% CI, 1.26-2.40).Conclusions and Relevance:As observed in this prospective cohort study, older adult drivers with ADHD may be at a significantly elevated crash risk compared with their counterparts without ADHD. These findings suggest that effective interventions to improve the diagnosis and clinical management of ADHD among older adults are warranted to promote safe mobility and healthy aging.