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.

Lessons Learned from Implementing a Prostate Cancer Risk Assessment Program for Underserved High-Risk Men in the Community: the Prostate REACH Project.

Prostate cancer disproportionately affects Black men, who may also encounter barriers to participation in prostate cancer risk assessment. The Prostate Risk, Education and Assessment in the Community with Help (REACH) project was a community-based extension of a comprehensive prostate cancer risk assessment program at a comprehensive cancer center. The goals of the REACH project were the following: (1) establish a community prostate cancer risk assessment clinic, (2) conduct targeted recruitment, and (3) provide navigation services including follow-up for uninsured men. Key implementation steps included the following: (1) choosing a clinic site, (2) establishing patient access procedures, (3) establishing navigator services, (4) developing subsidy fund use guidelines, and (5) designing recruitment and promotion. Through community-based promotion, 64 men inquired about the program and 26 (41 %) participated. Of those screened, 46 % had abnormal results, and 2 men were diagnosed with prostate cancer. Here, we describe a unique demonstration project to implement a comprehensive prostate cancer risk assessment program in an underserved Black community and describe successes and challenges to inform future efforts to promote access to underserved men.

Simulated Driving Assessment (SDA) for teen drivers: results from a validation study.

BACKGROUND: Driver error and inadequate skill are common critical reasons for novice teen driver crashes, yet few validated, standardised assessments of teen driving skills exist. The purpose of this study is to evaluate the construct and criterion validity of a newly developed Simulated Driving Assessment (SDA) for novice teen drivers. METHODS: The SDA's 35 min simulated drive incorporates 22 variations of the most common teen driver crash configurations. Driving performance was compared for 21 inexperienced teens (age 16-17 years, provisional license ≤90 days) and 17 experienced adults (age 25-50 years, license ≥5 years, drove ≥100 miles per week, no collisions or moving violations ≤3 years). SDA driving performance (Error Score) was based on driving safety measures derived from simulator and eye-tracking data. Negative driving outcomes included simulated collisions or run-off-the-road incidents. A professional driving evaluator/instructor (DEI Score) reviewed videos of SDA performance. RESULTS: The SDA demonstrated construct validity: (1) teens had a higher Error Score than adults (30 vs. 13, p=0.02); (2) For each additional error committed, the RR of a participant's propensity for a simulated negative driving outcome increased by 8% (95% CI 1.05 to 1.10, p<0.01). The SDA-demonstrated criterion validity: Error Score was correlated with DEI Score (r=-0.66, p<0.001). CONCLUSIONS: This study supports the concept of validated simulated driving tests like the SDA to assess novice driver skill in complex and hazardous driving scenarios. The SDA, as a standard protocol to evaluate teen driver performance, has the potential to facilitate screening and assessment of teen driving readiness and could be used to guide targeted skill training.

EMERGENCY BRAKING IN ADULTS VERSUS NOVICE TEEN DRIVERS: RESPONSE TO SIMULATED SUDDEN DRIVING EVENTS.

Motor vehicle crashes remain the leading cause of death in teens in the United States. Newly licensed drivers are the group most at risk for crashes. Their driving skills are very new, still very often untested, so that their ability to properly react in an emergency situation remains a research question. Since it is impossible to expose human subjects to critical life threatening driving scenarios, researchers have been increasingly using driving simulators to assess driving skills. This paper summarizes the results of a driving scenario in a study comparing the driving performance of novice teen drivers (n=21) 16-17 year olds with 90 days of provisional licensure with that of experienced adult drivers (n=17) 25-50 year olds with at least 5 years of PA licensure, at least 100 miles driven per week and no self-reported collisions in the previous 3 years. As part of a 30 to 35 simulated drive that encompassed the most common scenarios that result in serious crashes, participants were exposed to a sudden car event. As the participant drove on a suburban road, a car surged from a driveway hidden by a fence on the right side of the road. To avoid the crash, participants must hard brake, exhibiting dynamic control over both attentional and motor resources. The results showed strong differences between the experienced adult and novice teen drivers in the brake pressure applied. When placed in the same situation, the novice teens decelerated on average 50% less than the experienced adults (p<0.01).

Evaluation of a Risk Awareness Perception Training Program on Novice Teen Driver Behavior at Left-Turn Intersections.

Collisions at left turn intersections are among the most prevalent types of teen driver serious crashes, with inadequate surveillance as a key factor. Risk awareness perception training (RAPT) has shown effectiveness in improving hazard anticipation for latent hazards. The goal of this study was to determine if RAPT version 3 (RAPT-3) improved intersection turning behaviors among novice teen drivers when the hazards were not latent and frequent glancing to multiple locations at the intersection was needed. Teens aged 16-18 with ≤180 days of licensure were randomly assigned to: 1) an intervention group (n=18) that received RAPT-3 (Trained); or 2) a control group (n=19) that received no training (Untrained). Both groups completed RAPT-3 Baseline Assessment and the Trained group completed RAPT-3 Training and RAPT-3 Post Assessment. Training effects were evaluated on a driving simulator. Simulator (gap selection errors and collisions) and eye tracker (traffic check errors) metrics from six left-turn stop sign controlled intersections in the Simulated Driving Assessment (SDA) were analyzed. The Trained group scored significantly higher in RAPT-3 Post Assessment than RAPT-3 Baseline Assessment (p< 0.0001). There were no significant differences in either traffic check and gap selection errors or collisions among Trained and Untrained teens in the SDA. Though Trained teens learned about hazard anticipation related to latent hazards, learning did not translate to performance differences in left-turn stop sign controlled intersections where the hazards were not latent. Our findings point to further research to better understand the challenges teens have with left turn intersections.

Build it, and will they come? Unexpected findings from a study on a Web-based intervention to improve colorectal cancer screening.

Given the extensive use of the Internet for health information, Web-based health promotion interventions are widely perceived as an effective communication channel. The authors conducted this study to determine use of a Web-based intervention intended to improve colorectal cancer screening in a population of women who are at average risk and noncompliant to current screening recommendations. The study was a randomized controlled trial designed to compare the effectiveness of colorectal cancer screening educational materials delivered using the Internet versus a printed format. In 3 years, 391 women seen for routine obstetrics/gynecology follow-up at 2 academic centers provided relevant survey information. Of these, 130 were randomized to the Web intervention. Participants received voluntary access to a password-protected, study-specific Web site that provided information about colorectal cancer and colorectal cancer screening options. The main outcome measures were self-reported and actual Web site use. Only 24.6% of women logged onto the Web site. Age was the only variable that differentiated users from nonusers (p = .03). In contrast, 16% of participants self-reported Web use. There was significant discordance between the veracity of actual and self-reported use (p = .004). Among true users, most (81%) logged on once only. These findings raise questions about how to increase use of important health communication interventions.

Examining virtual driving test performance and its relationship to individuals with HIV-associated neurocognitive disorders.

Significance: Existing screening tools for HIV-associated neurocognitive disorders (HAND) are often clinically impractical for detecting milder forms of impairment. The formal diagnosis of HAND requires an assessment of both cognition and impairment in activities of daily living (ADL). To address the critical need for identifying patients who may have disability associated with HAND, we implemented a low-cost screening tool, the Virtual Driving Test (VDT) platform, in a vulnerable cohort of people with HIV (PWH). The VDT presents an opportunity to cost-effectively screen for milder forms of impairment while providing practical guidance for a cognitively demanding ADL. Objectives: We aimed to: (1) evaluate whether VDT performance variables were associated with a HAND diagnosis and if so; (2) systematically identify a manageable subset of variables for use in a future screening model for HAND. As a secondary objective, we examined the relative associations of identified variables with impairment within the individual domains used to diagnose HAND. Methods: In a cross-sectional design, 62 PWH were recruited from an established HIV cohort and completed a comprehensive neuropsychological assessment (CNPA), followed by a self-directed VDT. Dichotomized diagnoses of HAND-specific impairment and impairment within each of the seven CNPA domains were ascertained. A systematic variable selection process was used to reduce the large amount of VDT data generated, to a smaller subset of VDT variables, estimated to be associated with HAND. In addition, we examined associations between the identified variables and impairment within each of the CNPA domains. Results: More than half of the participants (N = 35) had a confirmed presence of HAND. A subset of twenty VDT performance variables was isolated and then ranked by the strength of its estimated associations with HAND. In addition, several variables within the final subset had statistically significant associations with impairment in motor function, executive function, and attention and working memory, consistent with previous research. Conclusion: We identified a subset of VDT performance variables that are associated with HAND and assess relevant functional abilities among individuals with HAND. Additional research is required to develop and validate a predictive HAND screening model incorporating this subset.

Exploring the potential of Web 2.0 to address health disparities.

This article addresses use of the Internet and Web 2.0 technologies by racial and ethnic minorities and explores the potential opportunities and challenges in leveraging Web 2.0 approaches to impact health disparities. These opportunities and challenges include developing approaches and methods to (a) identify strategies for integrating social media into health promotion interventions focused on major health-related issues that affect members of medically underserved groups; (b) amalgamate techniques to leverage and connect social-media technologies to other evidence-informed online resources; (c) integrate health communication best practices, including addressing health literacy issues; (d) capitalize on social networking to enhance access and communication with health care providers; and (e) advance current efforts and ongoing expansion of research participation by individuals from underserved communities.

Measuring Health Information Dissemination and Identifying Target Interest Communities on Twitter: Methods Development and Case Study of the @SafetyMD Network.

BACKGROUND: Little is known about the ability of individual stakeholder groups to achieve health information dissemination goals through Twitter. OBJECTIVE: This study aimed to develop and apply methods for the systematic evaluation and optimization of health information dissemination by stakeholders through Twitter. METHODS: Tweet content from 1790 followers of @SafetyMD (July-November 2012) was examined. User emphasis, a new indicator of Twitter information dissemination, was defined and applied to retweets across two levels of retweeters originating from @SafetyMD. User interest clusters were identified based on principal component analysis (PCA) and hierarchical cluster analysis (HCA) of a random sample of 170 followers. RESULTS: User emphasis of keywords remained across levels but decreased by 9.5 percentage points. PCA and HCA identified 12 statistically unique clusters of followers within the @SafetyMD Twitter network. CONCLUSIONS: This study is one of the first to develop methods for use by stakeholders to evaluate and optimize their use of Twitter to disseminate health information. Our new methods provide preliminary evidence that individual stakeholders can evaluate the effectiveness of health information dissemination and create content-specific clusters for more specific targeted messaging.

Comparison of teen and adult driver crash scenarios in a nationally representative sample of serious crashes.

Motor vehicle crashes are the leading cause of death and acquired disability during the first four decades of life. While teen drivers have the highest crash risk, few studies examine the similarities and differences in teen and adult driver crashes. We aimed to: (1) identify and compare the most frequent crash scenarios-integrated information on a vehicle's movement prior to crash, immediate pre-crash event, and crash configuration-for teen and adult drivers involved in serious crashes, and (2) for the most frequent scenarios, explore whether the distribution of driver critical errors differed for teens and adult drivers. We analyzed data from the National Motor Vehicle Crash Causation Survey, a nationally representative study of serious crashes conducted by the U.S. National Highway Traffic Safety Administration from 2005 to 2007. Our sample included 642 16- to 19-year-old and 1167 35- to 54-year-old crash-involved drivers (weighted n=296,482 and 439,356, respectively) who made a critical error that led to their crash's critical pre-crash event (i.e., event that made the crash inevitable). We estimated prevalence ratios (PR) and 95% confidence intervals (CI) to compare the relative frequency of crash scenarios and driver critical errors. The top five crash scenarios among teen drivers, accounting for 37.3% of their crashes, included: (1) going straight, other vehicle stopped, rear end; (2) stopped in traffic lane, turning left at intersection, turn into path of other vehicle; (3) negotiating curve, off right edge of road, right roadside departure; (4) going straight, off right edge of road, right roadside departure; and (5) stopped in lane, turning left at intersection, turn across path of other vehicle. The top five crash scenarios among adult drivers, accounting for 33.9% of their crashes, included the same scenarios as the teen drivers with the exception of scenario (3) and the addition of going straight, crossing over an intersection, and continuing on a straight path. For two scenarios ((1) and (3) above), teens were more likely than adults to make a critical decision error (e.g., traveling too fast for conditions). Our findings indicate that among those who make a driver critical error in a serious crash, there are few differences in the scenarios or critical driver errors for teen and adult drivers.

Acute urinary retention after cesarean delivery: a case-control study.

INTRODUCTION: This study aimed to identify risk factors for postpartum urinary retention (PPUR) after cesarean delivery (CD). METHODS: A case-control study design was used. Cases of PPUR after CD were identified using billing codes for CD and "urinary retention" and confirmed by chart review. Matched controls were identified in a 2:1 ratio using an obstetrics database and billing data. Patient demographics, operative, and anesthetic data were collected. Fisher exact tests and Wilcoxon rank sum tests were used to determine differences in medical risk factors, postoperative analgesic use, and catheter management between cases and controls. A modified Poisson conditional multivariate regression with robust error variances was used to estimate the odds ratios (ORs) for significant predictors. RESULTS: Thirty-four confirmed cases of PPUR were matched with 68 controls. The mean ages of cases and controls were 31 and 32 years, respectively. Cases and controls differed in gestational age (P = 0.01), diagnosis of diabetes (P = 0.05), and use of postoperative intravenous and oral narcotics (P < 0.01 and P = 0.03, respectively). In a multivariate model including these factors, increasing gestational age was associated with decreased risk of PPUR [OR, 0.07; 95% confidence interval (CI), 0.01-0.48; P < 0.01], whereas use of postoperative intravenous narcotics (OR, 4.51; 95% CI, 1.09-18.67; P = 0.038) and oral narcotics (OR, 4.99; 95% CI, 1.10-22.65; P = 0.037) were associated with increased risk. CONCLUSIONS: After matching for obstetric factors, use of postoperative narcotic analgesia was associated with increased risk of PPUR. Other operative and anesthetic factors had no association. Multicenter prospective studies are needed to investigate this association.

HEADWAY TIME AND CRASHES AMONG NOVICE TEENS AND EXPERIENCED ADULT DRIVERS IN A SIMULATED LEAD TRUCK BRAKING SCENARIO.

Driving simulators can be used to evaluate driving performance under controlled, safe conditions. Teen drivers are at particular risk for motor vehicle crashes and simulated driving can provide important information on performance. We developed a new simulator protocol, the Simulated Driving Assessment (SDA), with the goal of providing a new tool for driver assessment and a common outcome measure for evaluation of training programs. As an initial effort to examine the validity of the SDA to differentiate performance according to experience, this analysis compared driving behaviors and crashes between novice teens (n=20) and experienced adults (n=17) on a high fidelity simulator for one common crash scenario, a rear-end crash. We examined headway time and crashes during a lead truck with sudden braking event in our SDA. We found that 35% of the novice teens crashed and none of the experienced adults crashed in this lead truck braking event; 50% of the teens versus 25% of the adults had a headway time <3 seconds at the time of truck braking. Among the 10 teens with <3 seconds headway time, 70% crashed. Among all participants with a headway time of 2-3 seconds, further investigation revealed descriptive differences in throttle position and brake pedal force when comparing teens who crashed, teens who did not crash and adults (none of whom crashed). Even with a relatively small sample, we found statistically significant differences in headway time for adults and teens, providing preliminary construct validation for our new SDA.

Implementation of a Theory-based, Non-clinical Patient Navigator Program to Address Barriers in an Urban Cancer Center Setting.

Cancer patients face a myriad of psychosocial and practical issues. Especially challenging is the time from an initial diagnosis to the onset of treatment and patient navigation services are important to guide patients, especially underserved populations, through this maze of uncertainty. Here we report on the Pennsylvania Patient Navigator Demonstration Project (PaPND) designed to evaluate the acceptability, feasibility, and impact of a culturally and linguistically appropriate non-clinical navigator program. The development of the project, based on behavioral theory and community-based participatory research principles, is described. Forty-four cancer patients from diverse backgrounds participated, which included a baseline assessment, navigation services, and a four week and twelve week follow-up assessment. On average, participants experienced 1.8 barriers with transportation and insurance issues the most common barriers. The majority (56%) of the barriers required more than an hour of the navigator's time to address, with insurance, transportation and caregiver/support issues requiring the most time. Overall patients were fairly satisfied with the navigation services. The findings showed improvement patient's stress-related thoughts, cognition (understanding of their disease), expectancies and beliefs or values/goals, as well as self-efficacy of managing cancer related issues from the baseline to follow-up assessments. The evaluation results suggest that providing and connecting cancer patients to appropriate information to improve their understanding of their diagnosis and recommended treatments needs to be addressed, and where the integration of non-clinical and clinical navigation is essential. In addition, more attention to the assessment of psychosocial issues, such as the patients' emotional worries, and more comprehensive training in these areas would enhance navigation programs.