Overview
This section curates peer‑reviewed studies, preprints, and technical whitepapers directly relevant to Neurapulse. It is intended for researchers, clinicians, and technically inclined readers who want primary sources and methodological detail. Neurapulse is powered by Impirica’s research. For research papers on Impirica’s previous product evolutions (like Vitals), see impirica.tech. Impirica has performed over 150,000 assessments to date, including on-road and in-office tests, and has evolved its platform to Neurapulse (explained in the whitepaper below).Papers
-
Rapid cognitive testing predicts real-world driving risk in commercial and medically at-risk drivers – (Under Peer Review, 2025)
- Download: PDF
- Establishes the core validation of Neurapulse metrics and methodology.
- Sample size: n = 4,719.
Abstract
Abstract
Road safety is a major public and occupational health issue. Safe driving requires numerous cognitive and sensorimotor skills, and past literature suggests that cognitive testing can predict safe or unsafe driving in both healthy and medically at-risk drivers. However, such testing is often time-consuming and inaccessible. In this study, we designed a modified version of the Trail Making Test (TMT) which can be completed on a smartphone in approximately 5 minutes. We recruited 4405 commercially-licensed drivers and 314 medically at-risk drivers to complete the TMT, plus an on-road test of their driving abilities. We then trained and tested a logistic regression model using 50-50 splits on each dataset. The results of the model showed that the longer it took drivers in both groups to complete the TMT, the more likely they were to fail the on-road driving test. Accuracy for the commercial group was 83.8%, with a positive predictive value (PPV) of 34.4% and a negative predictive value (NPV) of 85.3%. Accuracy for the medically at-risk group was 63.1%, with a PPV of 55.8% and an NPV of 65.8%. Overall accuracy was 82.5%, with a PPV of 43.0% and an NPV of 84.3%. Log-transformed reaction time to targets was significantly associated with on-road failure in both driving groups. The results of this study suggest that a rapid and accessible version of the TMT can predict unsafe driving with comparable accuracy to more time-consuming and administratively burdensome means of testing.
-
Whitepaper – The Next Generation is Mobile
- Download: PDF
- Connects the validation findings to product design, deployment model, and real‑world usage.
-
The utility of cognitive testing to predict real world commercial driving risk (2023)
- Download: PDF
- Sample size: n = 1,924.
- Provides external evidence on predictive validity relevant to the cognitive constructs assessed in the validation paper.
Abstract
Background: Driving is a complex task which requires numerous cognitive and sensorimotor skills to be performed safely. On-road driver evaluation can identify unsafe drivers but can also be expensive, risky, and timeconsuming. Poor performance on off-road measures of cognition and sensorimotor control has been shown to predict on-road performance in privately-licensed light vehicle drivers, but commercial drivers have not yet been studied despite such vehicles generally being larger and heavier, thus increasing risks from unsafe driving.Method: Commercially-licensed truck, bus, and light vehicle drivers undertook the tablet-based Vitals cognitive screening tool, which measures reaction time, judgement, memory, and sensorimotor control, and also undertook an on-road driving evaluation using their vehicle. Accuracy and reliability of the Vitals tasks on predicting road test outcomes were investigated using a trichotomous classifier (pass, fail, borderline), and task performance was analyzed depending on vehicle type and road test outcome.Results: Performance on the Vitals tasks predicted on-road performance across all vehicle types. Participants who failed their on-road evaluation also demonstrated lower success on the Judgement task, fewer correctly replicated shapes on the Memory task, and less time on-target in the Control task compared to those who passed.Conclusion: Performance on cognitive and sensorimotor tasks is a good predictor of future driving performance and driver safety for commercially-licensed drivers. Regardless of vehicle type, stakeholders can use cognitive measures from the Vitals assessment to identify an increased driving risk. Use of the Vitals as a screening tool prior to on-road evaluation can benefit both drivers and evaluators. -
Validating the Vitals assessment: A replication study on cognitive assessments and commercial driving risk (2024)
- Download: PDF
- Replication on a random sample; replicated 2023 findings. Sample size: n = 2,167.
Abstract
Abstract
In a recently published article, the authors report a logistic regression model for predicting on-road driving risk in commercial drivers depending upon their performance on a battery of four cognitive and sensorimotor tasks (Scott et al., 2023). This tablet-based task battery, known as Vitals, consists of four tasks, which assess reaction time, decision making, working memory, and motor control, while on-road driving risk was assessed by modifying a standardized evaluation that is designed to identify errors characteristic of cognitive impairment risk. Past research has shown that this methodology offers good predictive value in assessing driver risk across a range of populations and vehicle types (Bakhtiari et al., 2020; Dobbs, 2013; Choi et al., 2015; Korner-Bitensky and Sofer, 2009). In Scott et al. (2023), we trained our regression model on a dataset of 1343 drivers recruited from a variety of commercial, judicial, medical, and academic sources, before validating it on our study sample, which consisted of 2167 commercial drivers recruited through their employers. Although we did not train our model exclusively on commercial drivers, it nevertheless showed good predictive value for our validation sample, with a strong relationship observed between a driver’s Vitals score and their likelihood of on-road evaluation failure (Fig. 1). This result suggests that the Vitals could be an effective screening tool for risky on-road driving in commercially licensed drivers.The study reported in Scott et al. (2023) was limited to a sample size of 2167 commercial drivers, but data collection continued following the cut-off date for inclusion in that study, and we now have a considerably larger sample of data to analyze. In part, we can affirm the credibility of a scientific result by the ability to replicate that result with new data collected under similar circumstances (Cesario, 2014; Nosek and Errington, 2020). Replication is not the only or essential method for affirming the credibility of a result, and even a replicable result can lack credibility if the methods lack validity (Devezer et al., 2019). Nevertheless, our ability to continuously collect data for this project offers a worthwhile opportunity to directly replicate the results of the model presented in Scott et al. (2023). Furthermore, the proprietary nature of that study’s tasks and dataset confers a responsibility on the authors to affirm or disaffirm the credibility of our study, given that direct replication cannot be performed by independent researchers.Using our new, post-validation sample, we re-ran the same logistic regression model reported in Scott et al. (2023) and then compared the model’s measures of positive predictive value (PPV), negative predictive value (NPV), false negative rate (FN%), and false positive rate (FP%) against those from our initial validation sample. Similar to the concept of a noninferiority trial in medicine (Mauri and D’Agostino, 2017), our aim with this new analysis is not to show that our model performs better on one sample versus the other, but instead to show that the model performs just as well on either sample. By performing this analysis, we hope to reinforce the credibility and utility of our model by validating it a second time on an independent sample of commercial drivers.
-
A Latent Variable Analysis of Psychomotor and Neurocognitive Performance After Acute Cannabis Smoking (2023)
- Download: PDF
- Informs construct validity and dimensional structure underlying psychomotor/neurocognitive measures connected to Neurapulse.
Abstract
Abstract
This paper evaluated a novel, tablet-based neurocognitive and psychomotor test battery for detecting impairment from acute cannabis smoking using advanced quantitative methods. The study was conducted in a state with legal, recreational cannabis use and included participants who use cannabis occasionally or daily, and a no use comparison group.Methods. Participants completed a tablet-based test assessing reaction time, decision making, working memory and spatial-motor performance. The test was completed before and after participants smoked cannabis (or after a rest period in the case of controls). An Exploratory Factor Analysis approach was implemented to reduce dimensionality and evaluate correlations across the four assessed domains. Linear regression models were utilized to quantify associations between factor scores and cannabis use groups (daily vs. occasional vs. no use).Results. Seven factors were identified explaining 56.7% of the variance among the 18 measures. Regression models of the change in factors after cannabis smoking indicated those who use cannabis daily demonstrated poorer performance on a latent factor termed Displaced and Delayed (standardized coefficient 0.567, 95% CI: 0.178, 0.955; P = 0.005) compared to those with no use. Those who use cannabis occasionally exhibited a decline in performance on a latent factor termed Recall and Reaction (standardized coefficient 0.714, 95% CI: 0.092, 1.336; P = 0.025) compared to no use.Conclusions. This analysis demonstrates an innovative, quantitative approach to study how cannabis consumption affects neurocognitive and psychomotor performance. Results demonstrated that acute cannabis use is associated with changes in neurocognitive and psychomotor performance, with differences based on the pattern of occasional or daily use.