A critical challenge for biomedical investigators is the delay between research and its adoption, yet there are few tools that use bibliometrics and artificial intelligence to address this translational gap. We built a tool to quantify translation of clinical investigation using novel approaches to identify themes in published clinical trials from PubMed and their appearance in the natural language elements of the electronic health record (EHR).

As a use case, we selected the translation of known health effects of exercise for heart disease, as found in published clinical trials, with the appearance of these themes in the EHR of heart disease patients seen in an emergency department (ED). We present a self-supervised framework that quantifies semantic similarity of themes within the EHR.

We found that 12.7% of the clinical trial abstracts dataset recommended aerobic exercise or strength training. Of the ED treatment plans, 19.2% related to heart disease. Of these, the treatment plans that included heart disease identified aerobic exercise or strength training only 0.34% of the time. Treatment plans from the overall ED dataset mentioned aerobic exercise or strength training less than 5% of the time.

Having access to publicly available clinical research and associated EHR data, including clinician notes and after-visit summaries, provided a unique opportunity to assess the adoption of clinical research in medical practice. This approach can be used for a variety of clinical conditions, and if assessed over time could measure implementation effectiveness of quality improvement strategies and clinical guidelines.

People with intellectual disability (PwID) and epilepsy have increased premature and potentially preventable mortality. This is related to a lack of equitable access to appropriate care. The Step Together guidance and toolkit, developed with patient, clinical, charity and commissioning stakeholders, allows evaluation and benchmarking of essential epilepsy service provision for PwID in eight key domains, at a care system level.

To evaluate care provisions for adult PwID and epilepsy at a system level in the 11 integrated care systems (ICSs) of the Midlands, the largest NHS England region (population: approximately 11 million), using the Step Together toolkit

Post training, each ICS undertook its benchmarking with the toolkit and submitted their scores to Epilepsy Action, a national UK epilepsy charity, who oversaw the process. The outcomes were analysed descriptively to provide results, individual and cumulative, at care domain and system levels.

The toolkit was completed fully by nine of the 11 ICSs. Across all eight domains, overall score was 44.2% (mean 44.2%, median 43.3%, range 52.4%, interquartile range 23.8–76.2%). The domains of local planning (mean 31.1%, median 27.5%) and care planning (mean 31.4%, median 35.4%) scored the lowest, and sharing information scored the highest (mean 55.2%, median 62.5%). There was significant variability across each domain between the nine ICS. The user/carer participation domain had the widest variation across ICSs (0–100%).

The results demonstrate a significant variance in service provision for PwID and epilepsy across the nine ICSs. The toolkit identifies specific areas for improvement within each ICS and region.

Medication nonadherence is a public health concern and can impact clinical trial data quality. Traditional compliance collection (pill counts, diaries) can be unreliable in central nervous system trials. As such, strategies such as adherence technologies may play a key role in trial outcomes. AiCure, a computer vision-assisted dosing mobile application (app), collects dosing data and connects patients to sites for dosing support. Phone-based computer vision algorithms confirm dosing and transfer videos for artificial intelligence and human review. Boehringer Ingelheim is partnering with AiCure on pilot trials using AiCure adherence data to improve patient retention and clinical trial data quality. Here we report initial findings.

This pilot used data from two Phase II trials on the efficacy and safety of BI 409306 in people with schizophrenia (NCT03351244) or Attenuated Psychosis Syndrome (NCT03230097). The AiCure mobile app alerted participants to dosing protocols. The dose event was visually confirmed, providing sites a real-time view of adherence and allowing for targeted outreach and intervention. Adherence data from the first 2 weeks generated quantitative, machine-learning models to predict the individual adherence over the trial. Predictive modeling explored different monitoring periods (7-, 10-, and 14-day) and adherence cutoff points (0.8, 0.7, 0.6).

Initial AiCure assessment identified 43% of participants in NCT03351244 as ≤80% compliant (definition of compliance >80% compliant). Variance in adherence rates between electronic case report forms (eCRF; 78%) and AiCure (26%) data was also observed in the highly compliant/adherent group in NCT03230097. Using the first 2 weeks of adherence data (both studies combined), a participant’s adherence predicted their average adherence for the remainder of the trial. Observation of a participant’s adherence for the latest 4 weeks predicted the probability of premature dropout from the trial. There were further correlations of lower predicted adherence with actual disposition-based dropouts.

The early adherence predictive model (0.6 adherence cutoff) identified 22%, 20%, and 19% of patients for trial NCT03351244 (total n=235) as high-risk patients (low-adherence prediction) across 7-, 10-, and 14-day monitoring periods, respectively. Of those high-risk patients, 81%, 90%, and 96%, respectively, were truly nonadherent based on actual adherence data. The 14-day monitoring period model provided the lowest false omission rate, indicative of a better performing model.

AiCure data provided insights into patient behavior and adherence patterns which would not be available via CRF. Predictive models developed with AiCure adherence data can identify and predict future poor adherers. This creates opportunities to plan interventions and mitigation strategies to improve patient adherence during trials, thereby providing test drugs the best opportunity at proving efficacy.

Boehringer Ingelheim International GmbH (NCT03351244/1289-0049 and NCT03230097/1289-0032)

While declarative learning is dependent on the hippocampus, procedural learning and repetition priming can operate independently from the hippocampus, making them potential targets for behavioral interventions that utilize non-declarative memory systems to compensate for the declarative learning deficits associated with hippocampal insult. Few studies have assessed procedural learning and repetition priming in individuals with amnestic mild cognitive impairment (aMCI).

This study offers an overview across declarative, conceptual repetition priming, and procedural learning tasks by providing between-group effect sizes and Bayes Factors (BFs) comparing individuals with aMCI and controls. Seventy-six individuals with aMCI and 83 cognitively unimpaired controls were assessed. We hypothesized to see the largest differences between individuals with aMCI and controls on declarative learning, followed by conceptual repetition priming, with the smallest differences on procedural learning.

Consistent with our hypotheses, we found large differences between groups with supporting BFs on declarative learning. For conceptual repetition priming, we found a small-to-moderate between-group effect size and a non-conclusive BF somewhat in favor of a difference between groups. We found more variable but overall trivial differences on procedural learning tasks, with inconclusive BFs, in line with expectations.

The current results suggest that conceptual repetition priming does not remain intact in individuals with aMCI while procedural learning may remain intact. While additional studies are needed, our results contribute to the evidence-base that suggests that procedural learning may remain spared in aMCI and helps inform behavioral interventions that aim to utilize procedural learning in this population.

Many mental disorders, including depression, bipolar disorder and schizophrenia, are associated with poor dietary quality and nutrient intake. There is, however, a deficit of research looking at the relationship between obsessive–compulsive disorder (OCD) severity, nutrient intake and dietary quality.

This study aims to explore the relationship between OCD severity, nutrient intake and dietary quality.

A post hoc regression analysis was conducted with data combined from two separate clinical trials that included 85 adults with diagnosed OCD, using the Structured Clinical Interview for DSM-5. Nutrient intakes were calculated from the Dietary Questionnaire for Epidemiological Studies version 3.2, and dietary quality was scored with the Healthy Eating Index for Australian Adults – 2013.

Nutrient intake in the sample largely aligned with Australian dietary guidelines. Linear regression models adjusted for gender, age and total energy intake showed no significant associations between OCD severity, nutrient intake and dietary quality (all P > 0.05). However, OCD severity was inversely associated with caffeine (β = −15.50, 95% CI −28.88 to −2.11, P = 0.024) and magnesium (β = −6.63, 95% CI −12.72 to −0.53, P = 0.034) intake after adjusting for OCD treatment resistance.

This study showed OCD severity had little effect on nutrient intake and dietary quality. Dietary quality scores were higher than prior studies with healthy samples, but limitations must be noted regarding comparability. Future studies employing larger sample sizes, control groups and more accurate dietary intake measures will further elucidate the relationship between nutrient intake and dietary quality in patients with OCD.