Clinical Research Directory

Benchmarking Large Language Models Against Tumour Boards for Oncology Treatment Recommendations

BEACON (Benchmarking AI for Clinical Oncology decisioNmaking) is a prospective, multicentre, comparative, blinded, non-interventional benchmark comparing the treatment recommendations of six frontier large language models (LLMs) with those of multidisciplinary tumour boards (RCP) in oncology treatment planning. One hundred standardised synthetic cases (20 per localisation, across breast, lung, urological, digestive and gynaecological cancers) are submitted as identical structured input to two independent tumour boards per localisation and to six frontier LLMs. Every recommendation, human or model, is decomposed into five predefined decision domains (intent, surgery, radiotherapy, systemic therapy with its line, work-up and biomarkers). For each domain, concordance between two recommendations is scored 2 when the same options are selected, 1 when at least one option is shared, and 0 when none is shared; the score is computed automatically from the recommendation forms, without human scoring. The primary endpoint is the mean domain score between each LLM and each tumour board, read against the same score computed between the two tumour boards of the same case, so that humans and models are measured by an identical rule and no respondent contributes to its own reference. A co-primary safety endpoint captures the proportion of recommendations carrying serious harm potential, because concordance alone can conceal dangerous errors. Where the two boards select different options, the case-domain is classified EQUIPOISE and, like every discordance, is adjudicated by an independent panel blinded to the source of the recommendation. Tumour boards record their recommendations during the meeting itself, on a dedicated platform (https://etude-beacon.fr) that reveals a case only once it is presented and time-stamps that reveal, so that no board can read a case in advance. BEACON is designed as reusable, openly licensed, pre-registered infrastructure: all synthetic cases, evaluation rubrics, scoring algorithms, verbatim prompts and raw model outputs are released for full reproducibility.

Training Diagnostic Specialists to Use Artificial Intelligence Safely: The DISCORD-Dx Study

This randomized study evaluated whether a structured reasoning strategy called DISCORD-Dx could help specialist doctors use artificial intelligence (AI) recommendations more safely during diagnostic decision-making. The strategy was designed to help specialists benefit from correct AI advice while resisting plausible but incorrect AI recommendations. Forty-six consultant specialists in pathology and diagnostic radiology from two hospitals in Bahawalpur, Pakistan, were randomly assigned to receive either DISCORD-Dx training or time-matched conventional AI-literacy training. During assessment, participants first recorded and locked their own diagnosis before seeing a standardized AI recommendation. They then reviewed the AI advice and entered a final diagnosis. The AI recommendations included both correct recommendations and deliberately generated plausible errors that had been independently reviewed by specialists. The main outcome was appropriate reliance on AI, defined as following correct AI advice or resisting erroneous AI advice immediately after training. Other outcomes included harmful switching from a correct diagnosis to an incorrect diagnosis after erroneous AI advice, over-reliance, under-reliance, final diagnostic accuracy, decision time, and appropriate reliance at 8 weeks. No participant interacted with a live AI system, and study responses did not affect patient care.

Supporting Just-In-Time Consent for Prenatal Screening: The INFORM Study

This clinical trial is about prenatal genetic screening. It will test an intervention to help people make decisions about screening. The intervention is a short set of information cards about screening. This intervention is for pregnant participants. They will use the intervention on their mobile phone before they see their doctor. The study has one main question: * Do participants who use the intervention feel more confident when they make a decision about screening? Researchers will compare participants who use the intervention to participants who do not. All participants will have their usual care when they visit their doctor. What will participants do? * Participants must be pregnant. They will sign up for the study before their first doctor's visit for their pregnancy. This is the visit where their doctor usually talks with them about screening. * Some participants will use the intervention before their first doctor's visit. Other participants will not use it. * All participants will talk with a researcher on the phone after their first doctor's visit. * Participants who use the intervention will answer a short survey on their phone. * A few participants who use the intervention will talk with a researcher a second time on the phone.

The Effect of Laughter Yoga on Individual and Organizational Outcomes in Nurse Managers

The goal of this clinical trial is to learn if laughter yoga can improve both individual and organizational outcomes in nurse managers. The main questions it aims to answer are: * Does laughter yoga lower burnout and stress levels in nurse managers? * Does laughter yoga improve work-life quality and job performance? * Does laughter yoga help nurse managers make better decisions and solve problems more effectively? * Does laughter yoga lower compassion fatigue and support positive approaches to workplace conflict? Researchers will compare a laughter yoga group with a control group to see if there are meaningful differences. Participants will: * Join structured laughter yoga sessions for a defined period (weekly sessions). * Complete surveys before and after the program about stress, burnout, work-life quality, decision-making, problem solving, job performance, compassion fatigue, and conflict approaches. * Continue their usual work while attending sessions.

Heart Rate Variability for Practitioner Stimulated Reflection and Decision-making Optimisation

At the heart of healthcare is the interaction between healthcare practitioners and patients. It is believed that optimisation of this interaction can improve patient relevant outcomes, safety and patient experience. Through utilisation of practitioner physiological data, heart rate variability (HRV), to help practitioners make better decisions and optimise practice, it is considered possible to improve decision making around patient care and improve outcomes and safety. The modern intensive care unit (ICU) is a dynamic data rich environment requiring rapid and accurate decision making. Advances in ventilator technology, electronic patient monitoring and electronic health records (EHR) have provided exponential growth in data produced for patients and the need for complex decision making. However, data overload and alarm fatigue can result in poor understanding and a delayed response from the practitioner in addressing the patient's needs. The aim of this study is to present and evaluate a psychophysiology training approach for practitioners derived from their cardiovascular response through the course of the working day, this will be measured using heart rate variability (HRV). Practitioner HRV has been shown to be linked to work related stress and is considered a biomarker of decision-making.

Development and Preliminary Application Evaluation of a Clinical Decision Support Training Platform for Dementia Care

This study consists of two phases: an observational phase and a single-arm interventional phase. In Phase 1, qualitative interviews will be conducted to explore the decision-making challenges faced by second-year students in a two-year undergraduate program who are approaching graduation when providing care for people with dementia. In Phase 2, a single-arm intervention will be implemented using an interactive web-based digital clinical decision support training platform. The following research questions will be examined: 1. Does the interactive web-based digital clinical decision support training platform significantly improve students' decision-making competency in providing assistance with activities of daily living for people with dementia? 2. Does the interactive web-based digital clinical decision support training platform significantly improve students' judgment competency in managing behavioral problems associated with dementia? 3. Does the interactive web-based digital clinical decision support training platform significantly improve students' competency in supporting family caregivers experiencing caregiving burden and in connecting them with appropriate resources?

Phosphatidylserine, Taurine, and Caffeine for Cognitive Fatigue in Professional Football Players

This randomized, double-blind, placebo-controlled, parallel-group trial evaluated neurocognitive fatigue resistance and football-specific decision-making following 28 days of taurine-caffeine supplementation with or without phosphatidylserine in professional male football players. Sixty-five male outfield football players from two professional clubs were randomized to placebo, taurine plus caffeine, or taurine plus caffeine plus phosphatidylserine. Neurocognitive fatigue resistance was evaluated during a standardized high-load Stroop/Flanker task, while football-specific tactical decision-making, visual-search behavior, and field-based reactive decision performance were assessed at baseline and after 28 days of supplementation.

Designing Effective Alcohol Health Warnings: An Experimental Study With Adults in the U.S.

Consuming alcohol is a dose-dependent and modifiable risk factor for breast cancer. Although alcohol consumption contributes to an estimated 16% of breast cancer cases, awareness of the link between alcohol and breast cancer risk remains low. Systematically developed and tested health warnings can support population-based approaches and intervention strategies to decrease alcohol consumption and breast cancer risk. For instance, the U.S. Food and Drug Administration can mandate specific warnings through statements (e.g., "WARNING: This product contains nicotine…") and color graphics depicting the negative health consequences of products that can harm public health, such as tobacco and alcohol. However, health warning statements and graphics should be assessed among intended audiences before implementation. Research has outlined principles for effective health warning statements. This project will test different health warning statements about the health effects of alcohol.

Building Relationship, Improving Dialogue, and Growing Empathy (BRIDGE): An Intervention to Support Decision Making for Critically Ill Children

Parents of young children in the intensive care unit may be faced with decisions about their child's care. The Building Relationship, Improving Dialogue, and Growing Empathy (BRIDGE) intervention was designed to help support parents as they make decisions for their child and communicate with the health care team. The main questions this study aims to answer are: 1. Do parents who receive the BRIDGE intervention report being better prepared to make decisions for their child? 2. Do parents who receive the BRIDGE intervention report less regret about the decisions they made for their child? Participants will complete surveys at baseline and approximately 2 weeks, 6 months, and 12 months following enrollment. Some participants will also participate in interviews about their experiences.

Effects of a Tactical Programme for Critical Thinking on Football-Specific Decision-Making in Under-9 Academy Players

This study evaluates whether two academy football training programmes are associated with different changes in football-specific cognitive-motor performance in under-9 male players. One academy cohort completed a Tactical Programme for Critical Thinking (TPCT) embedded within game-centred training, whereas a comparison cohort followed its usual repetition-oriented academy programme. Performance was assessed before and after 12 training sessions using the Stroop Task Football Test (STFT), including execution time, response accuracy, and a derived Total Index.

Critical Thinking Tactical Training in University Futsal Players

This study examined the effects of a tactical training program based on critical thinking (TPCT) on the tactical efficiency and decision-making performance of university futsal players. The intervention was designed to strengthen players' ability to interpret the dynamics of play, anticipate opponents' actions, and generate adaptive tactical responses under competitive conditions. The program followed a socio-constructivist framework, promoting learning through problem solving and interaction among teammates. Training sessions combined representative game situations, reflective questioning, and guided tactical discussions. A single-group pre-post design was implemented. Thirteen university players participated voluntarily after providing informed consent and receiving approval from the institutional ethics committee. Data were collected before and after the intervention to assess individual and collective tactical performance, goal effectiveness, and time of ball possession. The study aimed to provide evidence on the educational and performance impact of a critical thinking-based tactical approach in futsal, contributing to contemporary models of athlete development and pedagogical innovation in team sports.

Interventions in Mathematics and Cognitive Skills

The purpose of this study is to investigate neurocognitive mechanisms underlying response to intervention aimed at enhancing, and remediating weaknesses in, numerical skills in children, including those with mathematical learning disabilities (MLD).

Seeking Objectivity in Allocation of Advanced Heart Failure (SOCIAL HF) Therapies Trial

The primary goal of this study is to assess real-world effectiveness and implementation of an evidence-based multi-component strategy to reduce disparities in the allocation rate of advanced heart failure therapies, heart transplants and ventricular assist devices. This study proposes to implement evidence-based strategies that reduce unequal and unethical decision-making towards patients, replace subjective evaluations with objective criteria, and improve group dynamics in a randomized cluster trial. Our rigorously designed trial will inform national guidelines for advanced heart failure therapy allocation, and data are likely to be generalizable to other organ replacement treatments and advanced chronic disease decision-making processes across populations.

Testing Warning Labels for Retail Cannabis Products Using a Discrete Choice Experiment

This discrete choice experiment (DCE) study aims to address gaps in cannabis packaging regulatory research by testing how variations in cannabis packaging and health warning design impact reactions to packaging and intentions about cannabis use. The goal of this work is to identify the most effective combination of health warning features to improve consumer awareness of cannabis health risks. Establishing criteria for cannabis products in the US is critical because inconsistent state guidelines have resulted in contradictory policies in legal retail states, arguably leading to increased hazardous use and failure to meet public health standards. The contributions of this study's outcomes are expected to be significant because they will benefit public health as cannabis becomes available in legal retail markets and regulatory and governmental agencies seek effective ways to communicate cannabis risks to the public.

Initial Testing of a Behavioral Intervention About Genetic Services for Families at Risk of Lynch Syndrome

The purpose of the study is to see if our education materials help people at risk for Lynch syndrome decide about seeking genetic services. Untested relatives of patients with Lynch syndrome will be recruited to complete a baseline survey and will be randomized to receive either the an information letter or an information letter plus a booklet. Two follow-up surveys will be administered over the span of 6 months. Participants will also be invited to join an optional exit interview to provide feedback.

Effects of Cognitive Training on Executive Functions and Decision-Making in Adolescent Female Volleyball Players

This randomized controlled trial aims to evaluate the effects of a four-week tablet-based cognitive training program on executive functions and on-court decision-making performance in adolescent female volleyball players. Fifty licensed female volleyball players aged 12 to 14 years were randomly assigned to either an intervention group or a control group. The intervention group received cognitive training three times per week in addition to routine volleyball training, while the control group continued routine training only. Executive functions were assessed using the Stroop Test, Trail Making Test-A, Go/No-Go Test, and 2-Back Test. Volleyball-specific decision-making performance was evaluated using a video-based temporal occlusion test. The study investigates whether improvements in executive functions following cognitive training transfer to sport-specific decision-making performance.

K-ORCA: Testing a Decision Support Tool and Group Process for Selecting Interventions

This proposal responds to NIMH Objective 4.2.c to develop "decision-support tools and technologies that increase the effectiveness and continuous improvement of mental health interventions" by leveraging the Family First Prevention Services Act (FFPSA) policy opportunity. First, a web-based platform to host (a) a decision-support tool and (b) automated facilitation for group decisions with the tool will be developed with state partners' feedback. Next, decision makers leading their states' FFPSA quality improvement efforts will be engaged to pilot a decision-support intervention comprised of the tool and live or automated facilitation, and to evaluate the implementation quality of evidence-based programs adopted with the decision-support intervention.

Craving & Decision-Making

Craving is the strong desire for something, such as for substances in drug addiction and food or other activities in everyday life. Recent work suggests craving can influence how people make decisions and assign value to choice options available to them, yet the neural mechanisms underlying these interactions between craving and valuation remain unknown. To address this, this study uses cognitive decision-making tasks that measure how much individuals will pay (from a study endowment) to have everyday consumer items or snack foods when they crave something specific (opioids or a specific snack, respectively). First, the study will identify the neural mechanisms for how drug craving (craving for opioids) interacts with valuation for consumer items that have associations with drug use or not in people receiving treatment for opioid use disorder (OUD). This will be evaluated in the activity patterns and interactions among brain regions involved in craving and value assignment during decision-making. Then, the study will examine for parallel mechanisms for how food craving (craving for a specific snack) interacts with valuation for snack food items that have similar features to the craved snack or not in people receiving treatment for OUD and non-psychiatric community control participants.

Integrating Telehealth to Advance Lung Cancer Screening

The goal of this pragmatic trial is to learn if telehealth strategies can increase shared decision-making (SDM) for lung cancer screening (LCS). It will also learn about the equity of these strategies by conducting non-inferiority analysis by race and sex. The main questions it aims to answer are: 1. Does patient outreach using synchronous and asynchronous telehealth strategies increase completion of SDM visits for LCS? 2. Is the effectiveness of these telehealth strategies similar by race and sex? The study uses a Sequential Multiple Assignment Randomized Trial (SMART) design and includes two stages of interventions. The first stage of intervention includes direct patient outreach with an invitation to schedule either a 1) telehealth SDM visit or 2) telehealth or in-person SDM visit. Participants that do not respond to the first stage interventions receive a text message reminder encouraging SDM visit completion with or without digital care coordination.

"Safety in Dementia": An Online Caregiver Intervention

In an online randomized trial of Safety in Dementia with national recruitment and longitudinal follow-up, we will recruit informal caregivers of community-dwelling adults with dementia who have firearm access.

A Communication Tool to Assist Older Adults Facing Dialysis Choices

The purpose of this study is to test the effect of the "Best Case/Worse Case" (BC/WC) communication tool on receipt of palliative care and intensity of treatment at the end of life, quality of life, and quality of communication for older patients with end-stage renal disease (ESRD) receiving outpatient care at ten nephrology clinics. The intervention was developed and tested with acute care surgical patients at the University of Wisconsin (UW) and is now being testing to see if the intervention will work in a different setting. The intervention will be tested with 320 older adults who have end-stage renal disease (ESRD) and are receiving care from a nephrologist enrolled in the study. Randomly assigned nephrologists within each site will receive the intervention (training to use the BC/WC tool) or to be in the waitlist control, meaning that they will not be offered BC/WC training until the end of the study, when all participants have been enrolled. Participants will be on follow up with surveys and chart review for up to two years after study enrollment. Caregivers will also be invited to participate and complete surveys.

Perceptions of Key Domains of Home-Based Palliative Care Among Healthcare Professionals (MULTIPAL)

This observational cross-sectional study evaluates and compares healthcare professionals' perceptions of key domains of home-based palliative care. Using an anonymous online survey and multicriteria decision analysis (MCDA) methods, the study explores perceived importance, strategic prioritization, and self-assessed performance across five core palliative care domains. The study is conducted across Hospital-at-Home units throughout the Valencian Community (Spain).

Effects of Parents Included in Medical Round of Neonatal Intensive Care Unit

The goal of this cross-over randomized controlled study is to evaluate the effects of medical rounds with parents. The main questions it aims to answer are: * How feasible the protocol of this study is to include parents in the medical round? * Does the Family Round promote the quality of family centered care in the NICU perceived by parents and healthcare staff? * Does the Family Round promote parent-infant bonding? * Does the Family Round reduce parents' anxiety? * Does the Family Round increase parents' satisfaction? * Does the Family Round improve staff's communication skills to integrate parents in the discussion of medical rounds? Participants will participate in the Family Round for two weeks, which is organized by healthcare staff following a protocol aiming to integrate parents into the discussion. They will be compared to the two-week period without the Family Round.

Data2Action Oregon Project: Supporting Data-driven Decision-Making for Substance Use Services, Policy, and Overdose Prevention

Oregon's decision makers (e.g., community service providers, public health, justice, advocacy groups, payers) are calling for comprehensive, current, and trusted data to inform how they allocate resources to improve substance use services and mitigate the growing opioid and methamphetamine epidemics in their state. Consistent with the HEAL Data2Action call for Innovation projects that drive action with data in real-world settings, this study will refine and test the impact of a novel implementation strategy to engage cross- sector decision makers and make data that they identify as relevant to their decisions available to them in easy- to-use products. The proposed study aims to not only address critical knowledge gaps regarding how and when data can inform impactful, transparent decision-making, but to provide decision makers with the data that they need to achieve community-wide substance use prevention and treatment goals, including the increased delivery of high-quality, evidence-informed, services and the prevention of overdoses.