Clinical Research Directory

Silent Deployment and Prospective Evaluation of Zhunxin Agent for Emergency Chest Pain Assessment

The goal of this prospective, multicenter observational study is to evaluate how well Zhunxin Agent, an artificial intelligence system for chest pain assessment, performs in real-world emergency department settings. The study will include people who receive routine care for acute chest pain at participating hospitals. The main questions this study aims to answer are: 1. How accurately can Zhunxin Agent identify serious causes of acute chest pain during routine emergency care? 2. How well can Zhunxin Agent distinguish people at different levels of clinical risk? Zhunxin Agent will run in silent mode using clinical information collected during routine care. Its predictions will not be shown to treating clinicians and will not affect clinical decisions, diagnostic tests, or treatment. Researchers will compare the predictions made by Zhunxin Agent with the final clinical diagnoses established through routine medical care. Participants will: 1. Receive usual emergency care according to local clinical practice 2. Have routinely collected clinical data analyzed by Zhunxin Agent in the background 3. Receive no additional treatment or clinical intervention based on the Agent's predictions

"Discovery2" Study of Using MCG at Emergency Departments

The purpose of this research is to collect the magnetic signals from the heart to identify features that may help Emergency Department (ED) doctors differentiate high and low risk patients for heart related chest pain.

Validation of the HAR Score for Prioritization of Patients Calling the Emergency Medical Service for Chest Pain by Emergency Call Dispatcher

The lifetime prevalence of chest pain in the general population is 20-40%. The etiologies to be evoked from the outset of management are those of cardiovascular origin, such as acute coronary syndrome (ACS) and pulmonary embolism. ACS is responsible for almost 20% of deaths. Delay in treatment is a major prognostic factor, given the importance of coronary reperfusion. In France, one of the first contacts with the healthcare system is the medical regulation assistant (MRA) at the Centre 15. His or her role is to prioritize the call according to the identification of immediate signs of seriousness, and if necessary, to decide autonomously to send a rescue team before medical regulation. Depending on the reason for the call and any signs of seriousness, it prioritizes the call according to the expected response time. In line with current recommendations, all calls for chest pain should be answered by an emergency medical dispatcher (EMR) within 5 minutes. However, 60-90% of chest pain calls are not of cardiovascular origin. Their prioritization could therefore be re-qualified for longer response times. Given the frequency of this type of call, a more efficient MRA referral strategy is needed. To achieve this, decision-support tools would be essential. The performance of the HAR (History, Age and Risk Factors) score has been recently explored, derived from the HEART score, in a previous single-center prospective study in 2019. It stratifies the risk of a major cardiovascular event (MCE) into low (0 or 1 point), intermediate (2 or 3 points) or high (4, 5 or 6 points). Investigator's hypothesis is that the HAR score could be entrusted to MRA, to enable them to optimize the prioritization of patients calling with non-traumatic chest pain, by qualifying low-risk chest pain calls on the one hand, which could be prioritized in P2 SNP, and high-risk calls on the other, making it possible to anticipate the dispatch of an emergency service.

Safety and Clinical Performance of the Freesolve Resorbable Magnesium Scaffold (RMS) System in Subjects With Coronary Artery Lesions

The objective of this study is to assess the safety and efficacy of the Freesolve resorbable magnesium scaffold (RMS) in the treatment of subjects with up to two de novo lesions in native coronary arteries compared to the Xience coronary drug-eluting stent (DES) system

SMARTwatch for the Diagnosis of ST-segment Elevation Myocardial Infarction in Patients With Chest Pain

The main symptom that initiates the diagnostic and therapeutic process for patients with suspected acute coronary syndrome is chest pain. Based on a standard 12-lead electrocardiogram (ECG), patients can be diagnosed with ST-segment elevation myocardial infarction (STEMI), which requires immediate medical treatment. Recently, wearable devices like smartwatches with ECG capabilities have opened new pathways for cardiac triage, but their diagnostic precision and technical viability in a real, unselected Emergency Department setting need to be confirmed. The primary objective of this prospective, observational study is to compare the diagnostic capacity of a 9-lead ECG obtained with a smartwatch against the standard 12-lead ECG for diagnosing STEMI in patients consulting for chest pain. During the study, patients evaluated by the on-call cardiologist for ischemic chest pain will undergo their standard care. In addition to the standard 12-lead ECG, a 9-lead ECG will be sequentially recorded using a smartwatch. This is an observational study, meaning the smartwatch recording will not cause any delay in clinical action or negatively impact the patient's standard treatment. Specifically, the study aims to: * Analyze the diagnostic agreement between expert cardiologists when blindly and independently classifying the smartwatch recordings versus the standard ECG recordings as "STEMI" or "non-STEMI". * Evaluate the technical feasibility of using the smartwatch in an Emergency Department setting by assessing the percentage of unreadable records due to artifacts.

The Application of Large Language Model in Emergency Chest Pain Triage

This study will evaluate the accuracy and efficiency of large language model in emergency triage.

ER-VISION-AI Study

Prospective, multicenter, randomized, open-label, blinded-endpoint (PROBE-like) clinical trial evaluating whether physician-supervised Generative Pre-trained Transformer (GPT)-assisted multimodal diagnostic support improves diagnostic concordance in emergency department patients presenting with acute cardiopulmonary symptoms.

One-hoUr Troponin Using a High-sensitivity Point-Of-Care Assay in Emergency Primary Care

Acute chest pain is a prevalent medical emergency in primary emergency care settings. Triage of chest pain prior to hospital admission presents significant challenges due to the absence of sufficiently sensitive diagnostic tools. Clinical signs, symptoms, risk assessment scores, or a normal electrocardiogram (ECG) can reliably exclude acute myocardial infarction (MI). This diagnostic uncertainty has resulted in chest pain being the second most common cause for acute hospital referrals from Norwegian emergency primary care, even though chest pain is frequently non-cardiac in origin. In acute MI events, cardiac troponins are released into the bloodstream from the damaged myocardium, where low values are used to exclude MI. Until recently, such testing has necessitated using high-sensitivity cardiac troponin (hs-cTn) assays, which have been limited to hospital laboratories. However, recent technological advancements in point-of-care (POC) testing allow access to whole-blood assays that meet high-sensitivity criteria. In this upcoming project, the investigators will evaluate the implementation of a whole-blood POC assay (QuidelOrtho TriageTrue hs-cTnI) across six Norwegian emergency primary care clinics. The study plans to enrol 2,500 patients over a period of 1.5 years. The clinical performance of the novel strategy will be investigated, as well as its impact on healthcare utilization and hospital referrals compared to standard care. Additionally, the investigators will assess the prevalence of persistent chest pain and its effects on quality of life, alongside psychological stress and anxiety, through validated questionnaires. This project aims to offer better and more comprehensive management of the large group of emergency primary care patients with acute chest pain, contributing to reduced hospital referrals, improved quality of life, and more sustainable use of healthcare services.

Osteopathic Treatment in Adult Patients With Cystic Fibrosis

To study the contribution of osteopathy on the reduction of pain in adult patients with cystic fibrosis

Vericiguat in Patients With Coronary Microvascular Dysfunction Causing Stable Chest Pain (V-COM)

This is a randomised controlled trial to determine the effectiveness of Vericiguat to improve stress myocardial blood flow (MBF) and myocardial perfusion reserve as measured by cardiac magnetic resonance (CMR) imaging.

Risk Factors, Costs, and Impacts of ED Boarding

The goal of this observational study is to learn about the risk factors, costs, and operational impacts of emergency department boarding (patients admitted to the hospital but remaining in the emergency department awaiting placement on an inpatient floor) The main questions it aims to answer is: 1. What characteristics of patients make them more likely to experience ED boarding? 2. What is the impact of ED boarding on costs of health care? 3. How do high-boarding environments affect the clinical care of all patients in the emergency department, including those that do not board themselves. Data will be secondary in nature, collected in the regular Participants already taking intervention A as part of their regular medical care for RA will answer online survey questions about their joint pain for 5 years.

Contactless Ultrasound Data Acquisition in Emergency Departments to Discriminate the Origin of Dyspnea and Chest Pain

PAnDA-One is a prospective, multicenter, interventional study (10 centers, France) aimed at developing and validating a diagnostic support algorithm based on the ADx-One medical device, which non-invasively acquires thoracic vibrations using airborne ultrasound. The study will enroll 2,500 patients presenting to the emergency department with acute dyspnea or non-traumatic chest pain, divided into a development cohort (N = 1,500) and an independent test cohort (N = 1,000). The deep learning algorithm will be trained to discriminate cardiovascular from non-cardiovascular origins of symptoms, and its performance will be assessed by AUROC, sensitivity, and specificity against a final diagnosis established by an expert adjudication committee. Patient management will not be modified by study participation.

Hormones, Outcomes, and Pain Pathways in Exercise Study

The goal of the proposed project is to evaluate a mechanical intervention (sports bras designed specifically for full busted women) to alleviate neck, shoulder, arm, and back pain in full-busted women and investigate the contribution of non-mechanical pathways associated with this type of pain in women. Specifically, the investigators will investigate how sex-hormones, inflammation, and remapping of specific regions of the brain contribute to the manifestation of neck, shoulder, arm, and back pain in full-busted women across the lifespan.

Machine Learning for Diagnosis of Occlusive MI in LBBB Patients

This study investigates a new way to diagnose severe heart attacks in patients who have a specific electrical heart pattern called a Left Bundle Branch Block (LBBB). When patients present to the emergency department with chest pain, doctors routinely perform an electrocardiogram (ECG) to check for a heart attack. However, the presence of an LBBB can alter the heart's electrical signals on the ECG, effectively masking or hiding the typical signs of an ongoing acute coronary occlusion (a completely blocked artery). This making it highly challenging for emergency physicians to make an accurate and rapid diagnosis. The primary purpose of this prospective and observational research is to develop and evaluate an artificial intelligence/machine learning (ML) model that can analyze digital 12-lead ECG signals to accurately predict a true blocked coronary artery in patients with LBBB. The machine learning model will analyze raw digital ECG waveforms to detect subtle, microscopic patterns that might be missed by the human eye. To confirm the accuracy of the model, its predictions will be compared directly with invasive coronary angiography results, which is the gold standard reference method used to visualize blocked vessels. Additionally, the study aims to evaluate if the model can differentiate between a true heart attack caused by a blocked artery (Type 1 MI) and other non-occlusive conditions that cause elevated heart enzymes (Type 2 MI). Ultimately, the investigators intend to determine whether integrating this machine learning tool into emergency care can safely reduce the rate of unnecessary emergency invasive procedures for patients who do not have a true coronary blockage.

Evaluation and Optimization of Telephone Triage Using Artificial Intelligence (AI) Models for the Detection of Demands for Time-dependent Pathology at the Emergency and Urgent Care Coordination Center (CCUE).

Improving Telephone Triage in Emergency Calls with AI The Coordinating Centre for Urgencies and Emergencies in Andalusia (CCUE) handles thousands of calls every day. Each call needs to be assessed based on the information given over the phone to determine how serious the case is. The reasons for calling range from minor health issues to life-threatening emergencies like cardiac arrest (CPA). This project focuses on improving telephone triage for four key emergency situations that often indicate severe or life-threatening conditions: Unconsciousness / Cardiac arrest Difficulty breathing Chest pain (non-traumatic, possible heart-related issues) Stroke symptoms Our goal is to make telephone triage more accurate and efficient by using advanced Artificial Intelligence (AI) techniques, including Machine Learning (ML) and Natural Language Processing (NLP). These tools will help CCUE operators make better and faster decisions, ensuring that patients receive the right care as quickly as possible. How it will be done: The investigators will analyze anonymized historical call data from the emergency coordination system (CCR) and digital clinical records (HCDM). This includes: Structured data: Predefined fields, such as answers to standard triage questions. Unstructured data: Free-text notes and other information recorded during the call. A hybrid AI approach will be used, combining: Traditional AI methods (supervised learning and deep learning) to classify cases. Generative AI techniques (advanced language models) to extract useful insights from free-text data. Building the Best Prediction Model To find the most effective AI model, we will test different machine learning techniques, including: Decision Trees Random Forests Support Vector Machines (SVM) XGBoost Ensemble methods Neural Networks We will also analyze which questions and variables are the most important in predicting the severity of a case. Based on this, we will suggest improvements to the current triage questions to enhance accuracy. Measuring Success We will evaluate the AI model using key performance metrics, including: Accuracy (overall correctness) Sensitivity (ability to detect real emergencies) Specificity (ability to avoid false alarms) False Positive \& False Negative Rates (how often the system makes mistakes) Likelihood Ratios (how well the system distinguishes between urgent and non-urgent cases) F1-Score \& ROC Curve (overall performance indicators) Why This Matters This project will assess how effective the current telephone triage system is and develop a new AI-powered model to improve it. The goal is to help emergency operators quickly identify the most serious cases, reducing response times and improving patient outcomes. In the future, the investigators aim to integrate this improved AI model into the CCUE system to enhance emergency response across Andalusia.

Intraoperative Echocardiography in Low-Risk CABG Surgery

This goal of this study is to better understand when and where intraoperative transesophageal echocardiography (TEE) should (or should not) be used during coronary artery bypass graft (CABG) surgeries.

Triage and Recognition of Acute Aortic Dissection in Chest Pain by Electrocardiogram-Artificial Intelligence

The goal of this prospective multicenter observational study is to learn whether an artificial intelligence model based on electrocardiograms (ECGs) can help diagnose acute type A aortic dissection (TAAD) in adults who come to the emergency department with chest pain or related symptoms. The main question it aims to answer is: Can the AI-ECG model accurately distinguish TAAD from other causes of chest pain in a real-world emergency setting? Researchers will compare the AI model's ECG-based predictions with the final diagnosis confirmed by computed tomographic angiography (CTA), which is the reference standard. Participants will undergo routine emergency ECG testing and subsequent diagnostic evaluation as part of standard care. Clinical and ECG data will be collected from five tertiary hospitals, and the model's diagnostic performance will be assessed across centers.

Arterial Stiffness for Improved Prediction of Coronary Artery Disease by Coronary CT Angiography

This study will evaluate the ability of device-estimated pulse wave velocity and machine learning methods to improve the prediction of potential symptomatic coronary artery disease

CARE-CP (Testing a Cardiovascular Ambulatory Rapid Evaluation for Patients With Chest Pain)

The goal of this study is to determine if rapid outpatient evaluation vs hospitalization management is the best strategy (based on patient-centered measures and safe, equitable, and efficient resource use) for evaluating patients with acute chest pain who are at moderate risk for acute coronary syndrome (ACS). Patients will be randomized in the Emergency Department to either an outpatient evaluation (CARE-CP) or hospitalization evaluation for their symptoms.

Coronary Computed Tomographic Angiography Combined With CT-FFR in Intermediate-Risk Chest Pain Patients.

This study aims to investigate the guiding value of coronary CTA combined with CT-FFR in diagnostic and treatment decision-making for emergency chest pain patients at moderate risk, as well as its impact on clinical outcomes. Through a prospective multicenter randomized controlled trial, this research compares the preventive effects of early application of this technology versus standard care on major adverse cardiovascular and cerebrovascular events (MACCE), with the goal of optimizing the diagnostic and treatment processes for emergency chest pain patients.

CHEST-CA: Study of Chest Pain and Hidden Cardiac Amyloidosis

The objective of this observational, prospective study is to determine the prevalence of Cardiac Amyloidosis (CA) in males over the age of 65 who experience chest pain but show no signs of coronary artery disease (CAD). Prior to inclusion, all patients will have undergone a CT coronary angiogram or an Rb-PET scan to rule out the possibility of CAD. Participants will be subject to several examinations, including blood tests, urine samples, ECG, echocardiography, and bone scintigraphy. An endomyocardial biopsy may be conducted if necessary.

Artificial Intelligence Stress Echo (FINESSE) Project

The goal of this observational study is to learn whether combining stress echocardiography (stress echo) results with routine clinical information can better predict important heart outcomes in adults (18+) with chest pain who were assessed for suspected coronary artery disease. The main questions it aims to answer are: Can an artificial intelligence / machine learning model using stress echo findings plus clinical factors (such as blood pressure, diabetes, smoking, other health conditions, medications, and body measurements) predict major heart-related events (such as heart attack, stroke, death related to heart disease, or the need for coronary procedures) more accurately than stress echo results alone? Can the model help identify which patients are most likely to benefit from further invasive assessment and possible coronary revascularisation (for example, a stent or bypass surgery)? Which combination of stress echo measurements and clinical factors contributes most to risk prediction? Participants will: Not be asked to attend extra visits or have additional tests for this study. Have their existing stress echo reports and routinely collected hospital record data analysed (approximately 3,000 people who previously had dobutamine stress echo at Milton Keynes University Hospital). In some cases, if outcomes are not fully available from hospital records, the research team may check additional sources (such as GP records, or contacting the patient if appropriate) to confirm whether a major heart-related event occurred.

Virtual Reality for Non-cardiac Chest Pain

The purpose of this study is to determine if virtual reality (VR) will improve symptoms in non-cardiac chest pain (NCCP).

Early Warning and Classification Model for Acute Non-traumatic Chest Pain

Acute non-traumatic chest pain is one of the common causes of presentation in emergency patients, but the causes of acute non-traumatic chest pain are complex, the severity of the condition varies greatly, and the specificity of symptoms is not high. Machine learning and intelligent auxiliary models can greatly shorten the time of clinical decision-making, and improve the accuracy of etiological diagnosis in patients with chest pain, reduce the rate of misdiagnosis and missed diagnosis, and provide a clear direction for further treatment.