Clinical Research Directory

Diagnostic Performance of Ai vs Junior Dentists

OBJECTIVES * Compare diagnosis of Periapical lesions \& Proximal caries by AI and junior dentists * Evaluate Validity of a deep learning based convolutional neural network (CNN) for detecting proximal caries lesions, periapical lesions compared to junior dentists.

A Prospective, Multicenter, Portable Pulmonary Function Comparison Study Aimed at Evaluating the External Clinical Validation of the Chronic Obstructive Pulmonary Disease Auxiliary Diagnostic Software LH-002 (Version: 2.0.0) in Clinical Diagnosis Accuracy

Chronic Obstructive Pulmonary Disease (COPD) is widely underdiagnosed in low- and middle-income countries and regions, due to the lack of accessible tools. Conventional spiromery tests for COPD diagnosis are expensive, require trained personnel to operate properly. Portable spirometry highly relies on the quality assurance of the tests. Since artificial intelligence (AI)-based cough analysis has demonstrated promising results in COPD diagnosis, this study aimed to evaluate the accuracy of an AI-based cough analysis software (Cough Search) compared to a portable spirometer for the auxiliary diagnosis of COPD.

Early Temporal Dynamics of Optic Nerve Sheath Diameter After Therapy in GCA

Giant cell arteritis (GCA) is an inflammatory disease of large and medium arteries that can cause irreversible vision loss. Glucocorticoids (GCs) rapidly suppress inflammation, but diagnostic imaging tests such as temporal artery ultrasound or biopsy often become falsely negative within days of treatment. The optic nerve sheath diameter (ONSD), measurable by ocular ultrasound, reflects perineural edema and may serve as a quantitative biomarker of ocular inflammation in GCA. The SONIC-TIME study (Early Temporal Dynamics of Optic Nerve Sheath Diameter After Glucocorticoid Therapy in Giant Cell Arteritis) is a single-center, prospective observational substudy embedded within SONIC-GCA (NCT05749094) at Hôpital du Sacré-Cœur de Montréal. It aims to characterize how rapidly ONSD decreases after GC initiation and how this trajectory relates to cumulative GC exposure, intravenous methylprednisolone, and early use of steroid-sparing therapies. Sixty participants with newly diagnosed GCA will undergo serial optic nerve sheath ultrasound, blood tests (CRP, ESR), and when feasible, temporal artery ultrasound over the first two months of therapy (Days 3, 7, 10, 14, 21, 28, and Month 2). No experimental treatments are given; all participants receive standard-of-care therapy. The primary objective is to quantify the percent change in mean ONSD from baseline to Day 28. Secondary objectives include modeling ONSD change over time, assessing associations with cumulative steroid dose and inflammatory markers, and estimating the time to normalization below the SONIC-GCA cutoff. Findings will define the optimal imaging window and refine the diagnostic and monitoring role of optic nerve ultrasound in GCA.

Time for a Diagnostic Paradigm Shift From STEMI/NSTEMI to OMI/NOMI

The investigators hypothesize that occlusion myocardial infarction(MI)/non-occlusion MI approach to MI treatment will better predict acute coronary occlusion on coronary angiography, better limit infarct size, better preserve left ventricular function and result in lower long-term adverse cardiac events (all cause mortality, all cause rehospitalization) compared to standard ST-elevation/non-ST-elevation MI paradigm.

Chongqing Adrenogenic Autonomic Cortisol Secretion Cohort Study

To investige the etiology, pathogenesis, diagnosis and treatment of adrenogenic autonomic cortisol secretion in Chinese adults.

Tumor Staging T of Bladder Tumours: Correlation of MRI and Anatomopathologic Analysis

Urinary bladder tumors with a frequency of 13000 new cases a year, have a heterogeneity in terms of survival according to the stage of local flooding. This is an aggressive tumor because of the potential muscular infiltration. It seems important in this case (muscular invasion), to increase the global survival. The anatomopathological analysis of the TURB (biopsy byTrans-Urethral Resection of the Bladder) is actually the gold standard for the pathology of bladder tumor. No need an imaging to discuss about the small and non muscular invasive tumor. But in most cases, the use is to perform at last an ultrasound or a CT-Scan, specially for the invasive tumor. A lot of studies show that CT SCAN. is not the best way of investigation for the bladder muscle invasion. However, as in the prostate cancer with the PIRADS Score, the MRI can be useful for the bladder, thanks to the sequence improvement to the machine. The study from Panebianco 2018, starts to talk about the MRI in the urinary bladder cancer with new radiological terms. It creates a new score called VIRADS score (as the PIRADS score already used for the prostate cancer). But it is never compared with the results of the TURB. Our study compares the results of the MRI pre operative versus the pathology results on prospective analysis. Main objective : T tumoral score in urinary bladder tumor : MRI versus pathology results. Secondary objectives : the contribution of diffusion weighted MRI in the bladder neoplasm. Type of study : interventional study, prospective, mono centric, single arm, intent-to-treat

Diagnosing Asthma With Clinically Accessible, Non-invasive, and Efficient Tests: a Child-inclusive Translational Investigation

Asthma is a common inflammatory respiratory disease affecting 11% of Canadians, but its diagnosis remains challenging, leading to delays in treatment or overtreatment. Spirometry with a reversibility test and bronchial provocation testing (BPT), considered the gold standard, are the reference diagnostic methods. However, access to BPT is limited as it is performed in hospital settings. Type 2 inflammation biomarkers, the fractional exhaled nitric oxide (FeNO) and blood eosinophils (EOS), represent a potential alternative. In addition to their prognostic and theragnostic value, these markers predict a good response to inhaled corticosteroids in individuals aged ≥ 6 years with asthma. However, their use remains restricted to pulmonologists in specialized clinics and is not recommended as a diagnostic tool in Quebec. Despite studies demonstrating their diagnostic value in specialized settings, these tests remain underexplored in primary care and insufficiently studied in children under 12 years. The objective of ou study is to evaluate the relevance and performance of FeNO and blood eosinophils in the diagnosis of asthma in children referred in primary care with non-diagnostic spirometry.

Trop2-targeting NIR-II Molecular Probe for Precision Diagnosis of Oral Cancer

Given the morphological and clinical similarities between certain oral malignant neoplasms and benign conditions such as oral ulcerations or inflammatory lesions, the potential for misdiagnosis is significant. Currently, histopathological examination via tissue biopsy remains the diagnostic gold standard; however, this approach is inherently invasive and may yield incomplete diagnostic results due to sampling limitations and spatial heterogeneity of the lesion. These challenges underscore the urgent need for the development of simple, non-invasive, cost-effective, and real-time in vivo imaging modalities. To address this, the investigators propose the utilization of a previously developed near-infrared II (NIR-II) fluorescent molecular imaging probe, TTP-ICG, which exhibits high specificity for TROP2, a transmembrane glycoprotein frequently overexpressed in oral squamous cell carcinoma (OSCC). This study will evaluate the diagnostic accuracy of OSCC through localized application of the TROP2-targeted probe via clinical specimens being soaked in TTP-ICG solution. Furthermore, the investigators aim to explore the feasibility of employing a mouth wash-based delivery system for the probe, with the ultimate goal of establishing a precise, minimally invasive, and cost-effective real-time imaging strategy for the early detection and diagnosis of OSCC. Such an approach has the potential to significantly enhance diagnostic precision, improve patient outcomes, and increase survival rates.

Evaluating AI-Gatekeeper Software in Coronary Artery Stenosis Screening: A Multicenter RCT

The purpose of this study is to determine the efficacy, safety, and cost-effectiveness of AI-Gatekeeper software to assist clinicians in the diagnosis of coronary artery disease by predicting coronary artery stenosis (≥50%) from a multimodal AI technology that integrates clinical risk factors and baseline blood tests, including chest X-ray, electrocardiogram, and echocardiogram, in patients with suspected coronary artery disease (coronary stenosis).

Artificial Intelligence-enabled ECG Detection of Congenital Heart Disease in Children: a Novel Diagnostic Tool

Congenital heart disease (CHD) is the most common congenital disease in children. The early detection, diagnosis and treatment of CHD in children is of great significance to improve the prognosis and reduce the mortality of children, but the current screening methods have limitations. Electrocardiogram (ECG), as an economical and rapid means of heart disease detection, has a very important value in the auxiliary diagnosis of CHD.Big data and deep learning technologies in artificial intelligence (AI) have shown great potential in the medical field. The advent of the big data era provides rich data resources for the in-depth study of CHD ECG signals in children. The development of deep learning technology, especially the breakthrough in the field of image recognition, provides a strong technical support for the intelligent analysis of electrocardiogram. The particularity of children electrocardiogram requires the development of a special algorithm model. At present, the research on the application of deep learning models to identify children's electrocardiograms is limited, and the training and verification from large data sets are lacking. Based on the Chinese Congenital Heart Disease Collaborative Research Network, this project aims to integrate data and deep learning technology to develop a set of intelligent electrocardiogram assisted diagnosis system (CHD-ECG AI system) suitable for children with CHD, so as to improve the early detection rate of CHD and improve the efficiency of congenital heart disease screening.

DIALOZIC - Pilot Study of a Diagnostic Pathway for Heart Failure in Rural Areas: the Contribution of Telebiology and Telemedicine

Heart failure is under-diagnosed, even though it is a highly prevalent pathology. The difficulties are accentuated in areas with low medical density. The aim of this project is to demonstrate the value, in terms of diagnosing heart failure, of a Nt-Pro-BNP point of care Test (POCT)in general practices. The aim of this pilot study is to evaluate the reliability of a diagnosis pathway adapted to a low medical density region.

Mitigating Automation Bias in Physician-LLM Diagnostic Reasoning Using Behavioral Nudges

The goal of this randomized controlled trial is to evaluate whether behavioral nudges can reduce automation bias, the uncritical acceptance of automated output, in physicians using large language models (LLM) like ChatGPT-5.1 for clinical decision-making. The main question it aims to answer is: Does a dual-mechanism behavioral nudge intervention (baseline accuracy anchoring plus case-specific color-coded confidence signals) reduce physicians' uncritical acceptance of incorrect LLM recommendations? Researchers will compare physicians who receive LLM recommendations along with a behavioral nudge to those who receive LLM recommendations without the nudge to assess if the nudge reduces automation bias. Participants will: * Evaluate six clinical vignettes accompanied by LLM-generated recommendations (half containing deliberate, clinically significant errors). * Control group: Be able to view LLM recommendations in standard format without the nudge. * Treatment group: Be able to view ChatGPT's diagnostic accuracy on standard medical datasets as an initial anchor, then receive color-coded confidence signals alongside each recommendation (e.g., red for low confidence). * Have their responses evaluated by blinded reviewers using an expert-developed assessment rubric to detect uncritical acceptance of erroneous information.

Intraoral Scanners as Periodontal and Dental Pathologies Diagnosis Tools

Periodontal diseases and dental pathologies are highly prevalent oral diseases. Thirty-three to fifty percent of adult population presented at least one untreated caries and more than 50% of French population are affected by severe periodontitis. These diseases affect dental organ or periodontal attached system but could have negative impact on general health, quality of life, word and individual well-being. Association between chronic diseases as diabetes, rheumatoid arthritis, cardiovascular diseases, and oral health have been well investigated. Dental and periodontal diagnosis is dependent of various clinical parameters time consuming and dependent operator. It represents a public health challenge. Informatic analysis detecting diseases could be a time gain and a more precise diagnosis tool. Today, any software or algorithm allow automatized detection, clinical qualitative or quantitative indices recording while these informations are present in numeric models

Fast Brain MRI in Children With Suspected Brain Tumor

This study aims to assess the diagnostic performance of a new fast MRI sequence named Neuromix compared to routine clinical MRI for brain tumor in pediatric patients

MLPR As A Diagnostic Marker For Acute Pulmonary Embolism

A retrospective study to assess the utility of hematological marker (monocyte to large platelet ratio) to diagnose patients with pulmonary embolism

Cardiac Amyloidosis in HFpEF Tunisian Patients

Cardiac amyloidosis (CA) has recently been reported as a common cause of heart failure with preserved left ventricular ejection fraction (HFpEF), with a prevalence of 6% in elderly HFpEF patients. However, the diagnosis of CA is still challenging and requires multiple costly investigations. Regardless of the type of CA, TTR or AL, early diagnosis significantly improves prognosis. In this study, the investigators aimed to determine the prevalence of CA in Tunisian HFpEF patients and to identify clinical and ultrasound criteria predictive of CA.

HIBOC = Hepatic Imaging Biomarkers in Obese Children

The goal of this prospective, diagnostic observational study is to learn about how imaging based markers for components of liver disease appear in children with obesity. It aims to determine whether the imaging markers (ultrasound and MRI) for liver disease can be tools to improve diagnostics for liver affection in children with obesity and to ascertain how the markers are related to multiple clinical measures, for example BMI and serology measure, and treatment effects over time.

Screening, Characterization, and Longitudinal Follow-up of Patients With Cardiac Amyloidosis

Cardiac amyloidosis is a progressive disorder caused by extracellular deposition of amyloid fibrils in the heart, leading to heart failure and impaired cardiac function. Early diagnosis and targeted therapies are essential to improve patient outcomes. This prospective, single-center study aims to longitudinally follow patients with suspected cardiac amyloidosis to characterize disease progression and assess treatment effects. Participants will undergo cardiac magnetic resonance imaging (resting and exercise stress MRI), magnetic resonance spectroscopy, cardiopulmonary exercise testing (spiroergometry) and blood testing at baseline and at 6, 12, and 24 months

Benefit of Cone-beam CT and Robotic-Assisted Bronchoscopy During Bronchoscopy

This randomized controlled trial evaluates the integration of cone-beam computed tomography (CBCT) and robotic-assisted bronchoscopy (RAB) for diagnosing pulmonary lesions, hypothesizing improved diagnostic yield compared to traditional methods. The trial involves 2 study arms (2x46 lesions) over 24 months with 12 months of follow-up and the diagnostic yield (ATS 2024 criteria) as the primary endpoint.

Emergency Medicine Pulmonary Embolism Testing Multicentre Study

It is important to diagnose pulmonary embolism in a timely manner to prevent death and long-term disability. More than half a million people (4-5% of emergency department patients) are tested for pulmonary embolism, although the positive rate is low. Imaging for PE testing exposes patients to radiation, is expensive, adds time to the emergency visit, and can lead to a false positive diagnoses. Existing protocols aimed at reducing unnecessary pulmonary embolism imaging are complex and seldom used by emergency physicians. Too many patients undergo unnecessary pulmonary embolism imaging. A new tool (called Adjust-Unlikely) could safely reduce pulmonary embolism imaging in Canada. A research group composed of researchers, emergency physicians, and patients developed the Adjust-Unlikely clinical decision rule: a rule which has been customized for emergency physicians and emergency patients. Adjust-Unlikely is highly sensitive at the bedside, meaning there are very few false negative results. The study aim is to prospectively validate Adjust-Unlikely pulmonary embolism testing in emergency patients with suspected pulmonary embolism.

Evaluation of a Retrieval Augmented Large Language Model as a Diagnostic Copilot in Rheumatology

This trial evaluates whether providing physicians with access to Prof. Valmed, a clinical decision support medical product, improves identification of rheumatic diseases and formulation of differential diagnoses compared with conventional decision support.

Trans-Oral Sampling as an Alternative Surveillance of Barrett's Esophagus Pilot

The study aims to address the increasing incidence of esophageal cancer and Barrett's esophagus (BE) in the Western world by exploring a more efficient surveillance method. Esophageal adenocarcinoma (EAC) has a poor prognosis if diagnosed late, emphasizing the need for early detection strategies. Current surveillance methods, involving regular endoscopies, are burdensome and costly, particularly for low-risk patients. The study investigates the potential of the Endosign, a Trans Oral Sampling (TOS) device, as an alternative to endoscopic surveillance. The objective is to determine if Endosign can provide sufficient quality samples, containing columnar cells and clot preparations at least 5mm in size, thus offering a reliable substitute for endoscopic sampling. The study includes non-dysplastic and dysplastic BE patients undergoing surveillance or treatment and employs a single-center, prospective feasibility approach.

Social COgnition Screening

Social cognition refers to the mental processes involved in social interactions, including social perception, motivation, communication, emotion recognition, and theory of mind. Face perception plays a key role in children's social development, but children with Autism Spectrum Disorder (ASD) tend to look less at social stimuli, especially faces, than typically developing (TD) peers. Eye-tracking studies highlight these visual exploration differences, linked to difficulties in joint attention, emotion recognition, and theory of mind, as well as in executive and memory functions. Standard diagnostic tests often require active participation and sufficient language, which makes assessment challenging for children with ASD and additional cognitive or language impairments. This research project investigates how visual activity supports social cognition depending on cognitive and language levels, hypothesizing that eye-tracking can provide useful indicators for ASD screening and diagnosis.

Prospective Validation of the CoDE-HF Algorithm for the Diagnosis of Acute Heart Failure

Acute heart failure is a life-threatening condition where the heart is suddenly unable to pump blood around the body. It can be challenging to diagnose because the symptoms often mimic other conditions. Previous studies have showed that delays in making the correct diagnosis result in worse outcomes. We therefore developed a decision-support tool called CoDE-HF that uses a computer algorithm to combine levels of a blood test called NT-proBNP with patient factors to calculate the probability of acute heart failure for an individual. In this project, we wish to evaluate the performance of CoDE-HF in approximately 2,000 patients attending the Emergency Department with suspected acute heart failure. We will store surplus material from their blood tests to measure NT-proBNP and link information from their electronic health records with other routinely collected medical information in regional and national databases in order to evaluate this algorithm.