Clinical trials: Deep Learning
Chronic Coronary Syndrome, Coronary Artery Disease
Feasibility of a Deep Learning-based Algorithm for Non-invasive Assessment of Vulnerable Coronary Plaque
The primary objective of this study is to assess the accuracy in terms of sensitivity, specificity, negative and positive predicted values of the DL-based algorithm with respect to correct identification of the plaque and…
- Conditions
- Chronic Coronary Syndrome, Coronary Artery Disease, Stable Angina, Acute Coronary Syndrome
- Trial name
- FOCUS DL (NCT06186336)
- Testing
- Deep Learning-based Vulnerable Plaque Detection and Assessment Tool
- Where
- Italy
- Volunteers
- 200 people
- Sponsor
- GE Healthcare
Pulmnary Hypertension
Detecting Pulmonary Hypertension With the Eko CORE 500 Digital Stethoscope
This prospective, observational study will evaluate whether synchronized heart sound (phonocardiogram, PCG) and three-lead electrocardiogram (ECG) recordings (entered as separate interventions in PRS, though collected together in…
- Trial name
- EKO-PH (NCT07136623)
- Testing
- Eko CORE 500 phonocardiogram (PCG) recording, Eko CORE 500 three-lead electrocardiogram (ECG) recording
- Where
- 2 sites in United States
- Volunteers
- 1,513 people, healthy volunteers welcome
- Sponsor
- Eko Devices, Inc.
Breast Neoplasms, Breast Cancer Detection
Diagnostic Accuracy of Carebot AI MMG in Mammography Screening: Multicenter MRMC Study
This study evaluates the diagnostic performance of Carebot AI MMG, an artificial intelligence (AI)-enabled medical device for evaluating mammograms.
- Conditions
- Breast Neoplasms, Breast Cancer Detection, Breast Cancer - Female, Breast Cancer Screening
- Trial name
- CARE-MMG-MRMC (NCT07298252)
- Testing
- Carebot AI MMG software analysis
- Where
- 4 sites in Czechia, Slovakia
- Volunteers
- 222 people, healthy volunteers welcome
- Sponsor
- Carebot s.r.o.
Healthy
Retinal Deep Phenotyping.TM
This study aims to collect a baseline dataset of MHRC retinal scans that will be used for the pre-training of deep learning models from the hyperspectral retinal image phenotypic features that may form the basis for multiple…
- Trial name
- NCT05903664
- Where
- United States
- Volunteers
- healthy volunteers welcome
- Sponsor
- Optina Diagnostics Inc.
Dialysis Access Malfunction, Dialysis; Complications
Dialysis Access Monitoring Using a Digital Stethoscope-Based Deep Learning System
This study will enroll end-stage renal disease (ESRD) patients on hemodialysis with a maturing arteriovenous fistula (AVF) for hemodialysis access.
- Trial name
- NCT05105503
- Testing
- Eko CORE Digital Stethoscope
- Where
- United States
- Volunteers
- 22 people
- Sponsor
- Eko Devices, Inc.
Colon Cancer Patients
Spectral Precise Image-Colon Cancer
This is a single-center, comparative, observational study. Datasets will be collected from patients with pathologically confirmed colon cancer who undergo abdomen-pelvis enhanced spectral CT scan.
- Trial name
- NCT07620444
- Testing
- This is an observational study
- Where
- China
- Volunteers
- 100 people
- Sponsor
- Philips Clinical & Medical Affairs Global
Respiratory Rate
Evaluating the Non-Inferiority of Airmod to Capnostream™35
This study is a multi-center clinical study of non-invasive medical device in Taiwan. After pre-anaesthesia evaluation, subjects who are suitable for intravenous general anesthesia (IVG) and age 20 years or older will be…
- Trial name
- NCT05263791
- Testing
- Airmod
- Where
- 3 sites in Taiwan
- Volunteers
- 284 people
- Sponsor
- Heroic Faith Medical Science Co., Ltd.
Pulmonary Embolism
External Validation of a Deep Learning Based Model for Pulmonary Embolism Detection on Chest CT Scans
The scope of this study is the external validation of an explainable deep learning-based classifier for the diagnosis and detection of pulmonary embolism in computed tomography pulmonary angiography (CTPA) and contrast enhanced…
- Trial name
- NCT05333042
- Where
- Belgium
- Volunteers
- 5,000 people
- Sponsor
- OncoRadiomics
Sarcopenia, Body Composition
Validation of a Body-Composition Segmentation Software on a Diverse Public CT Scan Cohort
This study evaluates the standalone performance of Soma, a deep-learning software developed by Nucleo Research, Inc. for the automated segmentation of body-composition tissues (skeletal muscle, subcutaneous adipose tissue…
- Conditions
- Sarcopenia, Body Composition, Obesity
- Trial name
- SOMA (NCT07600866)
- Testing
- Soma Body-Composition Segmentation Software
- Where
- United States
- Volunteers
- 200 people, healthy volunteers welcome
- Sponsor
- Nucleo Research, Inc.
Pulmonary Hypertension
Development of an Algorithm to Detect Pulmonary Hypertension Using an Electronic Stethoscope
The major goal of the study is to determine whether phonocardiography (using the Eko DUO stethoscope which can capture a three lead ECG reading) can present features that relate to the presence of PH diagnosed by echocardiography…
- Trial name
- NCT05873387
- Testing
- Use of Eko DUO stethoscope (paired ECG/PCG)
- Where
- 3 sites in United States
- Volunteers
- 2,420 people, healthy volunteers welcome
- Sponsor
- Eko Devices, Inc.
Small for Gestational Age Infant, Fetal Growth Restriction
Developing and Testing AI Models for Fetal Biometry and Amniotic Volume Assessment in Fetal Ultrasound Scans.
Routine fetal ultrasound scan during the second trimester of the pregnancy is a low-cost, noninvasive screening modality that has been proven to lower fetal mortality by up to 20%.
- Conditions
- Small for Gestational Age Infant, Fetal Growth Restriction, Oligohydramnios, Polyhydramnios
- Trial name
- NCT05059093
- Testing
- Classification and segmentation deep learning models
- Where
- 6 sites in Morocco
- Volunteers
- 122 people, healthy volunteers welcome
- Sponsor
- Deepecho
Otitis Media Acute
Clinical Development of Deep Learning for the OtoSight
The objective of this study is to clinically develop and evaluate a machine learning approach to improve the performance and data interpretation of the PhotoniCare OtoSight Middle Ear Scope in pediatric patients presenting at the…
- Trial name
- NCT04722770
- Testing
- PhotoniCare OtoSight Middle Ear Scope
- Where
- United States
- Volunteers
- 188 people, healthy volunteers welcome
- Sponsor
- PhotoniCare, Inc.
High-risk Cardiac Patients
Registry Study for the Evaluation of High-risk Cardiac Patients by WILLEM AI-based ECG Platform
The WILLEM Registry is a large-scale, single-group, observational, registry study to collect continuous clinical evidence of Willem in real-world settings.
- Trial name
- WILLEMRegistry (NCT07333547)
- Testing
- Willem AI ECG assessment
- Where
- 5 sites in United States, Ecuador and 1 more
- Volunteers
- 200,000 people, healthy volunteers welcome
- Sponsor
- Idoven 1903 S.L.
Diabetic Retinopathy, Diabetic Eye Problems
Detection and Classification of Diabetic Retinopathy From Posterior Pole Images With A Deep Learning Model
The duration of diabetes is directly related to eye complications. Diabetic retinopathy affects 80 percent of those who have had diabetes for 20 years or more.
- Conditions
- Diabetic Retinopathy, Diabetic Eye Problems, Diabetic Macular Edema
- Trial name
- NCT04805541
- Testing
- Color Fundus Photography, Mydriatic Agent, EyeCheckup - AI Based DR Screening
- Where
- Turkey (Türkiye)
- Volunteers
- 900 people
- Sponsor
- Ural Telekomunikasyon Sanayi Ticaret Anonim Sirketi
Depression
A Feasibility Study of an AI-Powered Clinical Decision Aid for Personalized Depression Treatment Selection
The Clinical Decision Aid (CDA) is a predictive model that takes as input individual patient characteristics, called 'features', which are inputted by the physician or by patient self-report, and outputs a list of possible…
- Trial name
- NCT04061642
- Testing
- Clinical Decision Aid
- Where
- Canada
- Volunteers
- 17 people
- Sponsor
- Aifred Health Inc.
Cardiac
Spectral Precise Image Study for Coronary Artery
This is a single-center, comparative, observational, retrospective data study. Datasets from patients who underwent spectral coronary CT angiography (CCTA) for suspected coronary artery disease (CAD) or other diagnosis needs as…
- Trial name
- NCT07620457
- Testing
- Non-Interventional Study
- Where
- China
- Volunteers
- 200 people, healthy volunteers welcome
- Sponsor
- Philips Clinical & Medical Affairs Global
Deep Vein Thrombosis, Deep Vein Thrombosis, Pulmonary Embolus
Determining the Validity of ThinkSono Guidance for Ultrasound Image Acquisition and Remote Detection
The purpose of this study is to confirm the safety and efficacy of ThinkSono Guidance, a software data collection and communication tool designed to collect ultrasound data to help detect blood clots in veins.
- Trial name
- DVT GUARD (NCT06652568)
- Testing
- ThinkSono System
- Where
- 5 sites in United States
- Volunteers
- 634 people
- Sponsor
- ThinkSono, Ltd.
Breast Cancer, Breast Lesions
Breast Ultrasound Image Reviewed With Assistance of Deep Learning Algorithms
This study evaluates a second review of ultrasound images of breast lesions using an interactive "deep learning" (or artificial intelligence) program developed by Samsung Medical Imaging, to see if this artificial intelligence…
- Conditions
- Breast Cancer, Breast Lesions, Breast Mass
- Trial name
- NCT03706534
- Testing
- Ultrasound Image review with CADe, Ultrasound Image review with CADx, Ultrasound Image manual review
- Where
- United States
- Volunteers
- 300 people, healthy volunteers welcome
- Sponsor
- Samsung Medison
Aortic Stenosis
Multicenter Study for the Validation of Willem AI: Aortic StenoSis Early Diagnosis With AI-electrocardiogram Study
AoS-SEDAI study is an observational, multicenter, retrospective and prospective clinical study. This study aims to assess Willem Artificial Intelligence (AI) ability to distinguish between aortic stenosis (AS) and non-AS patients…
- Trial name
- AoS-SEDAI (NCT07479992)
- Testing
- Willem AI ECG assessment
- Where
- 2 sites in Germany
- Volunteers
- 5,000 people, healthy volunteers welcome
- Sponsor
- Idoven 1903 S.L.
Artificial Intelligence, Deep Learning
Feasibility of Gadolinium Contrast Reduced Brain MRI: the Potential of Deep Learning
MRI scans were performed using 3 different 1.5T scanners with an eight-channel head coils. Following a 3D pre-contrast T1w scan, a low-dose contrast-enhanced 3D T1w scan was obtained using 20% (0.02 mmol/kg) of the standard…
- Trial name
- NCT06462924
- Testing
- DeepGad
- Volunteers
- healthy volunteers welcome
- Sponsor
- DeepMeds