Artificial Intelligence (AI)

This research aims to evaluate how full-arch implant-supported prostheses affect lip support in patients undergoing complex dental rehabilitation. The study focuses on how different clinical and laboratory decisions between diagnosis and prosthesis delivery may influence the prosthetic design and the patient's facial profile. Advanced 3D facial scanning and superimposition techniques allow precise measurement of vertical occlusion and lip support. Participants will undergo removal of their full-arch implant-supported prostheses, with digital facial images captured before and after this procedure using a facial scanner. This observational study leverages modern digital technology to measure changes objectively and does not involve experimental treatments. During the study, researchers will assess changes in the volume around the mouth area, distances between the lips and esthetic lines on the facial profile, and angles related to the nose and lips. These measurements occur on the same day as the prosthesis removal. The study helps improve understanding of facial changes related to dental prostheses and involves participants collaborating with the research protocol through imaging and clinical assessments.

Researchers are evaluating a new deep learning model that uses ultrasound video data to estimate blood volume before surgery. This prospective, single-center observational study focuses on adult patients scheduled for surgery, aiming to provide an accurate, non-invasive way to assess blood volume, which is important to prevent complications during surgery. The study is led by Shanghai 6th People's Hospital and addresses the current lack of practical methods for direct blood volume measurement. Participants will undergo preoperative ultrasound scans capturing videos of four major blood vessels: the Internal Jugular Vein, Subclavian Vein, Inferior Vena Cava, and Common Carotid Artery. The true blood volume is calculated using a clinical method involving hemoglobin concentration changes before and after acute normovolemic hemodilution. The collected ultrasound videos will be used to train and validate a deep learning model that combines convolutional and temporal analysis techniques to estimate blood volume from the ultrasound data. During the study, participants will have ultrasound video clips taken shortly before surgery. Researchers will analyze these images alongside blood volume values determined by the clinical method. The main outcome measured is the accuracy of the blood volume estimate within 30 minutes before surgery. The study does not involve treatment changes but focuses on data collection and model validation. Participation lasts through the preoperative period up to surgery, with no additional follow-up specified.

Pulmonary hypertension is a condition that is often underdiagnosed due to its many causes. Researchers are evaluating an artificial intelligence-enabled electrocardiogram (AI-ECG) to screen for elevated pulmonary arterial pressure (PAP) in patients at high risk. This approach aims to identify pulmonary hypertension earlier, leading to further testing and potentially improving heart-related outcomes. The study is a randomized controlled trial sponsored by the National Defense Medical Center, Taiwan. Participants are divided into two groups. One group is screened with the AI-ECG system, and if they are identified as high-risk for pulmonary hypertension, they receive an echocardiogram to confirm the diagnosis and help guide treatment. The other group undergoes AI-ECG screening but continues with usual clinical care without additional echocardiography. The study uses this comparison to assess the value of AI-ECG-guided screening. During the study, participants will have ECGs and may have echocardiograms depending on their group and risk. Researchers will monitor heart measurements like pulmonary arterial pressure, left atrial size, right ventricular size, and left ventricular function within 90 days after starting the study. The main focus is on whether pulmonary arterial pressure exceeds 50 mmHg. The study lasts at least three months from randomization, with detailed heart imaging and function assessments to understand the AI-ECG's effectiveness in detecting pulmonary hypertension early.

Researchers are studying adolescents and young adults with autism spectrum disorder (ASD), a condition marked by difficulties in communication, social skills, and repetitive behaviors. The study aims to understand how a brain stimulation technique called transcranial direct current stimulation (tDCS) might reduce symptoms like anxiety and impulsivity. The research also seeks to use brain activity data and clinical information to predict who will respond well to this treatment. Participants will receive active tDCS for 10 sessions over two weeks, one session per day on working days. During each 20-minute session, they will perform exercises designed to improve processing speed and executive function while receiving brain stimulation. After treatment, participants will be classified as responders or non-responders based on improvements in social responsiveness scores. Throughout the study, participants will undergo various assessments including behavioral scales, cognitive tests, and neurophysiological measurements at the start and after the treatment period. Researchers will track changes in social communication, repetitive behaviors, and brain function. This will help determine the effects of tDCS and identify characteristics that predict treatment response, with the total study duration extending up to the final follow-up in 2026.

Researchers are conducting a multi-center clinical study to assess artificial intelligence (AI) algorithms for measuring heart function and size using echocardiography. The study aims to compare AI measurements with those of physicians at different experience levels, evaluate the accuracy and stability of AI, and explore its use in complex heart conditions like cardiomyopathy, valve disease, and coronary heart disease. The goal is to improve diagnostic consistency and clinical workflows across medical centers. The study involves measuring cardiac chamber size and function in 1600 participants using AI, senior physicians, and intermediate physicians. All measurements are made with Mindray ultrasonic machines. AI and intermediate physician results are completed within one day after data collection, while senior physician results are completed within one month. The study will establish a standardized reference system for AI-assisted echocardiographic measurements and evaluate AI's performance in special cases. Participants will undergo echocardiographic scans with measurements of left and right ventricular size and function, Doppler ultrasound indicators, and valve annulus displacements. Researchers will analyze data to compare AI and physician measurements, assess measurement deviations, and evaluate AI's efficiency in reducing analysis time. The study will run until July 2026, with ongoing data collection and analysis across multiple centers, aiming to promote wider clinical application of AI technology for cardiovascular disease diagnosis.

Pregnant women with aplastic anemia (AA), a rare blood disorder causing bone marrow failure and low blood counts, face serious risks including heavy bleeding, infections, and complications for their babies like preterm birth and restricted growth. This research aims to develop and validate a tool to predict adverse pregnancy outcomes in women with AA, helping guide early clinical decisions and improve health for mothers and infants. The study combines retrospective and prospective data collection across multiple centers to address the current lack of comprehensive data in this area. The study involves observing pregnant women diagnosed with AA either before or during their pregnancy. Researchers will gather baseline information and diagnostic data, then follow participants regularly through questionnaires, phone calls, video consultations, online platforms, and in-person visits. They will record treatments, other health conditions, and pregnancy outcomes, aiming to build a prediction model for adverse outcomes. Participants will be monitored from their first hospital visit during pregnancy until 42 days after delivery. Data collected includes clinical assessments and neonatal Apgar scores shortly after birth. The study will provide detailed information on the health and risks for mothers and babies affected by AA during pregnancy, helping improve care strategies. The total participation duration varies depending on the timing of enrollment and delivery.

Researchers are evaluating the accuracy of a new artificial intelligence system called EndoAIM for measuring colorectal polyp size during real-time endoscopy. Accurate measurement of polyp size, especially at the 10 mm threshold, is important for assessing the risk of advanced neoplasia and colorectal cancer, as well as deciding the best removal method. Current visual estimates by doctors can be inaccurate, leading to risks of delayed diagnosis or unnecessary procedures. In this study, EndoAIM will be used during the withdrawal phase of colonoscopy procedures to automatically estimate polyp diameters. This device aims to improve measurement accuracy compared to visual estimates or non-calibrated tools. The study focuses on real patients undergoing colonoscopy, assessing EndoAIM’s performance in real-time clinical settings. Participants will undergo colonoscopy with EndoAIM used to measure polyps during the procedure. Researchers will compare measurement accuracy at 10 mm and 5 mm thresholds and evaluate the correctness of size estimations. The primary outcome is the difference in percentage accuracy at the 10 mm threshold during colonoscopy. Secondary outcomes include accuracy at the 5 mm threshold and the proportion of polyps and subjects measured correctly. The study includes adults aged 18 and older and involves monitoring during the colonoscopy procedure.

Researchers are conducting a real-world, observational study to evaluate the efficacy and safety of immune checkpoint inhibitors (ICIs) as the first-line treatment for advanced malignant tumors. The study includes patients with stage IV solid tumors such as non-small-cell lung carcinoma, stomach, breast, and urinary system cancers. The goal is to build a database combining immunohistochemistry, gene detection, imaging data, and survival outcomes to develop predictive models for immunotherapy biomarkers and treatment responses. The study collects various data points including immunohistochemistry results, gene testing, imaging, overall survival, progression-free survival, and objective response rate. It also monitors immune-related adverse events over time. This observational study does not involve experimental treatments but instead observes patients receiving ICIs as part of their standard care. The study spans at least two years for some outcome measures to assess long-term effects and safety. Participants will undergo regular assessments including survival evaluations and monitoring for treatment-related side effects. Data on progression-free survival will be collected at six months, with overall survival and immune-related adverse events followed for up to two years. The study aims to validate the predictive value of biomarker systems for immunotherapy and improve understanding of treatment effects in advanced cancer patients. Total participation duration will vary depending on individual treatment and follow-up schedules.

Researchers are conducting a randomized controlled trial to compare the outcomes of screening mammography exams interpreted with and without the help of an FDA-cleared artificial intelligence (AI) decision-support tool in real-world U.S. settings. The study aims to determine if using AI improves breast cancer detection and recall rates during screening. This trial includes all adult patients undergoing screening mammography and all interpreting radiologists across six regional health systems. During the trial, each 3D screening mammogram will be randomly assigned to either the intervention group, where radiologists receive assistance from the AI decision-support tool, or the usual care group, where radiologists interpret the images alone. Randomization happens at the exam level immediately after image acquisition, and patients returning for screening in the second year will be re-randomized. Radiologists will see AI information only when it is available during interpretation, but they maintain full control over their final diagnosis. Participants will undergo routine screening mammograms, with data collected on cancer detection rates within 90 days and recall rates over about one year. Additional measures include false-positive rates, interval cancer rates, and trust in AI over several years. The study plans to assess these outcomes across approximately 400,000 screening exams, with monitoring done through the participating health systems. Radiologists and patients will contribute perspectives on AI use in medical imaging during the trial period.

Researchers are developing an artificial intelligence tool to predict adverse outcomes in patients with acute pulmonary embolism using data from CT pulmonary angiography. This observational study collects clinical, laboratory, and CT scan information from patients admitted with acute pulmonary embolism to better understand and forecast complications within 30 days of hospital admission. The goal is to improve early risk assessment by comparing the new AI-based prediction model with established risk systems. The study divides participants into two groups: a derivation cohort used to create and test a logistic regression model, and a validation cohort to confirm the model's consistency. No interventions or treatments are given as part of the study. Data collected include CT parameters, echocardiography results, and blood markers such as cardiac troponin I and NT-pro BNP. The model's accuracy is assessed by comparing predicted outcomes with actual adverse events. Participants will have their clinical and imaging data analyzed from hospital admission, with follow-up to track treatment-emergent adverse events within 30 days and up to 2 years. Researchers monitor the incidence of these adverse events to evaluate the AI tool's predictive value. The entire participation involves data collection without experimental treatment, and the study spans several years to gather long-term safety information.