Artificial Intelligence

To evaluate the usefulness of Deep neural network (DNN) in the evaluation of mediastinal and hilar lymph nodes with Endobronchial ultrasound (EBUS). The study will explore the feasibility of DNN to identify lymph nodes and blood vessel examined with EBUS.

This study investigates a novel, agentic Large Language Model (LLM) architecture designed to facilitate Shared Decision-Making (SDM) in healthcare. While patients increasingly use standard LLMs for health information, these models often struggle with multi-turn conversations and fail to adapt to varying reading levels, disadvantaging vulnerable groups. By utilizing an agentic state-machine, this project aims to overcome common LLM deficits-such as context loss and uncritical agreement-to ensure clinically accurate, participatory patient conversations. The study evaluates whether this architecture improves informed decision-making compared to standard LLMs, particularly for patients with low health literacy.

Computer-aided image-enhanced endoscopy can predict the nature of colorectal polyps with over 90% accuracy. This technology uses artificial intelligence (AI) to analyze video recordings of polyps, learning to make diagnoses in real-time. This means that doctors can get immediate predictions about small polyps during the procedure, reducing the need for separate pathology exams and saving costs, ultimately improving patient care. Human and AI interactions are complex and a framework to reap synergistic effects CADx systems when used by humans to harness optimal performance needs to be established. AI solutions in medicine are usually developed to be used as assistive devices, however, then they rely on humans to correct AI errors. Optical polyp diagnosis is a complex task. Non experts usually achieve diagnostic accuracy in 70-80%. CADx systems have a similar diagnostic accuracy when used autonomously. Clinical evaluation of CADx systems showed that CADx assisted OD performs equally to the operator performance when using non CADx assisted OD. To harness a benefit of clinical CADx implementation we would have to find a way that synergies between human and CADx come into play to eliminate cases in which CADx assisted and/ or human OD results in low diagnostic accuracy and also addresses the problem of serrated polyp recognition.

This is a pragmatic, double-blind, randomized, controlled trial, to evaluate the effect of implementing a Computer-assisted detection (CADe) system within the routine clinical practice of Canadian healthcare institutions. The main hypothesis of this study is that the ADR in the operating room equipped with the GI genius CADe system will be significantly higher than the ADR in the ordinary operating room.

The purpose of the study is to compare the impact of standard asthma education with the standard + Artificially Intelligent Robot (AIR) Control intervention.

Gliomas are common primary brain tumors in adults. Gliomas can be classified into different types based on tumor grade, histopathological features, and molecular characteristics. The common types of diffuse gliomas include glioblastoma, astrocytoma, and oligodendroglioma. The standard treatment for diffuse gliomas includes surgery followed by radiation and chemotherapy. As per standard institutional practice, a uniform dose of radiation is delivered to the disease area and MRI is done before and after the treatment. In this study, MRI and PET scan will be done before starting the treatment and standard dose of radiation will be delivered. The interval imaging will be done twice during the course of treatment with MRI and PET, followed by dose modifications. The CT, MRI, and PET will be combined. Based on PET imaging, specific dose will be altered and delivered to specific areas. Dose modification will be done with the help of artificial intelligence. Participant's assessment will be done at regular intervals. Modifications in radiation plans are done based on the changes in disease seen in scans is likely to improve the accuracy of RT treatments. Dose modifications based on imaging to resistant areas will help achieve better tumor control, reduce treatment-related toxicities, precise delivery of the RT and adjusting doses to the organs at risk (OAR) and changes in disease leading to better treatment compliance. Creating an artificial intelligence framework in radiation oncology promises to improve quality of workflow, treatment planning and RT delivery. The aim of the study is to develop an artificial intelligence workflow for treatment of glioma with adaptive radiotherapy. This study will be conducted in Tata Memorial Centre on a population of 60 patients for a duration of 2 years. The total study duration is 4 years.

This study intends to collect ophthalmologic examination results, pulmonary examination results and related indexes from patients with pulmonary disease and control populations, and combine big data analysis and artificial intelligence technology to explore whether new methods can be provided for early screening strategies for pulmonary disease with the aid of ophthalmologic examination, and thus assist in identifying the types of pulmonary disease and determining disease prognosis.

Mammography is the most common method for breast imaging, and it provides information for model building and analysis. Radiomics applied to mammography has the potential to revolutionize clinical decision-making by providing valuable insights into risk assessment and disease detection. Despite this, the influence of imaging parameters and clinical and biological factors on radiological texture features remains poorly understood. There is a pressing need to overcome the obstacle of system-inherent effects on mammographic images to facilitate the translation of radiological texture features into routine clinical practice by enabling reliable and robust AI-based or AI-aided decision-making. Furthermore, understanding the relationship between imaging parameters, textural features, and clinical and biological information supports the clinical use of AI. The objective of this study is to evaluate AI methods for clinical practice and to study how it relates to clinical factors and biological features.

Transthoracic echocardiography is an essential imaging modality for the diagnosis and follow-up of cardiovascular diseases. Comprehensive echocardiographic assessment requires multiple quantitative measurements of cardiac structure and function, which are time-consuming and highly dependent on operator expertise. US2.AI (Us2.v1) is an artificial intelligence (deep learning)-based software designed to automatically analyze standard two-dimensional and Doppler echocardiographic DICOM video clips acquired from different ultrasound vendors. The software provides automated measurements of cardiac morphology and function, including chamber dimensions and volumes, left and right ventricular systolic and diastolic function, myocardial strain, and Doppler-derived parameters, generating a comprehensive echocardiographic report based on current international guideline recommendations. In addition, the software may assist in identifying echocardiographic features suggestive of several cardiovascular conditions, including heart failure, pulmonary hypertension, hypertrophic cardiomyopathy, cardiac amyloidosis, valvular heart disease, and ischemic cardiomyopathy.

This study aims to develop and validate an artificial intelligence (AI)-assisted platform for musculoskeletal knee ultrasonography and to establish an interpretable prediction model for clinical outcomes following ultrasound-guided injection therapies in patients with degenerative knee disorders. The project seeks to improve the standardization, reproducibility, and clinical utility of knee ultrasound by reducing operator dependency and providing quantitative image analysis and outcome prediction. The study will be conducted in three phases. First, an AI foundation model for knee ultrasonography will be developed using standardized image acquisition protocols to enable automated localization, segmentation, and quantitative assessment of major anatomical structures, including tendons, ligaments, cartilage, fat pads, and peripheral nerves. Second, supervised machine learning models will be trained to classify normal and pathological ultrasound findings, including common degenerative and inflammatory abnormalities affecting the knee. Third, retrospective and prospective clinical data from approximately 150 patients receiving ultrasound-guided injection therapies will be integrated to develop and validate a predictive model for treatment outcomes using imaging biomarkers and clinical variables. Treatment response will be evaluated using validated patient-reported outcome measures, and explainable AI methods will be applied to improve model interpretability. The anticipated outcome of this study is the development of a comprehensive AI-assisted knee ultrasound platform that supports standardized image interpretation, quantitative assessment of musculoskeletal pathology, and personalized prediction of treatment response to ultrasound-guided injection therapies in degenerative knee disorders.

This educational reform study aims to explore whether a full English course built on the DeepSeek artificial intelligence platform can improve orthopedic nurses' professional English competence. It will also examine nurses' satisfaction with AI-assisted teaching. The main questions it seeks to answer include: Will the DeepSeek-based full English course improve orthopedic nurses' professional English test scores? Will nurses' transcultural nursing self-efficacy and nurse-patient therapeutic interaction ability improve after the course training? What are nurses' experiences when using the DeepSeek AI platform for learning? Researchers will compare the English proficiency changes of the same group of orthopedic nurses before and after the training to observe the course effects. Participants will: Attend an 11-week full English course based on the DeepSeek platform, approximately 1-2 hours per week Complete a professional English written test and an oral proficiency assessment before and after the training Complete the Transcultural Self-Efficacy Tool (TSET-CV) and the Nurse-Patient Therapeutic Interaction Scale (NuPTIS) before and after the training Complete a teaching satisfaction and AI learning experience questionnaire after the course

AI-powered tools that automatically document clinical conversations are being adopted rapidly in outpatient settings but have not been evaluated in hospital wards. Existing tools use audio recording only, which cannot capture physical examination findings, procedural observations, or clinical safety behaviours - elements of a ward round that are visible but not audible. This study evaluates an ambient audio-visual (AV) capture system - BlackFrame - that uses both microphone and camera to generate accurate clinical documentation and structured educational feedback in a real inpatient surgical ward setting. Medical students and doctors in training participate in supervised ward round encounters with consenting adult inpatients. The BlackFrame AI platform generates: (a) a structured draft clinical note for the supervising clinician to review and countersign before any use in the patient record; and (b) formative feedback for the trainee, delivered within 30 minutes, covering clinical communication, examination technique, and documentation quality. The study measures whether AI-generated feedback improves trainee clinical performance over a placement, how much documentation time is saved, and whether the system is acceptable to patients and clinicians. No AI-generated text enters the patient record without explicit clinician review and sign-off. All participation is voluntary.

This study aims to determine how applied artificial intelligence (AI) training affects nurses' ability to manage the nursing process and their perceptions and attitudes toward AI technology * The nursing process is a scientific, six-stage approach used by nurses to identify patient needs and provide holistic care The research is a randomized controlled trial involving 78 nurses at Yalova Education and Research Hospital . Participants will be split into two groups: Both groups will receive standard theoretical training on the nursing process . The intervention group will receive additional specialized training on using AI tools (such as ChatGPT and Deepseek) to help create nursing care plans through practical case studies . Nurses' skills and views will be measured using specific scales before the training and one month after the intervention to evaluate the training's effectiveness * This study is expected to provide valuable insights into how AI can support clinical decision-making and help healthcare providers adapt to new technologies * The research has been approved by the Yalova University Ethics Committee (Protocol 2026/183) and will be conducted between May and December 2026

To evaluate, in a randomized controlled trial, whether AI-guided monitoring and ovulation triggering leads to clinical outcomes comparable to those achieved through physician-led decision-making in patients undergoing ovarian stimulation for IVF.

We hypothesize that an AI-guided AF risk stratification approach, particularly when combined with intensified rhythm monitoring using wearable devices and extended ECG patches, will significantly increase AF detection rates compared with standard care. By enabling earlier identification of patients who may benefit from anticoagulation therapy, this strategy has the potential to improve clinical outcomes while minimizing unnecessary exposure to anticoagulant-related bleeding risks. Ultimately, this trial seeks to provide robust clinical evidence supporting the integration of AI-assisted ECG analysis into routine post-stroke care, advancing precision medicine and optimizing resource allocation for patients with ischemic stroke.

Clinical rounds in the intensive care unit (ICU) involve substantial manual documentation. Retrieving the correct protocol text and structuring notes at the bedside is time-consuming and may contribute to variation in documentation quality. Modern artificial intelligence (AI) can help structure existing information and automate protocol look-ups within a restricted, manually selected document set. The tool evaluated in this study acts as an AI-based informational assistant for clinicians. It (1) pre-populates a standardized physical-exam and daily-rounds format, (2) prepares a concise ICU course/overview using predefined formatting, and (3) retrieves relevant passages from protocols to enable rapid consistency checks by the clinician. The AI-based informational assistant does not provide treatment recommendations or patient-specific advice; all outputs require clinician verification and clinical responsibility remains with the physician.

The investigators aim to build a predictive tool for Adverse Outcome of Acute Pulmonary Embolism by Artificial Intelligence System Based on CT Pulmonary Angiography.

This is a prospective, single-center, exploratory study designed to evaluate the accuracy, user engagement, and user experience of the BaiXiaoAi Companion AI. Upon signing the informed consent form and enrollment, a dedicated "Doctor-Nurse-Patient-AI" WeChat group will be established for each participant. Within the group, the BaiXiaoAi AI will provide timely responses based on patient communications and proactively push information regarding disease management and patient education.

LOCATOR is a multicentre phase II randomised clinical trial that is looking at the process of contouring in radiation treatment for breast cancer patients. This study looks at whether contouring aided by artificial intelligence (AI) is comparable in quality to that of contouring done completely manually by a radiation oncologist. We are also looking at whether AI assisted contouring saves radiation oncologists time when compared to fully manual contouring. LOCATOR uses the LOCATOR software which is an in-house software developed locally and trained on local data.

Drug-related iatrogenesis is a major public health issue, accounting for a significant proportion of adverse events and hospitalizations in emergency departments. Optimizing prescription management in this context is critical to improve both patient safety and physician efficiency This study aims to evaluate the impact of the POSOS AI-driven device on the medical time required for prescription management in polymedicated patients admitted to emergency departments. The main objective is to establish whether the use of POSOS can reduce transcription time compared to standard electronic management.

Infertility affects approximately one in six individuals worldwide and is associated with significant psychological distress, particularly among women undergoing treatment. Increased anxiety levels are strongly linked to reduced quality of life during the infertility process. With the growing integration of artificial intelligence (AI) into healthcare, AI-based tools are increasingly used in infertility care to support decision-making and patient engagement. While many patients are familiar with AI technologies, individual attitudes toward AI may influence their acceptance and potential psychosocial benefits. This study aims to examine the relationship between attitudes toward artificial intelligence, anxiety levels, and quality of life among women undergoing infertility treatment.

This study will employ a prospective, multicenter, controlled design. It will be conducted across multiple centers, with participated centers randomly assigned to one of four groups: Group A, Group B, Group C, and Group D. The research will primarily focus on the AI-based analysis of colonoscopic images to calculate the following metrics: caecal intubation time, red-out percentage, and the AI-based red-out avoiding score. Based on the study's implementation protocol, a decision will be made regarding whether to provide real-time feedback. Additionally, the presence of any complications will be assessed both during and after the colonoscopy procedure.

The endoscopic grading system (EGGIM) has been widely used to assess the extent of gastric intestinal metaplasia during endoscopy. Investigators developed an artificial intelligence (AI) system to automatically evaluate the extent of gastric intestinal metaplasia (GIM) and calculate the EGGIM scores in endoscopy examination. This study is a prospective, multi-center study aimed at exploring the performance and reliability of AI-EGGIM scoring. This is a prospective study designed to validate the AI-EGGIM system in a larger cohort. The study protocol was developed based on preliminary experience from a prior investigation (NCT05464108).

This prospective randomized trial compares AI-assisted upper gastrointestinal endoscopy with high definition upper gastrointestinal endoscopy in term of missed rate of gastric neoplasm. The investigators hypothesize the miss rate of high definition upper gastrointestinal endoscopy is higher than AI-assisted upper gastrointestinal endoscopy.

This randomized clinical trial evaluates the effectiveness of an AI-enabled electric toothbrush and visual pedagogy materials in improving oral hygiene among children with autism spectrum disorder (ASD). The study compares plaque control, gingival health, and adherence between children using a manual toothbrush with visual pedagogy support and those using an AI-enabled electric toothbrush with app-based monitoring.