Artificial Intelligence Ai In Diagnosis

The goal of this randomized questionnaire-based study is to evaluate how different presentations of artificial intelligence (AI) decision support influence clinical judgment among medical doctors working in obstetrics and gynecology when assessing the risk of spontaneous preterm birth using clinical case vignettes with cervical ultrasound images. The study specifically compares two AI presentation formats: a binary classification (preterm vs term birth) and an individualized risk estimate of preterm birth. The main questions it aims to answer are: * Which AI presentation format leads to better alignment between clinicians' confidence and decision accuracy (diagnostic calibration)? * Do different AI presentation formats lead to helpful or harmful changes in clinical decisions? Participants will complete an online questionnaire in which they review clinical cases, make diagnostic and management decisions, rate their diagnostic confidence before and after seeing the AI output, and report their trust in the AI.

This retrospective diagnostic accuracy study evaluates the ability of two large language models (LLMs) - GPT-4o (gpt-4o-2024-11-20; OpenAI) and Claude 4.6 Sonnet (claude-sonnet-4-6; Anthropic) - to generate correct diagnoses from anonymized Turkish-language emergency department (ED) anamnesis notes, and compares their performance with the diagnosis entered by the treating emergency physician. A consensus gold standard is established by three independent board-certified emergency medicine specialists who blindly review each note and vote on the primary diagnosis using ICD-10 three-character codes; the majority vote (at least 2 of 3 specialists agreeing) constitutes the reference standard. Both LLMs are evaluated using a standardized zero-shot direct prompting strategy (temperature=0, stateless API sessions). The primary outcome is diagnostic accuracy (proportion of ICD-10 chapter-level matches) and Cohen's kappa for each LLM against the gold standard. Secondary outcomes include top-3 accuracy, treating physician accuracy, inter-model agreement, and subgroup analyses by ESI triage level and ICD-10 chapter. Inter-rater reliability among the three specialists is quantified using Fleiss' kappa. Analyses are performed in Jamovi. This study represents the first evaluation of LLM diagnostic accuracy using Turkish-language clinical notes and the first to benchmark LLM performance against an independent three-specialist majority-vote gold standard rather than against the treating physician's own diagnosis.

This prospective observational diagnostic accuracy study evaluates whether large language models (LLMs) - GPT-4o (OpenAI, gpt-4o-2024-11-20) and Claude (Anthropic, claude-sonnet-4-6) - can accurately calculate HEART scores from unstructured Turkish clinical notes and predict 30-day major adverse cardiac events (MACE) in emergency department patients presenting with non-traumatic chest pain. The study will enroll 600 consecutive adult patients. For each patient, the same anonymized data (free-text anamnesis, ECG report text, troponin value, and age) will be independently processed by both LLMs via separate API calls with deterministic settings (temperature=0, JSON format). A three-expert consensus HEART score - derived through blinded independent scoring by three emergency medicine physicians with majority-vote adjudication - serves as the reference standard for agreement analysis. Actual 30-day MACE (all-cause death, AMI Type 1/2/4b, unplanned revascularization) determined via national health database and telephone follow-up serves as the outcome for diagnostic accuracy analysis. A secondary documentation-quality sub-study will quantify how spontaneously Turkish emergency anamnesis notes capture HEART score parameters.

This study aims to evaluate the accuracy and reliability of artificial intelligence (AI)-based cephalometric analysis compared with digital manual tracing. A total of 100 standardized lateral cephalometric radiographs will be analyzed using Delta-Dent software with manual landmark identification and three fully automated AI-based systems (WebCeph, QuantX, and Smartee). Sagittal, vertical, dental, and soft tissue cephalometric parameters will be compared among the different methods. Statistical analysis will assess inter-method agreement and the clinical relevance of any observed discrepancies. The study seeks to determine whether AI-based systems provide measurements comparable to conventional digital tracing and whether they can be considered reliable adjunctive tools in orthodontic diagnosis and treatment planning.

The goal of this observational study is to learn if an AI assistant tool can help doctors who read chest CT scans (called radiologists) write their reports faster and just as well or better. Chest CT scans are common pictures taken of the inside of the chest to help with diagnosis. The main questions the study aims to answer are: (1) Does using the AI tool save radiologists time when writing their reports? (2) Are the final reports written with the AI tool's help as good as or better than reports written without it? To answer these questions, researchers will compare two time periods at several hospitals. They will look at how long it took to write reports and how good the reports were, both from a time before the AI tool was available and from a time after it was in regular use. In this study, radiologists will use the AI tool as part of their normal daily work. The tool is built into the computer system they already use to look at scans. Researchers will then measure the time and quality of the reports produced during their regular shifts.

This study prospectively evaluates whether the performance of an already-developed artificial intelligence (AI) model for predicting spontaneous preterm birth changes when cervical ultrasound images are obtained using different ultrasound image settings. The primary research question is whether the AI model performs differently across images acquired with different imaging settings.

Diabetic foot ulcer (DFU) is a major adverse outcome of diabetes, which itself is one of the most significant chronic diseases. The recurrence of DFU involves multiple risk factors, including altered foot loading patterns, patient compliance, family care capacity, blood glucose monitoring, degree of ischemia, and systemic disease control. Early identification of recurrence signs and timely follow-up interventions are crucial for improving prognosis, reducing disability rates, and lowering healthcare costs. However, traditional follow-up systems lack individualized strategies-such as risk stratification, inflexible follow-up intervals, and insufficient compliance management-often resulting in suboptimal outcomes. High-risk patients prone to recurrence may not be followed up frequently enough for early detection, while low-risk patients may undergo unnecessary visits, increasing burdens on both patients and healthcare providers. This inefficiency contributes significantly to the persistently high rates of disability and mortality among recurrent DFU patients. Establishing an individualized follow-up strategy for DFU, supported by advanced technology to address core bottlenecks such as delayed recurrence warnings and inadequate home-based management, represents an effective technical pathway to tackle these issues. Our center proposes to develop a dedicated DFU cohort with comprehensive active follow-up and a multimodal database encompassing well-defined indicators. We aim to explore a high-risk foot grading system for preventing DFU recurrence and design targeted follow-up protocols. By leveraging AI technology, we intend to build a wound warning system capable of identifying DFU recurrence. Furthermore, we seek to establish a telemedicine and AI-assisted, patient-centered home-based self-management framework for early warning and prevention of DFU recurrence.

This study aims to validate the use of an artificial intelligence-enabled electrocardiogram (AI-ECG) to screen for elevated PAP. We hypothesize that the AI-ECG model can early identify patients with pulmonary hypertension in high-risk patients, prompting further evaluation through echocardiography, potentially resulting in improving cardiovascular outcomes.

The goal of this clinical trial is to learn whether access to an artificial intelligence (AI) clinical decision support assistant can improve diagnostic accuracy during real-world telemedicine consultations among primary care physicians in El Salvador. The main questions it aims to answer are: * Does access to the AI assistant increase the proportion of correct diagnoses compared to telemedicine without AI assistance? * Does the effect of the AI assistant differ according to the physician's prior experience using AI in telemedicine? Researchers will compare physicians with the AI assistant enabled to physicians with the AI assistant temporarily disabled to see if access to AI improves diagnostic accuracy. Participants (physicians) will: * Provide telemedicine consultations as part of their routine clinical duties. * Be randomly assigned to either have the AI assistant enabled or disabled during the study period. * Continue documenting clinical encounters in the electronic platform as usual. * Have their anonymized consultation notes reviewed by an independent expert panel to determine diagnostic accuracy.

The goal of this clinical trial is to learn how artificial intelligence (AI) may help doctors make diagnoses in kidney medicine. The researchers want to know whether an AI tool called a large language model (LLM) can help doctors choose the correct diagnosis more often and feel more confident in their answers. Before starting the study, the research team tested several AI models and chose one of the best performers, a GPT-5-class model set to use high reasoning effort. The main questions this study aims to answer are: 1. Do doctors make more correct diagnoses when they can see AI suggestions? 2. Does seeing AI suggestions change how confident doctors feel about their diagnosis? Researchers will compare doctors who receive AI suggestions with doctors who do not receive AI suggestions to see how the AI affects accuracy, confidence, and decision-making. Participants will complete up to 10 online clinical cases. For each case, they will: 1. Read a short medical scenario 2. Suggest up to three possible diagnoses (If in the AI group) Review the AI's suggestions and decide whether to change their answer The study will also look at how long participants take to answer each case and how the AI's performance compares to the human answers.

This project aims to collaborate with multiple medical institutions to verify the accuracy, stability, and clinical application value of AI algorithms in echocardiographic quantitative measurement through multi-center clinical research. Specific objectives include: 1. Compare the automatic measurement results of AI with the manual measurement data from physicians of different levels, and analyze the measurement deviation and consistency of AI in key parameters such as intracardiac diameter, volume, and function. 2. Investigate whether AI-assisted measurement can significantly reduce echocardiogram analysis time and optimize clinical workflows. Through multi-center data validation, establish a standardized reference system for AI ultrasound measurement, promote the promotion and application of AI technology in medical institutions at all levels, and reduce diagnostic differences between different hospitals and physicians. 3. Exploring the application of AI in special cases: Assessing the measurement stability of AI algorithms in complex cases (such as cardiomyopathy, valvular disease, coronary heart disease, etc.), and optimizing AI models to meet broader clinical needs.

The goal of this clinical trial is to see if an artificial intelligence (AI)-assisted method helps doctors more accurately detect invasive breast cancer in people with a specific type of tumor called "extensive intraductal carcinoma" (EIC). This type of tumor is challenging to diagnose correctly using standard methods. The main question this study aims to answer is: Does the new AI-assisted method find more invasive breast cancer in EIC tumors compared to the standard method? Researchers will compare two groups: * Group 1 (INSIGHT): Doctors review breast tissue samples using an AI tool that highlights suspicious areas needing closer attention. * Group 2 (Conventional): Doctors review breast tissue samples without AI help, using the standard method. This comparison will show if the AI-assisted method works better at finding invasive cancer. What happens in the study? * Researchers will use stored breast tissue samples already collected during the participant's surgery. * Each sample will be randomly assigned to be reviewed using either the new AI-assisted method (Group 1) or the standard method (Group 2). * In Group 1, an AI program will scan the tissue images first and point out areas that might contain invasive cancer for the doctor to check closely. * In Group 2, doctors will review the tissue images without any AI help, using their standard process. * Researchers will measure which method finds invasive cancer more accurately, how long the review takes, and how many additional tests (called IHC stains) are needed. No new procedures are required from participants; the study uses existing tissue samples.

This study aims to evaluate the influence of artificial intelligence (AI) on the decision-making process for intervention after caries lesion detection. Participants will be dentists working in the Netherlands randomly divided into two groups. Dentists will be divided into two groups and receive a set of bitewing radiographs, which first will be evaluated with or without AI support according to their group. Participants will examine caries lesions on the radiographs and formulate treatment plans accordingly. Then, after a wash-out period of one month, the same radiographs, but in the opposite condition of AI support and again formulate treatment suggestions according to the present caries lesions.