[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"health-studies-list:{\"conditionNormalized\":\"artificial-intelligence-ai-in-diagnosis\",\"overallStatus\":[\"RECRUITING\",\"AVAILABLE\",\"NOT_YET_RECRUITING\"],\"orderBy\":\"LastUpdateSubmitDate:desc\",\"size\":25,\"offset\":0}":3,"health-study-condition:artificial-intelligence-ai-in-diagnosis":26},{"pageToken":4,"total":5,"offset":6,"count":5,"results":7},null,13,0,[8,47,75,104,132,158,183,210,239,260,294,319,348],{"id":9,"slug":10,"hasResults":11,"nctId":12,"briefTitle":13,"officialTitle":13,"acronym":4,"eligibilityCriteria":14,"healthyVolunteers":15,"sex":16,"minAge":4,"maxAge":4,"enrollmentInfo":17,"targetDuration":4,"studyType":20,"phases":21,"briefSummary":23,"conditions":24,"keywords":27,"overallStatus":34,"whyStopped":4,"lastUpdateSubmitDate":35,"lastUpdatePostDateStruct":36,"startDateStruct":39,"completionDateStruct":41,"leadSponsor":43,"locationsCount":46},"100623902","does-ai-make-clinicians-more-appropriately-confident-a-randomized-study-in-preterm-birth-prediction-100623902",false,"NCT07402668","Does AI Make Clinicians More Appropriately Confident? A Randomized Study in Preterm Birth Prediction","Inclusion Criteria:\n\n* Medical doctors currently working in or training within the field of obstetrics and gynecology.\n* Experience performing transvaginal cervical ultrasound examinations.\n\nExclusion Criteria:\n\n\\- No prior experience performing transvaginal cervical ultrasound examinations.",true,"ALL",{"count":18,"type":19},125,"ESTIMATED","INTERVENTIONAL",[22],"NA","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.\n\nThe main questions it aims to answer are:\n\n* Which AI presentation format leads to better alignment between clinicians' confidence and decision accuracy (diagnostic calibration)?\n* Do different AI presentation formats lead to helpful or harmful changes in clinical decisions?\n\nParticipants 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.",[25,26],"Preterm Birth","Artificial Intelligence (AI) in Diagnosis",[28,29,30,31,32,33],"Preterm birth","Premature birth","Diagnostic calibration","Diagnostic accuracy","Diagnostic confidence","Artificial intelligence","RECRUITING","2026-06-30",{"date":37,"type":38},"2026-07-01","ACTUAL",{"date":40,"type":38},"2026-02-03",{"date":42,"type":19},"2026-07",{"name":44,"class":45},"Rigshospitalet, Denmark","OTHER",18,{"id":48,"slug":49,"hasResults":11,"nctId":50,"briefTitle":51,"officialTitle":52,"acronym":53,"eligibilityCriteria":54,"healthyVolunteers":11,"sex":16,"minAge":55,"maxAge":4,"enrollmentInfo":56,"targetDuration":4,"studyType":58,"phases":4,"briefSummary":59,"conditions":60,"keywords":63,"overallStatus":34,"whyStopped":4,"lastUpdateSubmitDate":65,"lastUpdatePostDateStruct":66,"startDateStruct":68,"completionDateStruct":70,"leadSponsor":72,"locationsCount":74},"100642942","diagnostic-accuracy-of-gpt-4o-and-claude-46-sonnet-in-turkish-ed-anamnesis-notes-100642942","NCT07632859","Diagnostic Accuracy of GPT-4o and Claude 4.6 Sonnet in Turkish ED Anamnesis Notes","Diagnostic Accuracy of Large Language Models From Emergency Department Anamnesis Notes: A Comparison of GPT-4o and Claude 4.6 Sonnet With Emergency Medicine Specialists","LLM-ED-DX-TR","INCLUSION CRITERIA:\n\n* Adult patients (aged 18 years and older) presenting to the emergency department.\n* Complete electronic health record available in the hospital information system (HBYS) containing a detailed anamnesis note with chief complaint, symptom duration, associated symptoms, and relevant medical history.\n* A definitive primary diagnosis recorded by the treating emergency physician using ICD-10 codes at the time of patient file closure.\n\nEXCLUSION CRITERIA:\n\n* Emergency department anamnesis notes containing fewer than 50 words or completely lacking substantive clinical content\\[cite: 1\\].\n* Pediatric cases (age under 18 years)\\[cite: 1\\].\n* Patients critically ill and triaged to high-acuity resuscitation areas (Emergency Severity Index \\[ESI\\] level 1)\\[cite: 1\\].\n* Clinical notes containing residual identifying information that cannot be fully de-identified, preventing compliance with data privacy regulations\\[cite: 1\\].\n* Non-independent clinical notes consisting solely of a brief cross-reference to a prior hospital visit without a new history entry\\[cite: 1\\].","18 Years",{"count":57,"type":19},600,"OBSERVATIONAL","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.",[61,62,26],"Emergency Medicine","Diagnostic Errors",[64],"Large Language Model; GPT-4o; Claude 4.6 Sonnet; ICD-10; Clinical Coding; Turkish; Emergency Department; Diagnostic Accuracy; STARD; STARD-AI","2026-06-22",{"date":67,"type":38},"2026-06-25",{"date":69,"type":19},"2026-06",{"date":71,"type":19},"2026-10",{"name":73,"class":45},"Marmara University Pendik Training and Research Hospital",1,{"id":76,"slug":77,"hasResults":11,"nctId":78,"briefTitle":79,"officialTitle":80,"acronym":81,"eligibilityCriteria":82,"healthyVolunteers":11,"sex":16,"minAge":55,"maxAge":4,"enrollmentInfo":83,"targetDuration":4,"studyType":58,"phases":4,"briefSummary":85,"conditions":86,"keywords":89,"overallStatus":34,"whyStopped":4,"lastUpdateSubmitDate":65,"lastUpdatePostDateStruct":98,"startDateStruct":100,"completionDateStruct":101,"leadSponsor":103,"locationsCount":74},"100639433","diagnostic-accuracy-of-gpt-4o-and-claude-for-heart-score-calculation-in-chest-pain-100639433","NCT07626060","Diagnostic Accuracy of GPT-4o and Claude for HEART Score Calculation in Chest Pain","Diagnostic Accuracy of Large Language Models (GPT-4o and Claude) in HEART Score Calculation and 30-Day MACE Prediction in Emergency Department Chest Pain Patients: A Prospective Observational Validation Study Against Three-Expert Consensus","LLM-HEART","INCLUSION CRITERIA:\n\n* Age \\>=18 years\n* Chief complaint of non-traumatic chest pain at the emergency department\n* Written informed consent obtained from the patient or legally authorized representative\n* Availability for 30-day follow-up (reachable by telephone and\u002For actively registered in the e-Nabiz national health database)\n\nEXCLUSION CRITERIA:\n\n* Traumatic chest pain etiology\n* ST-elevation myocardial infarction (STEMI) at presentation requiring immediate reperfusion protocol\n* Refusal or subsequent withdrawal of informed consent\n* Inability to complete the mandatory 30-day follow-up period\n\nWITHDRAWAL CRITERIA:\n\n* Patient or representative requests data withdrawal after initial consent\n* Administrative identification of retrospective data entry after enrollment",{"count":84,"type":19},690,"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.\n\nThe 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\u002F2\u002F4b, unplanned revascularization) determined via national health database and telephone follow-up serves as the outcome for diagnostic accuracy analysis.\n\nA secondary documentation-quality sub-study will quantify how spontaneously Turkish emergency anamnesis notes capture HEART score parameters.",[61,87,26,88],"Artificial Intelligence (AI)","Chest Pain Rule Out Myocardial Infarction",[90,91,92,93,94,95,96,97],"Large Language Model","GPT-4o","Claude Sonnet","Emergency Department","Diagnostic Accuracy","Medical Informatics","Physician vs AI","HEART score",{"date":99,"type":38},"2026-06-23",{"date":69,"type":19},{"date":102,"type":19},"2027-06",{"name":73,"class":45},{"id":105,"slug":106,"hasResults":11,"nctId":107,"briefTitle":108,"officialTitle":109,"acronym":4,"eligibilityCriteria":110,"healthyVolunteers":11,"sex":16,"minAge":4,"maxAge":4,"enrollmentInfo":111,"targetDuration":4,"studyType":58,"phases":4,"briefSummary":113,"conditions":114,"keywords":117,"overallStatus":34,"whyStopped":4,"lastUpdateSubmitDate":123,"lastUpdatePostDateStruct":124,"startDateStruct":126,"completionDateStruct":128,"leadSponsor":130,"locationsCount":74},"100644086","comparison-of-digital-analysis-and-artificial-intelligence-for-cephalometric-tracing-100644086","NCT07664488","Comparison of Digital Analysis and Artificial Intelligence for Cephalometric Tracing","Cephalometric Tracing: A Comparison Between Digital Analysis and Artificial Intelligence","Inclusion Criteria:\n\n* Availability of digital lateral cephalometric radiographs of adequate diagnostic quality\n* Radiographs acquired with patients in centric occlusion and proper head positioning using a cephalostat\n* Patients of any age and sex\n* Absence of congenital or acquired craniofacial anomalies\n* No previous orthodontic treatment\n* No previous orthognathic surgical treatment\n* Absence of agenesis of incisors or first molars\n* Absence of supernumerary teeth overlapping the region of interest\n\nExclusion Criteria:\n\n* Radiographs presenting artifacts or inadequate visualization of anatomical structures\n* History of significant craniofacial trauma\n* Radiographs acquired without a cephalostat\n* Presence of severe skeletal asymmetries\n* Incomplete clinical or radiographic records\n* Radiographs unsuitable for manual or AI-based cephalometric landmark identification",{"count":112,"type":19},100,"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.",[115,116,87,26],"Cephalometric Analysis","Cephalometry",[118,119,120,121,122],"artificial intelligence","cephalometric analysis","lateral cephalogram","landmark identification","automated cephalometric tracing","2026-06-17",{"date":125,"type":38},"2026-06-24",{"date":127,"type":38},"2026-06-01",{"date":129,"type":19},"2026-09-30",{"name":131,"class":45},"University of Pavia",{"id":133,"slug":134,"hasResults":11,"nctId":135,"briefTitle":136,"officialTitle":137,"acronym":138,"eligibilityCriteria":139,"healthyVolunteers":11,"sex":16,"minAge":55,"maxAge":4,"enrollmentInfo":140,"targetDuration":4,"studyType":58,"phases":4,"briefSummary":142,"conditions":143,"keywords":146,"overallStatus":148,"whyStopped":4,"lastUpdateSubmitDate":149,"lastUpdatePostDateStruct":150,"startDateStruct":152,"completionDateStruct":153,"leadSponsor":155,"locationsCount":157},"100643559","ai-assisted-chest-ct-reporting-for-enhanced-speed-and-quality-the-double-ace-study-100643559","NCT07640906","AI-Assisted Chest-CT Reporting for Enhanced Speed and Quality (The DOUBLE-ACE Study)","A Multicenter Comparative Study Evaluating the Impact of an AI-Assisted Chest CT Reporting System on Real-world Radiologist Performance: The DOUBLE-ACE Study","DOUBLE-ACE","The study participants include both the radiologists whose performance is evaluated and the chest CT scans they interpret. Eligibility criteria are defined for both.\n\n1\\. Inclusion Criteria\n\n1.1 For Radiologists\n\n1. Board-certified radiologists specializing in or routinely performing thoracic imaging.\n2. Employed at one of the participating study centers for the entire duration of both the without-AI and with-AI study periods.\n3. Interpreted a minimum of eligible chest CT scans (e.g., \\> 50 scans) during both the without-AI and with-AI data collection periods.\n\n1.2 For Chest CT Scans\n\n1. Non-contrast chest CT examinations performed for any clinical indication.\n2. Scans completed and finalized during the defined with-AI or without-AI study periods.\n3. Patient age 18 years or older at the time of the scan.\n\n2\\. Exclusion Criteria\n\n2.1 For Radiologists:\n\n1. Radiologists who joined, left, or were on extended leave (e.g., \\>4 weeks) from the participating center between the with-AI and without-AI study periods.\n2. Radiologists who interpreted fewer than the minimum required number of eligible scans in either study period.\n3. Radiologists who voluntarily decline to have their de-identified performance data included in the study analysis.\n4. Radiologists who decline to provide demographic or occupational information (e.g., years of professional experience or sex)-variables that may serve as potential confounders-will be excluded from adjusted and stratified analyses that require such covariates.\n\n2.2 For Chest CT Scans\n\n1. CT scans of pediatric patients (age \\\u003C 18 years).\n2. Contrast-enhanced chest CT studies.\n3. Studies performed for specific procedural guidance (e.g., biopsy, ablation).\n4. Studies deemed technically inadequate for primary interpretation by radiologist (e.g., severe motion artifact, incomplete study).\n5. Studies for which the AI system fails to generate a valid preliminary report draft. This includes possible system failures, algorithm errors, or cases where the generated draft is deemed technically unusable (e.g., empty, garbled, or based on critically flawed image analysis).\n6. The lack of relevant information (diagnosis, clinical scenario, etc.). Chest CT data will be excluded from corresponding analyses if the required information, which is necessary for confounding control, subgroup analyses, or other pre-specified analyses, is unavailable. Such scenarios include data that cannot be retrospectively retrieved, incompletely recorded, or restricted due to ethical or institutional requirements.",{"count":141,"type":19},75,"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.",[144,145,26],"Thoracic Diseases","Chest CT Scan",[147,118],"Chest CT scan","NOT_YET_RECRUITING","2026-06-05",{"date":151,"type":38},"2026-06-11",{"date":69,"type":19},{"date":154,"type":19},"2026-12",{"name":156,"class":45},"Shanghai Zhongshan Hospital",2,{"id":159,"slug":160,"hasResults":11,"nctId":161,"briefTitle":162,"officialTitle":163,"acronym":4,"eligibilityCriteria":164,"healthyVolunteers":11,"sex":165,"minAge":55,"maxAge":4,"enrollmentInfo":166,"targetDuration":4,"studyType":58,"phases":4,"briefSummary":168,"conditions":169,"keywords":170,"overallStatus":34,"whyStopped":4,"lastUpdateSubmitDate":175,"lastUpdatePostDateStruct":176,"startDateStruct":178,"completionDateStruct":180,"leadSponsor":182,"locationsCount":74},"100640988","the-impact-of-image-acquisition-in-cervical-ultrasound-on-ai-based-prediction-of-preterm-birth-in-clinical-practice-100640988","NCT07598097","The Impact of Image Acquisition in Cervical Ultrasound on AI-Based Prediction of Preterm Birth in Clinical Practice","The Impact of Image Acquisition in Cervical Ultrasound on AI-Based Prediction of Preterm Birth in Clinical Practice: A Prospective Observational Study","Inclusion Criteria:\n\n* Pregnant women aged ≥18 years\n* Attending routine second-trimester scan (and scheduled transvaginal cervical assessment per local protocol\u002Fworkflow)\n\nExclusion Criteria:\n\n* Absence of transvaginal cervical assessment at the second-trimester scan\n* Missing follow-up data on pregnancy outcome (gestational age at delivery)\n* Inadequate image quality or missing required cervical ultrasound image","FEMALE",{"count":167,"type":19},2000,"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.\n\nThe primary research question is whether the AI model performs differently across images acquired with different imaging settings.",[25,26],[28,29,33,171,172,31,173,174],"Deep learning","Image acquisition","Cervical ultrasound","Prospective validation","2026-05-19",{"date":177,"type":38},"2026-05-20",{"date":179,"type":38},"2026-03-11",{"date":181,"type":19},"2027-02",{"name":44,"class":45},{"id":184,"slug":185,"hasResults":11,"nctId":186,"briefTitle":187,"officialTitle":188,"acronym":4,"eligibilityCriteria":189,"healthyVolunteers":11,"sex":16,"minAge":55,"maxAge":4,"enrollmentInfo":190,"targetDuration":192,"studyType":58,"phases":4,"briefSummary":193,"conditions":194,"keywords":198,"overallStatus":148,"whyStopped":4,"lastUpdateSubmitDate":201,"lastUpdatePostDateStruct":202,"startDateStruct":204,"completionDateStruct":206,"leadSponsor":208,"locationsCount":74},"100627724","ai-based-diabetic-foot-recurrence-cohort-100627724","NCT07452354","AI-Based Diabetic Foot Recurrence Cohort","Development and Validation of an AI-Based Wound Alert System With a Home-Based Management Model for a Diabetic Foot Recurrence Cohort","Inclusion Criteria:\n\n* The patient must be aged 18 years or older; have a confirmed diagnosis of type 1 or type 2 diabetes mellitus according to the World Health Organization criteria; the wound etiology attributable to diabetic foot ulcers, with complete wound healing post-treatment defined as a dry wound devoid of exudate, complete epithelialization of both the wound bed and margins, absence of surrounding erythema or edema, and sufficient tensile strength to withstand pressure without dehiscence; voluntary participation in this study with provision of written informed consent.\n\nExclusion Criteria:\n\n* Inability of the patient to cooperate or presence of psychiatric disorders; At the investigator's discretion, the subject is deemed unsuitable for this study or unable to comply with the study requirements.",{"count":191,"type":19},200,"3 Months","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.\n\nEstablishing 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.\n\nOur 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.",[195,196,197,26],"Diabetic Foot Ulcer (DFU)","Diabete Mellitus","Diabetic Foot Ulcer Treatment",[199,197,196,200,26],"Diabetic Foot Ulcer","Reccurrence","2026-02-28",{"date":203,"type":38},"2026-03-05",{"date":205,"type":19},"2026-03-15",{"date":207,"type":19},"2028-12-31",{"name":209,"class":45},"Peking University Third Hospital",{"id":211,"slug":212,"hasResults":11,"nctId":213,"briefTitle":214,"officialTitle":215,"acronym":216,"eligibilityCriteria":217,"healthyVolunteers":11,"sex":16,"minAge":218,"maxAge":219,"enrollmentInfo":220,"targetDuration":4,"studyType":20,"phases":222,"briefSummary":223,"conditions":224,"keywords":226,"overallStatus":34,"whyStopped":4,"lastUpdateSubmitDate":230,"lastUpdatePostDateStruct":231,"startDateStruct":233,"completionDateStruct":235,"leadSponsor":237,"locationsCount":74},"100599061","a-deep-learning-enabled-electrocardiogram-for-detecting-pulmonary-hypertension-100599061","NCT07079592","A Deep-Learning-Enabled Electrocardiogram for Detecting Pulmonary Hypertension","A Deep-Learning-Enabled Electrocardiogram for Detecting Pulmonary Hypertension: A Randomized Controlled Trial","ADDPH","Inclusion Criteria:\n\n* Men or women, ≥ 50 to 85 years of age\n* At least one 12-lead ECG within 3 months\n\nExclusion Criteria:\n\n* A diagnosis of PH WHO Groups 1, 2, 3, 4, or 5\n* A diagnosis of hypertrophic cardiomyopathy, restrictive cardiomyopathy, constrictive pericarditis, cardiac amyloidosis, or infiltrative cardiomyopathy\n* Prior heart, lung, or heart-lung transplants\n* Any systolic pulmonary artery pressure \\>50 mmHg by echocardiography before\n* Echocardiography in 3 months before index ECG","50 Years","85 Years",{"count":221,"type":19},8666,[22],"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.",[87,26,225],"Hypertension, Pulmonary",[33,227,228,229],"electrocardiogram","deep learning","pulmonary hypertension","2026-02-23",{"date":232,"type":38},"2026-02-24",{"date":234,"type":19},"2026-02",{"date":236,"type":19},"2026-06-15",{"name":238,"class":45},"National Defense Medical Center, Taiwan",{"id":240,"slug":241,"hasResults":11,"nctId":242,"briefTitle":243,"officialTitle":244,"acronym":4,"eligibilityCriteria":245,"healthyVolunteers":11,"sex":16,"minAge":55,"maxAge":4,"enrollmentInfo":246,"targetDuration":4,"studyType":20,"phases":248,"briefSummary":249,"conditions":250,"keywords":4,"overallStatus":148,"whyStopped":4,"lastUpdateSubmitDate":251,"lastUpdatePostDateStruct":252,"startDateStruct":254,"completionDateStruct":255,"leadSponsor":257,"locationsCount":74},"100624229","ai-telemedicine-support-for-primary-care-physicians-in-el-salvador-100624229","NCT07406919","AI Telemedicine Support for Primary Care Physicians in El Salvador","Pragmatic Randomized Clinical Trial of AI-Assisted Telemedicine to Improve Diagnostic Accuracy Among Primary Care Physicians in El Salvador","Inclusion Criteria:\n\n* Must be a physician employed by the DoctorSV telemedicine program\n* Must provide written informed consent to participate in the study\n* Consultations must be for acute pathologies of the digestive, respiratory, or urinary systems, or acute ophthalmic infections manageable in primary care\n* Consultation must be the first medical contact (first visit) for the current acute episode\n* The condition must correspond to specific ICD-11 codes defined in the study protocol\n\nExclusion Criteria:\n\n* Physicians who are inactive on the platform for more than 4 consecutive weeks\n* Physicians who transition to work modalities other than telemedicine or reduce their working hours to less than 20 hours per week\n* Physicians whose employment contract ends (resignation, dismissal, or contract completion) during the data collection period\n* Consultations classified by the physician as requiring immediate in-person attention\n* Consultations requiring referral to another level of care or specialty for definitive management\n* Consultations interrupted or incomplete due to connectivity or system failures\n* Consultations solely for administrative purposes (e.g., certificates, repeat prescriptions without clinical evaluation)\n* Consultations that are follow-up visits or controls for a previously evaluated episode",{"count":247,"type":19},180,[22],"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.\n\nThe main questions it aims to answer are:\n\n* Does access to the AI assistant increase the proportion of correct diagnoses compared to telemedicine without AI assistance?\n* Does the effect of the AI assistant differ according to the physician's prior experience using AI in telemedicine?\n\nResearchers 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.\n\nParticipants (physicians) will:\n\n* Provide telemedicine consultations as part of their routine clinical duties.\n* Be randomly assigned to either have the AI assistant enabled or disabled during the study period.\n* Continue documenting clinical encounters in the electronic platform as usual.\n* Have their anonymized consultation notes reviewed by an independent expert panel to determine diagnostic accuracy.",[26],"2026-02-13",{"date":253,"type":38},"2026-02-17",{"date":234,"type":19},{"date":256,"type":19},"2026-08",{"name":258,"class":259},"Hospital El Salvador","OTHER_GOV",{"id":261,"slug":262,"hasResults":11,"nctId":263,"briefTitle":264,"officialTitle":265,"acronym":266,"eligibilityCriteria":267,"healthyVolunteers":15,"sex":16,"minAge":55,"maxAge":4,"enrollmentInfo":268,"targetDuration":4,"studyType":20,"phases":269,"briefSummary":270,"conditions":271,"keywords":275,"overallStatus":34,"whyStopped":4,"lastUpdateSubmitDate":285,"lastUpdatePostDateStruct":286,"startDateStruct":288,"completionDateStruct":290,"leadSponsor":292,"locationsCount":74},"100620042","reasoning-enrichment-with-feedback-from-ia-in-nephrology-trial-100620042","NCT07352475","Reasoning Enrichment With Feedback From IA in NEphrology Trial","Reasoning Enhancement With Feedback From a Generative AI in Nephrology (REFINe): A Randomized Evaluation of Generative AI Support in Nephrology Diagnosis","REFINe","Inclusion Criteria:\n\nAdults aged 18 years or older.\n\nAble to read and answer clinical vignettes in English or French.\n\nAccess to a computer or smartphone with an internet connection.\n\nProvides informed consent online.\n\nParticipants are expected to have at least basic medical training (e.g., medical students, residents, fellows, or practicing clinicians), although no formal verification is required.\n\nExclusion Criteria:\n\nIndividuals under 18 years of age.\n\nInability to complete online study procedures.\n\nPrior involvement in the design, development, or evaluation of the AI system used in this study.",{"count":112,"type":19},[22],"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.\n\nBefore 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.\n\nThe main questions this study aims to answer are:\n\n1. Do doctors make more correct diagnoses when they can see AI suggestions?\n2. Does seeing AI suggestions change how confident doctors feel about their diagnosis?\n\nResearchers 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.\n\nParticipants will complete up to 10 online clinical cases. For each case, they will:\n\n1. Read a short medical scenario\n2. Suggest up to three possible diagnoses\n\n(If in the AI group) Review the AI's suggestions and decide whether to change their answer\n\nThe study will also look at how long participants take to answer each case and how the AI's performance compares to the human answers.",[272,273,26,274],"Diagnosis","Clinical Decision-making","Decision Support Systems, Clinical",[276,277,94,278,279,280,281,282,283,284],"Large Language Model (LLM)","Generative AI","Clinical Vignettes","Online Study","Randomized Controlled Trial","Nephrology Diagnosis","AI Clinical Decision Support","Human-AI Collaboration","Medical Reasoning","2026-01-12",{"date":287,"type":38},"2026-01-20",{"date":289,"type":38},"2025-11-20",{"date":291,"type":19},"2026-12-31",{"name":293,"class":45},"University Hospital, Lille",{"id":295,"slug":296,"hasResults":11,"nctId":297,"briefTitle":298,"officialTitle":298,"acronym":299,"eligibilityCriteria":300,"healthyVolunteers":15,"sex":16,"minAge":55,"maxAge":301,"enrollmentInfo":302,"targetDuration":4,"studyType":58,"phases":4,"briefSummary":304,"conditions":305,"keywords":308,"overallStatus":34,"whyStopped":4,"lastUpdateSubmitDate":309,"lastUpdatePostDateStruct":310,"startDateStruct":312,"completionDateStruct":314,"leadSponsor":316,"locationsCount":318},"100603207","a-multi-center-study-on-artificial-intelligence-based-quantitative-evaluation-of-echocardiography-100603207","NCT07133516","A Multi-center Study on Artificial Intelligence-Based Quantitative Evaluation of Echocardiography","MAIQUEE","Inclusion Criteria:\n\n1. Age ≥18 - 80 years;\n2. Types of diseases (8 in total, 200 cases each):\n\n   1. Normal heart\n   2. Coronary heart disease (with segmental thinning and abnormal movement)\n   3. Valve disease (valve stenosis or reflux)\n   4. Hypertensive heart disease\n   5. Atrial fibrillation\n   6. Heart failure\n   7. Dilated cardiomyopathy\n   8. Hypertrophic cardiomyopathy\n\nExclusion Criteria:\n\n1. Patients with congenital heart disease\n2. Patients with poor image quality","80 Years",{"count":303,"type":19},1600,"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:\n\n1. 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.\n2. 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.\n3. 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.",[87,26,306,307],"Cardiovascular Diseases (CVD)","Echocardiography",[87,26,306,307],"2025-08-18",{"date":311,"type":38},"2025-08-21",{"date":313,"type":38},"2025-07-22",{"date":315,"type":19},"2026-07-31",{"name":317,"class":45},"First Hospital of China Medical University",37,{"id":320,"slug":321,"hasResults":11,"nctId":322,"briefTitle":323,"officialTitle":324,"acronym":325,"eligibilityCriteria":326,"healthyVolunteers":11,"sex":165,"minAge":4,"maxAge":4,"enrollmentInfo":327,"targetDuration":4,"studyType":20,"phases":329,"briefSummary":330,"conditions":331,"keywords":332,"overallStatus":148,"whyStopped":4,"lastUpdateSubmitDate":339,"lastUpdatePostDateStruct":340,"startDateStruct":342,"completionDateStruct":344,"leadSponsor":346,"locationsCount":74},"100597600","human-ai-collaborative-insight-diagnostic-workflow-for-in-breast-cancer-with-extensive-intraductal-component-100597600","NCT07060599","Human-AI Collaborative INSIGHT Diagnostic Workflow for in Breast Cancer With Extensive Intraductal Component","A Prospective Multicenter Randomized Trial Comparing the Human-AI Collaborative INSIGHT Workflow vs. Conventional Pathology Diagnosis for Detecting Invasive Carcinoma in Breast Cancer With Extensive Intraductal Component (EIC)","INSIGHT-EIC","Inclusion Criteria:\n\n* DCIS (ductal carcinoma in situ) with or without invasive carcinoma, as confirmed by core needle biopsy prior to surgery.\n* Tumor size \\>2 cm (cT2-cT4 according to AJCC 8th edition staging) with extensive calcifications, as documented by ultrasound or MRI.\n* Undergone either mastectomy or breast-conserving surgery.\n* Histopathological examination showing DCIS comprising ≥80% of the total tumor volume in the surgical specimen.\n\nDCIS (ductal carcinoma in situ) with or without invasive carcinoma, as confirmed by core needle biopsy prior to surgery.\n\n\\- Minimum of 10 H\\&E-stained slides available for each case, with adequate tissue quality for analysis.\n\nExclusion Criteria:\n\n* Received neoadjuvant therapy (chemotherapy, endocrine therapy, or targeted therapy) before surgery.\n* History of vacuum-assisted biopsy (VAB) or other minimally invasive breast procedures that may alter tumor architecture.\n* Insufficient or degraded tissue samples (e.g., due to fixation artifacts, sectioning errors, or poor staining quality).\n* Tumors lacking a DCIS (ductal carcinoma in situ) component upon histological examination.",{"count":328,"type":19},480,[22],"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?\n\nResearchers will compare two groups:\n\n* Group 1 (INSIGHT): Doctors review breast tissue samples using an AI tool that highlights suspicious areas needing closer attention.\n* Group 2 (Conventional): Doctors review breast tissue samples without AI help, using the standard method.\n\nThis comparison will show if the AI-assisted method works better at finding invasive cancer.\n\nWhat happens in the study?\n\n* Researchers will use stored breast tissue samples already collected during the participant's surgery.\n* Each sample will be randomly assigned to be reviewed using either the new AI-assisted method (Group 1) or the standard method (Group 2).\n* 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.\n* In Group 2, doctors will review the tissue images without any AI help, using their standard process.\n* 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.\n\nNo new procedures are required from participants; the study uses existing tissue samples.",[26],[333,334,335,336,337,338,272],"Extensive Intraductal Component","Breast Cancer","Pathology","Human-AI Collaborative Workflow","Artificial Intelligence","DCIS","2025-07-01",{"date":341,"type":38},"2025-07-11",{"date":343,"type":19},"2025-08-01",{"date":345,"type":19},"2027-08-01",{"name":347,"class":45},"Sun Yat-sen University",{"id":349,"slug":350,"hasResults":11,"nctId":351,"briefTitle":352,"officialTitle":353,"acronym":354,"eligibilityCriteria":355,"healthyVolunteers":15,"sex":16,"minAge":4,"maxAge":4,"enrollmentInfo":356,"targetDuration":4,"studyType":20,"phases":358,"briefSummary":359,"conditions":360,"keywords":362,"overallStatus":148,"whyStopped":4,"lastUpdateSubmitDate":367,"lastUpdatePostDateStruct":368,"startDateStruct":370,"completionDateStruct":372,"leadSponsor":374,"locationsCount":74},"100595033","the-impact-of-artificial-intelligence-on-dentists-decision-making-process-during-caries-detection-100595033","NCT07027189","The Impact of Artificial Intelligence on Dentists' Decision-Making Process During Caries Detection","DECIDE-AI:The Impact of Artificial Intelligence on Dentists' Decision-Making Process During Caries Detection: A Randomized Controlled Study","DECIDE-AI","Inclusion Criteria:\n\n1. Graduated, practising dentists.\n2. At least three years of experience\n\nExclusion Criteria:\n\n1. Retired dentists.\n2. Specialized practitioners (e.g., orthodontists and oral surgeons) if their typical practice does not involve routine caries diagnostics and treatment planning.",{"count":357,"type":19},25,[22],"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.",[26,361],"Artificial Intelligence Supported Image Reviewing",[337,363,364,365,366],"Caries Detection","Decision-making","Dental Imaging","Treatment Planning","2025-06-10",{"date":369,"type":38},"2025-06-18",{"date":371,"type":19},"2025-10-02",{"date":373,"type":19},"2026-06-02",{"name":375,"class":45},"Radboud University Medical Center"]