[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"trial:NCT07706920":3,"trial-entities:NCT07706920":100,"trial-summary:NCT07706920":104},{"id":4,"nct_id":4,"org_study_id":5,"brief_title":6,"official_title":7,"overall_status":8,"completion_date":9,"status_verified_date":10,"last_update_date":11,"start_date":10,"sponsor_name":12,"lead_sponsor_class":13,"has_dmc":14,"brief_summary":15,"detailed_description":16,"conditions":17,"keywords":20,"study_type":25,"primary_purpose":26,"phases":27,"enrollment_info":29,"interventions":32,"primary_outcomes":42,"secondary_outcomes":50,"sex":62,"minimum_age":63,"maximum_age":16,"healthy_volunteers":64,"eligibility_criteria":65,"std_ages":76,"locations":79,"central_contacts":94,"overall_officials":95,"references":98,"see_also_links":99},"NCT07706920","85430","Testing an AI Tool to Help Primary Care Clinicians With Specialty Consultation Questions","Physician Usability and Output Quality Evaluation of a Retrieval-Augmented Language Model System for Specialty Medical Consultation: A Human-Computer Interaction Study","NOT_YET_RECRUITING","2026-09","2026-07","2026-07-16","Stanford University","OTHER",false,"The goal of this study is to test an artificial intelligence (AI) tool called SAGE. SAGE helps primary care doctors with questions that often need a specialist. Primary care doctors are the doctors people usually see first. SAGE reviews a case and suggests what a specialist might advise.\n\nThe main questions it aims to answer are:\n\n* Do doctors make sound, timely care decisions when they use SAGE?\n* Do those decisions match what a specialist would advise?\n\nResearchers will compare the decisions doctors make with and without SAGE.\n\nDoctors in the study will:\n\n* Review made-up patient cases (these are not real patients)\n* Make a decision for each case, their usual way and with SAGE",null,[18,19],"Decision Support Systems, Clinical","Referral and Consultation",[21,22,23,24],"clinical decision support","electronic consultation","primary care","artificial intelligence","INTERVENTIONAL","HEALTH_SERVICES_RESEARCH",[28],"NA",{"count":30,"type":31},15,"ESTIMATED",[33,38],{"type":13,"name":34,"description":35,"armGroupLabels":36},"SAGE (AI clinical decision support)","SAGE is an artificial intelligence (AI) based clinical decision support tool. It generates specialty-informed recommendations for a primary care consultation question. Physicians review the SAGE output while making a management decision for the synthetic case.",[37],"Primary care physicians",{"type":13,"name":39,"description":40,"armGroupLabels":41},"Standard eConsult","A standard electronic consultation (eConsult) format, without SAGE. Physicians review this information while making a management decision for the synthetic case.",[37],[43,47],{"measure":44,"description":45,"timeFrame":46},"Clinical actionability of the clinician's decision","For each case, independent reviewers judge whether the physician's decision is clinically actionable, meaning the physician can act on it now rather than wait for a specialist. The outcome is the proportion of cases judged actionable, measured separately for decisions made with SAGE and for decisions made the standard way.","Post-session independent review, through study completion (up to approximately 2 months)",{"measure":48,"description":49,"timeFrame":46},"Concordance of the clinician's decision with the specialist reference answer","Agreement between the physician's management decision and a specialist reference answer, rated by independent reviewers, with inter-rater agreement summarized. Assessed for decisions made with SAGE and for decisions made the standard way.",[51,55,59],{"measure":52,"description":53,"timeFrame":54},"System usability (System Usability Scale, SUS)","Perceived usability of SAGE measured with the 10-item System Usability Scale (SUS), scored from 0 to 100.","End of study session (Day 1, approximately 60 minutes)",{"measure":56,"description":57,"timeFrame":58},"Order acceptance in the SAGE condition","Proportion of SAGE-suggested orders that the clinician accepts, assessed in the SAGE condition.","During study session (Day 1)",{"measure":60,"description":61,"timeFrame":58},"Time to complete case review","Time (in minutes) taken to review each case and reach a management decision, compared between the SAGE and standard eConsult conditions.","ALL","18 Years",true,{"inclusion":66,"exclusion":71,"raw_text":75},[67,68,69,70],"Physician practicing in primary care internal medicine and\u002For family medicine","Attending physician, or resident physician at postgraduate year 2 (PGY-2) or higher","Stanford-affiliated (faculty, staff, or trainee)","Able to complete a single, approximately 60-minute remote (Zoom) session conducted in English",[72,73,74],"Not currently practicing in primary care internal medicine or family medicine","Member of the study team or otherwise involved in the development of SAGE","Unable to complete the remote study session","Inclusion Criteria:\n\n* Physician practicing in primary care internal medicine and\u002For family medicine\n* Attending physician, or resident physician at postgraduate year 2 (PGY-2) or higher\n* Stanford-affiliated (faculty, staff, or trainee)\n* Able to complete a single, approximately 60-minute remote (Zoom) session conducted in English\n\nExclusion Criteria:\n\n* Not currently practicing in primary care internal medicine or family medicine\n* Member of the study team or otherwise involved in the development of SAGE\n* Unable to complete the remote study session",[77,78],"ADULT","OLDER_ADULT",[80],{"facility":12,"city":81,"state":82,"zip":83,"country":84,"contacts":85,"geoPoint":91},"Stanford","California","94305","United States",[86],{"name":87,"role":88,"phone":89,"email":90},"Jonathan Chen, MD, PhD","CONTACT","650-725-3655","jonc101@stanford.edu",{"lat":92,"lon":93},37.42411,-122.16608,[],[96],{"name":87,"affiliation":12,"role":97},"PRINCIPAL_INVESTIGATOR",[],[],{"nct_id":4,"conditions":101,"biomarkers":103},[102],"Clinical Decision Support",[],{"nct_id":4,"found":64,"summary":105,"prompt_version":115},{"design":106,"status":107,"heading":108,"summary":109,"follow_up":110,"word_count":111,"commitments":112,"compensation":113,"drugs_mentioned":114},"This is an interventional study comparing decisions made with SAGE (AI clinical decision support) versus a standard electronic consultation format. It plans to enroll 15 primary care physicians.","completed","Testing an AI Tool for Primary Care Doctor Consultations","This study is testing an artificial intelligence (AI) tool called SAGE. SAGE is designed to help primary care doctors (the doctors you usually see first) when they have questions that might need a specialist's advice. SAGE reviews a patient's case and suggests recommendations, similar to what a specialist might provide. Researchers want to see if doctors make good, timely decisions using SAGE, and if those decisions match what a specialist would recommend. Doctors in the study will review made-up patient cases and make decisions both with and without SAGE. This study aims to enroll 15 primary care doctors who are affiliated with Stanford.","The study measures outcomes through study completion, which is up to approximately 2 months after the session.",103,"Participants will complete a single, approximately 60-minute remote (Zoom) session. During this session, they will review made-up patient cases and make management decisions.","Not stated in the trial record.",[],"v2"]