[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"health-study-detail:100627499":3},{"organization":4,"armGroups":7,"interventions":31,"overallOfficials":10,"centralContacts":41,"locations":10,"responsibleParty":47,"collaborators":10,"id":49,"slug":50,"hasResults":51,"nctId":52,"briefTitle":53,"officialTitle":54,"acronym":55,"eligibilityCriteria":56,"healthyVolunteers":51,"sex":57,"minAge":58,"maxAge":10,"enrollmentInfo":59,"targetDuration":10,"studyType":62,"phases":10,"briefSummary":63,"conditions":64,"keywords":10,"overallStatus":69,"whyStopped":10,"lastUpdateSubmitDate":70,"lastUpdatePostDateStruct":71,"startDateStruct":74,"completionDateStruct":76,"leadSponsor":78,"locationsCount":10},{"fullName":5,"class":6},"China National Center for Cardiovascular Diseases","OTHER_GOV",[8,15,19,23,27],{"label":9,"type":10,"description":11,"interventionNames":12},"Internal Development and Validation Cohort",null,"Retrospective cohort used for model development and internal validation. Inputs are de-identified admission HPI records (image or text) from the AIM-CHD dataset. Expert adjudication provides the reference standard labels for 4-class coronary syndrome subtyping (STEMI, NSTEMI, unstable angina, chronic coronary syndrome).",[13,14],"Device: OCR-Prompt-LLM Information Extraction and Classification Workflow (OCR-Prompt-LLM)","Device: Manual Clinical Data Review",{"label":16,"type":10,"description":17,"interventionNames":18},"Multicenter External Validation Cohort","Retrospective multicenter cohort used for external validation across heterogeneous EHR templates and documentation styles. De-identified admission HPI records are processed through the same OCR-LLM pipeline, and predictions are compared with expert adjudicated reference labels to assess generalizability.",[13,14],{"label":20,"type":10,"description":21,"interventionNames":22},"Emergency Department External Validation Cohort","Retrospective cohort representing real-world emergency department workflow. De-identified ED admission HPI records are used to evaluate model performance under time-sensitive, information-limited conditions and assess robustness to ED documentation variability.",[13,14],{"label":24,"type":10,"description":25,"interventionNames":26},"English EHR External Validation Cohort","Retrospective cohort derived from the public de-identified MIMIC-IV database. English admission notes\u002FHPI text are used to evaluate cross-language transportability and performance of the same classification prompts and post-processing rules against reference labels derived by adjudication\u002Fstructured diagnosis mapping (as prespecified in the protocol).",[13,14],{"label":28,"type":10,"description":29,"interventionNames":30},"Clinician Usability Cohort","Prospective usability evaluation cohort. Physicians complete a structured coronary syndrome subtyping task using admission HPI cases. Outcomes include diagnostic accuracy and time to completion; within-participant comparisons may be performed between unassisted and tool-assisted conditions as prespecified.",[13,14],[32,37],{"type":33,"name":34,"description":35,"armGroupLabels":36,"otherNames":10},"DEVICE","OCR-Prompt-LLM Information Extraction and Classification Workflow (OCR-Prompt-LLM)","An automated clinical data management workflow integrating Optical Character Recognition (OCR), optimized prompt engineering, and large language models (LLMs). The system processes unstructured inpatient\u002FED records (primarily admission history of present illness and related narrative text) to extract prespecified key clinical indicators (e.g., left ventricular ejection fraction, coronary syndrome subtype, medications) and to classify cases into prespecified coronary artery disease categories (e.g., unstable angina, STEMI, NSTEMI, chronic coronary syndrome). The workflow outputs structured fields and a classification result with supporting evidence excerpts.",[28,20,24,9,16],{"type":33,"name":38,"description":39,"armGroupLabels":40,"otherNames":10},"Manual Clinical Data Review","Standard manual process in which experienced clinicians review patient medical records and extract the same prespecified clinical indicators and coronary artery disease categories using routine clinical judgment and documentation review. This manual abstraction serves as the human benchmark for comparing diagnostic accuracy, completeness, and operational efficiency against the automated OCR-Prompt-LLM workflow.",[28,20,24,9,16],[42],{"name":43,"role":44,"phone":45,"phoneExt":10,"email":46},"Xiaojin Gao, Dr","CONTACT","+86010 88322415","sophie_gao@sina.com",{"type":48,"investigatorFullName":10,"investigatorTitle":10,"investigatorAffiliation":10,"oldNameTitle":10,"oldOrganization":10},"SPONSOR","100627499","a-privacy-preserving-ocr-llm-system-for-coronary-syndrome-subtyping-from-admission-hpi-multicenter-validation-in-china-and-the-us-100627499",false,"NCT07449429","A Privacy-Preserving OCR-LLM System for Coronary Syndrome Subtyping From Admission HPI: Multicenter Validation in China and the US","Development and Multicenter Validation of a Privacy-Preserving OCR-LLM Pipeline for Four-Subtype Coronary Syndrome Classification Using Admission HPI Across Heterogeneous EHR Systems","OCR-LLM-CHD","Inclusion Criteria:Hospital encounters with admission HPI documenting sym\n\n2a4afaef-9dc1-47fc-874f-9dffaf7…\n\nevant to coronary syndrome subtyping.\n\nCases with sufficient documentation to assign one of four target subtypes (STEMI, NSTEMI, UA, CCS) by adjudication.\n\n\\-\n\nExclusion Criteria: Unclear subtype or incomplete\u002Funcertain time information preventing gold standard assignment.\n\nNon-CHD primary reason for admission after screening (for MIMIC-IV cohort).\n\n\\-","ALL","18 Years",{"count":60,"type":61},10,"ESTIMATED","OBSERVATIONAL","This study develops and validates a privacy-preserving OCR-LLM pipeline that converts admission history of present illness (HPI) records into structured coronary syndrome subtypes (STEMI, NSTEMI, unstable angina, and chronic coronary syndrome). The system first extracts text from de-identified HPI images using locally deployed OCR, then applies large language models with a fixed diagnostic prompt to generate subtype classification and evidence. Performance is evaluated in an internal validation cohort and multiple external datasets covering heterogeneous EHR templates, emergency department cases, and an English dataset from MIMIC-IV. A clinician usability study assesses changes in diagnostic accuracy and time with and without tool assistance.",[65,66,67,68],"Coronary Artery Disease (CAD) (E.G., Angina, Myocardial Infarction, and Atherosclerotic Heart Disease (ASHD))","Acute Coronary Syndromes","ST-segment Elevation Myocardial Infarction (STEMI)","Non-ST-Segment Elevation Myocardial Infarction (NSTEMI)","NOT_YET_RECRUITING","2026-02-27",{"date":72,"type":73},"2026-03-04","ACTUAL",{"date":75,"type":61},"2026-02-28",{"date":77,"type":61},"2026-03-08",{"name":5,"class":6}]