NCT07626060

Brief Summary

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.

Trial Health

63
Monitor

Trial Health Score

Automated assessment based on enrollment pace, timeline, and geographic reach

Enrollment
690

participants targeted

Target at P75+ for all trials

Timeline
12mo left

Started Jun 2026

Shorter than P25 for all trials

Geographic Reach
1 country

1 active site

Status
not yet recruiting

Health score is calculated from publicly available data and should be used for screening purposes only.

Trial Relationships

Click on a node to explore related trials.

Study Timeline

Key milestones and dates

Study Progress4%
Jun 2026Jun 2027

First Submitted

Initial submission to the registry

May 27, 2026

Completed
5 days until next milestone

Study Start

First participant enrolled

June 1, 2026

Completed
3 days until next milestone

First Posted

Study publicly available on registry

June 4, 2026

Completed
9 months until next milestone

Primary Completion

Last participant's last visit for primary outcome

March 1, 2027

Expected
3 months until next milestone

Study Completion

Last participant's last visit for all outcomes

June 1, 2027

Last Updated

June 4, 2026

Status Verified

June 1, 2026

Enrollment Period

9 months

First QC Date

May 27, 2026

Last Update Submit

June 3, 2026

Conditions

Keywords

Large Language ModelGPT-4oClaude SonnetEmergency DepartmentDiagnostic AccuracyMedical InformaticsPhysician vs AIHEART score

Outcome Measures

Primary Outcomes (1)

  • Area Under the ROC Curve (AUC) of GPT-4o and Claude HEART Score for 30-Day MACE Prediction

    AUC calculated separately for GPT-4o and Claude using the Hanley-McNeil method. MACE is defined as a composite of all-cause death, acute myocardial infarction (Type 1/2/4b), and unplanned revascularization within 30 days. HEART score range is 0-10; a higher score indicates a higher risk of MACE. Analysis will be performed on complete cases only (0 indeterminate components).

    30 days after index emergency department visit

Secondary Outcomes (6)

  • Sensitivity and Specificity of GPT-4o and Claude HEART Score at Prespecified Thresholds

    30 days after index emergency department visit

  • Component-Level and Total-Score Agreement (Cohen's Kappa) Between LLMs and Expert Consensus

    Baseline (At index emergency department visit)

  • Comparative AUC Difference Between GPT-4o and Claude (DeLong Test)

    30 days after index emergency department visit

  • Proportion of Indeterminate Results for GPT-4o and Claude

    Baseline (At index emergency department visit)

  • HEART Parameter Documentation Rate in Routine Turkish Anamnesis Notes

    Baseline (At index emergency department visit)

  • +1 more secondary outcomes

Interventions

OpenAI GPT-4o (model: gpt-4o-2024-11-20, temperature=0, max\_tokens=500, response\_format=JSON). Each patient's anonymized anamnesis text, ECG report text, troponin value, and age are submitted via a separate API call with no conversation history. Output: HEART score components (0-2 each), total score (0-10), risk group, and indeterminate status.

Also known as: GPT-4o İndeks Testi

Anthropic Claude (model: claude-sonnet-4-6, temperature=0, max\_tokens=500, response\_format=JSON). Identical system prompt and input format as GPT-4o. Processed independently with no cross-contamination between models. Output: same JSON schema as GPT-4o.

Also known as: Claude İndeks Testi

Three emergency medicine physicians (\>=3 years experience, HEART-score trained) independently score each anonymized record. Majority vote (2/3) determines component scores; a 4th adjudicator resolves ties. Experts are blinded to LLM scores, each other's scores, and MACE outcomes.

Also known as: Referans Standart

Eligibility Criteria

Age18 Years+
Sexall
Healthy VolunteersNo
Age GroupsAdult (18-64), Older Adult (65+)
Sampling MethodNon-Probability Sample
Study Population

The study population consists of consecutive adult patients presenting with a chief complaint of non-traumatic chest pain to the emergency department of Marmara University Pendik Training and Research Hospital, a tertiary care academic medical center in Istanbul, Turkey. This target population comprises real-world emergency medicine admissions that require acute coronary syndrome risk stratification and evaluation with the HEART score. It excludes individuals presenting with traumatic pain etiologies or acute ST-elevation myocardial infarction (STEMI) requiring immediate, time-critical reperfusion pathways.

You may qualify if:

  • Age \>=18 years
  • Chief complaint of non-traumatic chest pain at the emergency department
  • Written informed consent obtained from the patient or legally authorized representative
  • Availability for 30-day follow-up (reachable by telephone and/or actively registered in the e-Nabiz national health database)

You may not qualify if:

  • Traumatic chest pain etiology
  • ST-elevation myocardial infarction (STEMI) at presentation requiring immediate reperfusion protocol
  • Refusal or subsequent withdrawal of informed consent
  • Inability to complete the mandatory 30-day follow-up period
  • WITHDRAWAL CRITERIA:
  • Patient or representative requests data withdrawal after initial consent
  • Administrative identification of retrospective data entry after enrollment

Contact the study team to confirm eligibility.

Sponsors & Collaborators

Study Sites (1)

Marmara University Pendik Training and Research Hospital

Istanbul, İ̇stanbul, 34870, Turkey (Türkiye)

Location

Related Publications (6)

  • Mahler SA, Riley RF, Hiestand BC, Russell GB, Hoekstra JW, Lefebvre CW, Nicks BA, Cline DM, Askew KL, Elliott SB, Herrington DM, Burke GL, Miller CD. The HEART Pathway randomized trial: identifying emergency department patients with acute chest pain for early discharge. Circ Cardiovasc Qual Outcomes. 2015 Mar;8(2):195-203. doi: 10.1161/CIRCOUTCOMES.114.001384. Epub 2015 Mar 3.

  • Singhal K, Azizi S, Tu T, Mahdavi SS, Wei J, Chung HW, Scales N, Tanwani A, Cole-Lewis H, Pfohl S, Payne P, Seneviratne M, Gamble P, Kelly C, Babiker A, Scharli N, Chowdhery A, Mansfield P, Demner-Fushman D, Aguera Y Arcas B, Webster D, Corrado GS, Matias Y, Chou K, Gottweis J, Tomasev N, Liu Y, Rajkomar A, Barral J, Semturs C, Karthikesalingam A, Natarajan V. Large language models encode clinical knowledge. Nature. 2023 Aug;620(7972):172-180. doi: 10.1038/s41586-023-06291-2. Epub 2023 Jul 12.

  • Collins GS, Moons KGM, Dhiman P, Riley RD, Beam AL, Van Calster B, Ghassemi M, Liu X, Reitsma JB, van Smeden M, Boulesteix AL, Camaradou JC, Celi LA, Denaxas S, Denniston AK, Glocker B, Golub RM, Harvey H, Heinze G, Hoffman MM, Kengne AP, Lam E, Lee N, Loder EW, Maier-Hein L, Mateen BA, McCradden MD, Oakden-Rayner L, Ordish J, Parnell R, Rose S, Singh K, Wynants L, Logullo P. TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ. 2024 Apr 16;385:e078378. doi: 10.1136/bmj-2023-078378.

  • Bossuyt PM, Reitsma JB, Bruns DE, Gatsonis CA, Glasziou PP, Irwig L, Lijmer JG, Moher D, Rennie D, de Vet HC, Kressel HY, Rifai N, Golub RM, Altman DG, Hooft L, Korevaar DA, Cohen JF; STARD Group. STARD 2015: an updated list of essential items for reporting diagnostic accuracy studies. BMJ. 2015 Oct 28;351:h5527. doi: 10.1136/bmj.h5527.

  • Backus BE, Six AJ, Kelder JC, Bosschaert MA, Mast EG, Mosterd A, Veldkamp RF, Wardeh AJ, Tio R, Braam R, Monnink SH, van Tooren R, Mast TP, van den Akker F, Cramer MJ, Poldervaart JM, Hoes AW, Doevendans PA. A prospective validation of the HEART score for chest pain patients at the emergency department. Int J Cardiol. 2013 Oct 3;168(3):2153-8. doi: 10.1016/j.ijcard.2013.01.255. Epub 2013 Mar 7.

  • Albrecht M. C4-bound imidazolylidenes: from curiosities to high-impact carbene ligands. Chem Commun (Camb). 2008 Aug 21;(31):3601-10. doi: 10.1039/b806924g. Epub 2008 Jul 8.

MeSH Terms

Conditions

Emergencies

Condition Hierarchy (Ancestors)

Disease AttributesPathologic ProcessesPathological Conditions, Signs and Symptoms

Central Study Contacts

Emir Unal, Assistant Professor

CONTACT

Emre Kudu, associate professor

CONTACT

Study Design

Study Type
observational
Observational Model
COHORT
Time Perspective
PROSPECTIVE
Sponsor Type
OTHER
Responsible Party
PRINCIPAL INVESTIGATOR
PI Title
MD, Assistant Professor

Study Record Dates

First Submitted

May 27, 2026

First Posted

June 4, 2026

Study Start

June 1, 2026

Primary Completion (Estimated)

March 1, 2027

Study Completion (Estimated)

June 1, 2027

Last Updated

June 4, 2026

Record last verified: 2026-06

Data Sharing

IPD Sharing
Will share

Anonymized individual participant data (including de-identified baseline demographics, clinical presentation characteristics, index test outputs from GPT-4o and Claude, and the reference standard expert consensus HEART scores) will be made publicly available to support academic transparency and replication. Additionally, the complete deterministic system prompt texts (verified with SHA-256 cryptographic hashes) and the complete statistical analysis code will be included as supplementary material.

Shared Documents
STUDY PROTOCOL, SAP, ANALYTIC CODE
Time Frame
The anonymized dataset, protocol documents, and analytic code will be made available immediately upon formal publication of the study results.
Access Criteria
Data and code will be accessible via an open-access repository on the Open Science Framework (OSF) for researchers and clinicians interested in replication or meta-analysis.

Locations