AI to improve telephone triage for emergency calls at CCUE Andalucía
Proyecto "trIAje": evaluación y optimización Del Triaje telefónico Mediante Modelos de Inteligencia Artificial (IA) Para la detección de Demandas Por patología Tiempo-dependiente en el Centro Coordinador de Urgencias y Emergencias (CCUE).
This project tests AI tools to help emergency call operators spot life-threatening problems like cardiac arrest, stroke, severe breathing trouble, and chest pain.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 5000000 (estimated) |
| Sex | All |
| Sponsor | Centro de Emergencias Sanitarias 061 Andalucía Academic / other |
| Locations | 1 site (Málaga, Málaga) |
| Trial ID | NCT07247669 on ClinicalTrials.gov |
What this trial studies
The project uses anonymized historical emergency call records from the CCUE (CES-061 Andalucía) to develop and optimize AI models for telephone triage. Researchers will combine structured fields (triage questions and codes) with unstructured free-text call notes and apply machine learning and natural language processing methods. The goal is to make operator decisions faster and more accurate for four high-risk call types: unconsciousness/cardiac arrest, respiratory distress, non-traumatic chest pain, and stroke. This is an observational analysis of recorded calls rather than an interventional patient treatment.
Who should consider this trial
Good fit: Ideal candidates are calls recorded in the CCUE database that match codes for unconsciousness/cardiac arrest (A36/A58), respiratory distress (A16), non-traumatic chest pain (A23), or stroke (A54).
Not a fit: Calls or patients with incomplete or missing key information in the record, or calls about conditions outside the four targeted categories, are unlikely to benefit from this project.
Why it matters
Potential benefit: If successful, the AI tools could speed up recognition of life-threatening calls and help get the right response to patients faster.
How similar studies have performed: Previous research using AI and NLP on emergency calls has shown promising results for detecting cardiac arrest and stroke, but broader real-world adoption remains limited.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: Telephone calls recorded with codes A36 + A58 (unconsciousness/cardiorespiratory arrest), A16 (respiratory distress), A23 (non-traumatic chest pain) and A54 (stroke). Exclusion Criteria: * Demands with relevant information about the patient or the event incomplete or absent.
Where this trial is running
Málaga, Málaga
- Centro de Emergencias Sanitarias 061 — Málaga, Málaga, Spain (Recruiting)
Study contacts
- Study coordinator: María José MJ Dr. Luque Hernández, MD PhD
- Email: mariajose.luque.sspa@juntadeandalucia.es
- Phone: 0034 617563352
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.