AI4PEP LLM – From Clinical Narratives to Public Health Signals
Home› Projects› AI4PEP LLM
AI4PEP - UNIVERSITY OF TORONTO

AI4PEP LLM

From Clinical Narratives to Public Health Signals

The AI4PEP LLM project develops and implements large language model (LLM)-based tools to transform unstructured clinical narratives into structured, actionable information for infectious disease surveillance in Indonesia. The project explores how information already available in clinical records can support earlier detection of disease patterns while complementing existing surveillance systems.

Ongoing
📍Yogyakarta, Indonesia
▣AI4PEP
Lead Institution
Center for Tropical Medicine,
Universitas Gadjah Mada
In collaboration with
University of Toronto /
AI4PEP Consortium
AI4PEP LLM Healthcare AI
Transforming Clinical Data
into Public Health Intelligence
ABOUT THE PROJECT

Extracting Public Health Signals
from Clinical Narratives

Routine surveillance systems such as EWARS/SKDR rely largely on structured and disease-specific reporting, while valuable clinical information may remain within unstructured medical records. The project develops LLM-based approaches to extract and classify relevant information from clinical narratives to support infectious disease surveillance.

Project Objectives

01

Develop LLM-Based System

Build and fine-tune NLP models to extract and classify clinical entities from unstructured medical text.

02

Integrate with Surveillance

Link extracted signals seamlessly with routine epidemiological pipelines like EWARS/SKDR.

03

Pilot and Evaluate

Conduct real-world validation across healthcare facilities to evaluate accuracy and utility.

04

Ensure Responsible AI

Implement stringent data privacy, medical ethics, algorithmic fairness, and human oversight frameworks.

THE LLM SURVEILLANCE PLATFORM

AI4PEP LLM Surveillance Platform

Transforming clinical narratives into structured surveillance signals.

  • Classify syndromes from clinical notes
  • Support SKDR priority diseases
  • Explainable AI output with confidence score
  • Designed for real-world healthcare settings
AI4PEP LLM

Clinical Note

Text Input File Upload
Pasien perempuan, 5 tahun, datang dengan demam tinggi sejak 2 hari, ruam di seluruh tubuh, nyeri sendi, tanpa riwayat perjalanan. 116/1000

Suggested Classification

Arboviral Syndrome (e.g. Dengue)
Confidence 0.87
Key Features Found:
  • Demam tinggi
  • Ruam
  • Nyeri sendi

Target SKDR Classes

  • Diarrhoea & Jaundice
  • Acute Respiratory Infection
  • Fever with Rash (Arboviral)
  • Vaccine Preventable Diseases
  • Zoonotic Diseases
  • NTDs and Other Priority Diseases
24 SKDR priority diseases
and syndromes
HOW IT WORKS →

From Clinical Notes to Public Health Action

Sistem mengubah data klinis tidak terstruktur menjadi informasi yang dapat digunakan untuk surveilans melalui alur sistem terintegrasi. Model memberikan rekomendasi klasifikasi dan informasi pendukung, sementara verifikasi dan keputusan akhir tetap berada pada tenaga kesehatan/pengelola surveilans.

01

Clinical Notes (EMR)

Free-text data from Puskesmas, hospitals, and laboratories.

02

Data Processing & Privacy

De-identification, normalization, and secure processing.

03

LLM / NLP

Interpret symptom patterns using large language models.

04

SKDR Classification

Map to 24 SKDR syndromes with confidence score and explanation.

05

Signal Analysis

Spatial & temporal trends and unusual anomaly detection.

06

Public Health Action

Support early investigation, targeted response, and decision-making.

PILOT IMPLEMENTATION →

Testing in Real-World Healthcare Settings

The system is being piloted in selected healthcare facilities in Yogyakarta to evaluate performance, usability, and real-world impact.

Pilot Sites

  • RS Akademik UGM (RSA)
  • RS Nyi Ageng Serang

Data Sources

  • Clinical records (unstructured text)
  • Laboratory data
  • Integration with EWARS/SKDR

Timeline

2026 – 2027

Pilot implementation and evaluation

Evaluation Focus

  • Detection of unusual syndromic signals
  • Usability and acceptability
  • Implementation feasibility
  • Integration with existing workflows
EXPECTED IMPACT →

Stronger Surveillance for a Safer Tomorrow

Earlier Detection of Outbreaks
Improved Reporting Coverage
Better Use of Clinical Data
Preparedness for "Disease X"
More Equitable Public Health Response
Responsible and Explainable AI
PEOPLE, PARTNERS & UPDATES →

Project Team

Riris Andono Ahmad
Riris Andono Ahmad
Citra Indriani
Citra Indriani
Aldilas Achmad Nursetyo
Aldilas Achmad Nursetyo
Anis Fuad
Anis Fuad
Erwan Budi Hartadi
Erwan Budi Hartadi
Ahmad Watsiq Maula
Ahmad Watsiq Maula
Diyah Utami K. Putri
Diyah Utami K. Putri
Nurul Kodriati
Nurul Kodriati
Putri Ardhani
Putri Ardhani
+4
View All Team

Partners & Funders

UGM
University of Toronto
AI4PEP
IDRC Canada
UK International Development

Latest News

View All News →
Memuat berita terbaru...

All Project Team Members

Riris Andono Ahmad
Riris Andono Ahmad
Citra Indriani
Citra Indriani
Aldilas Achmad Nursetyo
Aldilas Achmad Nursetyo
Anis Fuad
Anis Fuad
Erwan Budi Hartadi
Erwan Budi Hartadi
Ahmad Watsiq Maula
Ahmad Watsiq Maula
Diyah Utami K. Putri
Diyah Utami K. Putri
Nurul Kodriati
Nurul Kodriati
Putri Ardhani
Putri Ardhani
Qotru Al Naday
Qotru Al Naday
Siti Meisaroh
Siti Meisaroh
Wika Hartanti
Wika Hartanti
Awaludin
Awaludin

All Partners & Funders

UGM
University of Toronto
AI4PEP
IDRC Canada
UK International Development
Large Language Model (LLM)

Building Smarter Surveillance
for Faster Public Health Action.

Combining artificial intelligence, implementation science, and local public-health expertise to strengthen infectious disease preparedness, outbreak detection, investigation, and response.

People Data Learning A Healthier Indonesia