Related Experiment Videos
Baseline Corpus Construction and Proof-of-concept Experiments for AI/ML-Enabled Syndromic Surveillance
Lauren M Diaz1, Chenyi Ling1, Monique E Beaudoin1
1University of Maryland (UMD) Applied Research Laboratory for Intelligence and Security (ARLIS), College Park, MD 20742, United States.
Military Medicine
|August 6, 2026
Summary
Enhancing medical knowledge bases with diverse synonyms significantly improves the automated detection of Gulf War Illness (GWI) from clinical notes. This semantic enrichment boosts recall and precision for AI/ML syndromic surveillance.
Area of Science:
- Medical Informatics
- Natural Language Processing
- Syndromic Surveillance
Background:
- Subjective symptom variability hinders early detection of novel diseases like Gulf War Illness (GWI).
- Standardized symptom corpora are crucial for AI/ML tools to analyze Electronic Health Records (EHRs).
- This study addresses the need for improved automated pattern recognition in clinical notes.
Purpose of the Study:
- To construct a baseline medical knowledge base (KB) for GWI.
- To evaluate if semantic enrichment with synonyms improves automated syndrome detection.
- To enhance AI/ML capabilities for identifying emerging health threats in EHRs.
Main Methods:
- Developed a GWI symptom corpus mapped to ICD-10 codes.
- Created four knowledge bases: baseline, UMLS-enriched, LLM-enriched, and merged.
- Utilized a custom NLP pipeline to extract symptom mentions from MIMIC-IV clinical notes.
- Compared KB performance using precision, recall, F1 score, and AUPRC.
Main Results:
- All enriched KBs outperformed the baseline KB (F1 score 0.628).
- UMLS-Enriched KB achieved the highest F1 score (0.679 at K=5).
- Merged KB showed strongest precision and AUPRC, with optimal gains at moderate enrichment levels.
Conclusions:
- Semantic enrichment of symptom corpora enhances automated GWI detection in clinical notes.
- Expanding language beyond official codes improves detection sensitivity while maintaining precision.
- A reproducible framework using public data is presented for adaptation to other syndromes.
Related Concept Videos
01:26Principles of Disease Surveillance
Disease surveillance is the systematic collection, analysis, and interpretation of health data essential to the planning, implementation, and evaluation of public health practice. This process integrates data dissemination to entities responsible for preventing and controlling disease, injury, and disability. Surveillance systems provide crucial information for action, helping public health authorities make informed decisions to manage and prevent outbreaks, ensure public safety, optimize...
01:18Steps in Outbreak Investigation
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
01:23Investigation of Disease Outbreaks
Multistate foodborne outbreaks pose significant public health risks and require meticulous investigation to identify sources and implement control measures. The Centers for Disease Control and Prevention (CDC) utilizes a dynamic seven-step process for these investigations, integrating data from laboratories, interviews, and environmental assessments to protect public health.Outbreak Detection: The detection of multistate outbreaks typically begins with PulseNet, the CDC's national laboratory...