The Open Syndrome Definition

📅 2025-09-29
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
Public health has long lacked standardized, machine-readable formats for case and syndrome definitions, severely hindering cross-system interoperability, epidemiological analysis, qualitative data sharing, and AI modeling. To address this, we propose OpenSyndrome Schema—the first open, structured specification for syndrome definitions—and construct the first comprehensive, standardized dataset of case definitions covering multiple diseases. We further develop an NLP-based automated conversion pipeline and a collaborative platform that maps human-readable definitions to executable logical representations, enabling consistent expression, version-controlled management, and cross-system deployment. All artifacts are released as open-source software and data at https://opensyndrome.org. This work significantly enhances public health data integration efficiency and AI readiness, establishing foundational infrastructure for global disease surveillance and intelligent analytics.

Technology Category

Application Category

📝 Abstract
Case definitions are essential for effectively communicating public health threats. However, the absence of a standardized, machine-readable format poses significant challenges to interoperability, epidemiological research, the exchange of qualitative data, and the effective application of computational analysis methods, including artificial intelligence (AI). This complicates comparisons and collaborations across organizations and regions, limits data integration, and hinders technological innovation in public health. To address these issues, we propose the first open, machine-readable format for representing case and syndrome definitions. Additionally, we introduce the first comprehensive dataset of standardized case definitions and tools to convert existing human-readable definitions into machine-readable formats. We also provide an accessible online platform for browsing, analyzing, and contributing new definitions, available at https://opensyndrome.org. The Open Syndrome Definition format enables consistent, scalable use of case definitions across systems, unlocking AI's potential to strengthen public health preparedness and response. The source code for the format can be found at https://github.com/OpenSyndrome/schema under the MIT license.
Problem

Research questions and friction points this paper is trying to address.

Standardizing machine-readable format for case definitions
Enabling interoperability and data integration across organizations
Facilitating AI applications in public health research
Innovation

Methods, ideas, or system contributions that make the work stand out.

Open machine-readable format for case definitions
Comprehensive dataset and conversion tools provided
Online platform for browsing and analyzing definitions
🔎 Similar Papers
No similar papers found.
A
Ana Paula Gomes Ferreira
Center for Artificial Intelligence in Public Health Research, Robert Koch Institute, Berlin, Germany
Aleksandar Anžel
Aleksandar Anžel
Postdoctoral Researcher at Robert Koch Institute
BioinformaticsVisualizationComputer ScienceMachine LearningPublic Health
I
Izabel Oliva Marcilio de Souza
Center for Data and Knowledge Integration for Health, Gonçalo Moniz Institute, Fundação Oswaldo Cruz, Salvador, Brazil
H
Helen Hughes
Real-time Syndromic Surveillance Team, Field Services, Chief Medical Advisor Group, UK Health Security Agency, Birmingham, UK
Alex J Elliot
Alex J Elliot
Public Health England
syndromic surveillanceepidemiologyrespiratory viruses
J
Jude Dzevela Kong
Africa-Canada Artificial Intelligence and Data Innovation Consortium, Department of Mathematics and Statistics, York University, Toronto, Ontario, Canada
M
Madlen Schranz
Infectious Disease Epidemiology Department, Robert Koch Institute, Berlin, Germany
Alexander Ullrich
Alexander Ullrich
Robert Koch Institut
Data ScienceInfectious DiseaseBioinformaticsComputational BiologyBiophysics
Georges Hattab
Georges Hattab
Adjunct Professor of Computer Science, Freie Universität Berlin, Robert Koch Institute
Artificial IntelligenceData MiningVisualization