Related Experiment Video
Updated: Mar 16, 2026
08:20
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
Published on: October 27, 2023
2.7K
Computer-assisted initial diagnosis of rare diseases
Rui Alves1, Marc Piñol2, Jordi Vilaplana3
1Departament de Cienciès Mèdiques Bàsiques, Universitat de Lleida, Lleida, Catalunya, Spain; IRBLleida, Lleida, Catalunya, Spain.
Peerj
|August 23, 2016
Summary
This study introduces Rare Disease Discovery, a computational tool aiding clinicians in diagnosing rare diseases based on symptoms. The system demonstrates high precision and sensitivity, proving robust even with incomplete patient data.
Area of Science:
- Medical Informatics
- Genetics
- Computational Biology
Background:
- Rare diseases, often genetic, pose diagnostic challenges due to low prevalence.
- Phenotypic symptom-based diagnosis can be difficult for clinicians unfamiliar with specific rare conditions.
Purpose of the Study:
- To develop a computational approach for symptom-based rare disease diagnosis.
- To implement this approach in a user-friendly web prototype called Rare Disease Discovery.
- To evaluate the diagnostic performance of the developed system.
Main Methods:
- Utilized the ORPHANET dataset linking rare diseases and symptoms.
- Developed an expert system for predicting rare diseases from patient symptoms.
- Validated the system on 187 retrospectively diagnosed rare disease patients.
- Conducted large-scale Monte Carlo simulations to assess performance under various conditions, including absent/unrelated symptoms.
Main Results:
- The Rare Disease Discovery system achieved high diagnostic precision (≥80%) and sensitivity (≥99%).
- The system demonstrated robustness against absent and unrelated symptoms.
- The computational engine provides a fast and reliable method for initial differential diagnosis.
Conclusions:
- Rare Disease Discovery offers a valuable tool for assisted differential diagnosis of rare diseases.
- The system is accessible via a web interface and its code/database are publicly available.
- The tool can significantly aid clinicians in identifying rare diseases earlier and more accurately.
