SPARQL Query Generation and Semantic Similarity for Medical RDF Databases
Overview
Querying RDF databases is now made accessible to everyone through a natural text to SPARQL query converter Java program. For this specific project, query generation was done in the context of medical records of patients. To query for medical records, users, most likely doctors in this case, can enter in patient symptoms, clinical findings, or demographic information in natural text, which is the same format they would use when typing up a patient summary for their records. The program converts the information into a SPARQL query using a Natural Language Processer and referencing the UMLS Metathesaurus of the National Institute of Health (NIH) via the MetaMap API. The query is then run at a user determined endpoint, and the results are returned. Furthermore, the program also includes a Semantic Comparison component where two selected entities can receive a similarity score.
Competition history
- ISEF 2016
Resources
Related projects
ISEF · 2021
Augmenting Under-Researched Medical Domains with an Intuitive Querying System on Resourceful Crowd-Collected Data
ISEF · 2017
Cloud-Based Data Preparation for Medical Observational Research
ISEF · 2021
MediGraph: A Novel Clinical Assistant from Automated Biomedical Literature Extraction and Knowledge Graphs
ISEF · 2023
BioRx: An Integrative NLP Approach to Early Survival and Recurrence Prediction and Novel Biomarker Discovery in Unstructured Text-Based Clinical Narratives for Diabetes Patients
ISEF · 2025
Assessing Medical Condition Severity Through AI Analysis of Textual Symptoms
ISEF · 2017
PrediMed: Predicting Health with a Custom-Built Machine Learning Ensemble
ISEF · 2024
A ChatGPT Empowered Application in Biomedical Research
ISEF · 2024
A Lightweight Linguistic-Enhanced Word Embedding Framework for Medical Q&A Chatbot
Closest projects by meaning, across every fair and year in the corpus.
Browse more like this
Source: Regeneron International Science and Engineering Fair