NLDS-QL: From natural language data science questions to queries on graphs: analysing patients conditions & treatments

TL;DR

NLDS-QL is a system that converts natural language data science questions into graph database queries, enabling analysis of patient data from Synthea through a grammar-based translation approach.

Contribution

The paper presents NLDS-QL, a novel translator that converts simplified natural language questions into graph queries using a grammar-based method for healthcare data analysis.

Findings

Effective translation of natural language questions to graph queries demonstrated

Enables analysis of patient diagnoses data in graph databases

Shows potential for healthcare data exploration using natural language

Abstract

This paper introduces NLDS-QL, a translator of data science questions expressed in natural language (NL) into data science queries on graph databases. Our translator is based on a simplified NL described by a grammar that specifies sentences combining keywords to refer to operations on graphs with the vocabulary of the graph schema. The demonstration proposed in this paper shows NLDS-QL in action within a scenario to explore and analyse a graph base on patient diagnoses generated with the open-source Synthea.