Healthcare chatbot that simulates one on one conversation with users and helps to diagnose there diseases.

My contributions to the repository for Back end model using knowledge Graphs & NLU.

• Answer to the user their probable diseases and nearest doctors

This project is a starting point for a Flutter application.

Health Care Chatbot using Knowledge graphs + Text classification.

Knowledge graphs combine characteristics of several data management paradigms:

Database, because the data can be explored via structured queries; Graph, because they can be analyzed as any other network data structure; Knowledge base, because they bear formal semantics, which can be used to interpret the data and infer new facts.

Here, Knowledge graphs are created using GraphQL (like SQL) on neo4j platform.

Neo4j

Python wrapper (py2neo) for connecting graph database is used.

The python wrapper of neo4j is used to create the knowledge graph with specified nodes & relationships.

The GraphQL queries returns the data demanded from the node or relationship

Question-Answer Dataset

https://github.com/LasseRegin/medical-question-answer-data

Disease Dataset

https://github.com/liuhuanyong/QASystemOnMedicalKG/blob/master/data/medical.json https://www.kaggle.com/priya1207/diseases-dataset https://www.kaggle.com/usamag123/disease-prediction-through-symptoms

Medical terms dictionary

https://www.medicinenet.com/script/main/alphaidx.asp?p=a_dict

Result

After running queries in graphQL on neo4j browser, the output shows all relationships and nodes as:

User can ask for probable diseases based on their symptoms.

The underlying back end process can also suggest user the best foods, drugs, and the type of disease it could be.

A few resources to get you started if this is your first Flutter project:

• Lab: Write your first Flutter app
• Cookbook: Useful Flutter samples

For help getting started with Flutter, view our online documentation, which offers tutorials, samples, guidance on mobile development, and a full API reference.