Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Toward a Unified Graph-Based Representation of Medical Data for Precision Oncology Medicine

Davide Belluomo, Tiziana Calamoneri, Giacomo Paesani, Ivano Salvo

TL;DR

Some useful medical tasks are reduced to well-known problems in theoretical computer science for which efficient algorithms exist and the systematic use of different databases, managed throughout the built knowledge graph, gives new insights toward a better understanding of oncology medicine.

Abstract

We present a new unified graph-based representation of medical data, combining genetic information and medical records of patients with medical knowledge via a unique knowledge graph. This approach allows us to infer meaningful information and explanations that would be unavailable by looking at each data set separately. The systematic use of different databases, managed throughout the built knowledge graph, gives new insights toward a better understanding of oncology medicine. Indeed, we reduce some useful medical tasks to well-known problems in theoretical computer science for which efficient algorithms exist.

Toward a Unified Graph-Based Representation of Medical Data for Precision Oncology Medicine

TL;DR

Some useful medical tasks are reduced to well-known problems in theoretical computer science for which efficient algorithms exist and the systematic use of different databases, managed throughout the built knowledge graph, gives new insights toward a better understanding of oncology medicine.

Abstract

We present a new unified graph-based representation of medical data, combining genetic information and medical records of patients with medical knowledge via a unique knowledge graph. This approach allows us to infer meaningful information and explanations that would be unavailable by looking at each data set separately. The systematic use of different databases, managed throughout the built knowledge graph, gives new insights toward a better understanding of oncology medicine. Indeed, we reduce some useful medical tasks to well-known problems in theoretical computer science for which efficient algorithms exist.

Paper Structure

This paper contains 17 sections, 1 figure, 14 tables.

Table of Contents

  1. Introduction
  2. Data and Methods
  3. Preliminary Definitions
  4. The Knowledge Graph $H$
  5. Experiment Design
  6. Comparing medical knowledge and data evidence.
  7. Partitioning patients into homogenous groups.
  8. Optimized drug treatments.
  9. Results
  10. Analysis of data in public databases.
  11. Comparing medical knowledge and data evidence: Lung Adenocarcinoma.
  12. Partitioning patients into homogenous groups: survival period.
  13. Partitioning patients into homogenous groups: genetic mutation profile.
  14. Paritioning Patient in homogenous groups: coexisting mutations.
  15. Conclusions
  16. ...and 2 more sections

Figures (1)

  • Figure 1: A schematization of the knowledge graph $H$: green lines represent edges of $G$ (genetic information), red lines represent edges of $R$ (information from medical records) and magenta lines represent edges of $M$ (medical knowledge). $Di$ is the set of nodes representing the diseases, $\mathit{Pa}$ the patients, $\mathit{Mu}$ the genetic mutations, and $\mathit{Dr}$ the drugs.