Data aggregation and indexing support from multiple sources using graph model in medical expert system databases

One of the key problems in developing and integrating expert systems for medical research is the problem of data aggregation. Most of the times, general information about the patient and data about undergone research procedures exist as part of several disconnected information systems, each using it...

Full description

Saved in:
Bibliographic Details
Main Authors: A. V. Kurachkin, V. S. Sadau
Format: Article
Language:Russian
Published: National Academy of Sciences of Belarus, the United Institute of Informatics Problems 2020-09-01
Series:Informatika
Subjects:
Online Access:https://inf.grid.by/jour/article/view/1079
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:One of the key problems in developing and integrating expert systems for medical research is the problem of data aggregation. Most of the times, general information about the patient and data about undergone research procedures exist as part of several disconnected information systems, each using its own schema for presenting and storing information. The paper proposes a solution to aggregate research and patient data in medical establishments using formal projections mechanism, which allows to unify data extraction from separate data sources. Graph-based patient and research record representation is introduced, which allows to support and optimize complex queries for single patient and for a set of historical data from single research. Proposed representation mechanism is also shown to be effective for centralized processing using various data mining and intelligent analysis techniques.
ISSN:1816-0301