A Pipeline for Population and Analysis of Personal Health Knowledge Graphs (PHKGs)

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21460%2F22%3A00364139" target="_blank" >RIV/68407700:21460/22:00364139 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21730/22:00364139

Výsledek na webu

<a href="https://ceur-ws.org/Vol-3235/paper8.pdf" target="_blank" >https://ceur-ws.org/Vol-3235/paper8.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

A Pipeline for Population and Analysis of Personal Health Knowledge Graphs (PHKGs)

Popis výsledku v původním jazyce

Personal Health Knowledge Graphs (PHKGs) are not yet ubiquitous, even though they have a great potential to enrich general knowledge captured in various Knowledge Graphs by adding personal contexts. This poster paper presents work in progress about a pipeline for generating PHKGs from tree-structured Electronic Health Record (EHR) data by applying a hierarchical ontological approach. This pipeline could also be applied to other domains of Personal Knowledge Graphs. Moreover, this pipeline targets the intersection between the symbolic representation of knowledge used for computational semantics and numeric graph data representation used for graph analysis and machine learning. We present the first results from applying this pipeline to synthetic patient EHRs with the diagnosis of colorectal cancer (based on Synthea). The resulting numeric representation of PHKGs or their subgraphs can be used in many practical graph algorithms. Finally, our pipeline study uncovers future research on how this numeric representation of PHKGs should be embedded into continuous and low-dimensional vector space to utilize graph machine learning and deep learning methods

Název v anglickém jazyce

A Pipeline for Population and Analysis of Personal Health Knowledge Graphs (PHKGs)

Popis výsledku anglicky

Personal Health Knowledge Graphs (PHKGs) are not yet ubiquitous, even though they have a great potential to enrich general knowledge captured in various Knowledge Graphs by adding personal contexts. This poster paper presents work in progress about a pipeline for generating PHKGs from tree-structured Electronic Health Record (EHR) data by applying a hierarchical ontological approach. This pipeline could also be applied to other domains of Personal Knowledge Graphs. Moreover, this pipeline targets the intersection between the symbolic representation of knowledge used for computational semantics and numeric graph data representation used for graph analysis and machine learning. We present the first results from applying this pipeline to synthetic patient EHRs with the diagnosis of colorectal cancer (based on Synthea). The resulting numeric representation of PHKGs or their subgraphs can be used in many practical graph algorithms. Finally, our pipeline study uncovers future research on how this numeric representation of PHKGs should be embedded into continuous and low-dimensional vector space to utilize graph machine learning and deep learning methods

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

roceedings of Poster and Demo Track and Workshop Track of the 18th International Conference on Semantic Systems co-located with 18th International Conference on Semantic Systems (SEMANTiCS 2022)

ISBN

—

ISSN

1613-0073

e-ISSN

1613-0073

Počet stran výsledku

5

Strana od-do

—

Název nakladatele

CEUR Workshop Proceedings

Místo vydání

Aachen

Místo konání akce

Vienna

Datum konání akce

13. 9. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—