Evaluating the Predictive Features of Person-Centric Knowledge Graph Embeddings: Unfolding Ablation Studies.
Stud Health Technol Inform
; 316: 575-579, 2024 Aug 22.
Article
in En
| MEDLINE
| ID: mdl-39176807
ABSTRACT
Developing novel predictive models with complex biomedical information is challenging due to various idiosyncrasies related to heterogeneity, standardization or sparseness of the data. We previously introduced a person-centric ontology to organize information about individual patients, and a representation learning framework to extract person-centric knowledge graphs (PKGs) and to train Graph Neural Networks (GNNs). In this paper, we propose a systematic approach to examine the results of GNN models trained with both structured and unstructured information from the MIMIC-III dataset. Through ablation studies on different clinical, demographic, and social data, we show the robustness of this approach in identifying predictive features in PKGs for the task of readmission prediction.
Key words
Full text:
1
Collection:
01-internacional
Database:
MEDLINE
Main subject:
Neural Networks, Computer
Limits:
Humans
Language:
En
Journal:
Stud Health Technol Inform
/
Stud. health technol. inform.
/
Studies in health technology and informatics (Online)
Journal subject:
INFORMATICA MEDICA
/
PESQUISA EM SERVICOS DE SAUDE
Year:
2024
Document type:
Article
Affiliation country:
Belgium
Country of publication:
Netherlands