Improving Risk Assessment of Miscarriage During Pregnancy with Knowledge Graph Embeddings

Miscarriages are the most common type of pregnancy loss, mostly occurring in the first 12 weeks of pregnancy. Pregnancy risk assessment aims to quantify evidence to reduce such maternal morbidities, and personalized decision support systems are the cornerstone of high-quality, patient-centered care...

Full description

Saved in:
Bibliographic Details
Published in:Journal of healthcare informatics research 2021-12, Vol.5 (4), p.359-381
Main Authors: Tissot, Hegler C., Pedebos, Lucas A.
Format: Article
Language:English
Subjects:
Biomedical Engineering and Bioengineering
Computational Biology/Bioinformatics
Computational Intelligence
Computer Science
Data Mining and Knowledge Discovery
Health Informatics
Research Article
Special Issue on Data-Driven Health Technology
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Miscarriages are the most common type of pregnancy loss, mostly occurring in the first 12 weeks of pregnancy. Pregnancy risk assessment aims to quantify evidence to reduce such maternal morbidities, and personalized decision support systems are the cornerstone of high-quality, patient-centered care to improve diagnosis, treatment selection, and risk assessment. However, data sparsity and the increasing number of patient-level observations require more effective forms of representing clinical knowledge to encode known information that enables performing inference and reasoning. Whereas knowledge embedding representation has been widely explored in the open domain data, there are few efforts for its application in the clinical domain. In this study, we contrast differences among multiple embedding strategies, and we demonstrate how these methods can assist in performing risk assessment of miscarriage before and during pregnancy. Our experiments show that simple knowledge embedding approaches that utilize domain-specific metadata perform better than complex embedding strategies, although both can improve results comparatively to a population probabilistic baseline in both AUPRC, F1-score, and a proposed normalized version of these evaluation metrics that better reflects accuracy for unbalanced datasets. Finally, embedding approaches provide evidence about each individual, supporting explainability for its model predictions in such a way that humans understand.
ISSN:2509-4971
2509-498X
DOI:10.1007/s41666-021-00096-6