Unsupervised Annotation of Phenotypic Abnormalities via Semantic Latent Representations on Electronic Health Records

TL;DR

This paper introduces an unsupervised deep learning method that leverages semantic latent representations and the Human Phenotype Ontology to accurately and efficiently annotate phenotypic abnormalities in large-scale electronic health records.

Contribution

It presents a novel unsupervised framework that improves phenotypic annotation accuracy and efficiency using semantic latent representations and ontology integration.

Findings

Achieves state-of-the-art annotation performance on MIMIC-III data

Demonstrates high computational efficiency

Effectively standardizes phenotypic annotations using HPO

Abstract

The extraction of phenotype information which is naturally contained in electronic health records (EHRs) has been found to be useful in various clinical informatics applications such as disease diagnosis. However, due to imprecise descriptions, lack of gold standards and the demand for efficiency, annotating phenotypic abnormalities on millions of EHR narratives is still challenging. In this work, we propose a novel unsupervised deep learning framework to annotate the phenotypic abnormalities from EHRs via semantic latent representations. The proposed framework takes the advantage of Human Phenotype Ontology (HPO), which is a knowledge base of phenotypic abnormalities, to standardize the annotation results. Experiments have been conducted on 52,722 EHRs from MIMIC-III dataset. Quantitative and qualitative analysis have shown the proposed framework achieves state-of-the-art annotation performance and computational efficiency compared with other methods.