Article

Phe2vec: Automated Disease Phenotyping based on Unsupervised Embeddings from Electronic Health Records

2020-11-16

Abstract excerpt

<h4>Objective</h4> Robust phenotyping of patient data from electronic health records (EHRs) at scale is a current challenge in the field of clinical informatics. We introduce Phe2vec, an automated framework for disease phenotyping from EHRs based on unsupervised learning, and we assess its effectiveness against standard rule-based algorithms from the Phenotype KnowledgeBase (PheKB) . <h4>Materials and Methods</h4>...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 6aff790a-afaf-5574-a83d-1e59e5c7d0ef
DOI: 10.1101/2020.11.14.20231894

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Phe2vec: Automated Disease Phenotyping based on Unsupervised Embeddings from Electronic Health RecordsDOI 10.1101/2020.11.14.20231894Read

Automated disease cohort selection using word embeddings from Electronic Health Records.Semantic proximity Read

Enriching representation learning using 53 million patient notes through human phenotype ontology embedding.Semantic proximity Read

PhenoXtract: combining Large Language Model and Knowledge Graph embedding to extract phenotypes from clinical descriptionsSemantic proximity Read

Enriching Representation Learning Using 53 Million Patient Notes through Human Phenotype Ontology EmbeddingSemantic proximity Read

Language-model-based patient embedding using electronic health records facilitates phenotyping, disease forecasting, and progression analysisSemantic proximity Read

Identification of disease mechanisms and novel disease genes using clinical concept embeddings learned from massive amounts of biomedical dataSemantic proximity Read

Clinical Knowledge Extraction via Sparse Embedding Regression (KESER) with Multi-Center Large Scale Electronic Health Record DataSemantic proximity Read

Comparing natural language processing representations of disease sequences for prediction in the electronic healthcare recordSemantic proximity Read

Phecoder: semantic retrieval for auditing and expanding ICD-based phenotypes in EHR biobanksSemantic proximity Read

A Comparison of Representation Learning Methods for Medical Concepts in MIMIC-IVSemantic proximity Read

Phenotyping in clinical text with unsupervised numerical reasoning for patient stratification.Semantic proximity Read

Empirical Findings on the Role of Structured Data, Unstructured Data, and their Combination for Automatic Clinical Phenotyping.Semantic proximity Read