Rare Disease Identification from Clinical Notes with Ontologies and Weak Supervision (2021-05-05T00:00:00.000000Z)

TL;DR

Using MIMIC-III US intensive care discharge summaries as a case study, it is shown that the Text-to-UMLS process can be greatly improved with weak supervision, without any annotated data from domain experts.

Abstract

The identification of rare diseases from clinical notes with Natural Language Processing (NLP) is challenging due to the few cases available for machine learning and the need of data annotation from clinical experts. We propose a method using ontologies and weak supervision. The approach includes two steps: (i) Text-to-UMLS, linking text mentions to concepts in Unified Medical Language System (UMLS), with a named entity linking tool (e.g. SemEHR) and weak supervision based on customised rules and Bidirectional Encoder Representations from Transformers (BERT) based contextual representations, and (ii) UMLS-to-ORDO, matching UMLS concepts to rare diseases in Orphanet Rare Disease Ontology (ORDO). Using MIMIC-III US intensive care discharge summaries as a case study, we show that the Text-to-UMLS process can be greatly improved with weak supervision, without any annotated data from domain experts. Our analysis shows that the overall pipeline processing discharge summaries can surface rare disease cases, which are mostly uncaptured in manual ICD codes of the hospital admissions.

Authors

Hang Dong

4 papers

V'ictor Su'arez-Paniagua

2 papers

Huayu Zhang

1 papers

TL;DR

Abstract

Authors

References28 items

Using weak supervision and deep learning to classify clinical notes for identification of current suicidal ideation.

Extracting Lifestyle Factors for Alzheimer's Disease from Clinical Notes Using Deep Learning with Weak Supervision

Explainable Automated Coding of Clinical Notes using Hierarchical Label-wise Attention Networks and Label Embedding Initialisation

Experimental Evaluation and Development of a Silver-Standard for the MIMIC-III Clinical Coding Dataset

Health

Transfer Learning in Biomedical Natural Language Processing: An Evaluation of BERT and ELMo on Ten Benchmarking Datasets

A clinical text classification paradigm using weak supervision and deep representation

Bio-YODIE: A Named Entity Linking System for Biomedical Text

Few-Shot and Zero-Shot Multi-Label Learning for Structured Label Spaces

SemEHR: A general-purpose semantic search system to surface semantic data from clinical notes for tailored care, trial recruitment, and clinical research

MIMIC-III, a freely accessible critical care database

International Classification of Diseases

Scikit-learn: Machine Learning in Python

BioPortal

Scottish Government

Human-in-the-Loop Machine Learning: Active learning and annotation for human-centered AI

Does your rare disease have a code

Serving Google BERT in Production using Tensorflow and ZeroMQ

and other members of Hazy Lab

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

An Ontology-Based Approach to Estimate the Frequency of Rare Diseases in Narrative-Text Radiology Reports

Genetic Aspects of Uncommon Diseases

NCBO BioPortal , International Classification of Diseases , Version 9 - Clinical Modification , 2021

I and J

[Orphanet: a European database for rare diseases].

and as an in

Illnesses and long-term conditions

Paroma Varma and other members of Hazy Lab, Weak Supervision: A New Programming Paradigm for Machine Learning

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names