Ontology-driven weak supervision for clinical entity classification in electronic health records

Abstract

In the electronic health record, using clinical notes to identify entities such as disorders and their temporality (e.g. the order of an event relative to a time index) can inform many important analyses. However, creating training data for clinical entity tasks is time consuming and sharing labeled data is challenging due to privacy concerns. The information needs of the COVID-19 pandemic highlight the need for agile methods of training machine learning models for clinical notes. We present Trove, a framework for weakly supervised entity classification using medical ontologies and expert-generated rules. Our approach, unlike hand-labeled notes, is easy to share and modify, while offering performance comparable to learning from manually labeled training data. In this work, we validate our framework on six benchmark tasks and demonstrate Trove's ability to analyze the records of patients visiting the emergency department at Stanford Health Care for COVID-19 presenting symptoms and risk factors.

References in corpus (19)

• BioBERT: a pre-trained biomedical language representation model for biomedical text mining
• ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases
• Snorkel: Rapid Training Data Creation with Weak Supervision
• Publicly Available Clinical BERT Embeddings
• A Survey on Multi-Task Learning
• CORD-19: The COVID-19 Open Research Dataset
• Data Programming: Creating Large Training Sets, Quickly
• Enhancing Clinical Concept Extraction with Contextual Embeddings
• Introduction to the CoNLL-2000 Shared Task: Chunking
• Clinical Concept Extraction: a Methodology Review
• NegBio: a high-performance tool for negation and uncertainty detection in radiology reports
• Learning the Structure of Generative Models without Labeled Data
• Learning From Noisy Singly-labeled Data
• Machine-Learning-Based Multiple Abnormality Prediction with Large-Scale Chest Computed Tomography Volumes
• Ontology-driven weak supervision for clinical entity classification in electronic health records
• SwellShark: A Generative Model for Biomedical Named Entity Recognition without Labeled Data
• COVID-19 SignSym: a fast adaptation of a general clinical NLP tool to identify and normalize COVID-19 signs and symptoms to OMOP common data model
• Learning Dependency Structures for Weak Supervision Models
• Multi-Resolution Weak Supervision for Sequential Data

Cited by in corpus (10)

• Ontology-driven weak supervision for clinical entity classification in electronic health records
• Artificial Intelligence (AI) in Action: Addressing the COVID-19 Pandemic with Natural Language Processing (NLP)
• WRENCH: A Comprehensive Benchmark for Weak Supervision
• Ontology-Driven and Weakly Supervised Rare Disease Identification from Clinical Notes
• Leveraging Large Language Models for Knowledge-free Weak Supervision in Clinical Natural Language Processing
• Creating Training Sets via Weak Indirect Supervision
• Learning from Multiple Noisy Partial Labelers
• ULF: Unsupervised Labeling Function Correction using Cross-Validation for Weak Supervision
• A Benchmark Generative Probabilistic Model for Weak Supervised Learning
• Cheap Learning: Maximising Performance of Language Models for Social Data Science Using Minimal Data