Named Entity Recognition and Relationship Extraction in Biomedicine

National Library Of Medicine

Investigators

Linked publications, trials & patents

Abstract

Mining useful knowledge from the biomedical literature holds potentials for helping literature searching, automating biological data curation and many other scientific tasks. We have therefore focused on recognizing various types of biological entities in free text, such as gene/proteins, disease/conditions, and drug/chemicals, etc, and their relationships. Manually annotated data is key to developing text-mining and information-extraction algorithms. However, human annotation requires considerable time, effort and expertise. As an alternative, we investigated computational methods that take advantage of well-constructed ontologies in biomedicine, for the important task of recognizing phenotype information from free text. Specifically, we proposed PhenoTagger, a hybrid method that combines both dictionary and machine learning-based methods to recognize Human Phenotype Ontology (HPO) concepts in unstructured biomedical text. Experimental results on the NCBI disease corpus show that PhenoTagger without requiring manually annotated training data achieves competitive performance as compared with state-of-the-art supervised methods. Now that we have tools such as PubTator and PhenoTagger that do a good job identifying several biomedical entities, we want to know the relationships between these entities discussed in the literature. To this end, we have developed a new method that can identify these relationships, even when the description of the relationship is spread over multiple sentences. Our proposed method combines Bidirectional Encoder Representations from Transformers with Graph Transformer (BERT-GT), through integrating a neighborattention mechanism into the BERT architecture. BERT-GT is shown to be highly competitive when tested on several benchmarking datasets. As shown above, deep learning, a class of machine learning algorithms, has showed impressive results in several of our recent studies this year. In addition to applying it to natural language processing, we have also seen its success in our medical image analysis such as processing chest X-rays, CT images, and various kinds of retinal images for autonomous disease diagonosis and prognosis. As one of the most ubiquitous diagnostic imaging tests in medical practice, chest radiography requires timely reporting of potential findings and diagnosis of diseases in the images. Automated, fast, and reliable detection of diseases based on chest radiography is a critical step in radiology workflow. Previously, we have developed and evaluated various deep convolutional neural networks (CNN) for differentiating between normal and abnormal frontal chest radiographs, in order to help alert radiologists and clinicians of potential abnormal findings as a means of work list triaging and reporting prioritization. In 2020, we focused on zero-shot and few-shot learning techniques. Zero-shot learning (ZSL) is one of the most promising avenues of annotation-efficient machine learning. In the era of deep learning, ZSL techniques have achieved unprecedented success. However, the developments of ZSL methods have taken place mostly for natural images. ZSL for medical images has remained largely unexplored. We design a novel strategy for generalized zero-shot diagnosis of chest radiographs. Comparisons with a number of state-of-the-art techniques show the superiority of the proposed method for generalized zero-shot chest x-ray diagnosis. To mimic the fact that a trained radiologist may learn the visual presentation of a new disease by looking at a few relevant image examples in research articles, we designed a few-shot learning method that can diagnose new diseases from chest x-rays utilizing only a few relevant labeled x-ray images from the published literature. Our method uses prior knowledge about other diseases for feature extraction from x-rays of new diseases. We formulate a classifier that is initially trained with a few labeled feature vectors corresponding to low-resolution images from the PubMed Central. The classifier is subsequently re-trained using unlabeled feature vectors corresponding to high-resolution x-ray images. Another such project relates to Age-related macular degeneration (AMD), which is the leading cause of blindness in developed countries and, by 2040, will affect approximately 300 million people worldwide. Accurate AMD severity detection and progression prediction to sight-threatening late disease stage is thus of significant importance for personalizing monitoring and preventative interventions. As a joint effort between National Library of Medicine and National Eye Institute, we developed a deep learning model simultaneously (1) to perform automated detection of Geographic Atrophy (GA) presence or absence from OCT volume scans and (2) to provide interpretability by demonstrating which regions of which B-scans show GA. Specifically, Med-XAI-Net, an interpretable deep learning model was developed to detect GA presence or absence from OCT volume scans using only volume scan labels, as well as to interpret the most relevant B-scans and B-scan regions.