DNorm: disease name normalization with pairwise learning to rank

By Robert Leaman, Rezarta Islamaj Dogan, Zhiyong Lu. 2013

517 citations recorded by the source corpus.

Motivation: Despite the central role of diseases in biomedical research, there have been much fewer attempts to automatically determine which diseases are mentioned in a text—the task of disease name normalization (DNorm)—compared with other normalization tasks in biomedical text mining research. Methods: In this article we introduce the first machine learning approach for DNorm, using the NCBI disease corpus and the MEDIC vocabulary, which combines MeSH® and OMIM. Our method is a high-performing and mathematically principled framework for learning similarities between mentions and concept names directly from training data. The technique is based on pairwise learning to rank, which has not previously been applied to the normalization task but has proven successful in large optimization problems for information retrieval. Results: We compare our method with several techniques based on lexical normalization and matching, MetaMap and Lucene. Our algorithm achieves 0.782 micro-averaged F-measure and 0.809 macro-averaged F-measure, an increase over the highest performing baseline method of 0.121 and 0.098, respectively. Availability: The source code for DNorm is available at http://www.ncbi.nlm.nih.gov/CBBresearch/Lu/Demo/DNorm, along with a web-based demonstration and links to the NCBI disease corpus. Results on PubMed abstracts are available in PubTator: http://www.ncbi.nlm.nih.gov/CBBresearch/Lu/Demo/PubTator Contact: zhiyong.lu@nih.gov

Subfields: Artificial Intelligence, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Molecular Biology

Citations in the corpus

AI in Health: State of the Art, Challenges, and Future Directions (2019, methodology): “[98] developed DNorm, which is a machine learning approach for disease name normalization based on pairwise learningto-rank.”
Improving chemical disease relation extraction with rich features and weakly labeled data (2016, methodology): “The gold mentions are provided in the BC5 test set, and the text-mined mentions were computed via tmChem [27] and DNorm [26] for chemicals and diseases respectively.”
tmChem: a high performance approach for chemical named entity recognition and normalization (2015, background): “Abbreviations are highly ambiguous, and while our use of abbreviation post-processing significantly helped with their recognition, we found that Ab3P was not as successful at locating the full mentions as in our recent work on diseases [9].”
Assessing the state of the art in biomedical relation extraction: overview of the BioCreative V chemical-disease relation (CDR) task (2016, methodology): “DNorm is a competitive system which achieved the highest performance in a previous disease challenge (17, 27); its performance therefore provides a very strong benchmark.”
Development of phenotype algorithms using electronic medical records and incorporating natural language processing (2015, methodology): “21 30-32 Finally, we note that the general phenotyping method presented in this article were successfully applied to a range of defined diseases and conditions but has not been extensively tested on outcomes such as drug response or adverse events.”
CollaboNet: collaboration of deep neural networks for biomedical named entity recognition (2018, methodology): “Datasets We used 5 datasets (BC2GM [33], BC4CHEMD [34], BC5CDR [35–38], JNLPBA [22], NCBI [21]), all of which were collected by Crichton et al [24] (Table 1).”
A survey of current trends in computational drug repositioning (2016, background): “The biomedical and pharmaceutical knowledge available in literature [70, 71] or databases contains vast amount of information for drugs and diseases, which can be automatically mined [72–74] and retrieved [75], thanks to the recent advances in text mining research [76].”
NCBI disease corpus: A resource for disease name recognition and concept normalization (2014, methodology): “Finally, the disease normalization methods results reported in this paper and in DNorm [22] show that the NCBI disease corpus is a suitable resource of gold-standard data to build better, more accurate models for disease name recognition.”
BioMRC: A Dataset for Biomedical Machine Reading Comprehension (2020, methodology): “2 We use DNORM ’s biomedical entity annotations, which are more accurate than METAMAP ’s (Leaman et al., 2013).”
BioCreative V CDR task corpus: a resource for chemical disease relation extraction (2016, methodology): “To accelerate manual annotation (24), text-mined disease and chemical results were pre-computed using DNorm (25) and tmChem (26) and displayed to the annotators.”