Steven Jiang1, Weiyi Wu2, Naofumi Tomita2, Craig Ganoe2, Saeed Hassanpour3. 1. Department of Computer Science, Dartmouth College, Hanover, NH 03755, USA. 2. Department of Biomedical Data Science, Geisel School of Medicine at Dartmouth, Hanover, NH 03755, USA. 3. Department of Computer Science, Dartmouth College, Hanover, NH 03755, USA; Department of Biomedical Data Science, Geisel School of Medicine at Dartmouth, Hanover, NH 03755, USA; Department of Epidemiology, Geisel School of Medicine at Dartmouth, Hanover, NH 03755, USA. Electronic address: Saeed.Hassanpour@dartmouth.edu.
Abstract
OBJECTIVE: Currently, a major limitation for natural language processing (NLP) analyses in clinical applications is that concepts are not effectively referenced in various forms across different texts. This paper introduces Multi-Ontology Refined Embeddings (MORE), a novel hybrid framework that incorporates domain knowledge from multiple ontologies into a distributional semantic model, learned from a corpus of clinical text. MATERIALS AND METHODS: We use the RadCore and MIMIC-III free-text datasets for the corpus-based component of MORE. For the ontology-based part, we use the Medical Subject Headings (MeSH) ontology and three state-of-the-art ontology-based similarity measures. In our approach, we propose a new learning objective, modified from the sigmoid cross-entropy objective function. RESULTS AND DISCUSSION: We used two established datasets of semantic similarities among biomedical concept pairs to evaluate the quality of the generated word embeddings. On the first dataset with 29 concept pairs, with similarity scores established by physicians and medical coders, MORE's similarity scores have the highest combined correlation (0.633), which is 5.0% higher than that of the baseline model, and 12.4% higher than that of the best ontology-based similarity measure. On the second dataset with 449 concept pairs, MORE's similarity scores have a correlation of 0.481, based on the average of four medical residents' similarity ratings, and that outperforms the skip-gram model by 8.1%, and the best ontology measure by 6.9%. Furthermore, MORE outperforms three pre-trained transformer-based word embedding models (i.e., BERT, ClinicalBERT, and BioBERT) on both datasets. CONCLUSION: MORE incorporates knowledge from several biomedical ontologies into an existing corpus-based distributional semantics model, improving both the accuracy of the learned word embeddings and the extensibility of the model to a broader range of biomedical concepts. MORE allows for more accurate clustering of concepts across a wide range of applications, such as analyzing patient health records to identify subjects with similar pathologies, or integrating heterogeneous clinical data to improve interoperability between hospitals.
OBJECTIVE: Currently, a major limitation for natural language processing (NLP) analyses in clinical applications is that concepts are not effectively referenced in various forms across different texts. This paper introduces Multi-Ontology Refined Embeddings (MORE), a novel hybrid framework that incorporates domain knowledge from multiple ontologies into a distributional semantic model, learned from a corpus of clinical text. MATERIALS AND METHODS: We use the RadCore and MIMIC-III free-text datasets for the corpus-based component of MORE. For the ontology-based part, we use the Medical Subject Headings (MeSH) ontology and three state-of-the-art ontology-based similarity measures. In our approach, we propose a new learning objective, modified from the sigmoid cross-entropy objective function. RESULTS AND DISCUSSION: We used two established datasets of semantic similarities among biomedical concept pairs to evaluate the quality of the generated word embeddings. On the first dataset with 29 concept pairs, with similarity scores established by physicians and medical coders, MORE's similarity scores have the highest combined correlation (0.633), which is 5.0% higher than that of the baseline model, and 12.4% higher than that of the best ontology-based similarity measure. On the second dataset with 449 concept pairs, MORE's similarity scores have a correlation of 0.481, based on the average of four medical residents' similarity ratings, and that outperforms the skip-gram model by 8.1%, and the best ontology measure by 6.9%. Furthermore, MORE outperforms three pre-trained transformer-based word embedding models (i.e., BERT, ClinicalBERT, and BioBERT) on both datasets. CONCLUSION: MORE incorporates knowledge from several biomedical ontologies into an existing corpus-based distributional semantics model, improving both the accuracy of the learned word embeddings and the extensibility of the model to a broader range of biomedical concepts. MORE allows for more accurate clustering of concepts across a wide range of applications, such as analyzing patient health records to identify subjects with similar pathologies, or integrating heterogeneous clinical data to improve interoperability between hospitals.
Authors: A L Goldberger; L A Amaral; L Glass; J M Hausdorff; P C Ivanov; R G Mark; J E Mietus; G B Moody; C K Peng; H E Stanley Journal: Circulation Date: 2000-06-13 Impact factor: 29.690
Authors: Nishant Kumar; Laura J Tafe; John H Higgins; Jason D Peterson; Francise Blumental de Abreu; Sophie J Deharvengt; Gregory J Tsongalis; Christopher I Amos; Saeed Hassanpour Journal: Methods Inf Med Date: 2018-04-05 Impact factor: 2.176