Medical Concept Representation Learning from Multi-source Data

Bai, Tian; Egleston, Brian L.; Bleicher, Richard J.; Vučetić, Slobodan

doi:10.24963/ijcai.2019/680

Cited by 15 publications

(19 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The medical concept embedding was trained with the ICD code sequence from the EMR using a skip-gram of the Word2vec embedding method. In [18], modified pointwise mutual information (PMI) [24] and modified negative sampling [13] were used to embed medical codes from different ontologies of medical codes.…”

Section: Medical Concept Embeddingmentioning

confidence: 99%

See 1 more Smart Citation

MedionRep: Medical Ontology Representation using Graph Embedding with Medical Text

Kim

Song

Jun

2022

Preprint

View full text Add to dashboard Cite

Background: Electronic Medical Record (EMR) is an electronic record of a patient’s health information. Nowadays, the importance of EMR analysis is increasing in medical informatics. An EMR is multi-modal data containing medical text and medical concepts. Recent studies attempt to embed either medical text or medical concepts to analyze an EMR partially. However, no type of embedding understands an entire EMR, including both the medical text and the medical concepts. Moreover, most medical concept embeddings train concept sequences from the EMR. These embeddings do not reflect the ontology of the medical concepts, which contain medical semantics. Thus, this study proposes a novel medical ontology representation with medical text for understanding an entire EMR. Methods: First, we generated the International Classification of Disease (ICD)-10 graph using the ICD-10 graph dataset we created and initialized each node based on the pre-trained medical text embedding. Next, the ICD-10 nodes were trained by the code sequences sampled from the ontology using the encoder-decoder-based graph embedding. Lastly, we trained the ICD-10 nodes by the relation between the ICD code and the text.Results: For quantitative evaluation, we created similarity pairs of the ICD-10 codes dataset and compared the similarities of the ICD-10 code pairs. The average cosine similarity of ours is 0.87, which is the highest average among the comparison models. We also conducted a comparison of the similarity pairs using open datasets. The pearson correlation coefficients of ours are about 0.461 to 0.463, which is similar to the best model, 0.464. Both comparisons demonstrated that our medical ontology embedding performed well while maintaining the medical text embedding characteristics. Conclusions: In this study, we proposed a MedionRep which is a medical ontology representation method using graph embedding with medical text. MedionRep is a new medical concept embedding method with medical text and reflect the ontology of the medical concept including medical semantics. Our method could broaden the analysis of the EMR data, which includes several types of medical data.

show abstract

Section: Medical Concept Embeddingmentioning

confidence: 99%

“…Some studies try to embed medical concepts by the EMR concept sequence rather than medical concept ontology [15], [16]. Other studies attempted to reflect the ontology of the medical concept for drug-diseases relation extraction [17] and cross-referencing between different medical concepts [18].…”

Section: Introductionmentioning

confidence: 99%

MedionRep: Medical Ontology Representation using Graph Embedding with Medical Text

Kim

Song

Jun

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In the medical field, the above-mentioned task is often treated as embeddings learning for the medical concepts [1,6], implying ICD diagnosis codes, terms, and abbreviations, medication and procedure names, etc. Commonly such concepts are viewed within a temporal process associated with a patient.…”

Section: Related Workmentioning

confidence: 99%

“…To efficiently deal with sequentially organized medical data the notion of context becomes crucial. For this, some papers [1,6] use modifications of the Skip-gram algorithm [13] though it is limited to account for only a fixed-size context of a sequence. Models with Recurrent Neural Network (RNN) architectures offer a better context handling mechanism.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Patient Embeddings in Healthcare and Insurance Applications

Blinov¹,

Kokh²

2021

Preprint

View full text Add to dashboard Cite

The paper researches the problem of concept and patient representations in the medical domain. We present the patient histories from Electronic Health Records (EHRs) as temporal sequences of ICD concepts for which embeddings are learned in an unsupervised setup with a transformer-based neural network model. The model training was performed on the collection of one million patients' histories in 6 years. The predictive power of such a model is assessed in comparison with several baseline methods. A series of experiments on the MIMIC-III data show the advantage of the presented model compared to a similar system. Further, we analyze the obtained embedding space with regards to concept relations and show how knowledge from the medical domain can be successfully transferred to the practical task of insurance scoring in the form of patient embeddings.

show abstract

Knowledge guided multi-filter residual convolutional neural network for ICD coding from clinical text

Boukhers

Goswami

Jürjens

2023

Neural Comput & Applic

View full text Add to dashboard Cite

A common challenge encountered when using Deep Neural Network models for automatic ICD coding is their potential inability to effectively handle unseen clinical texts, especially when these models are only trained on a limited number of examples. This is because these models rely solely on the patterns and relationships present in the training data, and may not be able to effectively incorporate additional knowledge about the relationships between medical entities. To address this issue, we introduce KG-MultiResCNN—KnowledgeGuidedMulti-filterResidualConvolutionalNeuralNetwork model, which combines training examples with external knowledge from the Wikidata Knowledge Graph (KG) in order to better capture the relationships between medical entities. The KG is a structured database that contains a wealth of information about various entities, including medical concepts and their relationships with one another. By incorporating this external knowledge into our model, we are able to improve its ability to predict ICD codes for new clinical texts. In our experiments with the MIMIC-III dataset, we found that the KG-MultiResCNN model significantly outperformed the baseline approaches. This demonstrates the effectiveness of using external knowledge, in addition to training examples, to improve the performance of deep learning models for automatic ICD coding.

show abstract

Medical Concept Representation Learning from Multi-source Data

Cited by 15 publications

References 8 publications

MedionRep: Medical Ontology Representation using Graph Embedding with Medical Text

MedionRep: Medical Ontology Representation using Graph Embedding with Medical Text

Patient Embeddings in Healthcare and Insurance Applications

Knowledge guided multi-filter residual convolutional neural network for ICD coding from clinical text

Contact Info

Product

Resources

About