Breast Cancer Classification with Electronic Medical Records Using Hierarchical Attention Bidirectional Networks

Chen, Dehua; Qian, Guangjun; Pan, Qiao

doi:10.1109/bibm.2018.8621479

Cited by 10 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, deep learning techniques have achieved stateof-the-art performance on text classification benchmarks. 9 In medicine, various deep learning techniques have been used for text classification including, but not limited to, recurrent neural networks (RNNs), [10][11][12] convolutional neural networks (CNNs), 13,14 and hybrid models combining more than one technique. 15 These techniques have the potential for automatic detection of relevant clinical information in EHR text.…”

Section: Improve (International Medical Prevention Registry On Venousmentioning

confidence: 99%

Deep learning detects and visualizes bleeding events in electronic health records

Pedersen

Laursen

Savarimuthu

et al. 2021

Research and Practice in Thrombosis and Haemostasis

View full text Add to dashboard Cite

show abstract

Section: Improve (International Medical Prevention Registry On Venousmentioning

confidence: 99%

Deep learning detects and visualizes bleeding events in electronic health records

Pedersen

Laursen

Savarimuthu

et al. 2021

Research and Practice in Thrombosis and Haemostasis

View full text Add to dashboard Cite

show abstract

“…This method uses self-learning to automatically extract the high-level semantic information from EMRs. Chen et al [10] used an end-to-end hierarchical neural network to investigate breast cancer problems using EMRs. Hao et al [11] used a deep belief network [12] to integrate patients' structured data characteristics to predict the risk of cerebral infarction.…”

Section: Introductionmentioning

confidence: 99%

Combining External Medical Knowledge for Improving Obstetric Intelligent Diagnosis: Model Development and Validation

Zhang¹,

Cai²,

Yu³

et al. 2021

JMIR Med Inform

View full text Add to dashboard Cite

Background Data-driven medical health information processing has become a new development trend in obstetrics. Electronic medical records (EMRs) are the basis of evidence-based medicine and an important information source for intelligent diagnosis. To obtain diagnostic results, doctors combine clinical experience and medical knowledge in their diagnosis process. External medical knowledge provides strong support for diagnosis. Therefore, it is worth studying how to make full use of EMRs and medical knowledge in intelligent diagnosis. Objective This study aims to improve the performance of intelligent diagnosis in EMRs by combining medical knowledge. Methods As an EMR usually contains multiple types of diagnostic results, the intelligent diagnosis can be treated as a multilabel classification task. We propose a novel neural network knowledge-aware hierarchical diagnosis model (KHDM) in which Chinese obstetric EMRs and external medical knowledge can be synchronously and effectively used for intelligent diagnostics. In KHDM, EMRs and external knowledge documents are integrated by the attention mechanism contained in the hierarchical deep learning framework. In this way, we enrich the language model with curated knowledge documents, combining the advantages of both to make a knowledge-aware diagnosis. Results We evaluate our model on a real-world Chinese obstetric EMR dataset and showed that KHDM achieves an accuracy of 0.8929, which exceeds that of the most advanced classification benchmark methods. We also verified the model’s interpretability advantage. Conclusions In this paper, an improved model combining medical knowledge and an attention mechanism is proposed, based on the problem of diversity of diagnostic results in Chinese EMRs. KHDM can effectively integrate domain knowledge to greatly improve the accuracy of diagnosis.

show abstract

“…This method uses self-learning to automatically extract the high-level semantic information of EMRs. Chen et al [10] used an end-to-end hierarchical neural network to investigate breast cancer problems using EMRs. Hao et al [11] used a deep belief network (DBN) [12] to integrate patients' structured data characteristics to predict the risk of cerebral infarction.…”

Section: Introductionmentioning

confidence: 99%

Combining External Medical Knowledge for improving Obstetric Intelligent Diagnosis

Zhang

Cai

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: Data-driven medical health information processing has become a new development trend in obstetrics. Electronic medical records (EMRs) are the basis of evidence-based medicine and important information source for intelligent diagnosis. To obtain diagnostic results, doctors combine clinical experience and medical knowledge in their diagnosis process. External medical knowledge provides strong support for diagnosis. Therefore, how to make full use of EMRs and medical knowledge in intelligent diagnosis is worth studying.Methods: As an EMR usually contains multiple types of diagnostic results, the intelligent diagnosis can be treated as a multi-label classification task. We propose a novel neural network model called Knowledge-aware Hierarchical Diagnosis Model (KHDM) in which Chinese obstetric EMRs and external medical knowledge can be synchronously and effectively used for intelligent diagnostics. In the KHDM, EMRs and external knowledge documents are integrated by the attention mechanism contained in the hierarchical deep learning framework. In this way, we enrich the language model with curated knowledge documents, combining the advantages of both to make a knowledge-aware diagnosis.Results: We evaluate our model on a real-world Chinese obstetric EMR dataset show that KHDM achieves an accuracy of 0.8929, which exceeds that of the most advanced classification benchmark methods.Conclusion: In this paper, an improved model combining medical knowledge and an attention mechanism is proposed, which is based on the problem of the diversity of diagnostic results in Chinese EMRs. KHDM can effectively integrate domain knowledge to greatly improve the accuracy of diagnosis, and we also verify the model's interpretability advantage.

show abstract

Breast Cancer Classification with Electronic Medical Records Using Hierarchical Attention Bidirectional Networks

Cited by 10 publications

References 8 publications

Deep learning detects and visualizes bleeding events in electronic health records

Deep learning detects and visualizes bleeding events in electronic health records

Combining External Medical Knowledge for Improving Obstetric Intelligent Diagnosis: Model Development and Validation

Combining External Medical Knowledge for improving Obstetric Intelligent Diagnosis

Contact Info

Product

Resources

About