Leveraging Hierarchical Category Knowledge for Data-Imbalanced Multi-Label Diagnostic Text Understanding

Tsai, Shang-Chi; Chang, Ting-Yun; Chen, Yun-Nung

doi:10.18653/v1/d19-6206

Cited by 11 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, previous studies have considered the hierarchical structure of ICD codes (Xie and Xing, 2018 [25]), proposing a tree-of-sequences LSTM to capture both the hierarchical relationships among codes and the semantics of each code. Tsai et al (2019) [26] introduced various methods to leverage the hierarchical knowledge of ICD by adding refined loss functions.…”

Section: Automatic Ehrs Codingmentioning

confidence: 99%

Kohonen neural network and symbiotic-organism search algorithm for intrusion detection of network viruses

Zhou

Miao

Tang

et al. 2023

Front. Comput. Neurosci.

View full text Add to dashboard Cite

IntroductionThe development of the Internet has made life much more convenient, but forms of network intrusion have become increasingly diversified and the threats to network security are becoming much more serious. Therefore, research into intrusion detection has become very important for network security.MethodsIn this paper, a clustering algorithm based on the symbiotic-organism search (SOS) algorithm and a Kohonen neural network is proposed.ResultsThe clustering accuracy of the Kohonen neural network is improved by using the SOS algorithm to optimize the weights in the Kohonen neural network.DiscussionOur approach was verified with the KDDCUP99 network intrusion data. The experimental results show that SOS-Kohonen can effectively detect intrusion. The detection rate was higher, and the false alarm rate was lower.

show abstract

Section: Automatic Ehrs Codingmentioning

confidence: 99%

Kohonen neural network and symbiotic-organism search algorithm for intrusion detection of network viruses

Zhou

Miao

Tang

et al. 2023

Front. Comput. Neurosci.

View full text Add to dashboard Cite

show abstract

“…Based on EMRs, various diagnostic prediction methods have been developed. Among them, research on disease diagnosis based on English EMRs is more extensive (Yuwono et al, 2019; Grundmann et al, 2022; Gu et al, 2021; Tsai et al, 2019). Few predictors based on Chinese EMRs have been proposed (Li et al, 2019; Li et al, 2023; Zhang et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

An interpretable diagnostic approach for lung cancer: Combining maximal clique and improved BERT

et al. 2023

View full text Add to dashboard Cite

The lung cancer incidence and mortality in China have always been high. Moreover, due to the limited level of professional technology, misdiagnosis and missed diagnosis of lung cancer often occur. To improve the accuracy of diagnosis, this paper proposes an interpretable diagnostic method for lung cancer based on Chinese electronic medical records (EMRs). First, to overcome the difficulty in word segmentation of clinical texts in Chinese EMRs, a dictionary construction method is proposed based on the idea of maximal clique, and 730 medical professional terms related to lung diseases are identified. Then, the ProbSparse self‐attention mechanism and self‐attention distilling operation in Informer are used to improve the Bidirectional Encoder Representations from Transformer (BERT) to realize the representation of long clinical texts with lower time complexity and memory consumption. Finally, the convolutional neural network with an attention mechanism is employed to process the representation results to realize the interpretable prediction of lung cancer. This method is applied to the lung cancer diagnosis of inpatients in a tertiary hospital in Hunan Province, obtaining excellent results of about 0.9 for area under the receiver operating characteristic curve (AUROC) and area under the precision‐recall curve (AUPRC). In addition, the results of the comparative analysis with existing dictionaries, word embedding methods and diagnostic methods further confirm the superiority of the proposed method. Specifically, the proposed method improves the precision by at least 6%, the recall by at least 2.6%, the F1 score by at least 5.2%, AUROC by at least 7.3% and AUPRC by at least 7.7% compared with all these state‐of‐the‐art methods.

show abstract

“…However, the model is required to infer from lab results such as low level of RBC, Hgb, Hct, which leads to anemia. In order to fill in this knowledge gap, previous researches use additional information such as hierarchical code ontology (Tsai, Chang, and Chen 2019;Cai et al 2022), code co-occurrence (Cao et al 2020)…”

Section: Introductionmentioning

confidence: 99%

Multi-Label Few-Shot ICD Coding as Autoregressive Generation with Prompt

Yang

Kwon

Yao

et al. 2023

AAAI

View full text Add to dashboard Cite

Automatic International Classification of Diseases (ICD) coding aims to assign multiple ICD codes to a medical note with an average of 3,000+ tokens. This task is challenging due to the high-dimensional space of multi-label assignment (155,000+ ICD code candidates) and the long-tail challenge - Many ICD codes are infrequently assigned yet infrequent ICD codes are important clinically. This study addresses the long-tail challenge by transforming this multi-label classification task into an autoregressive generation task. Specifically, we first introduce a novel pretraining objective to generate free text diagnosis and procedure descriptions using the SOAP structure, the medical logic physicians use for note documentation. Second, instead of directly predicting the high dimensional space of ICD codes, our model generates the lower dimension of text descriptions, which then infer ICD codes. Third, we designed a novel prompt template for multi-label classification. We evaluate our Generation with Prompt (GP) model with the benchmark of all code assignment (MIMIC-III-full) and few shot ICD code assignment evaluation benchmark (MIMIC-III-few). Experiments on MIMIC-III-few show that our model performs with a marco F1 30.2, which substantially outperforms the previous MIMIC-III-full SOTA model (marco F1 4.3) and the model specifically designed for few/zero shot setting (marco F1 18.7). Finally, we design a novel ensemble learner, a cross attention reranker with prompts, to integrate previous SOTA and our best few-shot coding predictions. Experiments on MIMIC-III-full show that our ensemble learner substantially improves both macro and micro F1, from 10.4 to 14.6 and from 58.2 to 59.1, respectively.

show abstract

Leveraging Hierarchical Category Knowledge for Data-Imbalanced Multi-Label Diagnostic Text Understanding

Cited by 11 publications

References 5 publications

Kohonen neural network and symbiotic-organism search algorithm for intrusion detection of network viruses

Kohonen neural network and symbiotic-organism search algorithm for intrusion detection of network viruses

An interpretable diagnostic approach for lung cancer: Combining maximal clique and improved BERT

Multi-Label Few-Shot ICD Coding as Autoregressive Generation with Prompt

Contact Info

Product

Resources

About