Explainable Prediction of Medical Codes from Clinical Text

Mullenbach, James; Wiegreffe, Sarah; Duke, Jon; Sun, Jimeng; Eisenstein, Jacob

doi:10.48550/arxiv.1802.05695

Cited by 37 publications

(128 citation statements)

References 0 publications

Supporting

Mentioning

114

Contrasting

Order By: Relevance

“…Attention Model [29], [30] was first introduced in machine translation task and the attention weights were later widely used in natural language processing tasks as explanations in neural networks [31], [32]. Other than Natural Language Processing (NLP) tasks, the attention mechanism is also a near-ubiquitous method in recommendation tasks used as explanations in some works.…”

Section: Discussion Of Explanation For Recommendation With Attention ...mentioning

confidence: 99%

Reinforcement Learning based Path Exploration for Sequential Explainable Recommendation

Li¹,

Chen²,

Li³

et al. 2021

Preprint

View full text Add to dashboard Cite

Recent advances in path-based explainable recommendation systems have attracted increasing attention thanks to the rich information provided by knowledge graphs. Most existing explainable recommendations only utilize static knowledge graphs and ignore the dynamic user-item evolutions, leading to less convincing and inaccurate explanations. Although there are some works that realize that modelling user's temporal sequential behaviour could boost the performance and explainability of the recommender systems, most of them either only focus on modelling user's sequential interactions within a path or independently and separately of the recommendation mechanism. In this paper, we propose a novel Temporal Meta-path Guided Explainable Recommendation leveraging Reinforcement Learning (TMER-RL), which utilizes reinforcement item-item path modelling between consecutive items with attention mechanisms to sequentially model dynamic user-item evolutions on dynamic knowledge graph for explainable recommendation. Compared with existing works that use heavy recurrent neural networks to model temporal information, we propose simple but effective neural networks to capture users' historical item features and path-based context to characterize the next purchased item. Extensive evaluations of TMER on two real-world datasets show state-of-the-art performance compared against recent strong baselines.

show abstract

Section: Discussion Of Explanation For Recommendation With Attention ...mentioning

confidence: 99%

Reinforcement Learning based Path Exploration for Sequential Explainable Recommendation

Li¹,

Chen²,

Li³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In the case of NNs, however, this process poses challenges that are more complex. Established approaches are LIME (Local Interpretable Model-Agnostic Explanations) (Ribeiro et al, 2016), or the notion of saliency as being the norm of the gradient of the loss function to a given input, an approach successfully applied in the general (Li et al, 2015;Arras et al, 2017;Chae et al, 2017) and clinical NLP domains (Gehrmann et al, 2017) for explainable ML systems (Mullenbach et al, 2018).…”

Section: Neural Network Interpretationmentioning

confidence: 99%

Secondary Use of Clinical Problem List Entries for Neural Network-Based Disease Code Assignment

Kreuzthaler¹,

Schulz²

2021

Preprint

View full text Add to dashboard Cite

Clinical information systems have become large repositories for semi-structured annotated healthcare data, which have reached a critical mass that makes them interesting for supervised data-driven neural network approaches. We explored automated coding of 50 character long clinical problem list entries using the International Classification of Diseases (ICD-10) and evaluated three different types of network architectures on the top 100 ICD-10 three-digit codes. A fastText baseline reached a macro-averaged F 1 -measure of 0.83, followed by a character-level LSTM with a macro-averaged F 1 -measure of 0.84. Top performing was a downstreamed RoBERTa model using a custom language model with a macro-averaged F 1 -measure of 0.88. A neural network activation analysis together with an investigation of the false positives and false negatives unveiled inconsistent manual coding as a main limiting factor.

show abstract

“…Convolutional networks also play an important role in this field. Mullenbach et al [21] proposed Convolutional Attention network for Multi-Label classification (CAML). Li and Yu [16] utilized a Multi-Filter Residual Convolutional Neural Network (MultiResCNN), and Ji et al [10] developed a dilated convolutional network.…”

Section: Related Workmentioning

confidence: 99%

“…Since manual coding is error-prone and labor-consuming [22], automated coding is needed. Taking the ICD coding as an example, many publications have proposed automated coding approaches, including feature engineering-based machine learning methods [24,14] and deep learning methods [5,21,16]. However, the automated medical coding task is still challenging as reflected in the following two aspects.…”

Section: Introductionmentioning

confidence: 99%

“…Also, it is a challenge to benefit from the relationship between different medical codes, especially when the label is highdimensional. Existing automatic ICD coding models, such as CAML [21] and MultiResCNN [16], have limited performance because they do not consider the relationship between ICD codes. In the medical ontology, there exists certain connections between different concepts.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multitask Recalibrated Aggregation Network for Medical Code Prediction

Sun,

Ji,

Cambria

et al. 2021

Preprint

View full text Add to dashboard Cite

Medical coding translates professionally written medical reports into standardized codes, which is an essential part of medical information systems and health insurance reimbursement. Manual coding by trained human coders is time-consuming and error-prone. Thus, automated coding algorithms have been developed, building especially on the recent advances in machine learning and deep neural networks. To solve the challenges of encoding lengthy and noisy clinical documents and capturing code associations, we propose a multitask recalibrated aggregation network. In particular, multitask learning shares information across different coding schemes and captures the dependencies between different medical codes. Feature recalibration and aggregation in shared modules enhance representation learning for lengthy notes. Experiments with a real-world MIMIC-III dataset show significantly improved predictive performance.

show abstract

Explainable Prediction of Medical Codes from Clinical Text

Cited by 37 publications

References 0 publications

Reinforcement Learning based Path Exploration for Sequential Explainable Recommendation

Reinforcement Learning based Path Exploration for Sequential Explainable Recommendation

Secondary Use of Clinical Problem List Entries for Neural Network-Based Disease Code Assignment

Multitask Recalibrated Aggregation Network for Medical Code Prediction

Contact Info

Product

Resources

About