Comparing Rule-Based and Deep Learning Models for Patient Phenotyping

Gehrmann, Sebastian; Dernoncourt, Franck; Li, Yeran; Carlson, Eric T.; Wu, Joy T.; Welt, Jonathan; Foote, John; Moseley, Edward T.; Grant, David W.; Tyler, Patrick D.; Celi, Leo Anthony

doi:10.48550/arxiv.1703.08705

Cited by 10 publications

(14 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They also claimed to successfully learn the structure of highdimensional EHR data for phenotype stratification. Gehrmann et al [23] compared convolutional neural networks to the traditional rule-based entity extraction systems using the cTAKES and logistic regression using n-gram features. They tested ten different phenotyping tasks using discharge summaries.…”

Section: Deep Learning For Clinical Data Miningmentioning

confidence: 99%

Clinical Text Classification with Rule-based Features and Knowledge-guided Convolutional Neural Networks

Liang

Mao

Luo

2018

2018 IEEE International Conference on Healthcare Informatics Workshop (ICHI-W)

View full text Add to dashboard Cite

Clinical text classification is an important problem in medical natural language processing. Existing studies have conventionally focused on rules or knowledge sources-based feature engineering, but only a few have exploited effective feature learning capability of deep learning methods. In this study, we propose a novel approach which combines rule-based features and knowledge-guided deep learning techniques for effective disease classification. Critical Steps of our method include identifying trigger phrases, predicting classes with very few examples using trigger phrases and training a convolutional neural network with word embeddings and Unified Medical Language System (UMLS) entity embeddings. We evaluated our method on the 2008 Integrating Informatics with Biology and the Bedside (i2b2) obesity challenge. The results show that our method outperforms the state of the art methods.

show abstract

Section: Deep Learning For Clinical Data Miningmentioning

confidence: 99%

Clinical Text Classification with Rule-based Features and Knowledge-guided Convolutional Neural Networks

Liang

Mao

Luo

2018

2018 IEEE International Conference on Healthcare Informatics Workshop (ICHI-W)

View full text Add to dashboard Cite

show abstract

“…A recent systematic literature review regarding ICD coding systems was published by Kaur et al (2021). Gehrmann et al (2017) applied convolutional neural networks (CNNs) to the recognition of ten disease phenotypes using 1,610 manually annotated discharge summaries from the MIMIC-III corpus. CNNs outperformed n-gram models and concept-based prediction models using the clinical information extractor cTakes in combination with random forest and linear regression models, yielding a macro-average F 1 -measure of 0.76.…”

Section: Background and Related Workmentioning

confidence: 99%

“…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

“…There is a broad range of what is considered a cohort (sometimes referred to as a phenotype in the literature) and how they are learned. In some cases, cohorts are pre-defined: for example, Gehrmann et al have a group of physicians manually annotate examples with a set of 10 diseaserelated cohort classifications [13]. The process of manual annotation, however, is time-consuming, expensive and hard to scale.…”

Section: Patient Representationsmentioning

confidence: 99%

Learning Tasks for Multitask Learning

Suresh

Gong

Guttag

2018

Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

Machine learning approaches have been effective in predicting adverse outcomes in different clinical settings. These models are often developed and evaluated on datasets with heterogeneous patient populations. However, good predictive performance on the aggregate population does not imply good performance for specific groups.In this work, we present a two-step framework to 1) learn relevant patient subgroups, and 2) predict an outcome for separate patient populations in a multi-task framework, where each population is a separate task. We demonstrate how to discover relevant groups in an unsupervised way with a sequence-to-sequence autoencoder. We show that using these groups in a multi-task framework leads to better predictive performance of in-hospital mortality both across groups and overall. We also highlight the need for more granular evaluation of performance when dealing with heterogeneous populations.

show abstract

Comparing Rule-Based and Deep Learning Models for Patient Phenotyping

Cited by 10 publications

References 0 publications

Clinical Text Classification with Rule-based Features and Knowledge-guided Convolutional Neural Networks

Clinical Text Classification with Rule-based Features and Knowledge-guided Convolutional Neural Networks

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

Learning Tasks for Multitask Learning

Contact Info

Product

Resources

About