Comparing Rule-Based and Deep Learning Models for Patient Phenotyping

By Sebastian Gehrmann, Franck Dernoncourt, Yeran Li, Eric T. Carlson, Joy T. Wu, Jonathan Welt, John Foote Jr., Edward T. Moseley, David W. Grant, Patrick D. Tyler and 1 more. 2017

45 citations recorded by the source corpus.

Objective: We investigate whether deep learning techniques for natural language processing (NLP) can be used efficiently for patient phenotyping. Patient phenotyping is a classification task for determining whether a patient has a medical condition, and is a crucial part of secondary analysis of healthcare data. We assess the performance of deep learning algorithms and compare them with classical NLP approaches. Materials and Methods: We compare convolutional neural networks (CNNs), n-gram models, and approaches based on cTAKES that extract pre-defined medical concepts from clinical notes and use them to predict patient phenotypes. The performance is tested on 10 different phenotyping tasks using 1,610 discharge summaries extracted from the MIMIC-III database. Results: CNNs outperform other phenotyping algorithms in all 10 tasks. The average F1-score of our model is 76 (PPV of 83, and sensitivity of 71) with our model having an F1-score up to 37 points higher than alternative approaches. We additionally assess the interpretability of our model by presenting a method that extracts the most salient phrases for a particular prediction. Conclusion: We show that NLP methods based on deep learning improve the performance of patient phenotyping. Our CNN-based algorithm automatically learns the phrases associated with each patient phenotype. As such, it reduces the annotation complexity for clinical domain experts, who are normally required to develop task-specific annotation rules and identify relevant phrases. Our method performs well in terms of both performance and interpretability, which indicates that deep learning is an effective approach to patient phenotyping based on clinicians' notes.

Subfields: Artificial Intelligence, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Cao Xiao
2. Jimeng Sun
3. Yuan Luo
4. Edward Choi
5. Harini Suresh
6. John V. Guttag
7. Zexian Zeng
8. Tristan Naumann

In Molecular Biology

1. Zexian Zeng
2. Jimeng Sun
3. Edward Choi
4. Tristan Naumann
5. Xiaoyu Li
6. Yu Deng
7. Cao Xiao
8. Yuan Luo

Citations in the corpus

• Natural Language Processing for EHR-Based Computational Phenotyping (2018, methodology): “[104] compared convolutional neural networks (CNNs) to the tradi-”
• Learning Tasks for Multitask Learning: Heterogenous Patient Populations in the ICU (2018, background): “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 disease-related cohort classifications [13].”
• Filter pruning of Convolutional Neural Networks for text classification: A case study of cancer pathology report comprehension (2018, unknown): “The feasibility of such a model was studied in the Bioinformatics domain [6], which reported that the CNN models outperformed conventional machine learning techniques.”
• Opportunities and challenges in developing deep learning models using electronic health records data: a systematic review (2018, methodology): “Other types of concept embedding take only free-text as input, eg., 31 , to extract pre-defined medical concepts from discharge summaries from MIMIC III data and use them to predict patient phenotypes.”