2017
DOI: 10.48550/arxiv.1703.08705
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Comparing Rule-Based and Deep Learning Models for Patient Phenotyping

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
14
0

Year Published

2017
2017
2023
2023

Publication Types

Select...
5
1
1

Relationship

1
6

Authors

Journals

citations
Cited by 10 publications
(14 citation statements)
references
References 0 publications
0
14
0
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%
“…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%
“…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%
“…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%