# Unsupervised Numerical Reasoning to Extract Phenotypes from Clinical Text by Leveraging External Knowledge

arXiv: https://arxiv.org/abs/2204.10202 · HTML: https://mlsanity.com/paper/2204.10202/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 38 references that are in the map.
- First posted on arXiv 19 Apr 2022.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [Publicly Available Clinical BERT Embeddings](https://mlsanity.com/paper/1904.03323/) (2019)
- [DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs](https://mlsanity.com/paper/1903.00161/) (2019)
- [Stanza: A Python Natural Language Processing Toolkit for Many Human Languages](https://mlsanity.com/paper/2003.07082/) (2020)
- [BEHRT: Transformer for Electronic Health Records](https://mlsanity.com/paper/1907.09538/) (2019)
- [Injecting Numerical Reasoning Skills into Language Models](https://mlsanity.com/paper/2004.04487/) (2020)
- [NumNet: Machine Reading Comprehension with Numerical Reasoning](https://mlsanity.com/paper/1910.06701/) (2019)
- [A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning](https://mlsanity.com/paper/1908.05514/) (2019)
- [Two-stage Federated Phenotyping and Patient Representation Learning](https://mlsanity.com/paper/1908.05596/) (2019)
- [NumGPT: Improving Numeracy Ability of Generative Pre-trained Models](https://mlsanity.com/paper/2109.03137/) (2021)
- [NOAHQA: Numerical Reasoning with Interpretable Graph Question Answering Dataset](https://mlsanity.com/paper/2109.10604/) (2021)
- [MedCAT -- Medical Concept Annotation Tool](https://mlsanity.com/paper/1912.10166/) (2019)
- [Weakly Supervised Neuro-Symbolic Module Networks for Numerical Reasoning](https://mlsanity.com/paper/2101.11802/) (2021)
- [Self-Supervised Detection of Contextual Synonyms in a Multi-Class Setting: Phenotype Annotation Use Case](https://mlsanity.com/paper/2109.01935/) (2021)
- [A Deep Learning Pipeline for Patient Diagnosis Prediction Using Electronic Health Records](https://mlsanity.com/paper/2006.16926/) (2020)
- [Clinical Utility of the Automatic Phenotype Annotation in Unstructured Clinical Notes: ICU Use Cases](https://mlsanity.com/paper/2107.11665/) (2021)

## Built on by (most cited first, 2 of 2)

- [Explainable AI for clinical risk prediction: a survey of concepts, methods, and modalities](https://mlsanity.com/paper/2308.08407/) (2023)
- [Improving Downstream Task Performance by Treating Numbers as Entities](https://mlsanity.com/paper/2205.03559/) (2022)

## Abstract (arXiv)

Extracting phenotypes from clinical text has been shown to be useful for a variety of clinical use cases such as identifying patients with rare diseases. However, reasoning with numerical values remains challenging for phenotyping in clinical text, for example, temperature 102F representing Fever. Current state-of-the-art phenotyping models are able to detect general phenotypes, but perform poorly when they detect phenotypes requiring numerical reasoning. We present a novel unsupervised methodology leveraging external knowledge and contextualized word embeddings from ClinicalBERT for numerical reasoning in a variety of phenotypic contexts. Comparing against unsupervised benchmarks, it shows a substantial performance improvement with absolute gains on generalized Recall and F1 scores up to 79% and 71%, respectively. In the supervised setting, it also surpasses the performance of alternative approaches with absolute gains on generalized Recall and F1 scores up to 70% and 44%, respectively.