Interpretable Segmentation of Medical Free-Text Records Based on Word Embeddings
Authors:
Preprint
Abstract
Is it true that patients with similar conditions get similar diagnoses? In this paper we show NLP methods and a unique corpus of documents to validate this claim. We (1) introduce a method for representation of medical visits based on free-text descriptions recorded by doctors, (2) introduce a new method for clustering of patients' visits and (3) present an~application of the proposed method on a corpus of 100,000 visits. With the proposed method we obtained stable and separated segments of visits which were positively validated against final medical diagnoses. We show how the presented algorithm may be used to aid doctors during their practice.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Explainable Artificial Intelligence for Safe Intraoperative Decision SupportJAMA Surgery, 2019
- Insights into Analogy Completion from the Biomedical Domain2017
- Representation learning for very short texts using weighted word embedding aggregationPattern Recognition Letters, 2016
- Hybrid Text Segmentation for Hungarian Clinical RecordsLecture Notes in Computer Science, 2013
- Automatic segmentation of clinical texts2009
- The Unified Medical Language System (UMLS): integrating biomedical terminologyNucleic Acids Research, 2004