From Free Text to Clusters of Content in Health Records: An Unsupervised Graph Partitioning Approach

Abstract

Electronic Healthcare records contain large volumes of unstructured data in different forms. Free text constitutes a large portion of such data, yet this source of richly detailed information often remains under-used in practice because of a lack of suitable methodologies to extract interpretable content in a timely manner. Here we apply network-theoretical tools to the analysis of free text in Hospital Patient Incident reports in the English National Health Service, to find clusters of reports in an unsupervised manner and at different levels of resolution based directly on the free text descriptions contained within them. To do so, we combine recently developed deep neural network text-embedding methodologies based on paragraph vectors with multi-scale Markov Stability community detection applied to a similarity graph of documents obtained from sparsified text vector similarities. We showcase the approach with the analysis of incident reports submitted in Imperial College Healthcare NHS Trust, London. The multiscale community structure reveals levels of meaning with different resolution in the topics of the dataset, as shown by relevant descriptive terms extracted from the groups of records, as well as by comparing a posteriori against hand-coded categories assigned by healthcare personnel. Our content communities exhibit good correspondence with well-defined hand-coded categories, yet our results also provide further medical detail in certain areas as well as revealing complementary descriptors of incidents beyond the external classification. We also discuss how the method can be used to monitor reports over time and across different healthcare providers, and to detect emerging trends that fall outside of pre-existing categories.

arXiv comment25 pages, 2 tables, 8 figures and 5 supplementary figures

References in corpus (21)

• Efficient Estimation of Word Representations in Vector Space
• Fast unfolding of communities in large networks
• Distributed Representations of Words and Phrases and their Compositionality
• Finding community structure in very large networks
• Distributed Representations of Sentences and Documents
• Near linear time algorithm to detect community structures in large-scale networks
• Community detection algorithms: a comparative analysis
• A tool for filtering information in complex systems
• The map equation
• SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation
• Random Walks, Markov Processes and the Multiscale Modular Organization of Complex Networks
• Laplacian Dynamics and Multiscale Modular Structure in Networks
• Document Embedding with Paragraph Vectors
• The many facets of community detection in complex networks
• Markov dynamics as a zooming lens for multiscale community detection: non clique-like communities and the field-of-view limit
• Encoding dynamics for multiscale community detection: Markov time sweeping for the Map equation
• Flow-based network analysis of the Caenorhabditis elegans connectome
• The stability of a graph partition: A dynamics-based framework for community detection
• Interest communities and flow roles in directed networks: the Twitter network of the UK riots
• Finding role communities in directed networks using Role-Based Similarity, Markov Stability and the Relaxed Minimum Spanning Tree
• Semantic Word Clouds with Background Corpus Normalization and t-distributed Stochastic Neighbor Embedding

Cited by in corpus (3)

• Graph-based data clustering via multiscale community detection
• PyGenStability: Multiscale community detection with generalized Markov Stability
• Extracting information from free text through unsupervised graph-based clustering: an application to patient incident records