Risk stratification of ICU patients using topic models inferred from unstructured progress notes.
Authors:
- 3 November 2012
- journal article
- Vol. 2012, 505-11
Abstract
We propose a novel approach for ICU patient risk stratification by combining the learned "topic" structure of clinical concepts (represented by UMLS codes) extracted from the unstructured nursing notes with physiologic data (from SAPS-I) for hospital mortality prediction. We used Hierarchical Dirichlet Processes (HDP), a non-parametric topic modeling technique, to automatically discover "topics" as shared groups of co-occurring UMLS clinical concepts. We evaluated the potential utility of the inferred topic structure in predicting hospital mortality using the nursing notes of 14,739 adult ICU patients (mortality 14.6%) from the MIMIC II database. Our results indicate that learned topic structure from the first 24-hour ICU nursing notes significantly improved the performance of the SAPS-I algorithm for hospital mortality prediction. The AUC for predicting hospital mortality from the first 24 hours of physiologic data and nursing text notes was 0.82. Using the physiologic data alone with the SAPS-I algorithm, an AUC of 0.72 was achieved. Thus, the clinical topics that were extracted and used to augment the SAPS-I algorithm significantly improved the performance of the baseline algorithm.Keywords
This publication has 15 references indexed in Scilit:
- Multiparameter Intelligent Monitoring in Intensive Care II: A public-access intensive care unit database*Critical Care Medicine, 2011
- Probabilistic Topic ModelsIEEE Signal Processing Magazine, 2010
- ICU acuity: real-time models versus daily models.2009
- Semantic Classification of Diseases in Discharge Summaries Using a Context-aware Rule-based ClassifierJournal of the American Medical Informatics Association, 2009
- Automated Discovery of Functional Generality of Human Gene Expression ProgramsPLOS Computational Biology, 2007
- Acute Physiology and Chronic Health Evaluation (APACHE) IV: Hospital mortality assessment for today’s critically ill patients*Critical Care Medicine, 2006
- Mining a clinical data warehouse to discover disease-finding associations using co-occurrence statistics.2005
- Extracting diagnoses from discharge summaries.2005
- Automated Encoding of Clinical Documents Based on Natural Language ProcessingJournal of the American Medical Informatics Association, 2004
- A new Simplified Acute Physiology Score (SAPS II) based on a European/North American multicenter studyJAMA, 1993