N-gram support vector machines for scalable procedure and diagnosis classification, with applications to clinical free text data from the intensive care unit
| Autor: | R. Adams Dudley, Naomi S. Bardach, Jason M Davies, Ben J. Marafino, Mitzi L. Dean |
|---|---|
| Rok vydání: | 2014 |
| Předmět: |
Adult
Support Vector Machine Speech recognition medicine.medical_treatment Bigram SVM Jaundice Information Storage and Retrieval Health Informatics Machine learning computer.software_genre Medical and Health Sciences law.invention Engineering law Support Vector Machines Neonatal Information and Computing Sciences medicine Humans Electronic Health Records Medical diagnosis Mechanical ventilation Data collection business.industry Respiration Infant Newborn Infant n-gram Phototherapy Focus on Biomedical Natural Language Processing and Data Modeling Classification Newborn Intensive care unit Respiration Artificial Jaundice Neonatal Risk adjustment Support vector machine Intensive Care Units Artificial ICU Artificial intelligence business computer Classifier (UML) Medical Informatics |
| Zdroj: | Journal of the American Medical Informatics Association : JAMIA, vol 21, iss 5 Marafino, BJ; Davies, JM; Bardach, NS; Dean, ML; & Dudley, RA. (2014). N-gram support vector machines for scalable procedure and diagnosis classification, with applications to clinical free text data from the intensive care unit. Journal of the American Medical Informatics Association, 21(5), 871-875. doi: 10.1136/amiajnl-2014-002694. UCSF: Retrieved from: http://www.escholarship.org/uc/item/6pt5950p |
| DOI: | 10.1136/amiajnl-2014-002694. |
| Popis: | Background Existing risk adjustment models for intensive care unit (ICU) outcomes rely on manual abstraction of patient-level predictors from medical charts. Developing an automated method for abstracting these data from free text might reduce cost and data collection times. Objective To develop a support vector machine (SVM) classifier capable of identifying a range of procedures and diagnoses in ICU clinical notes for use in risk adjustment. Materials and methods We selected notes from 2001–2008 for 4191 neonatal ICU (NICU) and 2198 adult ICU patients from the MIMIC-II database from the Beth Israel Deaconess Medical Center. Using these notes, we developed an implementation of the SVM classifier to identify procedures (mechanical ventilation and phototherapy in NICU notes) and diagnoses (jaundice in NICU and intracranial hemorrhage (ICH) in adult ICU). On the jaundice classification task, we also compared classifier performance using n-gram features to unigrams with application of a negation algorithm (NegEx). Results Our classifier accurately identified mechanical ventilation (accuracy=0.982, F1=0.954) and phototherapy use (accuracy=0.940, F1=0.912), as well as jaundice (accuracy=0.898, F1=0.884) and ICH diagnoses (accuracy=0.938, F1=0.943). Including bigram features improved performance on the jaundice (accuracy=0.898 vs 0.865) and ICH (0.938 vs 0.927) tasks, and outperformed NegEx-derived unigram features (accuracy=0.898 vs 0.863) on the jaundice task. Discussion Overall, a classifier using n-gram support vectors displayed excellent performance characteristics. The classifier generalizes to diverse patient populations, diagnoses, and procedures. Conclusions SVM-based classifiers can accurately identify procedure status and diagnoses among ICU patients, and including n-gram features improves performance, compared to existing methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|