Support Vector Feature Selection for Early Detection of Anastomosis Leakage From Bag-of-Words in Electronic Health Records

• Published in: IEEE journal of biomedical and health informatics Vol. 20; no. 5; pp. 1404 - 1415
• Main Authors: Soguero-Ruiz, Cristina, Hindberg, Kristian, Rojo-Alvarez, Jose Luis, Skrovseth, Stein Olav, Godtliebsen, Fred, Mortensen, Kim, Revhaug, Arthur, Lindsetmo, Rolv-Ole, Augestad, Knut Magne, Jenssen, Robert
• Format: Journal Article
• Language: English
• Published: United States IEEE 01-09-2016; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Anastomosis leakage (AL); Anastomotic Leak - diagnosis; bag-of-words (BoWs); Cluster Analysis; colorectal cancer (CRC); Colorectal Neoplasms - surgery; Criteria; early detection; electronic health record (EHR); Electronic Health Records; Entropy; Feature extraction; feature selection (FS); Health; Humans; Kernel; kernel entropy; Leakage; Mathematical models; Medical Informatics - methods; Patients; Probability density function; Strategy; Studies; Support Vector Machine; support vector machine (SVM); Support vector machines; Surgery; Texts; Vectors
• ISSN: 2168-2194; 2168-2208
• DOI: 10.1109/JBHI.2014.2361688

The free text in electronic health records (EHRs) conveys a huge amount of clinical information about health state and patient history. Despite a rapidly growing literature on the use of machine learning techniques for extracting this information, little effort has been invested toward feature selection and the features' corresponding medical interpretation. In this study, we focus on the task of early detection of anastomosis leakage (AL), a severe complication after elective surgery for colorectal cancer (CRC) surgery, using free text extracted from EHRs. We use a bag-of-words model to investigate the potential for feature selection strategies. The purpose is earlier detection of AL and prediction of AL with data generated in the EHR before the actual complication occur. Due to the high dimensionality of the data, we derive feature selection strategies using the robust support vector machine linear maximum margin classifier, by investigating: 1) a simple statistical criterion (leave-one-out-based test); 2) an intensive-computation statistical criterion (Bootstrap resampling); and 3) an advanced statistical criterion (kernel entropy). Results reveal a discriminatory power for early detection of complications after CRC (sensitivity 100%; specificity 72%). These results can be used to develop prediction models, based on EHR data, that can support surgeons and patients in the preoperative decision making phase.