David Martinez1, Michelle R Ananda-Rajah2, Hanna Suominen3, Monica A Slavin4, Karin A Thursky5, Lawrence Cavedon6. 1. CIS Department, University of Melbourne, Australia. Electronic address: davidm@csse.unimelb.edu.au. 2. Infectious Diseases Unit, Alfred Health and The University of Melbourne, Australia. Electronic address: m.ananda-rajah@alfred.org.au. 3. NICTA and The Australian National University, Canberra, Australia; University of Canberra, Canberra, Australia; University of Turku, Finland. Electronic address: hanna.suominen@nicta.com.au. 4. Victorian Infectious Diseases Service, Royal Melbourne Hospital, Peter MacCallum Cancer Institute, Australia; Infectious Diseases Department, Peter MacCallum Cancer Institute, Australia. Electronic address: monica.slavin@mh.org.au. 5. Victorian Infectious Diseases Service, Royal Melbourne Hospital, Peter MacCallum Cancer Institute, Australia; Infectious Diseases Department, Peter MacCallum Cancer Institute, Australia. Electronic address: karin.thursky@petermac.org. 6. School of Computer Science and IT, RMIT University, Melbourne, Australia. Electronic address: lawrence.cavedon@rmit.edu.au.
Abstract
BACKGROUND: Invasive fungal diseases (IFDs) are associated with considerable health and economic costs. Surveillance of the more diagnostically challenging invasive fungal diseases, specifically of the sino-pulmonary system, is not feasible for many hospitals because case finding is a costly and labour intensive exercise. We developed text classifiers for detecting such IFDs from free-text radiology (CT) reports, using machine-learning techniques. METHOD: We obtained free-text reports of CT scans performed over a specific hospitalisation period (2003-2011), for 264 IFD and 289 control patients from three tertiary hospitals. We analysed IFD evidence at patient, report, and sentence levels. Three infectious disease experts annotated the reports of 73 IFD-positive patients for language suggestive of IFD at sentence level, and graded the sentences as to whether they suggested or excluded the presence of IFD. Reliable agreement between annotators was obtained and this was used as training data for our classifiers. We tested a variety of Machine Learning (ML), rule based, and hybrid systems, with feature types including bags of words, bags of phrases, and bags of concepts, as well as report-level structured features. Evaluation was carried out over a robust framework with separate Development and Held-Out datasets. RESULTS: The best systems (using Support Vector Machines) achieved very high recall at report- and patient-levels over unseen data: 95% and 100% respectively. Precision at report-level over held-out data was 71%; however, most of the associated false-positive reports (53%) belonged to patients who had a previous positive report appropriately flagged by the classifier, reducing negative impact in practice. CONCLUSIONS: Our machine learning application holds the potential for developing systematic IFD surveillance systems for hospital populations.
BACKGROUND: Invasive fungal diseases (IFDs) are associated with considerable health and economic costs. Surveillance of the more diagnostically challenging invasive fungal diseases, specifically of the sino-pulmonary system, is not feasible for many hospitals because case finding is a costly and labour intensive exercise. We developed text classifiers for detecting such IFDs from free-text radiology (CT) reports, using machine-learning techniques. METHOD: We obtained free-text reports of CT scans performed over a specific hospitalisation period (2003-2011), for 264 IFD and 289 control patients from three tertiary hospitals. We analysed IFD evidence at patient, report, and sentence levels. Three infectious disease experts annotated the reports of 73 IFD-positive patients for language suggestive of IFD at sentence level, and graded the sentences as to whether they suggested or excluded the presence of IFD. Reliable agreement between annotators was obtained and this was used as training data for our classifiers. We tested a variety of Machine Learning (ML), rule based, and hybrid systems, with feature types including bags of words, bags of phrases, and bags of concepts, as well as report-level structured features. Evaluation was carried out over a robust framework with separate Development and Held-Out datasets. RESULTS: The best systems (using Support Vector Machines) achieved very high recall at report- and patient-levels over unseen data: 95% and 100% respectively. Precision at report-level over held-out data was 71%; however, most of the associated false-positive reports (53%) belonged to patients who had a previous positive report appropriately flagged by the classifier, reducing negative impact in practice. CONCLUSIONS: Our machine learning application holds the potential for developing systematic IFD surveillance systems for hospital populations.
Authors: Michelle R Ananda-Rajah; Christoph Bergmeir; François Petitjean; Monica A Slavin; Karin A Thursky; Geoffrey I Webb Journal: JCO Clin Cancer Inform Date: 2017-11
Authors: Paul McGreevy; Peter Thomson; Navneet K Dhand; David Raubenheimer; Sophie Masters; Caroline S Mansfield; Timothy Baldwin; Ricardo J Soares Magalhaes; Jacquie Rand; Peter Hill; Anne Peaston; James Gilkerson; Martin Combs; Shane Raidal; Peter Irwin; Peter Irons; Richard Squires; David Brodbelt; Jeremy Hammond Journal: Animals (Basel) Date: 2017-09-26 Impact factor: 2.752