Exploratory analysis of methods for automated classification of laboratory test orders into syndromic groups in veterinary medicine

• Published in: PloS one 2013-03, Vol.8 (3), p.e57334-e57334
• Main Authors: Dórea, Fernanda C, Muckle, C Anne, Kelton, David, McClure, J T, McEwen, Beverly J, McNab, W Bruce, Sanchez, Javier, Revie, Crawford W
• Format: Article
• Language: English
• Subjects: Algorithms; Analysis; Animal Diseases - diagnosis; Animal Diseases - epidemiology; Animal populations; Animals; Artificial Intelligence; Automatic classification; Automation; Bayesian analysis; Biological & chemical terrorism; Biology; Classification; Classifiers; Clinical Laboratory Techniques; Computer Science; Data mining; Data processing; Decision Support Techniques; Decision trees; Diagnostic systems; Disease; End users; Epidemics; Food supply; Handbooks; Humans; Information processing; Knowledge discovery; Laboratories; Laboratory tests; Learning algorithms; Machine learning; Mathematics; Medicine; Methods; Ontario; Privacy; Public health; Public Health Surveillance; Rule based; Rule induction; Surveillance; Surveillance systems; Veterinary colleges; Veterinary medicine; Veterinary Science; Zoonoses
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0057334

Recent focus on earlier detection of pathogen introduction in human and animal populations has led to the development of surveillance systems based on automated monitoring of health data. Real- or near real-time monitoring of pre-diagnostic data requires automated classification of records into syndromes--syndromic surveillance--using algorithms that incorporate medical knowledge in a reliable and efficient way, while remaining comprehensible to end users. This paper describes the application of two of machine learning (Naïve Bayes and Decision Trees) and rule-based methods to extract syndromic information from laboratory test requests submitted to a veterinary diagnostic laboratory. High performance (F1-macro = 0.9995) was achieved through the use of a rule-based syndrome classifier, based on rule induction followed by manual modification during the construction phase, which also resulted in clear interpretability of the resulting classification process. An unmodified rule induction algorithm achieved an F(1-micro) score of 0.979 though this fell to 0.677 when performance for individual classes was averaged in an unweighted manner (F(1-macro)), due to the fact that the algorithm failed to learn 3 of the 16 classes from the training set. Decision Trees showed equal interpretability to the rule-based approaches, but achieved an F(1-micro) score of 0.923 (falling to 0.311 when classes are given equal weight). A Naïve Bayes classifier learned all classes and achieved high performance (F(1-micro)= 0.994 and F(1-macro) = .955), however the classification process is not transparent to the domain experts. The use of a manually customised rule set allowed for the development of a system for classification of laboratory tests into syndromic groups with very high performance, and high interpretability by the domain experts. Further research is required to develop internal validation rules in order to establish automated methods to update model rules without user input.