A genetic algorithm enabled ensemble for unsupervised medical term extraction from clinical letters

Abstract

Despite the rapid global movement towards electronic health records, clinical letters written in unstructured natural languages are still the preferred form of inter-practitioner communication about patients. These letters, when archived over a long period of time, provide invaluable longitudinal clinical details on individual and populations of patients. In this paper we present three unsupervised approaches, sequential pattern mining (PrefixSpan); frequency linguistic based C-Value; and keyphrase extraction from co-occurrence graphs (TextRank), to automatically extract single and multi-word medical terms without domain-specific knowledge. Because each of the three approaches focuses on different aspects of the language feature space, we propose a genetic algorithm to learn the best parameters of linearly integrating the three extractors for optimal performance against domain expert annotations. Around 30,000 clinical letters sent over the past decade from ophthalmology specialists to general practitioners at an eye clinic are anonymised as the corpus to evaluate the effectiveness of the ensemble against individual extractors. With minimal annotation, the ensemble achieves an average F-measure of 65.65 % when considering only complex medical terms, and a F-measure of 72.47 % if we take single word terms (i.e. unigrams) into consideration, markedly better than the three term extraction techniques when used alone.

Prediction of Effective Lens Position Using Multiobjective Evolutionary Algorithm

“…We used the nondominated sorting genetic algorithm (NSGA-II),25 which is well-known as an MOEA that shows stable performance in various applications 22–24. A detailed algorithm of NSGA-II has been reported 25.…”

“…However, to the best of our knowledge, research to minimize the prediction error of ELP has not been reported. Reports have indicated that EA is useful in solving optimization problems, including noise 21–24. In our study, which includes the measurement data of noise generated from the patient, examiner, measuring instruments, and condition, EA was considered to be a useful approach.…”

Approaches, tools, algorithms, and methods for automatic term extraction: A systematic literature mapping

“…Approaches, tools, algorithms, and methods for automatic term extraction: A systematic literature mapping 2015 Gaizauskas et al (2015), Khumalo (2015), Saneifar et al (2015), Gupta (2015), Pan and Zhao (2015), Kochetkova (2015), Lopes and Vieira (2015), Periñán-Pascual (2015), Gonçalves et al (2015), Guo et al (2015), Lahbib et al (2015), Astrakhantsev et al (2015), Bakar et al (2015), Liu et al (2015) 12,39% 2016…”

“…Gemkow et al (2018) use NLTK to perform tokenization, Part-of-Speech Tagging (POST), chunking, and lemmatization. NLTK is also used in other proposals such as Gaizauskas et al (2015), Kochetkova (2015), Bakar et al (2015), Liu et al (2015), Yu et al (2017), Giannakopoulos et al (2017) and Mykowiecka et al (2018). Its versatility for the construction of terminology extractors is highlighted.…”

Evaluation of a Novel Syndromic Surveillance Query for Heat-Related Illness Using Hospital Data From Maricopa County, Arizona, 2015

“…Indeed, research in the field of bioinformatics has demonstrated that the use of machine learning algorithms, natural-language processing, and logistic regression, alone or in combination with free text search, can increase query sensitivity and specificity >90%. [38][39][40][41] Public health agencies could explore the long-term use of these tools and strategies in syndromic surveillance as a way to save time and conserve labor resources. 42,43…”