The languages of health in general practice electronic patient records: a Zipf’s law analysis

• Published in: Journal of biomedical semantics Vol. 5; no. 1; p. 2
• Main Authors: Kalankesh, Leila R, New, John P, Baker, Patricia G, Brass, Andy
• Format: Journal Article
• Language: English
• Published: London BioMed Central 10.01.2014; BioMed Central Ltd; Springer Nature B.V
• Subjects: Algorithms; Analysis; Bioinformatics; Codes; Combinatorial Libraries; Communication; Computational Biology/Bioinformatics; Computational linguistics; Computer Appl. in Life Sciences; Computer applications; Data Mining and Knowledge Discovery; Information management; Language; Language processing; Languages; Laws, regulations and rules; Mathematics; Mathematics and Statistics; Medical coding; Medical law; Natural language interfaces; Power law; Rankings; Semantic Mining of Languages in Biology and Medicine; Words (language); Zipf's Law; United Kingdom > UK; Read Code; Computerise Patient Record System; British National Corpus; Electronic Patient Record; Electronic Patient Record System
• ISSN: 2041-1480; 2041-1480
• DOI: 10.1186/2041-1480-5-2

Background Natural human languages show a power law behaviour in which word frequency (in any large enough corpus) is inversely proportional to word rank - Zipf’s law. We have therefore asked whether similar power law behaviours could be seen in data from electronic patient records. Results In order to examine this question, anonymised data were obtained from all general practices in Salford covering a seven year period and captured in the form of Read codes. It was found that data for patient diagnoses and procedures followed Zipf’s law. However, the medication data behaved very differently, looking much more like a referential index. We also observed differences in the statistical behaviour of the language used to describe patient diagnosis as a function of an anonymised GP practice identifier. Conclusions This works demonstrate that data from electronic patient records does follow Zipf’s law. We also found significant differences in Zipf’s law behaviour in data from different GP practices. This suggests that computational linguistic techniques could become a useful additional tool to help understand and monitor the data quality of health records.