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

Abstract

BackgroundNatural 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.ResultsIn 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.ConclusionsThis 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.

Paediatric terminology in the Australian health and health‐education context: a systematic review

“…This was less skewed than typical 80/20 Pareto distributions, which may highlight the interchangeable use of terms. The low type–token ratio in this study suggested an appropriate sample for language analysis . Similar data sets from electronic health records used by general practitioners in England have viewed terms as a language distribution .…”

“…The low type–token ratio in this study suggested an appropriate sample for language analysis . Similar data sets from electronic health records used by general practitioners in England have viewed terms as a language distribution . Language distributions can assist in selecting paediatric terms to develop standard paediatric terminology when used in combination with an age definition.…”

“…The low type-token ratio in this study suggested an appropriate sample for language analysis. 33 Similar data sets from electronic health records used by general practitioners in…”

“…Power‐law distributions were used to summarize the frequency of specific paediatric terminology identified within the Australian health and health‐education context. The type–token ratio was calculated as an index of lexical diversity by dividing the number of unique terms (type) by the total number of terms (token) . Kalankesh et al .…”

“…England have viewed terms as a language distribution. 33,41 Language distributions can assist in selecting paediatric terms to develop standard paediatric terminology when used in combination with an age definition. Age ranges did not explicitly demarcate a third of the paediatric definitions found in this study.…”