Childhood respiratory illness presentation and service utilisation in primary care: a six-year cohort study in Wellington, New Zealand, using natural language processing (NLP) software

Abstract

ObjectivesTo identify childhood respiratory tract-related illness presentation rates and service utilisation in primary care by interrogating free text and coded data from electronic medical records.DesignRetrospective cohort study. Data interrogation used a natural language processing software inference algorithm.Setting36 primary care practices in New Zealand. Data analysed from January 2008 to December 2013.ParticipantsThe records from 77 582 children enrolled were reviewed over a 6-year period to estimate the presentation of childhood respiratory illness and service utilisation. This cohort represents 268 919 person-years of data and over 650 000 unique consultations.Main outcome measureChildhood respiratory illness presentation rate to primary care practice, with description of seasonal and yearly variation.ResultsRespiratory conditions constituted 46% of all child-general practitioner consultations with a stable year-on-year pattern of seasonal peaks. Upper respiratory tract infection was the most common respiratory category accounting for 21.0% of all childhood consultations, followed by otitis media (12.2%), wheeze-related illness (9.7%), throat infection (7.4%) and lower respiratory tract infection (4.4%). Almost 70% of children presented to their general practitioner with at least one respiratory condition in their first year of life; this reduced to approximately 25% for children aged 10–17.ConclusionThis is the first study to assess the primary care incidence and service utilisation of childhood respiratory illness in a large primary care cohort by interrogating electronic medical record free text. The study identified the very high primary care workload related to childhood respiratory illness, especially during the first 2 years of life. These data can enable more effective planning of health service delivery. The findings and methodology have relevance to many countries, and the use of primary care ‘big data’ in this way can be applied to other health conditions.

Health service utilization following symptomatic respiratory tract infections and influencing factors among urban and rural residents in Anhui, China

“…The finding that RTIs are very prevalent and a large proportion of infection episodes leads to health service use is consistent with research across various countries (Yawson et al, 2012;Gounder et al, 2017;Dowell et al, 2017). However, the implications of these findings for clinical practice and policy-making have yet to be fully explored.…”

Damp mouldy housing and early childhood hospital admissions for acute respiratory infection: a case control study

“…The mean DMI was 1.61 for the healthy control group and 1.60 for the mild ARI control group. Given both the high incidence of ARI in the general population and the high rate of attendance at primary care for such events (ie, almost 70% of children presenting to their GP with at least one respiratory condition in their first year of life), we considered the pooling of these two control groups to be valid 4. It should be noted that ARI accounts for around half of GP consultations in preschool-aged children,3 4 so the group of controls with mild ARI will not be too dissimilar from the general population.…”

“…ARIs are a leading cause of avoidable hospitalisation and account for 50% of general practitioner (GP) consultations in preschool-aged children 3. Upper respiratory tract infections (URTI) are the most common, accounting for 21% of all GP consultations in New Zealand,4 but ARI also includes important lower respiratory tract infections (LRTIs), including bronchiolitis, bronchitis and bronchopneumonia. In 2015, in the Wellington region of New Zealand, there were 9003 children under 2 years old hospitalised for ARI out of an estimated population of 118 580, a rate per population of 7.6%.…”

Natural language processing for disease phenotyping in UK primary care records for research: a pilot study in myocardial infarction and death

“…NLP has been applied to primary care records in other countries for research studies attempting early diagnosis of multiple sclerosis [27], classification of childhood respiratory illnesses [28, 29] and identification of heart failure symptoms [30]. However, NLP of primary care notes can be challenging – the language is terse, often ungrammatical and abbreviated [17].…”