What is the presentation and service utilisation of childhood respiratory illness in primary care?
Respiratory illness is a major global contributor to childhood morbidity. Accurate assessment of illness presentation and health service utilisation is important for planning and clinical management. Very few large datasets exist which describe community respiratory illness burden. Information could be obtained by analysing consultation notes within electronic medical records but this is prevented by difficulties extracting and analysing available structured and unstructured data.
A natural language processing software inference algorithm was developed to interrogate quantitative and qualitative cross-sectional and retrospective cohort data from computerised medical records. The records from 77,582 children enrolled in 36 New Zealand primary care practices were reviewed over a six-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.
Respiratory conditions constituted the greatest proportion of all child-GP consultations with a remarkably stable year on year pattern of seasonal peaks. The methodology enabled accurate categorization, prevalence and service utilization of the major childhood respiratory conditions; Upper Respiratory Tract Infection , otitis media, wheeze-related illness, throat infection and Lower Respiratory Tract Infection.
A software inference algorithm that uses primary care Big Data was able to accurately classify the content of clinical consultations and the prevalence of childhood respiratory illness in primary care and resultant service utilisation. The study identified the very high primary care workload related to childhood respiratory illness, especially during the first two years of life. These data can enable more effective planning of primary care service delivery and indicate areas in which to focus preventive programmes. The findings and methodology have relevance to many OECD countries, and the use of primary care ‘big data’ applied to other health conditions.