Castro‐Rodríguez, José A.

Introduction The lack of effective, consistent, reproducible and efficient asthma ascertainment methods results in inconsistent asthma cohorts and study results for clinical trials or other studies. We aimed to assess whether application of expert artificial intelligence (AI)-based natural language processing (NLP) algorithms for two existing asthma criteria to electronic health records of a paediatric population systematically identifies childhood asthma and its subgroups with distinctive characteristics. Methods Using the 1997–2007 Olmsted County Birth Cohort, we applied validated NLP algorithms for Predetermined Asthma Criteria (NLP-PAC) as well as Asthma Predictive Index (NLP-API). We categorised subjects into four groups (both criteria positive (NLP-PAC+/NLP-API+); PAC positive only (NLP-PAC+ only); API positive only (NLP-API+ only); and both criteria negative (NLP-PAC−/NLP-API−)) and characterised them. Results were replicated in unsupervised cluster analysis for asthmatics and a random sample of 300 children using laboratory and pulmonary function tests (PFTs). Results Of the 8196 subjects (51% male, 80% white), we identified 1614 (20%), NLP-PAC+/NLP-API+; 954 (12%), NLP-PAC+ only; 105 (1%), NLP-API+ only; and 5523 (67%), NLP-PAC−/NLP-API−. Asthmatic children classified as NLP-PAC+/NLP-API+ showed earlier onset asthma, more Th2-high profile, poorer lung function, higher asthma exacerbation and higher risk of asthma-associated comorbidities compared with other groups. These results were consistent with those based on unsupervised cluster analysis and lab and PFT data of a random sample of study subjects. Conclusion Expert AI-based NLP algorithms for two asthma criteria systematically identify childhood asthma with distinctive characteristics. This approach may improve precision, reproducibility, consistency and efficiency of large-scale clinical studies for asthma and enable population management.

AbstractBackgroundFrequent wheezing in original asthma predictive index (API) was defined by parental report of recurrent wheezing within 1 year during the first 3 years of life. The nature of frequent wheezing in children, particularly aged over 3 years, has not been studied. We aimed to assess the frequency and interval of wheezing to define frequent wheezing in ascertaining asthma for children using medical records.MethodsAmong children who participated in a previous study (n = 427), all wheezing episodes documented in medical records were collected for children who had ≥2 wheezing episodes PLUS met one major criterion or two minor criteria of API. We compared the distribution of known risk factors for asthma between subjects having two consecutive wheezing episodes with shorter interval (≤1 year) compared to those with longer interval (1 to 3 years).ResultsA total of 62 children met API at median age of 2.3 years. During follow‐up period (median age: 11.3 years), a total of 198 wheezing episodes were observed. 81% of wheezing intervals were within 3 years from the earlier wheezing episode, including 60% within 1 year. Children who met API based on 1‐year interval (n = 40) vs 1‐ to 3‐year interval (n = 13) appeared to be similar in regard to the known risk factors for asthma.ConclusionsOur exploratory study finding suggests that children who had frequent wheezing episodes with longer interval (<3 years) need to be considered to be determined as asthma cases when API is applied to retrospective medical records. Prospective studies with a larger sample size need to replicate this finding.