โก Quick Summary
A novel natural language processing (NLP) algorithm has been developed to automatically ascertain adult asthma status from electronic health records (EHRs). This breakthrough tool demonstrates high sensitivity (92%) and specificity (99%), paving the way for improved asthma management in adults.
๐ Key Details
- ๐ Cohort Size: 1,898 adult subjects
- ๐งฉ Gender Distribution: 43% male
- โ๏ธ Technology Used: NLP-PAC algorithm
- ๐ Performance Metrics: Sensitivity 92%, Specificity 99%
- ๐ EHR System: Epic, implemented in 2018
๐ Key Takeaways
- ๐ NLP-PAC successfully identifies asthma in adults using EHR data.
- ๐ก High sensitivity and specificity make it a reliable tool for asthma ascertainment.
- ๐ฉโ๐ฌ Manual chart review and NLP-PAC identified similar asthma cases.
- ๐ฅ Feasibility of automatic asthma ascertainment is confirmed.
- ๐ Implications for large-scale clinical research and population management.
- ๐ Consistency in performance metrics before and after EHR system implementation.
- ๐ Reference Standard: Manual chart review used as a benchmark.
๐ Background
Asthma is a prevalent chronic condition that significantly impacts the quality of life for many adults. Traditional methods of asthma ascertainment often rely on manual chart reviews, which can be time-consuming and prone to human error. The integration of natural language processing into EHR systems offers a promising solution to streamline this process, enabling quicker and more accurate identification of asthma cases.
๐๏ธ Study
The study aimed to validate the NLP-PAC algorithm for ascertaining adult asthma status from EHRs. Researchers applied this algorithm to a cohort of 1,898 adults who had previously participated in population-based studies, using manual chart reviews as a reference standard for asthma status.
๐ Results
The results showed that both manual chart review and NLP-PAC identified a similar number of asthma cases, with 97 and 98 subjects respectively. The algorithm demonstrated impressive performance metrics, with a sensitivity of 92% and specificity of 99% before the implementation of the new EHR system, which remained robust after the transition.
๐ Impact and Implications
The successful application of the NLP-PAC algorithm signifies a major advancement in asthma management for adults. By automating the ascertainment process, healthcare providers can enhance their ability to identify and manage asthma cases effectively. This innovation not only streamlines clinical workflows but also holds the potential for significant improvements in patient outcomes and population health management.
๐ฎ Conclusion
The validation of the NLP-PAC algorithm marks a significant step forward in the use of technology for asthma ascertainment in adults. With its high sensitivity and specificity, this tool can transform how asthma is identified and managed in clinical settings. Continued research and development in this area could lead to even more sophisticated applications of NLP in healthcare, ultimately benefiting patient care.
๐ฌ Your comments
What are your thoughts on the use of NLP in healthcare, particularly for asthma management? We would love to hear your insights! ๐ฌ Share your comments below or connect with us on social media:
Application of a natural language processing algorithm to early asthma ascertainment for adults in the era of electronic health records.
Abstract
BACKGROUND: The natural language processing (NLP) algorithm for predetermined asthma criteria (NLP-PAC) was successfully developed and validated for automatically ascertaining pediatric asthma from electronic health record (EHRs) systems. A scalable, efficient, and automated tool for ascertaining adult asthma status from EHRs remains nonexistent.
OBJECTIVE: We validated NLP-PAC enabling ascertainment and early identification of adult asthma status in their EHRs.
METHODS: We applied the validated NLP-PAC to EHRs of a convenient sample (adult cohorts who participated in our previous population-based studies) in which a reference standard (ie, asthma status defined by manual chart review) is available. The performance of NLP-PAC was assessed by determining criterion validity against manual chart review and construct validity before and after the new EHR (Epic) system was implemented in 2018.
RESULTS: The cohort consisted of 1,898 subjects, with 43% male and a median age at time of last follow-up of 65 years (interquartile range, 55-76). Manual chart review and NLP-PAC identified 97 (5.1%) and 98 (5.1%) subjects with asthma, respectively, with 89 subjects commonly identified by both methods. The sensitivity, specificity, positive predictive value, and negative predictive value of NLP-PAC were 92%, 99%, 91%, and 99%, respectively, before the new EHR system was implement, which remained similar after introducing the system (95%, 88%, 96%, and 85%, respectively). The risk factors for asthma identified either by NLP-PAC or manual chart review were similar.
CONCLUSION: Automatic asthma ascertainment for adults based on EHR data is feasible with our NLP algorithm, offering immense scientific and clinical value for large-scale clinical research and population management for adult asthma care.
Author: [‘Wi CI’, ‘Pongdee T’, ‘Seol HY’, ‘Sohn S’, ‘Sagheb E’, ‘Agnikula Kshatriya BS’, ‘Overgaard SM’, ‘Sharma DK’, ‘Moon S’, ‘Krusemark EA’, ‘Watson D’, ‘Chiarella SE’, ‘Park MA’, ‘Greenwood JD’, ‘Foss RM’, ‘Liu Z’, ‘Gupta M’, ‘Davis CM’, ‘Schulz W’, ‘Liu H’, ‘Juhn YJ’]
Journal: J Allergy Clin Immunol Glob
Citation: Wi CI, et al. Application of a natural language processing algorithm to early asthma ascertainment for adults in the era of electronic health records. Application of a natural language processing algorithm to early asthma ascertainment for adults in the era of electronic health records. 2026; 5:100618. doi: 10.1016/j.jacig.2025.100618