Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Jun 12:2:e44191.
doi: 10.2196/44191.

Automated Identification of Aspirin-Exacerbated Respiratory Disease Using Natural Language Processing and Machine Learning: Algorithm Development and Evaluation Study

Thanai Pongdee  1 , Nicholas B Larson  2 , Rohit Divekar  1 , Suzette J Bielinski  3 , Hongfang Liu  4 , Sungrim Moon  4
Affiliations

Automated Identification of Aspirin-Exacerbated Respiratory Disease Using Natural Language Processing and Machine Learning: Algorithm Development and Evaluation Study

Thanai Pongdee et al. JMIR AI. .

Abstract

Background: Aspirin-exacerbated respiratory disease (AERD) is an acquired inflammatory condition characterized by the presence of asthma, chronic rhinosinusitis with nasal polyposis, and respiratory hypersensitivity reactions on ingestion of aspirin or other nonsteroidal anti-inflammatory drugs (NSAIDs). Despite AERD having a classic constellation of symptoms, the diagnosis is often overlooked, with an average of greater than 10 years between the onset of symptoms and diagnosis of AERD. Without a diagnosis, individuals will lack opportunities to receive effective treatments, such as aspirin desensitization or biologic medications.

Objective: Our aim was to develop a combined algorithm that integrates both natural language processing (NLP) and machine learning (ML) techniques to identify patients with AERD from an electronic health record (EHR).

Methods: A rule-based decision tree algorithm incorporating NLP-based features was developed using clinical documents from the EHR at Mayo Clinic. From clinical notes, using NLP techniques, 7 features were extracted that included the following: AERD, asthma, NSAID allergy, nasal polyps, chronic sinusitis, elevated urine leukotriene E4 level, and documented no-NSAID allergy. MedTagger was used to extract these 7 features from the unstructured clinical text given a set of keywords and patterns based on the chart review of 2 allergy and immunology experts for AERD. The status of each extracted feature was quantified by assigning the frequency of its occurrence in clinical documents per subject. We optimized the decision tree classifier's hyperparameters cutoff threshold on the training set to determine the representative feature combination to discriminate AERD. We then evaluated the resulting model on the test set.

Results: The AERD algorithm, which combines NLP and ML techniques, achieved an area under the receiver operating characteristic curve score, sensitivity, and specificity of 0.86 (95% CI 0.78-0.94), 80.00 (95% CI 70.82-87.33), and 88.00 (95% CI 79.98-93.64) for the test set, respectively.

Conclusions: We developed a promising AERD algorithm that needs further refinement to improve AERD diagnosis. Continued development of NLP and ML technologies has the potential to reduce diagnostic delays for AERD and improve the health of our patients.

Keywords: artificial intelligence; aspirin; aspirin exacerbated respiratory disease; asthma; electronic health record; identification; machine learning; natural language processing; natural language processing algorithm; respiratory illness.

PubMed Disclaimer

Conflict of interest statement

Conflicts of Interest: HL is the Associate Editor of JMIR AI. The other authors declare that they have no conflicts of interest.

Figures

Figure 1
Figure 1
Area under the receiver operating characteristic curve (AUC) scores at different threshold values on the training set.
Figure 2
Figure 2
Receiver operating characteristic (ROC) on the test set.
See this image and copyright information in PMC

References

    1. Haque R, White AA, Jackson DJ, Hopkins C. Clinical evaluation and diagnosis of aspirin-exacerbated respiratory disease. J Allergy Clin Immunol. 2021 Aug;148(2):283–291. doi: 10.1016/j.jaci.2021.06.018.S0091-6749(21)00975-1 - DOI - PubMed
    1. Szczeklik A, Nizankowska E, Duplaga M. Natural history of aspirin-induced asthma. AIANE Investigators. European Network on Aspirin-Induced Asthma. Eur Respir J. 2000 Sep;16(3):432–6. doi: 10.1034/j.1399-3003.2000.016003432.x. http://erj.ersjournals.com/cgi/pmidlookup?view=long&pmid=11028656 - DOI - PubMed
    1. Cahill KN, Johns CB, Cui J, Wickner P, Bates DW, Laidlaw TM, Beeler PE. Automated identification of an aspirin-exacerbated respiratory disease cohort. J Allergy Clin Immunol. 2017 Mar;139(3):819–825.e6. doi: 10.1016/j.jaci.2016.05.048. https://europepmc.org/abstract/MED/27567328 S0091-6749(16)30700-X - DOI - PMC - PubMed
    1. Berges-Gimeno MP, Simon RA, Stevenson DD. The natural history and clinical characteristics of aspirin-exacerbated respiratory disease. Ann Allergy Asthma Immunol. 2002 Nov;89(5):474–478. doi: 10.1016/s1081-1206(10)62084-4. - DOI - PubMed
    1. Stevens WW, Jerschow E, Baptist AP, Borish L, Bosso JV, Buchheit KM, Cahill KN, Campo P, Cho SH, Keswani A, Levy JM, Nanda A, Laidlaw TM, White AA. J Allergy Clin Immunol. 2021 Mar;147(3):827–844. doi: 10.1016/j.jaci.2020.10.043. https://europepmc.org/abstract/MED/33307116 S0091-6749(20)31708-5 - DOI - PMC - PubMed

LinkOut - more resources