Algorithms Identifying Patients With Acute Exacerbation of Interstitial Pneumonia and Acute Interstitial Lung...

Area of Science:

• Pulmonary Medicine
• Health Informatics
• Data Science

Background:

• Japanese administrative data presents a valuable resource for studying interstitial lung diseases.
• Accurate identification of patients with acute exacerbation of interstitial pneumonia (AEIP) and acute interstitial lung diseases (AILD) is crucial for research.

Purpose of the Study:

• To develop and validate algorithms for identifying patients with AEIP and AILD using Japanese administrative data.
• To assess the accuracy of these algorithms through positive predictive value calculations.

Main Methods:

• A single-center validation study was conducted.
• Algorithms were developed based on claims data for patients admitted between January 2016 and December 2021.
• Diagnoses were confirmed by expert review, and positive predictive values were calculated.

Main Results:

• Algorithms for AEIP and AILD demonstrated high positive predictive values (0.82 and 0.82, respectively).
• Combined algorithms for AEIP or AILD also showed high accuracy (PPV: 0.89).
• Alternative algorithms offered a balance between predictive value and capturing more true positive cases.

Conclusions:

• Developed algorithms possess high positive predictive value for identifying AEIP and AILD patients.
• These algorithms are suitable for future large-scale database studies utilizing Japanese administrative data.