The study aim is to optimize the Kaiser Permanente Northern California (KPNC) Interstitial Lung Disease (ILD) algorithm and establish the KPNC-ILD cohort. The KPNC-ILD cohort will consist of approximately 10,000 patients with ILD. It will be built through electronic health record-based case identification using an algorithm. We will optimize the existing algorithm and have a fully operational case identification process to build the cohort. The algorithm will be useful to clinical researchers worldwide who are interested in using large, electronic health record-based datasets to identify ILD cohorts.