OBJECTIVES: The purpose of this study was to develop clinical decision support systems (CDSS) that are integrated with hospital information systems for the differential diagnosis of idiopathic pulmonary fibrosis (IPF). METHODS: The integrated CDSS were validated and evaluated by physicians. Knowledge modeling for diagnosing IPF was performed by knowledge working groups, composed of radiologists and respiratory specialists. In order to develop the model for CDSS diagnosis, the clinical cases were collected from 290 cases from Seoul National University Hospital and Sevrance Hospital of Yonsei University. For the evaluation of integrated CDSS, interviews were conducted with respiratory specialists and radiologist 2 weeks after applying CDSSs in clinical settings. The CDSS was integrated with the computer vision system (CVS) and diffuse parenchymal lung diseases (DPLD), CDSS developed in our previous project. RESULTS: Eighteen cases diagnosed as IPF were applied to the collection of diagnostic knowledge and the refined knowledge, the former diagnosed 1 case (6%) and the latter diagnosed 14 cases (78%). Therefore, the refined knowledge performed better than collected knowledge. The validation results of integrated CDSSs showed that 81 cases (74.3%) were diagnosed correctly. CONCLUSIONS: There were 109 cases of IPF diagnosed and initiated on treatment. The significance of this study is in developing integrated CDSS with PACS by acquiring and redefining the knowledge needed for IPF diagnosis. In addition, it is significant for the integration of CDSS to verification and clinical evaluation.
Decision Support Systems, Clinical ; Diagnosis, Differential ; Hospital Information Systems ; Idiopathic Pulmonary Fibrosis ; Lung Diseases, Interstitial ; Machine Learning ; Pulmonary Fibrosis ; Radiology Information Systems ; Specialization

Background: We evaluated the achievement of low-density lipoprotein cholesterol (LDL-C) targets in patients with type 2 diabetes mellitus (T2DM) according to up-to-date Korean Diabetes Association (KDA), European Society of Cardiology (ESC)/European Atherosclerosis Society (EAS), and American Diabetes Association (ADA) guidelines. Methods: This retrospective cohort study collected electronic medical record data from patients with T2DM (≥20 years) managed by endocrinologists from 15 hospitals in Korea (January to December 2019). Patients were categorized according to guidelines to assess LDL-C target achievement. KDA (2019): Very High-I (atherosclerotic cardiovascular disease [ASCVD]) <70 mg/dL; Very High-II (target organ damage [TOD], or cardiovascular risk factors [CVRFs]) <70 mg/dL; high (others) <100 mg/dL. ESC/EAS (2019): Very High-I (ASCVD): <55 mg/dL; Very High-II (TOD or ≥3-CVRF) <55 mg/dL; high (diabetes ≥10 years without TOD plus any CVRF) <70 mg/dL; moderate (diabetes <10 years without CVRF) <100 mg/dL. ADA (2019): Very High-I (ASCVD); Very High-II (age ≥40+ TOD, or any CVRF), for high intensity statin or statin combined with ezetimibe. Results: Among 2,000 T2DM patients (mean age 62.6 years; male 55.9%; mean glycosylated hemoglobin 7.2%) ASCVD prevalence was 24.7%. Of 1,455 (72.8%) patients treated with statins, 73.9% received monotherapy. According to KDA guidelines, LDL-C target achievement rates were 55.2% in Very High-I and 34.9% in Very High-II patients. With ESC/EAS guidelines, target attainment rates were 26.6% in Very High-I, 15.7% in Very High-II, and 25.9% in high risk patients. Based on ADA guidelines, most patients (78.9%) were very-high risk; however, only 15.5% received high-intensity statin or combination therapy. Conclusion According to current dyslipidemia management guidelines, LDL-C goal achievement remains suboptimal in Korean patients with T2DM.