Abstract
Background: FHIR (Fast Healthcare Interoperability Resources) has been proposed to enable health data interoperability. So far, its applicability has been demonstrated for selected research projects with limited data. Here, we designed and implemented a conceptual medical intelligence framework to leverage real-world care data for clinical decision-making.Methods: A Python package for the utilization of multimodal FHIR data was developed and pioneered in five real-world clinical use cases, i.e., myocardial infarction (MI), stroke, diabetes, sepsis, and prostate cancer (PC). Patients were identified based on ICD-10 codes, and outcomes were derived from laboratory tests, prescriptions, procedures, and diagnostic reports. Results were provided as browser-based dashboards.Findings: For 2022, 1,303,687 patient encounters were analyzed. MI: In 72.7% of cases (N=261) medication regimens fulfilled guideline recommendations. Stroke: Out of 1,277 patients, 165 patients received thrombolysis and 108 thrombectomy. Diabetes: In 443,866 serum glucose and 16,180 HbA1c measurements from 35,494 unique patients, the prevalence of dysglycemic findings was 39% (N=13,887). Among those with dysglycemia, diagnosis was coded in 44.2% (N=6,138) of the patients. Sepsis: In 1,803 patients, Staphylococcus epidermidis was the primarily isolated pathogen (n=773, 28.9%) and piperacillin/tazobactam was the primarily prescribed antibiotic (n=593, 36%). PC: Three out of 54 patients who received radical prostatectomy were identified as cases with PSA persistence or biochemical recurrence.Interpretation: Leveraging FHIR data through large-scale analytics can enhance healthcare quality and improve patient outcomes across five clinical specialties. We identified i) sepsis patients requiring less broad antibiotic therapy, ii) patients with myocardial infarction who could benefit from statin and antiplatelet therapy, iii) stroke patients with longer than recommended times to intervention, iv) patients with hyperglycemia who could benefit from specialist referral and v) PC patients with early increases in cancer markers.Funding: Dr, C.M. Sauer is supported by the German Research Foundation funded UMEA Clinician Scientist Program, grant number FU356/12-2. J. Salazar is supported by the Helmholtz Association under the joint research school “HIDSS4Health Helmholtz Information and Data Science School for Health” Prof. T. Brenner received research funding from the German Research Foundation (DFG), Dietmar Hopp Stiftung, Stiftung Universitätsmedizin Essen, Heidelberger Stiftung Chirurgie, and Innovationsfonds des Gemeinsamen Bundesausschusses (G-BA)). This project received funding from the Cancer Research Center Cologne Essen, the Helmholtz Information & Data Science School for Health, and KI Translation Essen (EFRE).Declaration of Interest: I declare no competing interests.Ethical Approval: This study was carried out in accordance with the Declaration of Helsinki and was approved by the Ethics Committee of the Medical Faculty of the University Duisburg-Essen (No. 22- 10881-BO).
Alexander Brehmer
PhD Student
Julius Keyl
Medical Doctor
Boris Hadaschik
Chair Departement of Urology
Ken Herrmann
Chair Department of Nuclear Medicine
Michael Gertz
Head Database Systems Research
Jan Egger
Team Lead AI-guided Therapies
