Using FHIR to Improve Clinical Management
Author Information
Author(s): Xie Feng, Asuzu Chidi, Chu Yuanchia, Nolen Kim, Hidki Asmaa, Brehmer Alexander, Sauer Christopher Martin, Salazar Rodríguez Jayson, Herrmann Kelsey, Kim Moon, Keyl Julius, Bahnsen Fin Hendrik, Frank Benedikt, Köhrmann Martin, Rassaf Tienush, Mahabadi Amir-Abbas, Hadaschik Boris, Darr Christopher, Herrmann Ken, Tan Susanne, Buer Jan, Brenner Thorsten, Reinhardt Hans Christian, Nensa Felix, Gertz Michael, Egger Jan, Kleesiek Jens
Primary Institution: University Hospital Essen
Hypothesis
This study aimed to design and implement a conceptual medical intelligence framework to leverage real-world care data for clinical decision-making.
Conclusion
Leveraging FHIR data through large-scale analytics can enhance health care quality and improve patient outcomes across five clinical specialties.
Supporting Evidence
- In 72.7% of myocardial infarction cases, medication regimens fulfilled guideline recommendations.
- 86.7% of patients treated with thrombolysis received therapy within the recommended time window.
- 39% of patients were identified as having dysglycemia based on serum glucose and HbA1c measurements.
- 28.9% of sepsis patients had Staphylococcus epidermidis as the primarily isolated pathogen.
- 3 patients out of 54 treated with radical prostatectomy showed PSA persistence or biochemical recurrence.
Takeaway
The study shows that using a special data system can help doctors make better decisions for patients by analyzing a lot of health information.
Methodology
A Python package for multimodal FHIR data was developed and tested in five clinical use cases, analyzing patient encounters based on ICD-10 codes.
Limitations
The study relies on the quality of data entered into primary systems, which can be incomplete or incorrect.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website