DICOM Metadata Analysis for Population Characterization: A Feasibility Study

Abstract

In clinical environments the information resulting from the provision of healthcare is increasingly used to improve the delivery of healthcare. In the radiology context, the data analysis used to characterize the population that accesses different radiology departments is often supported by software applications from different manufacturers, which makes data integration very difficult. And it makes very difficult to characterize, in a centralized manner, the studies performed on each patient. In this context, is there a way to perform population characterization and patient centered studies by analyzing the DICOM metadata stored on Picture Archiving and Communication Systems (PACS) from different healthcare facilities?This paper presents the results of population characterization with chest radiographic studies performed on Computed Radiography (CR) and Digital Radiography (DX) modalities in three healthcare facilities. It also identifies the studies conducted on the patient that, in each healthcare facility, in addition to chest radiographic studies, had a higher number of radiological studies involving ionizing radiation. The final sample consists of 95.433 images, corresponding to 89.980 studies belonging to 56.547 patients. The methodology used made it possible to characterize the population by age group, gender and modality, the average number of studies per patient in each age group, as well as the patient with the highest number of chest radiographic studies per modality in each of the healthcare facilities. The results clearly demonstrate the relevance of the use of DICOM metadata stored in disperse PACS archives for population characterization, as well as to identify resources utilization trends and situations that may represent patient radiation over-exposure.