New Open-source Software To Remove ID From Patient Reports
- Date:
- March 6, 2006
- Source:
- BioMed Central
- Summary:
- Researchers have developed a new reliable open-source software to remove identifiers from patient reports. In a study published today in the open access journal BMC Medical Informatics and Decision Making, researchers report on a new open-source computer programme able to remove 98.3 percent of all identifiers from 1254 pathology reports processed. This programme provides a basis for others to develop customized tools specific to report types or institutional styles.
- Share:
Researchers have developed new reliable open-source software to remove identifiers from patient reports. In a study published today in the open access journal BMC Medical Informatics and Decision Making, researchers report on a new open-source computer programme able to remove 98.3% of all identifiers from 1254 pathology reports processed. This programme provides a basis for others to develop customized tools specific to report types or institutional styles.
Bruce Beckwith from Beth Israel Deaconess Medical Center, Boston, USA and colleagues from other institutions in the USA designed a programme, or 'scrubber', to remove all identifiers from pathology reports. Nineteen different types of identifiers, including name, address and social security number may be found in pathology reports. The authors implemented the programme in three hospitals and processed a total of 1800 individual pathology reports, 1254 of which had unique identifiers, in XML format. The files were then checked manually.
Beckwith et al.'s results show that 98.3% of the 3499 unique identifiers in the pathology reports scanned were correctly removed. Only 19 of them were missed. The performance varied from 94.7% to 99% between the three hospitals and the authors conclude that hospital-specific customization might be needed to obtain the best performance.
Article: "Development and evaluation of an open source software tool for deidentification of pathology reports." Bruce A Beckwith, Rajeshwarri Mahaadevan, Ulysses J Balis and Frank Kuo. BMC Medical Informatics and Decision Making (in press)
Story Source:
Materials provided by BioMed Central. Note: Content may be edited for style and length.
Cite This Page: