Clinical Laboratory Test Reports

This dataset includes 260 clinical laboratory test reports issued by 24 laboratories in Egypt. It is used as a part of a laboratory test data extraction research. The research is concerned with tagging unstructured and semi-structured heterogeneous lab test data for future unification. The body of all reports is in English; however, headers and footers are in both English and Arabic languages.

The dataset includes pdf-to-image, scanner-scanned, and mobile-scanned lab test reports. Some of the issuers are Alfa Laboratories, Alborg Labs, Almokhtabar Laboratories, Royal Lab, Alshams Labs, Labmed Egypt, Mabaret Elasafra Laboratories, Grand Lab, Green Lab, Omega Labs, and Nasr City Hospital. Many of the reports are issued by different branches. In addition, some of the laboratories exist in governorates such as Cairo, Giza, Alexandria, and Red Sea.

This data was collected from volunteers with full authorization for the researcher to allow conducting data extraction research. This dataset is split into two parts. Firstly, the first part is training lab test reports that are used to extract test patterns to generate training data. Secondly, the other part is used for testing and evaluation of named-entity recognition models.