A linked data-based approach for clinical treatment selecting support

Abstract

Treatment plan selection is a complex process because it sometimes needs sufficient experience and clinical information. Nowadays it is even harder for doctors to select an appropriate treatment plan for certain patients since doctors might encounter difficulties in obtaining the right information and analyzing the diverse clinical data. In order to improve the effectiveness of clinical decision making in complicated information system environments, we first propose a linked data-based approach for treatment plan selection. The approach integrates the patients' clinical records in hospitals with open linked data sources out of hospitals. Then, based on the linked data net, treatment plan selection is carried on aided by similar historical therapy cases. Finally, we reorganize the electronic medical records of 97 colon cancer patients using the linked data model and count the similarity of these records to help treatment selecting. The experiment shows the usability of our method in supporting clinical decisions.

Keywords:

• linked data
• cancer treatment
• semantic web
• case-based reasoning
• clinical decision support

Notes

1. http://www.drugbank.ca/

2. http://dailymed.nlm.nih.gov/

3. http://www.ncbi.nlm.nih.gov/pubmed

4. http://www.drugbank.ca/

5. http://dailymed.nlm.nih.gov/

6. http://diseasome.eu/

Additional information

Funding

This work was supported by the National Natural Science Foundation of China, [grant number 71171132, 61373030].