Using Semantic Web Technologies to Reproduce a Pharmacovigilance Case Study
1. Using Semantic Web Technologies
to Reproduce
a Pharmacovigilance Case Study
a Pharmacovigilance Case Study
a Pharmacovigilance Case Study
Michiel Hildebrand, Rinke Hoekstra & Jacco van Ossenbruggen
4. pharmacovigilance
detect side effects of drugs: disproportional correlation
between a drug and an associated adverse event
prov:Entity
prov:Activity
prov:Entity
8. 3.525
+1
23,865,029
+1,847,073
all drug names were unified into generic names by a
text-mining approach. Spelling errors were detected by
GNU Aspell and carefully confirmed by working
pharmacists.
?
debugging requires intermediate datasets
debugging requires intermediate datasets
1,664,078
Foods beverages, treatments (e.g. X-ray
radiation), and unspecified names (e.g.
beta-blockers) were omitted
-142
2,231,038
+9
reproduction
12. PROV helps to communicate
PROV helps to communicate
>> share your provenance graph
>> share your provenance graph
debugging requires intermediate datasets
debugging requires intermediate datasets
>> share each prov:Entity
>> share each prov:Entity
computation is never trivial
computation is never trivial
(applies also to “preprocessing” & “well known” formula’s)
(applies also to “preprocessing” & “well known” formula’s)
>> share each computational prov:Activity
>> share each computational prov:Activity