Drug Exposure Side Effects from Mining Pregnancy Data1

1
Drug Exposure Side Effects from Mining Pregnancy
Data1

• Difficulties in finding side effects
• Small number of patients suffer side effect
• Sensitive to the drug exposure time
• Exposure to sequence of multiple drugs

• Statistical analysis
• Infeasible to test all potential hypotheses for
  large number of attributes
• Testing hypotheses with small sample size has
  limited statistical power

• Data mining
• No hypothesis, mine associa-tion in large dataset
  with multiple temporal attributes
• Can generate association rules independent of the
  sample size
• Derive rules with temporal information of drug
  exposure

2
Discover Side Effects from MFI Data Mining

• Hierarchically organize rules into trees
• View general rules and then extend to specific
  rules
• Use spreadsheet to present the rule trees
• Easy to sort, filter or extend the rule trees to
  search for the interesting rules

3
New Findings

• Based on the large-scale Danish National Birth
  Cohort (DNBC) dataset
• Finding combined exposure to citalopram and
  alcohol in pregnancy is associated with an
  increased risk of preterm birth
• Not initially discovered by epidemiology study
  due to the large number of combinations among all
  the attributes and their values

1Yu Chen, Lars Henning Pedersen, Wesley W. Chu
and Jorn Olsen. "Drug Exposure Side Effects from
Mining Pregnancy Data" In SIGKDD Explorations
(Volume 9, Issue 1), Special Issue on Data Mining
for Health Informatics, June 2007