Section: New Results

Discriminant chronicles mining: Application to care pathways analytics

Participants : Yann Dauxais, Thomas Guyet, David Gross-Amblard [Druid] , André Happe [Brest University Hospital/REPERES] .

Pharmaco-epidemiology (PE) is the study of uses and effects of drugs in well defined populations. As medico-administrative databases cover a large part of the population, they have become very interesting to carry PE studies. Such databases provide longitudinal care pathways in real condition containing timestamped care events, especially drug deliveries. Temporal pattern mining becomes a strategic choice to gain valuable insights about drug uses. We propose DCM [8], [7], a new discriminant temporal pattern mining algorithm. It extracts chronicle patterns that occur more in a studied population than in a control population. We present satisfactory results on the identification of possible associations between hospitalizations for seizure and anti-epileptic drug switches in care pathway of epileptic patients.

A stable release of the DCM algorithm (see Section 6.5) have been deposed to the Program Protection Agency (APP) and is available online.