Damped window based high average utility pattern mining over data streams.

•We suggest a novel algorithm of recent high average utility pattern mining based on the damped window model.•Novel data structures and pruning techniques are devised to prevent useless mining operations.•Various experiments are conducted with actual medical datasets composed of various attributes.•We show that the proposed algorithm has better performance in terms of runtime, memory, scalability and significant test.•We analyze significant medical patterns mined from actual medical dataset for showing the usefulness of our approach.