RHPTree—Risk Hierarchical Pattern Tree for Scalable Long Pattern Mining

Risk patterns are crucial in biomedical research and have served as an important factor precision health disease prevention. Despite recent development parallel high-performance computing, existing risk pattern mining methods still struggle with problems caused by large-scale datasets, such redundant candidate generation, inability to discover long significant patterns, prolonged post filtering. In this article, we propose a novel dynamic tree structure, Hierarchical Pattern Tree (RHPTree), top-down search method, RHPSearch, which capable of efficiently analyzing large volume data overcoming the limitations previous works. The nature RHPTree avoids costly reconstruction for iterative process dataset updates. We also introduce two specialized methods, extended target (RHPSearch-TS) approach (RHPSearch-SD), further speed up retrieval certain items interest. Experiments on both UCI machine learning datasets sampled Simons Foundation Autism Research Initiative (SFARI)—Simon’s Simplex Collection (SSC) demonstrate that our method is not only faster but more effective identifying comprehensive than Moreover, proposed new structure generic applicable other problems.