Abstract: Acute hypotension is a significant risk factor for in-hospital mortality at intensive care units (ICUs). Prolonged hypotension can cause tissue hypoperfusion, leading to cellular dysfunction and severe injuries to multiple organs. Prompt medical interventions are thus extremely important for dealing with acute hypotensive episodes (AHE). This talk will tell you a pattern mining algorithm to extract informative sequential contrast patterns from hemodynamic data, for the prediction of hypotensive episodes. The hypotensive and normotensive patient groups are extracted from the MIMIC-II critical care research database. The proposed method consists of a data pre-processing step to convert the blood pressure time series into symbolic sequences, using a symbolic aggregate approximation algorithm. Then, distinguishing subsequences are identified using the sequential contrast mining algorithm. These subsequences are used to predict the occurrence of an AHE in a future time window separated by a user-defined gap interval.

Biography of the speaker: Associate Professor Li specialises in bioinformatics, computational biology, data mining, graph theory, information theory, machine learning and theoretical biology. He has published 70 journal articles and 65 conference papers of which many are highly cited. He is known for his theoretical research work on emerging patterns that has produced numerous follow-up research interests in data mining, machine learning, and bioinformatics. Current google citation for this paper is 960 times. Jinyan’s bachelor degree is obtained from National University of Defence Technology, Master degree from Hebei University of Technology, and PhD degree from the University of Melbourne.