Title :
A System for Mining Temporal Physiological Data Streams for Advanced Prognostic Decision Support
Author :
Sun, Jimeng ; Sow, Daby ; Hu, Jianying ; Ebadollahi, Shahram
Author_Institution :
T.J. Watson Res. Center, IBM, Hawthorne, NY, USA
Abstract :
We present a mining system that can predict the future health status of the patient using the temporal trajectories of health status of a set of similar patients. The main novelties of this system are its use of stream processing technology for handling the incoming physiological time series data and incorporating domain knowledge in learning the similarity metric between patients represented by their temporal data. The proposed approach and system were tested using the MIMIC II database, which consists of physiological waveforms, and accompanying clinical data obtained for ICU patients. The study was carried out on 1500 patients from this database. In the experiments we report the efficiency and throughput of the stream processing unit for feature extraction, the effectiveness of the supervised similarity measure both in the context of classification and retrieval tasks compared to unsupervised approaches, and the accuracy of the temporal projections of the patient data.
Keywords :
data mining; feature extraction; information retrieval; learning (artificial intelligence); medical administrative data processing; patient monitoring; time series; ICU patient; MIMIC II database; advanced prognostic decision support; classification task; clinical data; feature extraction; patient health status; physiological time series data; retrieval task; supervised similarity measure; temporal physiological data stream mining; Patient similarity; Physiological streams;
Conference_Titel :
Data Mining (ICDM), 2010 IEEE 10th International Conference on
Conference_Location :
Sydney, NSW
Print_ISBN :
978-1-4244-9131-5
Electronic_ISBN :
1550-4786
DOI :
10.1109/ICDM.2010.102
