PMID- 19900575 OWN - NLM STAT- MEDLINE DCOM- 20100622 LR - 20211020 IS - 1532-0480 (Electronic) IS - 1532-0464 (Print) IS - 1532-0464 (Linking) VI - 43 IP - 2 DP - 2010 Apr TI - A data mining framework for time series estimation. PG - 190-9 LID - 10.1016/j.jbi.2009.11.002 [doi] AB - Time series estimation techniques are usually employed in biomedical research to derive variables less accessible from a set of related and more accessible variables. These techniques are traditionally built from systems modeling approaches including simulation, blind decovolution, and state estimation. In this work, we define target time series (TTS) and its related time series (RTS) as the output and input of a time series estimation process, respectively. We then propose a novel data mining framework for time series estimation when TTS and RTS represent different sets of observed variables from the same dynamic system. This is made possible by mining a database of instances of TTS, its simultaneously recorded RTS, and the input/output dynamic models between them. The key mining strategy is to formulate a mapping function for each TTS-RTS pair in the database that translates a feature vector extracted from RTS to the dissimilarity between true TTS and its estimate from the dynamic model associated with the same TTS-RTS pair. At run time, a feature vector is extracted from an inquiry RTS and supplied to the mapping function associated with each TTS-RTS pair to calculate a dissimilarity measure. An optimal TTS-RTS pair is then selected by analyzing these dissimilarity measures. The associated input/output model of the selected TTS-RTS pair is then used to simulate the TTS given the inquiry RTS as an input. An exemplary implementation was built to address a biomedical problem of noninvasive intracranial pressure assessment. The performance of the proposed method was superior to that of a simple training-free approach of finding the optimal TTS-RTS pair by a conventional similarity-based search on RTS features. CI - 2009 Elsevier Inc. All rights reserved. FAU - Hu, Xiao AU - Hu X AD - Neural Systems and Dynamics Lab, Department of Neurosurgery, Geffen School of Medicine at University of California, Los Angeles, CA 90095, USA. xhu@mednet.ucla.edu FAU - Xu, Peng AU - Xu P FAU - Wu, Shaozhi AU - Wu S FAU - Asgari, Shadnaz AU - Asgari S FAU - Bergsneider, Marvin AU - Bergsneider M LA - eng GR - R21 NS055045-02/NS/NINDS NIH HHS/United States GR - R01 NS054881-03/NS/NINDS NIH HHS/United States GR - R01-NS054881/NS/NINDS NIH HHS/United States GR - R21 NS059797-02/NS/NINDS NIH HHS/United States GR - R21 NS055998/NS/NINDS NIH HHS/United States GR - R21-NS055998/NS/NINDS NIH HHS/United States GR - R21-NS055045/NS/NINDS NIH HHS/United States GR - R21 NS055045/NS/NINDS NIH HHS/United States GR - R21 NS059797/NS/NINDS NIH HHS/United States GR - R21-NS059797/NS/NINDS NIH HHS/United States GR - R21 NS055998-02/NS/NINDS NIH HHS/United States GR - R01 NS054881/NS/NINDS NIH HHS/United States PT - Journal Article PT - Research Support, N.I.H., Extramural DEP - 20091110 PL - United States TA - J Biomed Inform JT - Journal of biomedical informatics JID - 100970413 SB - IM MH - Blood Pressure/physiology MH - Computer Simulation MH - Data Mining/*methods MH - Databases, Factual MH - Humans MH - Intracranial Pressure/physiology MH - *Models, Biological MH - Time Factors PMC - PMC2839011 MID - NIHMS158325 EDAT- 2009/11/11 06:00 MHDA- 2010/06/23 06:00 PMCR- 2011/04/01 CRDT- 2009/11/11 06:00 PHST- 2008/08/28 00:00 [received] PHST- 2009/10/13 00:00 [revised] PHST- 2009/11/02 00:00 [accepted] PHST- 2009/11/11 06:00 [entrez] PHST- 2009/11/11 06:00 [pubmed] PHST- 2010/06/23 06:00 [medline] PHST- 2011/04/01 00:00 [pmc-release] AID - S1532-0464(09)00148-8 [pii] AID - 10.1016/j.jbi.2009.11.002 [doi] PST - ppublish SO - J Biomed Inform. 2010 Apr;43(2):190-9. doi: 10.1016/j.jbi.2009.11.002. Epub 2009 Nov 10.