MARC 主機 00000nam  2200409   4500 
001    AAI3457618 
005    20121203122719.5 
008    121203s2011    ||||||||||||||||| ||eng d 
020    9781124683812 
035    (UMI)AAI3457618 
040    UMI|cUMI 
100 1  Lee, Noah 
245 10 Synergizing human-machine intelligence: Visualizing, 
       labeling, and mining the electronic health record 
300    180 p 
500    Source: Dissertation Abstracts International, Volume: 72-
       08, Section: B, page: 4792 
500    Adviser: Andrew F. Laine 
502    Thesis (Ph.D.)--Columbia University, 2011 
520    We live in a world where data surround us in every aspect 
       of our lives. The key challenge for humans and machines is
       how we can make better use of such data. Imagine what 
       would happen if you were to have intelligent machines that
       could give you insight into the data. Insight that will 
       enable you to better 1) reason about, 2) learn, and 3) 
       understand the underlying phenomena that produced the 
       data. The possibilities of combined human-machine 
       intelligence are endless and will impact our lives in ways
       we can not even imagine today 
520    Synergistic human-machine intelligence aims to facilitate 
       the analytical reasoning and inference process of humans 
       by creating machines that maximize a human's ability to 1)
       reason about, 2) learn, and 3) understand large, complex, 
       and heterogeneous data. Combined human-machine 
       intelligence is a powerful symbiosis of mutual benefit, in
       which we depend on the computational capabilities of the 
       machine for the tasks we are not good at, and the machine 
       requires human intervention for the tasks it performs 
       poorly on. This relationship provides a compelling 
       alternative to either approach in isolation for solving 
       today's and tomorrow's arising data challenges 
520    In his regard, this dissertation proposes a diverse 
       analytical framework that leverages synergistic human-
       machine intelligence to maximize a human's ability to 
       better 1) reason about, 2) learn, and 3) understand 
       different biomedical imaging and healthcare data present 
       in the patient's electronic health record (EHR). 
       Correspondingly, we approach the data analyses problem 
       from the 1) visualization, 2) labeling, and 3) mining 
       perspective and demonstrate the efficacy of our analytics 
       on specific application scenarios and various data domains
520    In the first part of this dissertation we explore the 
       question how we can build intelligent imaging analytics 
       that are commensurate with human capabilities and 
       constraints, specifically for optimizing data 
       visualization and automated labeling workflows. Our 
       journey starts with heuristic rule-based analytical models
       that are derived from task-specific human knowledge. From 
       this experience, we move on to data-driven analytics, 
       where we adapt and combine the intelligence of the model 
       based on prior information provided by the human and 
       synthetic knowledge learned from partial data 
       observations. Within this realm, we propose a novel 
       Bayesian transductive Markov random field model that 
       requires minimal human intervention and is able to cope 
       with scarce label information to learn and infer object 
       shapes in complex spatial, multimodal, spatio-temporal, 
       and longitudinal data. We then study the question how 
       machines can learn discriminative object representations 
       from dense human provided label information by 
       investigating learning and inference mechanisms that make 
       use of deep learning architectures. The developed 
       analytics can aid visualization and labeling tasks, which 
       enables the interpretation and quantification of 
       clinically relevant image information 
520    The second part explores the question how we can build 
       data-driven analytics for exploratory analysis in 
       longitudinal event data that are commensurate with human 
       capabilities and constraints. We propose human-intuitive 
       analytics that enable the representation and discovery of 
       interpretable event patterns to ease knowledge absorption 
       and comprehension of the employed analytics model and the 
       underlying data. We propose a novel doubly-constrained 
       convolutional sparse-coding framework that learns 
       interpretable and shift-invariant latent temporal event 
       patterns. We apply the model to mine complex event data in
       EHRs. By mapping the event space to heterogeneous patient 
       encounters in the EHR we explore the linkage between 
       healthcare resource utilization (HRU) in relation to 
       disease severity. This linkage may help to better 
       understand how disease specific co-morbidities and their 
       clinical attributes incur different HRU patterns. Such 
       insight helps to characterize the patient's care history, 
       which then enables the comparison against clinical 
       practice guidelines, the discovery of prevailing practices
       based on common HRU group patterns, and the identification
       of outliers that might indicate poor patient management 
520    In general, we present novel approaches that exploit the 
       synergistic aspect of human-machine intelligence by 
       addressing problems from biomedical imaging to healthcare 
       informatics. The generic nature and applicability of the 
       proposed techniques, when integrated together, enable the 
       holistic analysis of the electronic health record and its 
       diverse data sources, which in turn can reveal hidden 
       patterns across the different data sources 
590    School code: 0054 
650  4 Engineering, Biomedical 
650  4 Artificial Intelligence 
650  4 Computer Science 
690    0541 
690    0800 
690    0984 
710 2  Columbia University.|bBiomedical Engineering 
773 0  |tDissertation Abstracts International|g72-08B 
856 40 |u