Integrating Imaging and Clinical Data for Decision Support

2009 ◽  
pp. 18-33 ◽  
Author(s):  
William Hsu ◽  
Alex A.T. Bui ◽  
Ricky K. Taira ◽  
Hooshang Kangarloo
Keyword(s):  
Graphical Models ◽  
Clinical Data ◽  
Data Model ◽  
Medical Knowledge ◽  
Bayesian Belief Networks ◽  
Routine Care ◽  
Medical Decision ◽  
Disease Models ◽  
Open Problems ◽  
Clinical Observations

Though an unparalleled amount and diversity of imaging and clinical data are now collected as part of routine care, this information is not sufficiently integrated and organized in a way that effectively supports a clinician’s ability to diagnose and treat a patient. The goal of this chapter is to present a framework for organizing, representing, and manipulating patient data to assist in medical decision-making. We first demonstrate how probabilistic graphical models (specifically, Bayesian belief networks) are capable of representing medical knowledge. We then propose a data model that facilitates temporal and investigative organization by structuring and modeling clinical observations at the patient level. Using information aggregated into the data model, we describe the creation of multi-scale, temporal disease models to represent a disease across a population. Finally, we describe visual tools for interacting with these disease models to facilitate the querying and understanding of results. The chapter concludes with a discussion about open problems and future directions.

GRAPHICAL INDUCTION OF QUALIFIED MEDICAL KNOWLEDGE

2013 ◽  
Vol 07 (04) ◽  
pp. 377-405 ◽  
Author(s):  
TRAVIS GOODWIN ◽  
SANDA M. HARABAGIU
Keyword(s):  
Language Processing ◽  
Clinical Data ◽  
Medical Knowledge ◽  
Knowledge Bases ◽  
Clinical Knowledge ◽  
Biomedical Knowledge ◽  
Clinical Text ◽  
Relational Information ◽  
Processing Techniques ◽  
Medical Concepts

The introduction of electronic medical records (EMRs) enabled the access of unprecedented volumes of clinical data, both in structured and unstructured formats. A significant amount of this clinical data is expressed within the narrative portion of the EMRs, requiring natural language processing techniques to unlock the medical knowledge referred to by physicians. This knowledge, derived from the practice of medical care, complements medical knowledge already encoded in various structured biomedical ontologies. Moreover, the clinical knowledge derived from EMRs also exhibits relational information between medical concepts, derived from the cohesion property of clinical text, which is an attractive attribute that is currently missing from the vast biomedical knowledge bases. In this paper, we describe an automatic method of generating a graph of clinically related medical concepts by considering the belief values associated with those concepts. The belief value is an expression of the clinician's assertion that the concept is qualified as present, absent, suggested, hypothetical, ongoing, etc. Because the method detailed in this paper takes into account the hedging used by physicians when authoring EMRs, the resulting graph encodes qualified medical knowledge wherein each medical concept has an associated assertion (or belief value) and such qualified medical concepts are spanned by relations of different strengths, derived from the clinical contexts in which concepts are used. In this paper, we discuss the construction of a qualified medical knowledge graph (QMKG) and treat it as a BigData problem addressed by using MapReduce for deriving the weighted edges of the graph. To be able to assess the value of the QMKG, we demonstrate its usage for retrieving patient cohorts by enabling query expansion that produces greatly enhanced results against state-of-the-art methods.

scholarly journals Index Structures for XML Databases

2010 ◽  
pp. 98-124 ◽  
Author(s):  
Samir Mohammad ◽  
Patrick Martin
Keyword(s):  
Rapid Growth ◽  
Data Model ◽  
Information Exchange ◽  
World Wide ◽  
Semistructured Data ◽  
Open Problems ◽  
Xml Databases ◽  
The World ◽  
Extensible Markup ◽  
History Of

Extensible Markup Language (XML), which provides a flexible way to define semistructured data, is a de facto standard for information exchange in the World Wide Web. The trend towards storing data in its XML format has meant a rapid growth in XML databases and the need to query them. Indexing plays a key role in improving the execution of a query. In this chapter the authors give a brief history of the creation and the development of the XML data model. They discuss the three main categories of indexes proposed in the literature to handle the XML semistructured data model and provide an evaluation of indexing schemes within these categories. Finally, they discuss limitations and open problems related to the major existing indexing schemes.

scholarly journals Computer model of oxygenation in neonates

2019 ◽  
Vol 5 (1) ◽  
pp. 73-76
Author(s):  
Jakub Rafl ◽  
Veronika Huttova ◽  
Knut Möller ◽  
Thomas E. Bachman ◽  
Leos Tejkl ◽  
...  
Keyword(s):  
Oxygen Saturation ◽  
Clinical Data ◽  
Physiological Model ◽  
Routine Care ◽  
Target Range ◽  
Model Parameters ◽  
Diffusion Resistance ◽  
Peripheral Oxygen Saturation ◽  
Automatic Feedback ◽  
Baseline Testing

AbstractMaintaining a prescribed peripheral oxygen saturation (SpO2) target during routine care of neonates is challenging and inspired fraction of oxygen (FiO2) titration practices differ among caregivers and centers. Algorithms for automatic feedback control of SpO2 are being developed and tested, that would adapt to the changing neonatal organism and better maintain the required SpO2 target range. While clinical data is necessary to validate differences in the titration strategies, a continuous physiological model of oxygenation in neonates would facilitate baseline testing of different approaches, manual or automated. The objective of our study was to enhance a mathematical model of oxygenation of the neonate and to compare the performance of the model with available clinical data. We have implemented the diffusion resistance into the model as well as a variable oxyhemoglobin dissociation relationship and the bias between arterial and peripheral oxygen saturation. Values of model parameters were scaled to fit preterm infant scenarios. The comparison of the clinical data and computer simulations suggest that the model can reliably simulate episodes of oxygen desaturation and describe the relation between ventilation, FiO2and SpO2. It appears that the model may be an effective tool to test manual and automatic FiO2titration strategies.

Harmonization of clinical data across Gen3 data commons.

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. e18094-e18094 ◽  
Author(s):  
LaRon Hughes ◽  
Robert L. Grossman ◽  
Zachary Flamig ◽  
Andrew Prokhorenkov ◽  
Michael Lukowski ◽  
...  
Keyword(s):  
Open Source ◽  
Clinical Data ◽  
Open Source Software ◽  
Data Model ◽  
Reference Standards ◽  
Data Dictionary ◽  
Software Platform ◽  
Operating Data ◽  
External Reference ◽  
Data Commons

e18094 Background: Gen3 is an open source software platform for developing and operating data commons. Gen3 systems are now used by a variety of institutions and agencies to share and analyze large biomedical datasets including clinical and genomic data. One of the challenges of working with these datasets is disparate clinical data standards used by researchers across different studies and fields. We have worked to address these hurdles in a variety of ways. Methods: Gen3 is an open source software platform for developing and operating data commons. Detailed specification and features can be found at https://gen3.org/ with code located on GitHub ( https://github.com/UC-cdis ). Results: The Gen3 data model is a graphical representation of the different nodes or classes of data that have been collected. Examples include diagnosis, demographic, exposure, and family history. The properties and values on each node are controlled by the data dictionary specified by the data commons creator. While each commons may have a unique data model and dictionary, specifying external standards allows for easier submission of new data and assists data consumers with interpretation of results. A variety of external references can be supported, but here we demonstrate the use of the National Cancer Institute Thesaurus (NCIt). NCIt provides reference terminologies and biomedical standards that contain a rich set of terms, codes, definitions, and concepts. Using the same reference standards across commons allows for the export of clinical data between commons. The Portable Format for Biomedical Data (PFB) was created to facilitate data export and to allow the data dictionary schema as well as the raw data to be compressed and exported. This new file format, which utilizes an Avro serialization, is small, fast, easy to modify, and enables simple data export and import. PFB also has the ability to house entire external reference ontologies and it is easy to update the PFB references as changes are introduced. Conclusions: We have shown here how the Gen3 data model, use of external reference standards for clinical data, and the export/import format of PFB enable the harmonization of clinical data across different data commons.

A Bayesian Belief Network Methodology for Modeling Social Systems in Virtual Communities

2010 ◽  
pp. 125-152
Author(s):  
Ben K. Daniel ◽  
Juan-Diego Zapata-Rivera ◽  
Gordon I. McCalla
Keyword(s):  
Graphical Models ◽  
Bayesian Model ◽  
Computational Models ◽  
Virtual Communities ◽  
Knowledge Engineering ◽  
Social Systems ◽  
Bayesian Belief Networks ◽  
Current Approach ◽  
Interactive Simulation ◽  
Engineering Effort

Bayesian Belief Networks (BBNs) are increasingly used for understanding and simulating computational models in many domains. Though BBN techniques are elegant ways of capturing uncertainties, knowledge engineering effort required to create and initialize the network has prevented many researchers from using them. Even though the structure of the network and its conditional & initial probabilities could be learned from data, data is not always available and/or too costly to obtain. Further, current algorithms that can be used to learn relationships among variables, initial and conditional probabilities from data are often complex and cumbersome to employ. Qualitative-based approaches applied to the creation of graphical models can be used to create initial computational models that can help researchers analyze complex problems and provide guidance/support for decision-making. Once created, initial BBN models can be refined once appropriate data is obtained. This chapter extends the use of BBNs to help experts make sense of complex social systems (e.g., social capital in virtual communities) using a Bayesian model as an interactive simulation tool. Scenarios are used to update the model and to find out whether the model is consistent with the expert’s beliefs. A sensitivity analysis was conducted to help explain how the model reacted to different sets of evidence. Currently, we are in the process of refining the initial probability values presented in the model using empirical data and developing more authentic scenarios to further validate the model. We will elaborate on how database technologies were used to support the current approach and will describe opportunities for future database tools needed to support this type of work.

Sign in / Sign up

Export Citation Format

Share Document