Computational Diagnostic: A Novel Approach to View Medical Data.
- Ketan Kirtiraj
- Katy
A transition from traditional paper-based medical records to electronic health record is largely underway. The use of electronic records offers tremendous potential to personalize patient diagnosis and treatment. In this paper, we discuss a computational diagnostic tool that uses digital medical records to help doctors gain better insight about a patient's medical condition. The paper details different interactive features of the tool which offer potential to practice evidence-based medicine and advance patient diagnosis practices. The healthcare industry is a constantly evolving domain. Research from this domain is often translated into better understanding of different medical conditions. This new knowledge often contributes towards improved diagnosis and treatment solutions for patients. But the healthcare industry lags behind to seek immediate benefits of the new knowledge as it still adheres to the traditional paper-based approach to keep track of medical records. However recently we notice a drive that promotes a transition towards electronic health record (EHR). An EHR stores patient medical records in digital format and offers potential to replace the paper health records. Earlier attempts of an EHR replicated the paper layout on the screen, representation of medical history of a patient in a graphical time-series format, interactive visualization with 2D/3D generated images from an imaging device. But an EHR can be much more than just an 'electronic view' of the paper record or a collection of images from an imaging device. In this paper, we present an EHR called 'Computational Diagnostic Tool', that provides a novel computational approach to look at patient medical data. The developed EHR system is knowledge driven and acts as clinical decision support tool. The EHR tool provides two visual views of the medical data. Dynamic interaction with data is supported to help doctors practice evidence-based decisions and make judicious choices about patient treatment. Further, these two visual views work in unison as multiple coordinated views to provide additional insights about the medical data. In this paper, we will present inbuilt functionality of the computational diagnostic tool that can help doctors identify medical dataset characteristics such as: What patients show worst values for any given variables? What pattern is seen in medical variables of patients undergoing same treatment? From any given dataset, what patient population has severity values for different variables? Do a selected group of patients share similar trend across all different variables of interest? Can we compare two patient groups to see if they share similar trends across different variables? Is it possible to simultaneously compare trends and patterns for selected patients? The paper is organized as follows: Section 2 describes the medical dataset that is used with the computational diagnostic tool. Section 3 introduces the computational diagnostic tool. Further it discusses the two visualization views used to show medical data. The section also covers different data interaction support for both visualizations along with its usage for medical data analysis. Section 4 demonstrates the use of visual views as multiple coordinated views and how they complement each other to show different data characteristics. The paper concludes with discussion of results and future work.
- Research Organization:
- Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
- Sponsoring Organization:
- USDOE
- OSTI ID:
- 978012
- Report Number(s):
- LA-UR-07-1486; TRN: US201012%%605
- Resource Relation:
- Conference: 5th International Conference on Coordinated&Multiple Views in Exploratory Visualization, July 2, 2007, ETH, Zurich, Switzerland
- Country of Publication:
- United States
- Language:
- English
Similar Records
SU-F-P-20: Predicting Waiting Times in Radiation Oncology Using Machine Learning
TU-AB-204-00: Advances in Cone-Beam CT and Emerging Applications