Related Experiment Video
Updated: Jun 28, 2026
07:41
Performing Data Mining And Integrative Analysis Of Biomarker in Breast Cancer Using Multiple Publicly Accessible Databases
Published on: May 17, 2019
SPOT--towards temporal data mining in medicine and bioinformatics.
Guenter Tusch1, Chris Bretl, Martin O'Connor
1Grand Valley State University, One Campus Drive, Allendale, MI, USA.
AMIA ... Annual Symposium Proceedings. AMIA Symposium
|November 13, 2008
Summary
This study introduces SPOT, an open-source platform for temporal data analysis in clinical research. SPOT enhances Knowledge-based Temporal Abstraction using R and Semantic Web tools for better pattern discovery.
Area of Science:
- Bioinformatics
- Clinical Data Mining
- Temporal Data Analysis
Background:
- Analyzing temporal data in large clinical and bioinformatics databases is crucial for identifying complex patient patterns, such as post-transplantation complications.
- Existing methods like Knowledge-based Temporal Abstraction convert time-stamped data into interval-based representations.
Purpose of the Study:
- To extend the Knowledge-based Temporal Abstraction framework by developing a novel open-source platform.
- To facilitate the exploration of temporal patterns in clinical and bioinformatics data.
Main Methods:
- Developed SPOT, an open-source platform integrating the R statistical package.
- Incorporated knowledge representation standards (OWL, SWRL) using Protégé-OWL.
- Applied temporal data transformation techniques for pattern identification.
Main Results:
- SPOT provides a robust framework for temporal data abstraction.
- The platform supports integration with R and Semantic Web technologies.
- Enables detailed analysis of time-series data in medical research.
Conclusions:
- SPOT enhances the analysis of temporal clinical data.
- The platform offers a flexible and extensible solution for researchers.
- Facilitates advanced pattern discovery in time-dependent biomedical datasets.
