Mass data exploration in oncology: An information synthesis approach

TL;DR

This paper presents a synthesis-based information retrieval approach to help oncology researchers understand large datasets, facilitating data mining and experimental design in tissue microarray studies.

Contribution

It introduces a task-oriented information retrieval model inspired by IR paradigms to improve data exploration in oncology research.

Findings

Validated prototype system through case and user studies

Enhanced understanding of large oncology datasets

Potential for extending the model to other domains

Abstract

New technologies and equipment allow for mass treatment of samples and research teams share acquired data on an always larger scale. In this context scientists are facing a major data exploitation problem. More precisely, using these data sets through data mining tools or introducing them in a classical experimental approach require a preliminary understanding of the information space, in order to direct the process. But acquiring this grasp on the data is a complex activity, which is seldom supported by current software tools. The goal of this paper is to introduce a solution to this scientific data grasp problem. Illustrated in the Tissue MicroArrays application domain, the proposal is based on the synthesis notion, which is inspired by Information Retrieval paradigms. The envisioned synthesis model gives a central role to the study the researcher wants to conduct, through the task notion. It allows for the implementation of a task-oriented Information Retrieval prototype system. Cases studies and user studies were used to validate this prototype system. It opens interesting prospects for the extension of the model or extensions towards other application domains.