Semi-automated extraction of research topics and trends from NCI funding in radiological sciences from 2000-2020

TL;DR

This paper presents a semi-automated method to extract and analyze research topics and funding trends from a large dataset of NCI radiological sciences grants spanning 21 years, revealing key thematic axes and funding shifts.

Contribution

The authors developed a novel semi-automated approach combining clustering of biomedical word embeddings, expert naming, and visualization to analyze research trends in large-scale funding data.

Findings

Funding for therapeutics- and physics-based research has increased more than diagnostics- and biology-based research.

Two dominant axes identified: physics-biology and therapeutic-diagnostic.

Funding trends show shifts towards therapeutics and physics over time.

Abstract

Investigators, funders, and the public desire knowledge on topics and trends in publicly funded research but current efforts in manual categorization are limited in scale and understanding. We developed a semi-automated approach to extract and name research topics, and applied this to \$1.9B of NCI funding over 21 years in the radiological sciences to determine micro- and macro-scale research topics and funding trends. Our method relies on sequential clustering of existing biomedical-based word embeddings, naming using subject matter experts, and visualization to discover trends at a macroscopic scale above individual topics. We present results using 15 and 60 cluster topics, where we found that 2D projection of grant embeddings reveals two dominant axes: physics-biology and therapeutic-diagnostic. For our dataset, we found that funding for therapeutics- and physics-based research have outpaced diagnostics- and biology-based research, respectively. We hope these results may (1) give insight to funders on the appropriateness of their funding allocation, (2) assist investigators in contextualizing their work and explore neighboring research domains, and (3) allow the public to review where their tax dollars are being allocated.