Improving the quality of communication in grant proposals.

Novel Designs

We have been working on a series of improvements to our grant writing pipeline and thought that it would be interesting to share these features with our collaborators.

  1. Plots and tables to represent preliminary work. We have now further integrated our AI-based research design system – something that we previously mentioned in one of our previous posts – to create tables and plots based on preliminary work relevant to the grant project. These tables and plots are directly connected to the underlying data, meaning that any modification to our research design will be automatically present in the written plan.
  2. Use of international methodological standards for reporting. All of our methods descriptions are now automatically connected to templates based on reporting guidelines listed under the Equator network. This feature means that if our Data Scientists accept a suggestion from our AI system to use, for example, a health economics evaluation to a given project, our proposal will automatically include all recommended elements from the corresponding guidelines such as the CHEERS statement.
  3. Vectors images, color schemes, and fonts. Although we use elements of international reporting guidelines, we have substantially enhanced these elements with vector graphics representing the design, all provided in a color scheme that is consistent across the document. The final documentation is compliant with funding agency requirements, also having fonts designed to improved readability.
  4. Unit tests applied to grant proposal materials for internal consistency checking. When handling proposals, it is easy to lose track of what we mentioned in different portions of the project and create inconsistencies. For example, we might state one exclusion criterion in one section, while stipulating something slightly different in another part. Portions of the proposal written by our team now include “unit tests” which check whether different instances of the same concept are indeed coherent. Data scientists can then address any inconsistency. Unfortunately, this system cannot recognize discrepancies concerning sections written by teams not using our AI system, but we are working toward a solution.
  5. Data simulations. Also aligned with our AI design system, we have embedded a system that facilitates the inclusion of simulations within our proposals. These simulations include, for example, Return on Investment (ROI) calculations for project commercialization (known as exploitation in the EU), study recruitment simulations, sample size calculations, among others.
  6. Copy-editing. Outside of our AI system, we have implemented a copy-editing workflow aimed at catching spelling, grammatical, and style issues, delivering a high-quality final proposal copy.
  7. Transatlantic teams with parallel proposal submission integrating teams in the US and European Union. Finally, we also attempt to match researchers across the two sides of the Atlantic. These collaborations occur through the submission of parallel proposals to European and American agencies, or, when applicable, through joint submissions to international agencies.