Small Team Large Organization: Building Impactful Shiny Dashboards at NIH
summary
A three-person team builds a Shiny dashboard fed by an R Markdown pipeline and dbplyr, scheduled on RStudio Connect to update daily, consolidating >700 projects and over half a billion dollars of funding into one source of truth; users add/remove projects with reasons and inputs write back to a database. A supervised ML classifier trained on 7,500 coded grants and tested on 3,200 uses logistic regression 88.5% accuracy to prelabel grants, cutting human coding time from about five minutes toward one–two minutes.
AI-written summary · about
chapters (15)
- 0:00NIH and NIAID mission
- 1:11Science policy and R journey
- 1:53Shiny dashboards for funding
- 4:01Tracking funding challenges
- 5:28Research tracking tool
- 6:33Transparency and collaboration
- 7:41Predicting funding
- 8:47Automating processes
- 9:09NIH grant types
- 10:58Grant coding challenges
- 12:23Machine learning for grants
- 13:29AI-assisted grant coding
- 14:32User feedback and collaboration
- 15:38ML impact on productivity
- 16:01Conclusion and future goals
related talks
01h 46mBrian & Brock's App Adventure
21mUnlocking Synergy: PowerBI and PowerApps Collaboration for Data-Driven Decision-Making
32mA Tale of Two Architectures
23mProgressive Web Apps: An easy answer to unequal housework
01h 45mBrian & Brock's App Adventure
01h 01mMobile Business Intelligence, Apprentice Style!
28mThe Path to Scaling a Digital Enterprise
22mReact Native and PWA: A Tale of Two Architectures