Dylan Thibault
Senior Biostatistician & AI Innovator
10+ years advancing clinical research through statistical modeling, risk prediction, and AI-driven tools. Building the next generation of healthcare analytics at DCRI.
About
I'm a Senior Biostatistician at the Duke Clinical Research Institute (DCRI), where I lead statistical analysis and AI initiatives across cardiovascular registries, clinical trials, and health outcomes research.
My work spans survival analyses with Medicare data, risk prediction modeling for the Society of Thoracic Surgeons (STS), propensity score methods, and the development of interactive dashboards and risk calculators. I've authored 100+ peer-reviewed publications in journals including Circulation, The Lancet Neurology, JAMA Network Open, and Annals of Thoracic Surgery.
In recent years, I've pivoted heavily into AI, building tools that automate statistical analysis plan generation, quality review systems, and patient-facing informed consent platforms. I'm passionate about training the next generation of biostatisticians in Python, R, Git, and AI-driven workflows.
Education
MS Biostatistics — Georgetown University
BS Biological Sciences — University of Vermont
BA Philosophy — University of Vermont
Recognition
DCRI Innovator Award (2024)
100+peer-reviewed publications
Experience
Senior Biostatistician
2021 – PresentDuke Clinical Research Institute (DCRI)
- ›Lead AI initiatives: automated SAP generation with RAG, agent-based SAP review, AI-enabled informed consent platforms
- ›Statistical analysis across outcomes, registry, claims, and administrative datasets
- ›Primary supervisor/mentor for junior biostatisticians
- ›Department-wide AI training and biweekly AI office hours
- ›DCRI Innovator Award recipient (2024) for ChatSum meeting minutes AI app
Biostatistician III
2016 – 2021Duke Clinical Research Institute (DCRI)
- ›Lead statistician on the Society of Thoracic Surgeons (STS) registry across all three datasets: adult, thoracic, and congenital
- ›Published 50+ peer-reviewed manuscripts including risk prediction models
- ›Built COVID hospital resource utilization predictive calculator
Biostatistician
2013 – 2016University of Pennsylvania, Department of Neurology
- ›Data analysis on NIS, Medicare CMS, KID, and NEDS datasets
- ›Statistical methods: survival analysis, mixed effects models, propensity score methods
- ›Published multiple first-author manuscripts in peer-reviewed journals
AI & Innovation
Building tools that streamline clinical trial workflows and enhance research quality through artificial intelligence.
Automated SAP Generation
Next.js app using retrieval-augmented generation (RAG) to generate Statistical Analysis Plans. Upload a protocol, receive a tailored, downloadable SAP.
Agent-Based SAP Review
CLI tool with dual-agent framework (drafting + reviewer agents) that iteratively refines SAPs against CRO/industry guidelines.
ChatSum — Meeting Minutes AI
GPT-4o powered meeting minutes summarizer. Won the 2024 DCRI Innovator Award.
AI Informed Consent Platform
Real-time patient-facing chatbot for informed consent evaluation. FastAPI + Next.js with GPT-4o/5, evaluating 17 quality metrics for regulatory review.
COVID Resource Calculator
Predictive calculator for hospital resource utilization during COVID — blood products, ventilation, LOS, readmission.
Azure AI Studio
AI-powered content generation studio with TTS, video, and image capabilities using Azure OpenAI.
Publications
Live search powered by the PubMed database.
Searching PubMed…
Open Source & Projects
AI-powered chatbot to help patients understand clinical trial informed consent documents.
Next.js app for GWTG statistical analysis plans using RAG.
CLI for creating statistical analysis plans with AI assistance.
PRE-EMPT chatbot for clinical trial screening and evaluation.
AI-powered content generation studio with TTS, video, and image using Azure OpenAI.
Download and organize Microsoft Teams meeting transcripts via CLI or web interface.
Web dashboard to check Azure OpenAI model capacity across regions.
This day in American history — daily trivia webapp.
Interactive Tools
Live R Shiny applications built for Duke Clinical Research Institute — deployed and used by research teams and clinical collaborators.
Built with R Shiny · Hosted on shinyapps.io · Duke School of Medicine
Skills & Expertise
Statistical Methods
Programming
AI & Tools
Domains
Consulting
I help organizations leverage AI to transform their workflows — from strategy and tool development to hands-on team enablement. Whether you're exploring AI for the first time or scaling existing initiatives, I bring deep expertise in both the technology and the regulated environments where it matters most.
AI Strategy & Integration
Identify high-impact opportunities to embed AI into your existing workflows — from document processing to decision support systems.
Custom AI Tool Development
Purpose-built tools using RAG, multi-agent systems, and LLMs — tailored to your domain, data, and compliance requirements.
AI Personal Assistants
Deploy autonomous AI assistants that manage tasks, automate communications, and integrate with your existing tools — powered by platforms like OpenClaw.
Team Training & Workshops
Hands-on training for teams adopting AI tools — covering prompt engineering, workflow automation, and responsible AI use in regulated industries.
Powered by OpenClaw
I run my own OpenClaw AI assistant — an open-source personal AI that automates tasks, manages communications, and integrates with everyday tools. I can help you deploy one tailored to your needs.