Pediatric surgeon by training. Meta-researcher by conviction.
I study how AI changes the way we do science — not just faster, but structurally differently. My work sits at the intersection of clinical research, AI systems, and philosophy of science.
The problem I named: When AI assists research, it introduces epistemic drift — a silent corruption of the reasoning chain that leaves no trace in final results. Peer review can't catch it. Reproducibility checks miss it. Current safeguards assume human-controlled reasoning. AI breaks that assumption.
What I'm building:
| Project | What it does |
|---|---|
| Epistemic Drift | Taxonomy of how AI corrupts scientific reasoning — companion to my submitted paper |
| CiteCheck | Verify manuscript citations against PubMed, CrossRef, OpenAlex — trust but verify |
| SR/MA Pipeline | End-to-end systematic review with human checkpoints at every step (coming soon) |
| MedEvo | Multi-agent evolutionary simulation for biological systems — one engine, infinite diseases (in development) |
I write about responsible AI use in academic research at aiforacademic.world — practical workflows, not hype.
Core belief: AI assists thinking. You own the science.
- Submitted: "Artificial Intelligence and the Epistemic Drift of Scientific Research" — defining a new class of epistemic failure in AI-assisted research
- In progress: Constitutional framework for AI in science — why research needs pre-commitment constraints, not just post-hoc guidelines
- Clinical: Network meta-analysis in pediatric surgery (submitting to Pediatric Surgery International)
"The crisis is not that AI makes bad science — it's that AI makes science that looks indistinguishable from good science."