The future of medical AI will not be decided only by which model scores highest on a benchmark. It will be decided by whether systems can support clinical work without hiding uncertainty, increasing noise, or breaking the logic of care.
Useful systems need more than accuracy
Accuracy matters, but clinical usefulness requires a wider frame. A system can be accurate in a dataset and still fail if the input distribution changes, if the output is not actionable, or if clinicians cannot tell when the model is uncertain.
- Medical AI should be evaluated for failure modes, calibration, and clinical relevance.
- Outputs should match real decisions, not only labels that are easy to benchmark.
- Systems should make it easier to audit where an answer came from and why it may be wrong.
The connector role matters
Medical AI projects often fail between disciplines. Clinicians understand the workflow and risk, researchers understand the study question, and engineers understand the system. The best work needs translation across all three.
This is where I see my strongest role: understanding the clinical problem, framing it as a research question, building or evaluating the technical workflow, and staying honest about what would happen in real use.
The most interesting medical AI problems are not only model problems. They are evidence, workflow, reliability, and implementation problems.
What I want to build toward
My long-term direction is radiology AI and medical computer vision, but the broader goal is practical clinical AI: systems that can be studied rigorously, explained clearly, and used responsibly. That means treating evaluation and workflow design as central parts of the technical work.
Back to insights