Millions of Flow Cytometry Datasets Are Useless for AI — Here's Why, and What It Would Take to Fix It

References

1. [1] NIST/FDA/NIAID AI and Flow Cytometry Workshop https://www.nist.gov/news-events/events/2025/06/ai-and-flow-...
2. [2] AI and Flow Cytometry — Lin et al. (J Immunol 2025) https://www.nist.gov/publications/ai-and-flow-cytometry
3. [3] Robust FCS Parsing: 211,359 Files — Bras (Cytometry A 2020) https://onlinelibrary.wiley.com/doi/full/10.1002/cyto.a.2418...
4. [4] ML framework for cross-institute AML classification (2025) https://www.sciencedirect.com/science/article/pii/S001048252...
5. [5] Robinson et al. BioEssays 2026 https://onlinelibrary.wiley.com/doi/10.1002/bies.70091
6. [6] Yue — AI in flow cytometry (Cytometry B 2025) https://onlinelibrary.wiley.com/doi/10.1002/cyto.b.22255
7. [7] NIST Flow Cytometry Standards Consortium https://www.nist.gov/programs-projects/nist-flow-cytometry-s...
8. [8] NIST FCSC WG5: AI/ML https://www.nist.gov/mml/bbd/fcsc-membership/fcsc-working-gr...
9. [9] ML Methods in Clinical FCM (Cancers 2025) https://www.mdpi.com/2072-6694/17/3/483