Does DeepSeek Provide Clinically Acceptable Intraocular Lens (IOL) Power Predictions in Cataract Surgery? A Proof-of-Concept Study
Giovanni Ottonelli, Giacomo De Rosa, Jacopo Celada Ballanti, Alessandro Gaeta, Paolo Vinciguerra, Alessandra Di Maria · 2025
Read Does DeepSeek Provide Clinically Acceptable Intraocular Lens (IOL) Power Predictions in Cataract Surgery? A Proof-of-Concept Study by Giovanni Ottonelli, Giacomo De Rosa, Jacopo Celada Ballanti, Alessandro Gaeta, Paolo Vinciguerra, Alessandra Di Maria (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12733728.txt.
Description
Giovanni Ottonelli and five co-authors ask whether a chatbot can pick lens powers for cataract surgery. Their 2025 proof-of-concept study tests DeepSeek, an open generative AI. Surgeons must choose an implant lens that lands the eye on target focus. Standard formulas, not chatbots, hold that job today.
Fifty eyes from fifty patients at a Milan hospital formed the test set. All had smooth surgery with one lens model. A month later, measured focus was compared with each method's forecast. DeepSeek's errors were set against the Barrett Universal II formula. Accuracy statistics and error spreads were tallied for both. The study probes whether a cheap, open tool can approach clinical grade. Lens choice is unforgiving, so the bar is high.
Catalog record
| CREATOR | Giovanni Ottonelli, Giacomo De Rosa, Jacopo Celada Ballanti, Alessandro Gaeta, Paolo Vinciguerra, Alessandra Di Maria |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 41 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |