Ingesting PDFs and why Gemini 2.0 changes everything

Re:Ingesting PDFs and why Gemini 2.0 changes everything by rjcrystal on Wednesday February 05, 2025 @10:39PM (#42958773)

I work in healthcare domain, We've had great success converting printed lab reports (95%) to Json format using 1.5-Flash model. This post is really exciting for me. will definitely try out 2.0 models.

The struggle which almost every ocr usecase faces is with handwritten documents(doctor prescriptions with bad handwriting) With gemini 1.5 flash we've had ~75-80% percent accuracy (based on random sampling by pharmacists). we're planning to improve this further by fine-tuning gemini models with medical data.

What could be other alternative services/models for accurate handwriting ocr?

[ Parent | on HN ]

Re:Ingesting PDFs and why Gemini 2.0 changes everything by myaccountonhn on Thursday February 06, 2025 @03:57AM (#42960475)

> We've had great success converting printed lab reports (95%) to Json format using 1.5-Flash model

Sounds terrifying. How can you be sure that there were no conversion mistakes?

[ Parent | on HN ]

Re:Ingesting PDFs and why Gemini 2.0 changes everything by Havoc on Thursday February 06, 2025 @05:11AM (#42960899)

How on earth is anyone ok with 75% accuracy in prescriptions context?!? Or medical anything

That’s literally insane

[ Parent | on HN ]

Re:Ingesting PDFs and why Gemini 2.0 changes everything by martimchaves on Thursday February 06, 2025 @06:40AM (#42961428)

I'm guessing that human accuracy may be lower or around that value, given that handwritten notes are generally difficult to read. A better metric for document parsing might be accuracy relative to human performance (how much better the LLM performs compared to a human).

[ Parent | on HN ]

Re:Ingesting PDFs and why Gemini 2.0 changes everything by knowaveragejoe on Thursday February 06, 2025 @04:31PM (#42966692)

Nobody said they're okay with it, nor did they describe what they use the data for.

[ Parent | on HN ]