top of page
OUR SPEAKERS
Share on:
Rachel Wities is an NLP Data Scientist at Zebra Medical Vision, working on extracting insights from free-text medical records.
Rachel is a researcher and public speaker addressing Healthcare domain challenges, and believes that understanding doctors and their needs is the key to successfully implementing AI Healthcare algorithms.
She holds an M.Sc. from BIU NLP lab, researching knowledge graph representation of text semantics. In her previous role she was a research scientist in PayPal.
Loves her family, God and Oxford Comma jokes.
Rachel Wities
NLP Data Scientist at Zebra Medical
English, Hebrew
Languages:
Location:
Givat Shmuel, Israel
Can also give an online talk/webinar
Paid only. Contact speaker for pricing!
MY TALKS
It’s Not Just The Doctor’s Handwriting - NLP In The Healthcare Domain, Why Is It Hard?
Data / AI / ML
In this talk I will present the latest research in the medical NLP field, focusing on generic methods and tools that proved to be effective.
Breaking The Rule-Based Barrier: Hybrid Algorithms In Healthcare NLP
Data / AI / ML
NLP is widely used in the healthcare domain to extract structured data from free-text medical
records and reports. But in contrast with NLP state-of-the-art, which is achieved using neural
networks, in the healthcare domain we find that rule-based systems are still very common, both
in the industry and in medical academic research.
In this lecture I will show the extent of this phenomenon, explain its reasons and propose a
possible solution.
Sending BERT to Med School - How Structured Knowledge Can Help Us Improve Healthcare NLP
Data / AI / ML
Natural Language Processing in the Healthcare domain is slow to adopt state-of-the-art neural network algorithms like BERT, because of the lack of labeled data and the high need for expert knowledge and explainability. But at the same time, the Healthcare domain has a key advantage in the form of high-quality structured knowledge resources.
In this lecture Rachel will introduce a few examples of structured knowledge sources, like UMLS and ConceptNet, and will show how to utilize them in order to inject knowledge into neural networks.
This lecture is intended for people interested in the challenges of healthcare language processing, and for people in other specialized domains who want to get their structured knowledge bases out of the attic.
Doctor-in-the-loop: Interactive Machine Learning in Healthcare AI
Data / AI / ML
Working in a Healthcare startup, one of my most frustrating experiences was to ask doctors to do tedious work of data annotation or result verification. Surely there’s a better way, I told myself, to exploit the knowledge and expertise of doctors, than to turn them into a labeling conveyor belt!
Well, it turns out there is.
Human-in-the-loop ML refers to human-machine interaction in data annotation and model training. In Zebra Medical we used Human-in-the-loop techniques to compensate for lack of tagged data and to better exploit clinical expert knowledge. In this lecture I will show how to make data annotation quicker and smarter by turning it into an interactive process, and how an interactive process of experts and models writing rules together can improve your model performance without additional training.
This talk is intended for AI researchers interested in better ways to exploit the knowledge and experience of domain experts, and for people interested in the challenges of AI in
It’s Not Just The Doctor’s Handwriting - NLP In The Healthcare Domain, Why Is It Hard?
Completed
true
Visible
true
Order
3
Breaking The Rule-Based Barrier: Hybrid Algorithms In Healthcare NLP
Completed
true
Visible
true
Order
3
Sending BERT to Med School - How Structured Knowledge Can Help Us Improve Healthcare NLP
Completed
true
Visible
true
Order
3
Doctor-in-the-loop: Interactive Machine Learning in Healthcare AI
Completed
true
Visible
true
Order
3
bottom of page