Applying off-the-shelf NLP in healthcare? More dangerous than you think

Transformers have come to define what NLP means in 2021. Not only are these black-box decision-makers, but also interpret the free-text in a counter-intuitive way. This introduces hidden risk especially for mission-intensive NLP applications e.g. healthcare.

In this talk, we will see how this behavior can make your systems go sideways in production.

I’ll also cover how even the simpler models and preprocessing techniques exhibit these attributes, if not used with due diligence. We’ll study its implications in the context of NLP on healthcare data.

Lastly, I will provide guardrails you can put on your systems before and after you train your models. This will make sure you’re not only deploying ethically sound but also trustworthy models in the wild.

About the speaker

Ayush Singh

Sr. NLP Machine Learning Engineer at Cigna

Ayush Singh works as Sr. NLP ML Engineer at Cigna.

He also works part-time as medical computer vision researcher at Boston Children’s Hospital developing methods that improve the state of fetal MRI.

He is driven to improve education and healthcare using AI.

When not working, he paints and watches cat & dog videos on internet.