Better Medicine Through Machine Learning | Suchi Saria | TEDxBoston

Share it with your friends Like

Thanks! Share it with your friends!


Faster medical treatment saves lives. Machine Learning is already saving lives, by scouring a multitude of patients’ data and comparing them to one patient’s health data to detect symptoms 12 to 24 hours sooner than a doctor could. "In many pressing medical problems, the answers to knowing whom to treat, when to treat, and what to treat with, might already be in your data" says Suchi Saria. Learn how TREWS (Targeted Real-time Early Warning Score) is leading the way to save lives.

Suchi Saria is a professor of computer science and health policy, and director of the Machine Learning and Health Lab at Johns Hopkins University. Her research is focused on designing data solutions for providing individualized care.

This talk was given at a TEDx event using the TED conference format but independently organized by a local community. Learn more at


Ramessur Husanand says:

Many lives can be saved ……..through this dignified technology- as said machine learning…..

Dilip Kumar says:

Very nice speech..!! I really admire you.

Jeramie Curtice says:

Her nephew's legacy lives on with her passion to help others.
With that said, does anyone else see this digital practice a replacement for physician practice?

Open Sesame says:

all good but i find it kinda weird the irreverence she shows when talking about people's deaths. It's crude; almost like she's just bringing them up for the benefit of her presentation.

adwait patil says:

what u r saying what u want to say and what you want to do…????ans this to yourself 1 st

abhirup dasgupta says:

Very nice one

Dig Biqk says:

This talk is like a plug for this TREWS system no ?

Kimberly Alvarez says:

I am a computer science major but i want a career related to computer vision specifically in medical imaging where i can diagnose and identify diseases like cancer. Should i stick with my computer science major or should i do a different major?

Rushil Thareja says:

but even if u know that the body is going through such a severe immune response a day earlier what can u do to stop it?i think that if the body decides to use its own nuclear missiles on itself then there is no going back .that's why diseases like ebola just kill!

akshay khairnar says:

Dead audience

John Ngo says:

Good presentation!

Neftali Watkinson says:

This presentation has no structure whatsoever, the whole robot analogy doesn't even remotely relate to the ML TREWscore actually uses, that time would've been better spent explaining the actual mechanism of TREWscore instead of presenting it as some magical blackbox

Hoda Yousry says:

Really impressive talk

Machin396 says:

Great talk, I found it difficult to focus because of the pretty presenter.

Naveed Farrukh says:

Fantastic Talk. Loads of potential and addressing a salient issue that has so far eluded our best efforts – Sepsis. The push for more open health records…albeit balanced with the right to privacy…should be a major policy goal for us. Available data + processing power of AI/ML can exponentially provide new insights and improve healthcare.

Loved the juxtaposition between big and and small data. Never thought of it like that!

Arun Kumar says:

MLM concept will changed the world thinking.

Og Special says:

is it taking into account holistic medicines and natural remedies??? which is a whole field of medical science being neglected by big pharma, doctors and programmers.

sharontatesbaby says:

She must be an expert. She keeps telling us she is!

MikeB26 says:

It is frustrating that Ms. Saria doesn't identify the source of Ms. Manning's sepsis. Was it the sore on her foot? Did she have an asymptomatic sepsis before she showed up at the clinic complaining of a sore foot? Or was it a hospital acquired pneumonia? If it was the latter, perhaps reliance on technology is the villain here, not the solution. Maybe just a little plain wisdom would have convinced doctors to discharge Ms. Manning from the hospital before she spent the night in this notoriously dangerous vector for bacterial pneumonia.

Dan Xia says:

The TREWScore showed a sensitivity of 85% and specificity of 67%. It means it misses 15% sick people and treat 33% who does not need to be treated. A routine screening protocol that doctors in USA used have sensitivity of 74% at a comparable specificity of 64%. Perhaps, we need to collect different parameters.

Write a comment