NLM Invests in AI
NLM is a Partner in an AI-Empowered Health Care System
#ai #machinelearning #library
Transcript:
[Music starts] [Michael F. Chiang, MD]
There's never been a time in history where we've had so much access to science and technology as being applied to health care.
And I think one of the challenges for the future is how to move things like biomedical informatics and artificial intelligence and data science into the mainstream of healthcare.
[Dina Demner-Fushman, MD, PhD]
There is no one, other than NLM, who is specifically dedicated to biomedical information retrieval.
We keep people focused on what really matters for health and advancing medicine.
[Zhiyong Lu, PhD]
Our research focuses on AI and machine learning.
In the long run, what we really aim to do is to teach computers to read and understand scientific papers like scientists, to interpret x-rays or retinal images like radiologists, at a speed and at a accuracy that's above and beyond human ability.
[Nigam H. Shah, MBBS, PhD]
Medicine has been dreaming about having this ability to consult a large library of patient records to make better decisions. We've been thinking about this as a field for 40 years.
Finally, with the support of the National Library of Medicine, we have established its feasibility, its safety, and long-term viability.
[Sameer Antani, PhD]
Every clinician have seen a certain number of patients in their clinical training and they become very adept at that population.
Machines, on the other hand, could be trained on data that is free of bias from different parts of the world, from different ethnicities, different age groups so that there's an improved caregiving and therefore a better expectation on treatment and care.
[Alan McMillan, PhD]
What we've started to notice is that AI can be somewhat fragile. If it's given an unexpected input, it can give a very unexpected output.
And so really, the whole goal of our research is to understand how can we investigate where AI is fragile. How can we essentially break it so that we can understand how to fix it and make it stronger.
But really, it comes down to the ability to take what is theoretical research and apply it to health care and improve the treatment that we can provide patients.
[Music fades to Silence]