Pratik Shah: How AI is making it easier to diagnose disease
Pratik Shah: Kako umjetna inteligencija dijagnosticira oboljenja
Dr. Pratik Shah creates novel intersections between engineering, medical imaging, machine learning and medicine. Full bio
Double-click the English transcript below to play the video.
are performing incredible tasks
nevjerojatne stvari danas
using human-like intelligence.
koristeći inteligenciju sličnu ljudskoj.
is often referred to as AI
se često naziva UI
on our lives in the future.
utjecaj na naše živote.
we still face massive challenges
sa velikim izazovima
several life-threatening illnesses,
mnogih opasnih oboljenja,
due to liver and oral cancer.
raka jetre i usne šupljine.
pomoći ovim pacijentima
and diagnoses of these diseases.
i dijagnosticiramo ova oboljenja.
and can artificial intelligence help?
i može li umjetna inteligencija pomoći?
are suspected of these diseases,
da boluju od ovih oboljenja
medical imaging technologies
zdravstvenog snimanja
CTs, MRIs, to be performed.
rendgene i magnetne rezonance.
those images and talks to the patient.
te snimke i razgovara sa pacijentom.
a very resource-intensive process,
i iscrpljujući proces,
expensive medical imaging technologies,
i skupe tehnologije snimanja,
for the developing world.
za zemlje u razvoju.
industrialized nations, as well.
razvijenije zemlje, također.
using artificial intelligence?
umjetnom inteligencijom?
artificial intelligence architectures
metode umjetne inteligencije
of these very expensive medical images
skupih medicinskih snimaka
to an expert physician,
kod stručnog doktora,
those images for me.
or a deep learning network
mrežu ili duboku samo-učeću mrežu
intelligence approaches
and expert medical imaging technologies.
i stručne tehnologije snimanja.
intelligence architectures
problems facing us today?
s kojim smo suočeni danas?
what my group at MIT Media Lab does.
u MIT Media Lab-u.
of unorthodox AI architectures
neuobičajenih UI metoda
challenges facing us today
izazova s kojim se susrećemo
i kliničkom ispitivanju.
with you today, we had two goals.
s vama, imali smo dva cilja.
the number of images
broj snimaka potrebnih
artificial intelligence algorithms.
umjetne inteligencije.
of expensive medical imaging technologies
skupih tehnologija snimanja
with tens and thousands
like traditional AI,
kao tradicionalna UI,
figured out a very clever way
smo na pametan način
of information packets.
paketa informacija.
included colors, pixels, geometry
on the medical image.
into billions of training data points,
u milijardu podatkovnih tačaka za trening,
needed for training.
podataka potrebnih za trening.
imaging technologies to screen patients,
snimanja kod pacijenata,
white light photograph,
fotografijom sa bijelim svijetlom,
or a mobile phone, for the patient.
ili mobilnim uređajem, za pacijenta.
billions of information packets?
milijardi paketa informacija?
the medical image onto this image,
sa ovom slikom,
that we call a composite image.
kompozitna slika.
we only required 50 --
bilo je potrebno samo 50 -
our algorithms to high efficiencies.
bi algoritme učinili jako efikasnim.
very expensive medical images,
vrlo skupih medicinskih snimaka,
in an unorthodox way,
na jedan neobičan način,
but standard photographs,
visoke rezolucije,
and mobile phones,
kamerom i mobitelom,
in the future and even right now,
u budućnosti ali i sada,
photographs from the patient,
svijetlom od pacijenta,
medical imaging technologies.
tehnologije snimanja.
to enter an era
impact on our future.
za našu budućnost.
about traditional AI,
o tradicionalnoj UI,
ali siromašna primjenama,
intelligence architectures,
umjetne inteligencije,
problems facing us today,
problema današnjice,
ABOUT THE SPEAKER
Pratik Shah - Medical technologistDr. Pratik Shah creates novel intersections between engineering, medical imaging, machine learning and medicine.
Why you should listen
Dr. Shah's research program at the MIT Media Lab develops scalable and low-cost diagnostics and therapeutics. His ongoing research areas at MIT include: 1) artificial intelligence and machine learning methods for detection of cancer biomarkers using standard photographs vs. expensive medical images; 2) unorthodox artificial intelligence and machine learning algorithms to design optimal and faster clinical trials and to reduce adverse effects on patients; and 3) low-cost and open source imaging devices, paper diagnostics, algorithms and mobile phones to improve public health and generate real-world data.
Clinical studies with Pratik's medical technologies have revealed "missing sick" patients, who otherwise remain undiagnosed in conventional healthcare settings. Dr. Shah's graduate and postdoctoral research contributed to the discovery of a vaccine component to prevent pneumococcal (Streptococcus pneumoniae) diseases; the identification of new pathways, technologies and metabolites as antimicrobials to target gastrointestinal infections; and a nonprofit to deploy a low-cost water quality test for the developing world.
Past recognition for Dr. Shah includes the American Society for Microbiology's Raymond W. Sarber national award, the Harvard Medical School and Massachusetts General Hospitals ECOR Fund for Medical Discovery postdoctoral fellowship, the AAAS-Lemelson Invention Ambassador Award and a TED Fellowship. Pratik has been an invited discussion leader at Gordon Research Seminars; a speaker at Cold Spring Harbor Laboratories, Gordon Research Conferences and IEEE bioengineering conferences; and a peer reviewer for leading scientific publications and funding agencies. Pratik has a BS, MS, and a PhD in Microbiology and completed fellowship training at The Broad Institute of MIT and Harvard, Massachusetts General Hospital and Harvard Medical School.
Pratik Shah | Speaker | TED.com