Pratik Shah: How AI is making it easier to diagnose disease
Pratik Shah: Como a IA está a tornar mais fácil diagnosticar doenças
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
desempenham tarefas incríveis
using human-like intelligence.
parecida com a humana.
is often referred to as AI
é frequentemente chamada IA,
on our lives in the future.
um enorme impacto na nossa vida.
we still face massive challenges
enfrentamos desafios enormes
several life-threatening illnesses,
de muitas doenças letais,
due to liver and oral cancer.
a um cancro do fígado ou da boca.
de ajudar esses doentes
and diagnoses of these diseases.
dessas doenças mais cedo.
and can artificial intelligence help?
e como a IA pode ajudar?
are suspected of these diseases,
haja suspeitas dessas doenças,
medical imaging technologies
de imagiologia médica,
CTs, MRIs, to be performed.
um TC, ou um MRI.
those images and talks to the patient.
das imagens e fala com o doente.
a very resource-intensive process,
um processo muito dispendioso
expensive medical imaging technologies,
tecnologia de imagiologia médica cara
for the developing world.
para os países em desenvolvimento.
industrialized nations, as well.
com as nações industrializadas.
using artificial intelligence?
com a inteligência artificial?
artificial intelligence architectures
tradicionais de inteligência artificial
of these very expensive medical images
dessas imagens médicas muito caras
to an expert physician,
a um médico especialista,
those images for me.
or a deep learning network
ou uma rede de aprendizagem profunda
da inteligência artificial
intelligence approaches
and expert medical imaging technologies.
médicos especialistas
de tecnologias de imagiologia.
arquitecturas de IA
e mais valiosas,
intelligence architectures
problems facing us today?
importantes que hoje enfrentamos?
what my group at MIT Media Lab does.
o meu grupo no MIT Media Lab.
of unorthodox AI architectures
de arquitecturas IA pouco ortodoxas
challenges facing us today
mais importantes que temos hoje
with you today, we had two goals.
tínhamos dois objetivos.
the number of images
reduzir o número de imagens
artificial intelligence algorithms.
da inteligência artificial.
of expensive medical imaging technologies
de imagiologia médica cara
com dezenas e milhares
with tens and thousands
like traditional AI,
como a IA tradicional,
figured out a very clever way
encontrámos uma forma inteligente
of information packets.
de pacotes de informações.
included colors, pixels, geometry
incluíam cores, pixeis, geometria
on the medical image.
na imagem médica.
into billions of training data points,
em milhares de milhões de pontos de dados,
needed for training.
de dados necessários para o treino.
imaging technologies to screen patients,
de imagiologia médica cara
white light photograph,
normal, com luz natural,
or a mobile phone, for the patient.
ou um telemóvel, para o doente.
de pacotes de informações?
billions of information packets?
the medical image onto this image,
da imagem médica nesta imagem,
that we call a composite image.
uma imagem composta.
we only required 50 --
só precisámos de 50
our algorithms to high efficiencies.
treinar o algoritomo para alta eficiência.
very expensive medical images,
imagens médicas muito caras,
in an unorthodox way,
da IA, de uma forma pouco ortodoxa,
but standard photographs,
normais, mas de alta resolução
and mobile phones,
ou um telemóvel,
in the future and even right now,
no futuro e até mesmo agora,
photographs from the patient,
à luz normal, do doente,
medical imaging technologies.
de imagiologia médica cara.
to enter an era
preparados a entrar numa era
impact on our future.
no nosso futuro.
about traditional AI,
mas pobre em aplicações,
intelligence architectures,
ortodoxas para a inteligência artificial
problems facing us today,
que enfrentamos hoje em dia,
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