Pratik Shah: How AI is making it easier to diagnose disease
Pratik Shah: Comment l'intelligence artificielle facilite les diagnostics médicaux
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
des tâches incroyables,
à une échelle massive,
using human-like intelligence.
similaire à l'homme.
is often referred to as AI
est souvent appelée IA,
on our lives in the future.
extraordinaire sur nos vies.
we still face massive challenges
several life-threatening illnesses,
plusieurs maladies mortelles
ou le cancer.
due to liver and oral cancer.
du foie ou buccal.
pour aider ces patients
and diagnoses of these diseases.
précoces de ces affections.
and can artificial intelligence help?
et l'usage de l'IA fait-il sens ?
are suspected of these diseases,
semble avoir une de ces affections,
medical imaging technologies
d'imagerie médicale
CTs, MRIs, to be performed.
une tomodensitométrie ou un IRM.
those images and talks to the patient.
et parle avec le patient.
a very resource-intensive process,
beaucoup de ressources,
expensive medical imaging technologies,
de l'imagerie médicale très onéreuse,
dans les pays en développement.
for the developing world.
industrialized nations, as well.
nations industrialisées.
using artificial intelligence?
avec l'intelligence artificielle ?
artificial intelligence architectures
les architectures classiques d'IA
nous aurions besoin de 10 000 --
of these very expensive medical images
de ces images médicales si chères.
to an expert physician,
à un spécialiste
those images for me.
or a deep learning network
ou réseau d'apprentissage profond,
intelligence approaches
sont pénalisées par le même problème :
and expert medical imaging technologies.
des médecins spécialistes
des architectures d'IA
intelligence architectures
plus efficaces et plus utiles,
auxquels nous sommes confrontés ?
problems facing us today?
what my group at MIT Media Lab does.
au Media Lab du MIT.
of unorthodox AI architectures
d'architectures d'IA inhabituelles
challenges facing us today
les plus importants
et les tests cliniques.
with you today, we had two goals.
nous avions deux objectifs.
the number of images
à réduire le nombre d'images
artificial intelligence algorithms.
les algorithmes de l'IA.
of expensive medical imaging technologies
de technologies d'imagerie médicale chères
avec des dizaines de milliers
with tens and thousands
like traditional AI,
comme pour une IA traditionnelle,
on a trouvé une manière très ingénieuse
figured out a very clever way
of information packets.
de paquets de données.
included colors, pixels, geometry
des couleurs, des pixels, la géométrie,
on the medical image.
sur l'image médicale.
into billions of training data points,
en milliards de données de formation,
de données nécessaire à cette formation.
needed for training.
de technologies d'imagerie médicale
imaging technologies to screen patients,
white light photograph,
normale, à la lumière du jour,
or a mobile phone, for the patient.
reflex mono-objectif, ou un smartphone.
billions of information packets?
des milliards de paquets d'informations.
the medical image onto this image,
à partir de l'image médicale,
that we call a composite image.
une image composite.
we only required 50 --
nous n'avons eu besoin de seulement 50,
our algorithms to high efficiencies.
pour entraîner notre algorithme
very expensive medical images,
médicales très chères,
de l'IA avec des moyens non traditionnels
in an unorthodox way,
but standard photographs,
de haute résolution certes, mais standard,
and mobile phones,
et des smartphones,
in the future and even right now,
déjà aujourd'hui
prises à la lumière du jour
photographs from the patient,
medical imaging technologies.
onéreuses d'imagerie médicale.
to enter an era
sur le point d'entrer dans une ère
un impact incroyable sur notre avenir.
impact on our future.
about traditional AI,
de l'IA traditionnelle,
mais avec peu d'application,
dans le développement
intelligence architectures,
des petits volumes de données
problems facing us today,
les plus importants,
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