Pratik Shah: How AI is making it easier to diagnose disease
Pratik Shah: Wie KI es leichter macht, Krankheiten zu diagnostizieren
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
unglaubliche Aufgaben
using human-like intelligence.
durch menschenähnliche Intelligenz.
is often referred to as AI
wird oft als KI bezeichnet
on our lives in the future.
auf unser Leben in der Zukunft zu haben.
we still face massive challenges
enormen Herausforderungen gegenüber
einigen lebensgefährlichen Krankheiten,
several life-threatening illnesses,
due to liver and oral cancer.
diesen Patienten zu helfen,
and diagnoses of these diseases.
dieser Krankheiten durchzuführen.
and can artificial intelligence help?
und kann künstliche Intelligenz helfen?
auf eine solche Krankheit
are suspected of these diseases,
medical imaging technologies
CTs, MRIs, to be performed.
CTs, MRTs, zur Ausführung an.
those images and talks to the patient.
und spricht mit dem Patienten.
ressourcenintensiver Prozess,
a very resource-intensive process,
teure Bildgebungsverfahren benötigt
expensive medical imaging technologies,
als ungeeignet angesehen wird.
for the developing world.
industrialized nations, as well.
in vielen Industrieländern.
indem wir künstliche Intelligenz nutzen?
using artificial intelligence?
artificial intelligence architectures
künstlicher Intelligenz nutzen würde,
of these very expensive medical images
diesen sehr teuren medizinischen Bildern
to an expert physician,
those images for me.
analysieren würde.
or a deep learning network
"Deep Learning"-Netzwerk trainieren,
unter dem gleichen Problem.
intelligence approaches
and expert medical imaging technologies.
und High-Tech in der Bilddiagnostik.
künstlicher Intelligenz erfinden,
intelligence architectures
vor denen wir heute stehen?
problems facing us today?
what my group at MIT Media Lab does.
beim MIT Media Lab.
of unorthodox AI architectures
unorthodoxen KI-Architekturen,
challenges facing us today
Herausforderungen
klinischen Prozessen zu lösen.
hatten wir zwei Ziele.
with you today, we had two goals.
die Anzahl der Bilder zu reduzieren,
the number of images
artificial intelligence algorithms.
um KI-Algorithmen zu trainieren.
of expensive medical imaging technologies
der teuren Bilddiagnose zu reduzieren,
with tens and thousands
medizinischen Bilder zu starten,
like traditional AI,
medizinischen Bild angefangen.
figured out a very clever way
und ich einen cleveren Weg,
of information packets.
Informationspakete zu extrahieren.
included colors, pixels, geometry
Farben, Pixel, Geometrie
auf den medizinischen Bildern.
on the medical image.
into billions of training data points,
in Milliarden Trainingsdaten gewandelt
die für das Training benötigt wird.
needed for training.
imaging technologies to screen patients,
beim Screening zu verringern,
white light photograph,
normalen Weißlichtaufnahme,
mit einer Telefonkamera für den Patienten.
or a mobile phone, for the patient.
die Milliarden Informationspakete?
billions of information packets?
the medical image onto this image,
medizinischen Bildern überlagert
das wir Verbund-Bild nennen.
that we call a composite image.
we only required 50 --
benötigten wir nur 50 --
our algorithms to high efficiencies.
auf hohe Effizienz zu bringen.
very expensive medical images,
sehr teuren Bilder zu verwenden,
auf unkonventionelle Art trainieren,
in an unorthodox way,
but standard photographs,
hochauflösenden Standard-Fotos verwenden,
aufgenommen worden sind,
and mobile phones,
in der Zukunft und sogar schon jetzt,
in the future and even right now,
photographs from the patient,
des Patienten annehmen,
medical imaging technologies.
medizinischen Bildtechnologien.
to enter an era
in eine Ära gelangen,
auf unsere Zukunft hat.
impact on our future.
dem Nachdenken über traditionelle KI,
about traditional AI,
aber arm an Anwendungen ist,
intelligence architectures,
akzeptieren können
vor denen wir stehen, lösen kann,
problems facing us today,
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