MIT_JameelClinic_Logo.png
139-1398819_wellcome-trust-wellcome-trust-logo-svg.png

For the benefit of humanity

Group 75.jpg
Hot Air Balloons

Building and deploying trustworthy clinical AI

The recent decade witnessed significant developments in clinical AI technologies. These advancements include all the areas of clinical care, ranging from risk assessment and diagnostics, to treatment personalization and prediction of treatment outcomes.

 

If implemented in clinical practice, these new technologies can save lives and improve quality of care while controlling its costs.

This research has to be done in close collaboration with clinicians who will be the main users of these tools.

Another important aspect of safe clinical AI deployment relates to its ability to robustly handle different patient populations, clinical settings, etc. We have already seen multiple cases where AI tools developed on one population were unable to scale up to other demographics, leading to inequitable outcomes in patient care.

 

The only way to address this concern is by broadly testing AI tools across many hospitals that represent diverse demographics and clinical facilities.

35

8

Hospitals

Countries

sepulveda-1.jpg

Fernando Sepúlveda,
CEO of Angeles AI

State-of-the-art AI tools should be made available to every hospital around the world.

 

Las herramientas de inteligencia artificial de última generación deben estar disponibles para todos los hospitales del mundo.

6195817a7824dfa5f90de0cb_Foto_Sergio_Prada.jpg

Fernando Sepúlveda,
CEO of Angeles AI

The use of AI in both present and future healthcare delivery exemplifies excellence in innovation and research — this is what our collaboration with Jameel Clinic is all about.

El uso de IA en la prestación de servicios de salud hoy y en el futuro ejemplifica excelencia en innovación y en investigación — de esto se trata nuestra colaboración con Jameel Clinic.

1617962107799.jpg

Giacomo Feliciani
Medical Physics Expert at IRST Cancer Center

State-of-the-art AI tools should be made available to every hospital around the world.

Gli strumenti di intelligenza artificiale all'avanguardia dovrebbero essere messi a disposizione di tutti gli ospedali del mondo.

In the news

Is artificial intelligence about to transform the mammogram?

When Regina Barzilay returned to work after her breast cancer leave seven years ago, she was struck by an unexpected thought.

 

The MIT artificial-intelligence expert had just endured chemotherapy, two lumpectomies and radiation at...

Hear from our collaborators

Regina_WaPo.jpg
In the news

The downside of machine learning in healthcare

While working toward her dissertation in computer science at MIT, Marzyeh Ghassemi wrote several papers on how machine-learning techniques from artificial intelligence could be applied to clinical data in order to predict patient outcomes. “It wasn’t until the end of my PhD work that one of my committee members asked: ‘Did you ever check to see how well your model worked across different groups of people?’”

brain-gears.jpg
In the news

Robust artificial intelligence tools to predict future cancer

To catch cancer earlier, we need to predict who is going to get it in the future. The complex nature of forecasting risk has been bolstered by artificial intelligence (AI) tools, but the adoption of AI in medicine has been limited by poor performance on new patient populations and neglect to racial minorities. 

MIT-Mirai.jpg
People
regina.png

Regina Barzilay

07-Tommi_Jakkola-e1565383992801.jpg

Tommi Jaakkola

dim.png

Dimitris Bertsimas

me.jpeg

Muriel Médard

mg.png

Marzyeh Ghassemi

50-Vinod-Vaikuntanathan.jpg

Vinod Vaikuntanathan

Wellcome Trust Fellows
alexander.jpeg

Leo
de Castro

Prof. Vaikuntanathan

sule.png

Suleeporn Sujichantararat

Prof. Bertsimas

yu.png

Yu Ma
 

Prof. Bertsimas

vinith.png

Vinith
Suriyakumar

Prof. Ghassemi

alexander.jpeg

Alexander 
Mariona

Prof. Medard


Strategic Initiatives and Communications
6.png

Ignacio Fuentes

1593705835405.jpg

Alex Ouyang

ann.png

Ann McLaughlin

Join our collaboration

Thank you! We'll be in touch.