Thread by @NightingaleOS

🎉🚀 We just launched Nightingale Open Science, a computing platform housing massive new medical imaging datasets for the public good

We hope Nightingale will help shed light on some of the biggest medical problems of our time

A 🧵on our vision & how to get involved (1/12)

Most health data today are locked up in small sandboxes, controlled by a handful of private companies and well-resourced researchers

Nightingale unlocks such data securely and ethically, and makes them available for cutting-edge research (2/12)

Think of all the discoveries that haven’t been made—all the questions that haven’t been asked—because the right people haven’t had access to the right data

Nightingale makes groundbreaking data available to a diverse community of researchers (3/12)

Nightingale also fights ‘dataset bias’: insufficient data, especially for underrepresented groups

Our datasets come from range of hospitals—not just Boston or Palo Alto (though we have those too): from a county system in the Bay Area to a huge public hospital in Taipei (4/12)

Nightingale is a non-profit entity and open platform, and it’s free to use

We fund and collaboratively build the datasets with health systems around the world, then make deidentified data available on a secure cloud platform (5/12)

Why are we doing this? Humans have made huge strides understanding how the body works and how it fails

But deep mysteries remain

Sudden cardiac death kills 300,000 Americans yearly, but even in the rear-view mirror, doctors can find no identifiable cause for the majority (6/12)

On cancer, we’re finding more small tumors with screening mammograms and colonoscopies, but have hardly moved the needle on rates of late-stage diagnoses or death

Doctors are missing something. Could AI complement human intelligence in the race to save our own lives? (7/12)

The key to solving these problems will lie in the massive volumes of complex, high-dimensional data produced every day: electrocardiograms, x-rays, CT scans, digital pathology images, and more

In our current health system, such imaging data are interpreted by humans (8/12)

But machines have new ways of ‘seeing’ signals and patterns in the data that humans cannot

By focusing on data that link medical images with real patient outcomes, Nightingale enables the creation of algorithms that learn from nature—not from human judgment (9/12)

Just as ImageNet jump-started ‘machine vision’, we want to help build a new field of ‘computational medicine’

Nightingale’s mission is to bring together researchers, incl. computer scientists and clinicians, around questions pushing the boundaries of medical science (10/12)

Nightingale is co-founded by @oziadias, a physician–scientist @UCBerkeley, and @m_sendhil, a computational and behavioral scientist @UChicago

Nightingale is generously supported by @SchmidtFutures @MooreFound Ken Griffin @PJMFnd (11/12)

Through a multi-funder collaborative, in partnership with our existing funders, we will build many new datasets over the coming years

Read more about our current datasets, and sign up for access here: nightingalescience.org (12/12)

cc: @AICenter_Booth @UCBerkeleySPH @LacunaFund @abiylfoyp @black_in_ai @QueerinAI @DS_x_HE @NetworkShuri
@GHFutures2030 @turinginst @AdaLovelaceInst @DataJusticeLab