In parallel with Nightingale Open Science, Ziad Obermeyer and Sendhil Mullainathan also lead Nightingale Open Labs, a research network housed jointly at UC Berkeley and the University of Chicago. We work on research projects that blend machine learning, economics, and medicine, to answer some of the most important questions in health. Here are some of the projects we're working on now:
Drawing on our work showing that machine learning can help doctors diagnose heart attack in the ER, we are designing and deploying a large-scale randomized trial of the algorithm in multiple hospitals across the Providence system. This will teach us about how doctors interact with and adopt algorithms, and whether or not better predictions actually translate into better health outcomes.
In the US alone, 300,000 people drop dead of sudden cardiac death every year. What makes this particularly tragic is that implantable defibrillators could have prevented many of these deaths—if we had just known which patients needed it. Machine learning predictions on risk of sudden cardiac death could one day help target defibrillators to patients who need them.
In ERs across the world, doctors facing bed shortages must decide if patients with respiratory infections like COVID-19 are safe to go home, or need hospital-level monitoring. The current state of medical knowledge is failing here: some patients in the hospital ultimately do not require advanced care, wasting beds; others are sent home, only to deteriorate rapidly. Linking chest x-ray data to pulmonary outcomes will enable us to create tools to optimize triage and diagnosis.
The United States performs 2 million breast biopsies, at a cost of $4 billion per year, to find out who needs treatments for early-stage breast cancer, when success rates are highest. But 98.6% of biopsies come back negative, and breast cancer remains the second cause of cancer death among women. Linking cancer biopsy slides to cancer registry data and Social Security mortality data would allow for the study of outliers: low-grade biopsies that progress, metastasize, or kill; high-grade biopsies that do not. This work can yield new insights into which cancers will spread and which can be left alone, and also about tumor biology, by identifying potentially new features of the image (e.g., stromal tissue) linked to prognosis.
In ERs across the world, doctors facing bed shortages must decide if patients with suspected or confirmed COVID-19 are safe to go home, or need hospital-level monitoring. The current state of medical knowledge is failing here: some patients in the hospital ultimately do not require advanced care, wasting beds; others are sent home, only to deteriorate rapidly. Linking chest x-ray data to a set of hard pulmonary outcomes will enable the development of develop models that can predict pulmonary deterioration due to COVID and other similar respiratory illnesses. This could be applied to create tools for triage and diagnosis, and optimize over-burdened hospitals.
Every year, millions of heart attacks happen around the world. But up to 78% of them are undiagnosed or “silent”. This means a large fraction of people with heart attack never get the cocktail of drugs known to save lives, by preventing future heart attacks and sudden death. Today, doctors can order tests (like MRIs or ultrasounds) to diagnose patients when they suspect a prior heart attack. But the reason so many heart attacks remain silent is precisely because doctors and patients don’t even suspect a heart attack has happened. Linking electrocardiogram waveforms (ECG) to electronic health records will allow the exploration of new ways to diagnose these undiagnosed heart attacks at scale and could dramatically expand access to life-saving medications
The opiate epidemic has shown how widespread pain is—but what causes it? Decades of research have shown poor correlation between findings on imaging and patients’ reports of pain, e.g. MRI findings and low back pain. Linking lower extremity x-rays (hips, legs) to patient reports of pain, and downstream outcomes like fractures, joint replacements can enable researchers and clinicians to gain a better understanding of the organic drivers of pain.
For many older patients—and some younger ones—a fracture marks the beginning of the end. Even though the fracture itself is seldom fatal, it sets off a downward spiral: pain, decreased mobility, worse physical fitness, debility, and death. This is why screening for osteoporosis is so critical: the appearance of bones on a special type of x-ray (called a DEXA scan) shows us who is at high risk of fractures, and lets us start treatments to prevent them before they happen. Routine x-rays combined with algorithms may do just as well for diagnosing low bone mineral density. In fact, they could do better: by predicting future fractures, machine learning could provide new ways to screen for frailty, and proactively identify those who would benefit from early treatment and physical therapy.