Our Faculty Research
The Center for Applied AI is proud to share research from our talented faculty members and affiliates.
Our Faculty Research
Our Research Focus
At the Center, we pursue cutting-edge research that investigates how machine learning and AI change the way we do business, science, and social policy. Our work challenges assumptions and pushes the boundaries of social science.
NEW: Machine Learning As a Tool for Hypothesis Generation
We found a way to communicate with an algorithm to generate an original hypothesis. Read on to see how we applied it to predict judges' decisions.
NEW: Machine Learning As a Tool for Hypothesis Generation
NEW: Automating Automaticity
Our algorithmic audits of Facebook in the US and India find significant out-group bias in the News Feed algorithm (e.g., whites are less likely to be shown Black friends’ posts, and Muslims less likely to be shown Hindu friends’ posts), suggesting a need to rethink how large-scale algorithms use data on human behavior.
NEW: Automating Automaticity
Nightingale Open Science
We are building a secure, open data hub that will bring together health systems and research communities from across the world, enabling researchers to identify breakthroughs in diagnostics and clinical decision-making. Our mission is to revolutionize the field of computational medicine by connecting world class researchers to forward thinking medical systems.
Nightingale Open Science
Algorithmic Bias in Healthcare
Our researchers published an article in Science that showed significant racial bias in a widely deployed health-care algorithm that selects patients for a managed care plan. Were that bias to be eliminated, the number of African American patients selected would nearly double. Working with the developer of the algorithm, we found solutions to dramatically reduce the bias and improve the care of many patients.
Algorithmic Bias in Healthcare
Reducing Racial Disparities in Knee Pain using Artificial Intelligence
Reducing health disparities using artificial intelligence is a key focus area for the Center for Applied Artificial Intelligence. The Center's Nightingale Open Science has recently done research using AI to address the racial disparities associated with knee pain.
Reducing Racial Disparities in Knee Pain using Artificial Intelligence
Making the Invisible Epidemic Visible
New approaches can help connect domestic violence survivors to services. Our faculty bring to light the missed opportunities of the healthcare industry in regards to domestic violence reporting.
Making the Invisible Epidemic Visible
Nightingale Challenge
The goal of this challenge is to use the provided labels to predict whether there are any TB bacilli present in the microscopy images of the holdout dataset. The challenge will run from March 1-April 1, 2024. Win up to $5,000.
Learn more here
—
Data Sources
We are happy to provide access for Booth researchers and affiliated faculty to datasets for relevant research projects. Please email the Center if you're interested in learning more about any of the datasets listed below.
SetuServ
SetuServ can provide access to datasets of customer/fan reviews, social media commentary, survey responses, call center data and other forms of customer/fan feedback in a variety of domains.
IBM MarketScan®
CAAI partners with the Center for Health and the Social Sciences to offer Booth researchers access to a variety of Marketscan health datasets. You can find more info on their website.
ShareThis
ShareThis has access to consumer behavior data from its 3.5m websites across the US and the world.
NightingaleOpenScience
Nightingale is preparing to launch its data research platform, offering access to health datasets from systems in the US and abroad, focusing primarily on image data, including x-rays, ECGs, etc.
If you are interested in a dataset you do not see listed, please reach out. We are happy to work with PhD students, post-docs, and Booth faculty to help them acquire interesting and relevant datasets for their research.
Former Projects
COVID-19 Research
We are creating a tool to help doctors make important triage decisions for COVID-19 patients. Using chest x-rays, we are working to predict the likelihood that a patient may suffer from pulmonary collapse within the next few days, helping physicians better distribute care and save lives.
COVID-19 Research
Pause Regulations
We crowdsourced recommendations for regulatory pauses from frontline physicians and workers who are most affected by unnecessary bureaucracy. After an in-depth analysis, we identified the most feasible regulations to pause and are pursuing meaningful changes.
Pause Regulations
Precision Epidemiology
Partnering with the Harris School, we are assembling a detailed dataset that will allow researchers, governors, mayors, and even the federal government to create highly targeted interventions.
Precision Epidemiology
Contact the Center for Applied Artificial Intelligence
Learn more about how you can engage with the Center for Applied Artificial Intelligence.
Contact Us
