You need to be screened for a disease – would you rather have your photo taken, or go through extensive, expensive and invasive genetic testing?
Sounds too good to be true, but it’s a real question thanks to advancements in artificial intelligence and the work of Wael AbdAlmageed, research director at USC’s Information Sciences Institute (ISI), who is using AI and facial recognition analysis to accurately predict congenital adrenal hyperplasia, a disease that causes mild facial changes.
This is just one example of the work being done by the researchers at ISI who are coming together to form the Center on Artificial Intelligence Research for Health (AI4Health).
The center, led by director Michael Pazzani, principal scientist at ISI, will focus on research that enables breakthroughs in ethical artificial intelligence algorithms and systems to improve health care, fight misinformation and analyze big data.
Finding the Intersection of AI and Medicine
Pazzani said, “ISI has already been using AI for health research, one of the goals of AI4Health is to do it more systematically to make it easier for medical school researchers to find people with expertise in AI.”
With that goal in mind, AI4Health will be holding a number of events in collaboration with Keck School of Medicine at USC. The first event is set for Thursday, December 1, 2022, 11am to 1pm at the USC Health Sciences Campus. At this event, six researchers from ISI and six researchers from Keck will each give five-minute talks on their work. Pazzani explained these events will seek to “find intersections between Keck and ISI and increase the number of collaborations.” Register at AI4Health.isi.edu.
“Health data has become much more plentiful in recent years,” said Pazzani. Electronic health records, genomic data, information from sensors and wearables, and medical images – all of this data is ripe for analysis by AI. Information can also be gleaned from scientific journal publications and social media posts, both of which continue to rapidly increase in quantity.
And this level of big data is where AI and machine learning work best: looking for patterns within the data, pulling information from text (ie. journals and social media), and making predictions based on data analysis.
AI4Health will use AI to capitalize on the increasing amounts of health data, as well as find solutions for the challenges that come along with big data.
AI4Health Research Areas
For data to be useful, researchers need to be able to find it; it’s helpful if it’s curated, organized and annotated; and it must be accessible or distributed to interested parties. Making all of that happen is what’s known as data management, and several ISI researchers have been active in this space as it applies to health.
Carl Kesselman, ISI Fellow and director of the Informatics Systems Research Division, created the pipelines and workflows that enable the FaceBase 3 Data Management and Integration Hub to collect and curate huge datasets on craniofacial and dental development in humans and animal models. All of which are available to the wider craniofacial research community with the goal of advancing research into craniofacial development and malformation.
Yigal Arens, ISI Senior Administrative Director and Interim AI Division Director, and his team have worked for years with the National Institutes of Health and the National Institute of Mental Health to create the NIMH Repository and Genomic Resource (NRGR). The NRGR is a collection biosamples and data from people diagnosed with mental health issues and their relatives. Datasets from the repository are made available to researchers with the goal of stimulating research and development by providing timely access to primary data and biomaterials.
Important work like this — work that facilitates the use of the plethora of health data that is out there — will continue as part of AI4Health.
Knowledge Discovery and Data Analytics
Thanks to the plethora of health data, researchers are able to use AI to tease out the patterns that can lead to breakthroughs. This often means analyzing electronic health records, medical images, or data from wearable sensors to discover new relations.
What does this look like in practice? The work of ISI senior research lead Greg Ver Steeg that has found predictive factors for Alzheimer’s disease among patient medical data.
Or ISI research lead Abigail Horn’s work to understand behaviors that lead to diet-related diseases. Horn has linked vast amounts of cell phone mobility data and health data to show that food environment is strongly correlated to diet-related diseases. The research also analyzes digital restaurant menus to to determine the quality of food available to communities, hopefully paving the way for more effective public health policies or interventions for demographic groups affected by poor diet.
But there is some health data that, at first glance, might not seem like “health data.” Social media posts, for example. Emilio Ferrara, ISI research team leader, has worked to counter social media manipulation and misinformation regarding a number of public health issues: COVID-19 conspiracies; anti-vax campaigns; tobacco promotion; and the conflation of politics and public health policies online.
Another dataset ripe for knowledge discovery and analysis is the ever-growing body of electronic journal publications. With AI, these can be analyzed to create databases of health care information.
“Knowledge discovery refers to the research of how to use machine learning to find patterns in the data” said Pazzani, who followed up by explaining that precision health refers to “finding the disease risks and treatments that will work best for each person.”
A priority for the Keck School of Medicine at USC, precision health uses the identification of genomic data or other factors to improve the health of a subset of the population. This can mean tailoring treatments to a group of patients, looking at a virus with a specific genome, and more.
Pazzani gave an example, “There are a number of drugs for Parkinson’s Disease that unfortunately are only about 25 percent effective, but for a certain group of patients they’re 90 percent effective.”
This is where AI comes in. He continued, “So if you can understand the relationship between a patient’s genetic background and the drug, then you can tailor a drug to a specific patient or a specific group of patients.”
And this type of analysis can have tangible consequences: “Getting something that’s 25 percent effective approved by the FDA is difficult. Getting something approved that’s 90 percent effective for people with a certain genome is much easier.”
Machine Learning for Health
AI and machine learning (ML) can also be used for clinical decision-making by suggesting diagnoses or recommending interventions to clinicians. AbdAlmageed’s work using facial recognition analysis to predict congenital adrenal hyperplasia is an example, and many researchers at ISI are already heavily involved in this field.
Pazzani, who has an extensive background in machine learning, has worked to use ML to detect cognitive impairment, recommend treatment for HIV patients, analyze chest x-rays, diagnose glaucoma, and more. AI4Health researchers, including Pazzani, will continue their work with ML for health, while also looking for new opportunities and applications for ML in the health space, with the goal of creating both better patient experiences and improved health outcomes.
Improving patient experience can also be done through telehealth by using AI systems to assist in remote health care. AI can analyze text in chat, voice and images to provide quick feedback to clinicians or patients. Again, the analysis of those facial changes done by AbdAlmageed is a great example of this, however there is a wide range of how telehealth can improve with AI.
Pazzani said, “This could be a doctor’s visit on chat to decide which type of doctor you need to see. Or perhaps we can give reassurance and say ‘take two aspirin and call me in the morning’ for some people. And others, we might see that it’s an emergency and we’ll get them to the right specialist.”
Catalyzing Research and Looking for Breakthroughs
More than a dozen researchers already working on AI research as it applies to health will be joining the AI4Health initiative. Alongside Pazzani as director, the center will be co-directed by ISI’s Wael AbdAlmageed, Jose-Luis Ambite, Abigail Horn and Greg Ver Steeg as co-directors. This team, along with researchers from ISI and across USC will work to catalyze research, look for breakthroughs, and most importantly, work to improve health outcomes for patients.
Published on November 22nd, 2022
Last updated on November 28th, 2022