AI4Health: A Collaboration for the Future of Health Care – USC Viterbi

Photo Credit: phonelamephotos

You need to be screened for a disease – do you want to have your picture taken, or go through extensive, expensive and invasive genetic testing?

Sounds too good to be true, but it’s a real question, thanks to advances in the work of artificial intelligence and wal abd alamjeedon research director USC’s Informatics 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 ISI researchers, who are coming together to form the Center on Artificial Intelligence Research for Health (AI4Health).

Center headed by the Director Michael PazzaniISI’s leading scientists will focus on research that enables breakthroughs in ethical artificial intelligence algorithms and systems to improve health care, fight misinformation, and analyze big data.

Tracing the Intersection of AI and Medicine

“ISI is already using AI for health research, one of the goals of AI4Health is to make it more systematic to make it easier for medical school researchers to find people with expertise in AI,” Pazani said. have to do.”

With that goal in mind, AI4Health will organize a number of events in collaboration with Keck School of Medicine at USC, The first event is scheduled for Thursday, December 1, 2022, from 11 a.m. to 1 p.m. on the USC Health Sciences Campus. In this programme, six researchers from ISI and six researchers from KK will give a five-minute talk each on their work. pazzini explained that these events would “try to find intersections and increase the number of collaborations between Keck and ISI.” Register at

data galore

“Health data has become much more plentiful in recent years,” Pazani said. Electronic health records, genomic data, information from sensors and wearables, and medical images – all data ready for analysis by AI. Information can also be obtained from publications in scientific journals and from social media posts, both of which continue to grow rapidly in volume.

And this level of big data is where AI and machine learning work best: looking for patterns within data, extracting information from text (i.e. magazines and social media), and making predictions based on data analysis.

AI4Health will use AI to capitalize on the growing amount of health data, while also finding solutions to the challenges that come with big data.

AI4Health Research Area

data management
For data to be useful, researchers need to be able to find it; It is helpful when it is curated, organized and annotated; And it should be accessible or distributed to interested parties. it’s all about doing data managementAnd many ISI researchers have been active in this area as it applies to health.

Carl Kesselmann, ISI Fellow Ad Director of Informatics Systems Research Division, built pipelines and workflows that enable Facebase 3 Data Management and Integration Hub To collect and curate huge datasets On craniofacial and dental development in humans and animal models. available to the wider craniofacial research community with the aim of all Advancing research in craniofacial development and malformation.

Yigal ArensISI’s Senior Administrative Director and Interim AI Division Director, and his team have worked closely with the National Institutes of Health and the National Institute of Mental Health over the years. NIMH Repository and Genomic Resource (NRGR). NRGR is a repository of biosamples and data of people suffering from mental health problems 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 available – will continue as part of AI4Health.

Knowledge Discovery and Data Analytics
Thanks to a plethora of health data, researchers are able to use AI to tease out patterns that may lead to breakthroughs. This often means analyzing electronic health records, medical images or data from wearable sensors to find new relationships.

How does this look in practice? Work of Senior Research Lead of ISI Greg Ver Steeg got that predictive factors for alzheimer’s Disease among patient medical data.

or ISI Research Lead abigail hornjob of To understand the behaviors that lead to diet-related diseases. Horn has linked a large amount cell phone mobility data and Health data to show that the food environment is strongly associated with diet-related diseases. Research also analyzes digital restaurant menus to determine the quality of food available to communities, hopefully paving the way Pathways to more effective public health policies or interventions for demographic groups most affected by poor diet.

But there are some health data that may not seem like “health data” at first glance. For example social media posts. Emilio Ferrara, leader of the ISI research team, 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 confluence of online politics and public health policies.

Another dataset for knowledge discovery and analysis is the ever-growing body of mature electronic journal publications. With AI, these can be analyzed to create databases of healthcare information.

perfect health
“Knowledge discovery refers to the research of how to use machine learning to find patterns in data,” Pazani said. perfect health “Refers to disease risk and finding the treatment that will work best for each individual.”

have priority for Keck School of Medicine at USCPrecision health uses genomic data or the identification of other factors to improve the health of a subset of the population. This could mean tailoring treatments to a group of patients, looking at viruses with a specific genome, and more.

Pazani gave an example, “There are many drugs for Parkinson’s disease that unfortunately are only about 25 percent effective, but for a certain group of patients they are 90 percent effective.”

This is where the role of AI comes in. He added, “So if you can understand the relationship between the patient’s genetic background and the drug, you can tailor the drug to a specific patient or a specific group of patients.”

And this type of analysis can have concrete results: “It’s hard to get something 25 percent effective approved by the FDA. It’s much easier to get something 90 percent effective approved for people with a certain genome.”

machine learning for health
AI and machine learning (ML) can also be used for clinical decision making by suggesting diagnoses or recommending interventions to physicians. using Abdalmalmaged’s work facial recognition analysis Predicting congenital adrenal hyperplasia is one example, and many of the ISI researchers are already heavily involved in this area.

Pazani, who has an extensive background in machine learning, has worked on using ML to detect cognitive impairment, recommend treatments for HIV patients, analyze chest X-rays, diagnose glaucoma, and more. Have done AI4Health researchers, including Pazzani, will continue their work with ML for health, while also exploring new opportunities and applications for ML in the health sector, aiming to create both better patient experiences and better health outcomes.

Improving the patient experience can also be done through telehealth By using AI systems to assist in remote health care. AI can analyze text in chats, voices and images to provide quick feedback to physicians or patients. Again, the analysis of those facial changes by Abd Alamjid is a great example of this, although there is a wide range of how telehealth can be improved with AI.

Pazani said, β€œIt can be a doctor’s appointment over chat to decide what kind of doctor you need to see. Or perhaps we can reassess and say ‘take two aspirin and call me in the morning’ for some people. And others, we can see that it’s an emergency and we’ll get them to the right specialist.

Catalysing Research and Seeking Breakthroughs

More than a dozen researchers already working on AI research as it applies to health will join the AI4Health initiative. With Pazhani as director, the center will be co-directed by ISI wal abd alamjeed, Jose-Luis Ambite, abigail horn And Greg Ver Steeg as co-director. This team, along with researchers from ISI and USC Will work to catalyze research, seek breakthroughs, and most importantly, work to improve health outcomes for patients.

Published on November 22, 2022

Last updated on November 22, 2022

Leave a Comment