WPI professor says global health equity lies at intersection of technology, science and humanities

WPI professor says global health equity lies at intersection of technology, science and humanities

As humanitarian needs reach an all-time high, the pursuit of global health equity becomes even more important.Last year, the World Health Organization established Half of the world’s population is not fully covered by basic health services, and 2 billion people face financial hardship due to out-of-pocket costs.

These disparities are not new, but they are growing—especially when huge obstacles like pandemics and climate change make addressing inequality an even greater challenge. We’re told that advanced technologies promise to improve health outcomes and access, but how do we get there?

Karen Oates, professor of biology and biotechnology, is also directing a new projectGlobal Health Degree Program Attended Worcester Polytechnic Institute, joined GBH All circumstances have been considered Host Arun Rath discusses how to ensure new technologies are used effectively and ethically. What follows is a lightly edited transcript of the conversation.

Aaron Russ: Starting with a big picture question, can you give us a sense of what global health equity looks like now and how it has changed over the past decade?

Karen Oates: certainly. I think it’s important for us to understand the difference between public health and global health. Global health is really interested in the major health problems faced by many different countries.

While public health may be geographically located within a certain element, global health is actually looking at those big, broad, interdisciplinary problems and understanding who is affected, why they are affected and what we can do to help mitigate them Some health inequalities exist across the globe.

Lars: So are issues like pandemics and climate change truly global issues?

Oates: Of course, even in the United States there are things we have to think about – things like water or nutrition, things that impact the overall health of our planet.

Lars: As I mentioned, Worcester Polytechnic Institute will soon be offering a master’s program led by you that will focus on global public health. You said the program’s courses will focus on how the future of global health lies at the intersection of technology, science and the humanities. Can you talk about that?

Oates: I think we’re really making progress on health inequalities and understanding how to mitigate them. We can do this largely because artificial intelligence, machine learning, epidemiology, and big databases are now virtually within our reach.

What we plan to do is connect patterns, different sources of inequality, and find those patterns—the connections between them. It’s almost like triangulating different types of problems for which it’s difficult for individual researchers to pinpoint the root cause. It will take years, but with machine learning and artificial intelligence, it will take us a fraction of the time to actually try to solve some of the world’s biggest problems.

Lars: What you call triangulation is like solving a problem by looking at it from multiple angles. How can artificial intelligence and machine intelligence help you do this?

Oates: What we’re doing is creating a database that looks at specific groups of people who are affected by heavy metals and so on. We can then look at the geographical location of different factories. We can then look at the flow of water or even well water in the area. Is this the number of parameters we can start combining? What could be the reason? Where could the cause come from? Ultimately, what can we do? All this is powered by artificial intelligence. We’re putting these large databases together to solve problems like this.

Lars: When it comes to underserved and under-resourced communities, which are often disproportionately impacted and often left out of these conversations, I know that’s a concern with AI and data as well, that data gaps may reflect bias. How do we implement this technology in a way that ensures we take everything into account?

Oates: This is an important question on several levels. One is: whose data? Where does the data come from? What are the biases of the researchers entering the data? But I actually think what’s more important is that when we get this data, that data is transparent.

I think one of the beautiful things about this program is that we’re very focused on the fact that it’s going to be live work, and the people involved are the people most affected by it. WPI is really lucky. We have had beautiful project centers around the world for over 40 years and we will take advantage of this by bringing in individuals from the region to take part in any research we undertake.

Lars: It sounds like the data collection part is a pretty big human undertaking. How do you scale?

Oates: We want to be able to go into a country and collect data ourselves with the help of people on site and in the field. We want them to be part of the solution. We really don’t want to come in and say, “This is your problem.” We want them to be involved, and when we do that, we’re going to make them partners in everything we do.

Lars: It’s amazing to hear you talk about it – how to combine very basic human data collection with really advanced machine intelligence.

Oates: that’s right. One thing that developments in global health tell us is that both artificial intelligence and machine learning are at the next level. We can now design even something as simple as a water filtration system on site. We can design using materials you would find in a country where the talent is available.

Lars: How close are we now to having all the data you’d like to see to start implementing a solution like this?

Oates: I think it’s very situation specific. I think we’re pretty close when it comes to using GIS to identify water sources. When we look at things like metal poisoning and its effects on children, we’re able to create pretty good databases.

We’re still in the data accumulation phase, but this is already moving very quickly. The future of global health will really lie in being able to identify good data sources, go into the field, create and validate what’s in the database, and then start connecting.

When it comes to big data machine learning, we are still in its infancy. This project from WPI uses artificial intelligence to connect and find patterns that would be difficult to see without the use of big data and artificial intelligence. We use this data to help define and understand global issues.

Leave a Comment

Your email address will not be published. Required fields are marked *