AI is becoming more accessible to researchers of any age after The Penn Medicine Institute for Biomedical Informatics launched a free, open-source automated machine learning system for anyone to use, Penn AI.
The system aims to lower the barrier to entry in the AI world. Penn AI is meant to be used for many reasons, such as high school students twiddling with basketball statistics or trained researchers seeking correlations between environmental factors and cancer, according to a press release.
“The problem with machine learning tools is that machine learning people build them, so they’re usually only usable by those with high levels of training,” Jason Moore, PhD, director of the Institute for Biomedical Informatics and a professor of Biostatistics, Epidemiology and Informatics, said in a statement. “My team has taken three years to develop this system so that it can be approachable by anyone, regardless of their training or experience. Our goal has been to make a free and simple system that is still robust enough to transform the way we approach biomedical research—which I think we’ve accomplished.”
Users are able to bring in their own datasets on the system or use the hundreds already available on the platform. The dashboard can be run on any laptop, and the system is designed to learn as it goes along and improve with more experiences. The system also helps solve one of the biggest challenges in AI––the black box problem, where researchers can’t see how an AI system landed on its results. Penn AI’s analysis is open source, giving insight into the mechansims behind each analysis. Not to mention, Penn AI is free.
The barrier to use is lowered, in part, because the system is uses automated machine learning, allowing the AI to run different analyses with different variables and methods without human input. Machine learning without automation is more complex to use and still requires some “guesswork,” even for experts, according to the press release.
“I want this to be self-service, clinical AI,” Moore said. “I believe that this tool can make it so that it will soon be routine for a doctor to say, ‘I want to look at the associations between sex, age, smoking and different diseases,’ and then have this tool answer their questions.”
The National Institutes of Health research grants and infrastructure and support grants helped fund the development of the tool.