Penn offers free machine learning platform to analyze data

By | May 20, 2019

The Penn Medicine Institute for Biomedical Informatics has launched a free, open-source automated artificial intelligence tool for both laymen and experts to conduct data analysis.

“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,” says Jason Moore, director of the Institute for Biomedical Informatics.

According to Moore, his team “has taken three years to develop this system so that it can be approachable by anyone, regardless of their training or experience,” with the goal of creating a “free and simple system that is still robust enough to transform the way we approach biomedical research—which I think we’ve accomplished.”

The tool, called PennAI, was developed with funding from the National Institutes of Health to constantly learn the best approaches for analyzing data and to provide recommendations to users.

“PennAI is a platform to help researchers leverage supervised machine learning techniques to analyze data without needing an extensive data science background, and can also assist more experienced users with tasks such as choosing appropriate models for data,” according to the description on GitHub. “Users interact with PennAI via a web interface that allows them to execute machine learning experiments and explore generated models, and has an AI recommendation engine that will automatically choose appropriate models and parameters.”

Also See: More organizations embrace open source for analytics

In addition, Moore contends that by making this kind of analysis open source, PennAI addresses the “black box” phenomenon by enabling physicians to understand internal workings of the tool and how it arrived at the results.

Read More:  Dermicoll Pure Marine Collagen to Aid Psoriasis Treatment, Eczema Treatment, Pruritus, Skin Irritation & Dryness - Removes Scales, Soothes Skin, Promotes Collagen Production - Steroids Free - 100 ml

“If you’re going to use machine learning for patients, you want to trust it completely,” added Moore. “You want to be able to look under the hood. This allows for that, which builds some faith among clinicians, which is important for user buy-in.”

For reprint and licensing requests for this article, click here.

Health Data Management: Feed