{"id":367,"date":"2020-09-15T09:00:00","date_gmt":"2020-09-15T13:00:00","guid":{"rendered":"https:\/\/www.macloo.com\/ai\/?p=367"},"modified":"2020-09-14T10:09:18","modified_gmt":"2020-09-14T14:09:18","slug":"journalists-use-machine-learning-to-examine-medical-device-records","status":"publish","type":"post","link":"https:\/\/www.macloo.com\/ai\/2020\/09\/15\/journalists-use-machine-learning-to-examine-medical-device-records\/","title":{"rendered":"Journalists use machine learning to examine medical device records"},"content":{"rendered":"\n

Some investigations in the public interest require journalists<\/strong> to search through large quantities of official documents. Often the set of documents is very diverse \u2014 that is, the format, structure, and even language of the documents might vary greatly.<\/p>\n\n\n\n

One of the more impressive investigations I know of is the ongoing Implant Files<\/a> project, conducted originally by 250 journalists in 36 countries. The purpose: To examine how medical devices (specifically, those implanted into human bodies) are “tested, approved, marketed, and monitored” (source<\/a>). I’ve heard this project discussed at conferences, and I’m full of admiration for the editors and reporters involved, led by the International Consortium of Investigative Journalists<\/a> (ICIJ).<\/p>\n\n\n\n

At the heart of the investigation, with its first results published in 2018, was “an analysis of more than 8 million<\/strong> device-related health records, including death and injury reports and recalls.”<\/p>\n\n\n\n

“The entire process involved text mining, clustering, feature selection, association rules and classification algorithms to identify events not always described consistently in different parts of the data.”<\/p>\u2014How ICIJ Used Machine Learning to Help Find Medical Device Issues<\/a><\/cite><\/blockquote>\n\n\n\n

These implanted devices \u2014 hip replacements, defibrillators, breast implants, intraocular lenses, and more \u2014 are used all around the world<\/em>. When something goes wrong and a product recall is issued, however, the news might not spread to all the locations where the devices continue to be used<\/em> in new surgeries for new patients. Moreover, people who already have a faulty implant might not be notified<\/em>. This is why a global investigation was sorely needed.<\/p>\n\n\n\n

\n