• Subscribe

Can AI solve the opioid crisis?

Speed read
  • Opioid addiction is a US public health emergency
  • Prescription medications as well as 'street' drugs are part of the problem
  • Watson’s capacity to capture and analyze unstructured data will increase understanding of patients’ needs

Since 1999, the number of deaths resulting from opioid overdose has quadrupled, rising to 100 a day in 2017. Prescription opioids are considered the main factor driving this spike. 

To address the problem, Measure Action Prevent (MAP) Health Management and IBM Watson Health have joined forces.

Mapping an AI solution

Founded in 2011, MAP was formed in reaction to the pattern of poor outcomes for patients treated for substance use disorder (SUD). Using tools like telehealth, remote Bluetooth enabled breathalyzers, and biometric pill dispensation devices, MAP has engaged over 200 providers to improve behavioral health and addiction treatment, 

Courtesy Centers for Disease Control.

Jacob Levenson, MAP’s chief executive officer, calls SUD a chronic disease that the US treats using an acute care model. In other words, patients must fend for themselves after leaving a rehab program.

To help patients keep their disease in remission, MAP offers post-acute support to identify which patients are more likely to have addiction relapse.

MAP relies on predictive analytics and machine learning, and has been using cognitive computing since 2011. They expect Watson to enhance their services by exploiting its capacity to organize large amounts of currently unstructured data.

Though there is no end in sight to the national opioid epidemic, data-informed treatment is essential to effectively manage chronic disease. ~Jacob Levenson

Watson is IBM’s question-answering artificial intelligence system, famous for its victorious Jeopardy outing. Harnessing the computational power of ninety IBM servers, Watson runs at roughly 80 Tera FLOPs and can process 500 GB per second.

Since its television debut, Watson has been applied to many domains, such as education, meteorology, and healthcare.

A minimum of 50,000 new individuals are slated to receive MAP services in the next 12 months, and Levenson says the partnership with Watson will enable MAP to improve the way they use patient data to understand relapse risk.

<strong>$64,000 question.</strong> Among the more than 64,000 drug overdose deaths estimated in 2016, the sharpest increase occurred among deaths related to fentanyl and fentanyl analogs (synthetic opioids) with over 20,000 overdose deaths. Courtesy CDC WONDER.

MAP delivers its services in two ways. First, health insurance plans contract with them to provide peer recovery support.

MAP also provides in-depth analytics to insurance plans about patient risk and provider quality level.

With sound data and Watson’s analytical capacity, MAP can precisely tailor treatment to an individual’s needs. The use of technology in peer recovery support is in its early stages, but health plans are beginning to adopt it, Levenson notes.

“22.5 million Americans fit the criteria for SUD,” Levenson explains. "Though there is no end in sight to the national opioid epidemic, data-informed treatment is essential to effectively manage chronic disease."

Join the conversation

Do you have story ideas or something to contribute? Let us know!

Copyright © 2017 Science Node ™  |  Privacy Notice  |  Sitemap

Disclaimer: While Science Node ™ does its best to provide complete and up-to-date information, it does not warrant that the information is error-free and disclaims all liability with respect to results from the use of the information.

Republish

We encourage you to republish this article online and in print, it’s free under our creative commons attribution license, but please follow some simple guidelines:
  1. You have to credit our authors.
  2. You have to credit ScienceNode.org — where possible include our logo with a link back to the original article.
  3. You can simply run the first few lines of the article and then add: “Read the full article on ScienceNode.org” containing a link back to the original article.
  4. The easiest way to get the article on your site is to embed the code below.