https://www.iotworldtoday.com/wp-content/themes/ioti_child/assets/images/logo/mobile-logo.png
  • Home
  • News
    • Back
    • Roundups
  • Strategy
  • Special Reports
  • Business Resources
    • Back
    • Webinars
    • White Papers
    • Industry Perspectives
    • Featured Vendors
  • Other Content
    • Back
    • Q&As
    • Case Studies
    • Features
    • How-to
    • Opinion
    • Podcasts
    • Strategic Partners
    • Latest videos
  • More
    • Back
    • About Us
    • Contact
    • Advertise
    • Editorial Submissions
  • Events
    • Back
    • Embedded IoT World (Part of DesignCon) 2022
Iot World Today
  • NEWSLETTER
  • Home
  • News
    • Back
    • Roundups
  • Strategy
  • Special Reports
  • Business Resources
    • Back
    • Webinars
    • White Papers
    • Industry Perspectives
    • Featured Vendors
  • Other Content
    • Back
    • Q&As
    • Case Studies
    • Features
    • How-to
    • Opinion
    • Podcasts
    • Strategic Partners
    • Latest videos
  • More
    • Back
    • About Us
    • Contact
    • Advertise
    • Editorial Submissions
  • Events
    • Back
    • Embedded IoT World (Part of DesignCon) 2022
  • newsletter
  • IIoT
  • Cities
  • Energy
  • Homes/Buildings
  • Transportation/Logistics
  • Connected Health Care
  • Retail
  • AI
  • Metaverse
  • Development
  • Security
ioti.com

Connected Health Care


Getty Images

Microsoft’s AI Model Identifies When Medical Treatments Harm More Than Help

Dead-end Discovery uses the reinforcement learning ML framework because it's well-suited for health care
  • Written by Deborah Yao
  • 14th February 2022

Microsoft researchers have built an AI model that can identify when medical treatments meant to help patients actually ended up harming them.

The model, Dead-end Discovery, uses the reinforcement learning ML framework – where an agent learns from trial and error – because it is well-suited to health care. Health care is characterized by sequential decision-making: After looking at a patient’s condition, providers apply a treatment and observe the results. If the patient improves, the process repeats.

Medical care today is characterized by a focus on what to do to help the patient recover. But the researchers argued that this can be an “infeasible” goal. Instead, they propose an opposite approach: identify treatments to avoid and prevent a point of no return for the patient.

The researchers applied their model on real-world medical data that was publicly available, focusing on critically ill patients with sepsis in intensive care.

Their goal was to help providers “identify which subset of treatments could statistically cause further health deterioration so they could eliminate them when deciding on the next steps,” the researchers said in a blog.

They used a dataset of 53,400 hospital admissions between 2001 and 2012 and extracted a group of nearly 20,000 ICU patients with sepsis. (They applied offline reinforcement learning because they used a fixed dataset.) The researchers studied 72 hours of the patients’ stay in ICU, 44 observation variables and 25 treatments. They also used their AI model to identify patients showing signs of slipping into death.

The results: More than 12% of treatments given to patients who later died could have been detrimental – 24 hours before they passed away. Also, the AI model identified as much as 10 percent of patients slipping into a point of no return up to 48 hours before they died.

“While these percentages may seem small, more than 200,000 patients die of sepsis every year in U.S. hospitals alone, and any reduction of this rate would result in possibly tens of thousands of individuals who would otherwise survive,” they said.

The researchers said further uses of their AI model could include other areas of health care. Another possible application could be in finance, to alert investors when certain buy or sell decisions are likely to lose money – a financial dead end.

To access the code: https://github.com/microsoft/med-deadend

This article first appeared in IoT World Today’s sister publication AI Business. 

Tags: Artificial intelligence/machine learning Microsoft AI Dead-end Discovery Connected Health Care News

Related


  • VR Platform Trains Health Care Workers Caring for Dementia Patients.
    The platform deploys a 360-degree, video-shot VR world to help professionals conduct enhanced patient care
  • Quantum-Based AI Startup Partners With South Korean Giant to Develop Drugs
    InCerebro’s use of quantum mechanics is highly unusual for AI platforms.
  • ScaleUp AI 2022: Risks of ‘Wild West’ AI in Health Care
    Patients need to be put first when designing AI for health care deployments
  • Brain Implants Help Paralyzed Man Communicate Entire Sentences
    The groundbreaking medical technology helps nonverbal patients make requests through thoughts

Leave a comment Cancel reply

-or-

Log in with your IoT World Today account

Alternatively, post a comment by completing the form below:

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

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Related Content

  • UBTECH’s Mobile Disinfectant Robot Hits the Market
  • CES 2022: LG Picks Winning Startups
  • CES 2022: Bosch, Highmark Health to Tap AI for Pediatric Pulmonary Research
  • CES 2022 to Close One Day Early

Roundups

View all

IoT Product Roundup: PTC, Nokia, Arm and More

19th May 2022

IoT Deals, Partnerships Roundup: Intel, Nauto, Helium and more

14th May 2022

IoT Product Roundup: Amazon, Synaptics, Urban Control and More

27th April 2022

White Papers

View all

The Role of Manufacturing Technology in Continuous Improvement Ebook

6th April 2022

IIoT Platform Trends for Manufacturing in 2022

6th April 2022

Latest Videos

View all
Dylan Kennedy of EMQ

Embedded IoT World 2022: Dylan Kennedy of EMQ

Dylan Kennedy, EMQ’s VP of global operations, sat down with Chuck Martin at Embedded IoT World 2022.

Embedded IoT World 2022: Omdia’s Sang Oh Talks Vehicle Chip Shortage

Omdia’s automotive semiconductor analyst sits down with Chuck Martin at this year’s event

E-books

View all

How Remote Access Helps Enterprises Improve IT Service and Employee Satisfaction

12th January 2022

An Integrated Approach to IoT Security

6th November 2020

Webinars

View all

Rethinking the Database in the IoT Era

18th May 2022

Jumpstarting Industrial IoT solutions with an edge data management platform

12th May 2022

AI led Digital Transformation of Manufacturing: Time is NOW

9th December 2021

Special Reports

View all

Omdia’s Smart Home Market Dynamics Report

7th January 2022

Cybersecurity Protection Increasingly Depends on Machine Learning

28th October 2020

IoT Security Best Practices for Industry and Enterprise

20th October 2020

Twitter

IoTWorldToday, IoTWorldSeries

3D Home Printer to Build 72 Residences for National Homebuilder dlvr.it/SQhWSF https://t.co/XJOs70DqzH

19th May 2022
IoTWorldToday, IoTWorldSeries

Microsoft Ramping up Cybersecurity Service Offerings dlvr.it/SQhPR0 https://t.co/nYzaDRnyVY

19th May 2022
IoTWorldToday, IoTWorldSeries

IoT Product Roundup: PTC, Nokia, Arm and More dlvr.it/SQhNNF https://t.co/ZApdw3RHdu

19th May 2022
IoTWorldToday, IoTWorldSeries

Britain’s postal service has plans to run a fleet of autonomous #drones to make rural postal deliveries easier.… twitter.com/i/web/status/1…

19th May 2022
IoTWorldToday, IoTWorldSeries

Britain’s postal service has plans to run a fleet of autonomous #drones to make rural postal deliveries easier.… twitter.com/i/web/status/1…

19th May 2022
IoTWorldToday, IoTWorldSeries

Tesla Plans ‘Many Cool Updates’ at Annual Event dlvr.it/SQhLLP https://t.co/kgSTGBrYrG

19th May 2022
IoTWorldToday, IoTWorldSeries

@JohnDeere’s acquisition of #AI startup Light continues to advance its roadmap toward @autonomous farming.iotworldtoday.com/2022/05/19/joh…

19th May 2022
IoTWorldToday, IoTWorldSeries

📣JUNE DIGITAL SYMPOSIUM Drive your strategy forward and stay on the #Healthcare and #IndustrialIoT pulse with key… twitter.com/i/web/status/1…

19th May 2022

Newsletter

Sign up for IoT World Today newsletters: vertical industry coverage on Tuesdays and horizontal tech coverage on Thursdays.

Special Reports

Our Special Reports take an in-depth look at key topics within the IoT space. Download our latest reports.

Business Resources

Find the latest white papers and other resources from selected vendors.

Media Kit and Advertising

Want to reach our audience? Access our media kit.

DISCOVER MORE FROM INFORMA TECH

  • IoT World Series
  • Channel Futures
  • RISC-V
  • Dark Reading
  • ITPro Today
  • Web Hosting Talk

WORKING WITH US

  • Contact
  • About Us
  • Advertise
  • Login/Register

FOLLOW IoT World Today ON SOCIAL

  • Privacy
  • CCPA: “Do Not Sell My Data”
  • Cookies Policy
  • Terms
Copyright © 2022 Informa PLC. Informa PLC is registered in England and Wales with company number 8860726 whose registered and Head office is 5 Howick Place, London, SW1P 1WG.
This website uses cookies, including third party ones, to allow for analysis of how people use our website in order to improve your experience and our services. By continuing to use our website, you agree to the use of such cookies. Click here for more information on our Cookie Policy and Privacy Policy.
X