Predicting Health Outcomes With Machine Learning

Posted on 25th October 2013 in health

Eric Horvitz, MD, PhD co-director, Microsoft Research

  • from data to predictive models to decision-making
  • costly challenge of re-admissions: they worked with Washington Medical Center, which had been accumulating lots of data on ER visits. Built a predictive model of readmissions: identified relevant evidence out of 25,000 indicators: if “fluid” is in the record, that’s an indicator the person will be readmitted.
  • Created tool called “Readmissions Manager.
  • running this program worldwide
  • example of Congestive Heart Failure. $35 b. annual cost. Should you invest in an intervention program?
  • another big challenge is hospital-associated infection. $20 b.  a year cost. In top 10 causes of deaths in the US. Beyond looking at EMR, they introduced analysis by space and time. Another factor is the patient’s path through various parts of the hospital: could predict what % of the patient population got infections in what part of the hospital. Analyzed various factors, such as which unit of hospital they were in, who was the attending doc.
  • New kinds of predictions: “surprise models” — looked at people who were re-admitteed in 72 hrs. for a condition that wasn’t on chart before.
  • new set of data: patients searching web. For example, nutritional content in logs of downloaded recipes. (Maine people downloaded a lot of recipes with high carb content). This was because they found a lot of older ppl in DC area had downloaded recipes with high sodium content in holiday season.
  • looked at Twitter feeds about birth of child — overlaid lots of people who’d just had babies: about 12% of women showed signs of crashing in terms of mood (post-partu m depression is underreported). Suggests you might be able to intervene in advance to help them.
comments: Comments Off on Predicting Health Outcomes With Machine Learning tags: ,

More Demos of Connected Health Devices

Posted on 25th October 2013 in health
  • Connected Wellness
    • patient controls record
    • each patient has “personal circle of care” — providers, relatives, etc.
    • plain-English plans from templates
    • links to videos, etc.
    • can track vital signs, subjective feelings, etc.
  • Reflexion Health
    • platform to reach patient in home. TV perhaps most used device in home? Why don’t we use it for health?
    • Use Kinect
    • TV-based PT
    • 40-50 exercises in system now
comments: Comments Off on More Demos of Connected Health Devices tags: ,

President of EPIC on future of EMRs

Posted on 24th October 2013 in health

Carl Dvorak, ceo of EPIC, talked about amazing range of ways they’re using apps to integrate patients into EMRs:

  • lots of emphasis on mobile devices
  • messaging & e-visits
  • mobile check in
  • patient-reported outcomes
comments: Comments Off on President of EPIC on future of EMRs tags: ,

Innovations in Virtual Care: Engaging Consumers in their Health

Posted on 24th October 2013 in health

Presentations @ Center for Connected Health Symposium:

  • Michael McGarry, Ascension Health
    • directs their Innovations Accelerator Team.
    • how do we engage patients during 99% of time when they’re not getting care?
  • Eric Rock, CEO, Vivify Health
    • emphasis on connection and simplifiecation
  • Dr. Dmitri Talantov
    • he’s with Janssen Healthcare Innovation @ J & J
      • integrated care systems,
      • focus on orthopedic, cardio-vascular rehab
      • need strong incentives for providers to engage under new delivery systems
  • how do you engage consumers?
    • barriers: need is for high-risk patient who doesn’t understand the tech
    • new incentives in several states for daily reporting
    • may have population that doesn’t want to engage — want to sit on couch!
    • “restaurants probably have more impact on their condition than anything we can do”
    • “insane opportunity in keeping people healthy!”
  • how do you sell virtual care to providers?
    • “pay them!”
    • simplicity for them
    • can’t expect them to interrupt their routines for something new.
  • patients own their data

comments: Comments Off on Innovations in Virtual Care: Engaging Consumers in their Health tags: ,

New IDC report says IoT has reached tipping point for government

As you may know, I’ve been critical of the Obama Administration in the past for ignoring the Internet of Things’ potential. Maybe this report will light a fire under them!

IDC has just released a major report, The Coming of Age of the Internet of Things in Government. Research Director Massimiliano Claps concludes that:

“The Internet of Things is reaching a tipping point that will make it a sustainable paradigm for practical applications. The public sector’s use of the IoT is still limited but emerging strongly in the transport, public security, and environmental sustainability domains …. IoT applications in the public sector can span a variety of domains: public security, defense, environmental protection, transport, and health. In each of these domains, connected objects can provide situational awareness that can help citizens and government personnel act and react at the operational level, monitor the status or behavior of people and assets to make management decisions, and support very fine-grained, sensor-driven analytics that help with planning decisions.”

Couldn’t agree more!

The report says that despite the IoT’s promise to revolutionize a wide range of governmental services, most of the applications to date have focused on environmental monitoring, transportation and security. “The limitations have to do as much with the early stages of the technology as with the management approach to using it.”

It cites some of the emerging m-medicine services that promise to both improve patient care and reduce costs such as around-the-clock mobile vital signs monitoring.

The Coming of Age of the Internet of Things in Government urges agencies to:

“…consider multiple management factors that will influence the ability to harness the benefits of IoT, including the volume, variety, velocity and value of data that are going to be generated, the massive scale of the infrastructure, the complexity of governance, the financial sustainability and the legal aspects.”

I hope this report will prove the impetus for a major new emphasis on governmental applications for the IoT!">Stephenson blogs on Internet of Things Internet of Things strategy, breakthroughs and management