Watson Health Scientific Update
At IBM Watson Health, we are focused on applying next-generation AI, data and analytic technologies to major healthcare challenges so people around the world can live better, healthier, longer lives.  In the three short years since IBM launched Watson Health, we are now working with more than 15,000 client and partners around the globe and our efforts are having an  impact across various areas of health – whether it’s helping people with diabetes better manage glucose levels, informing clinical decision-making related to cancer with a suite of oncology products or supporting important new findings that could accelerate new treatments for diseases like ALS and Parkinson’s.

So far this year, IBM and our partners have published more than 200 pieces of evidence highlighting scientific progress and achievement across Watson Health AI and real-world evidence solutions, as well as health and life science advances from IBM Research.  We are proud of the progress we’re making and we have learned and improved Watson Health based on continuous feedback from clients, new scientific evidence and new cancers and treatment alternatives.  

This report highlights scientific progress from the third quarter of 2018 and spotlights some of the new data that was recently published in peer-reviewed medical literature and at major scientific events.  It also features an in depth look at one of our most recent pieces of evidence and profiles a scientist who is helping to drive innovation in healthcare here at IBM and with our clients and partners.
We hope you will enjoy!   
Meet the Scientists: Yuan-Chi Chang
Yuan-Chi Chang is a Principal Research Staff Member at IBM Research in Yorktown Heights, New York. He is currently the Watson Health analytics lead for  Sugar.IQ , a Medtronic intelligent app assistant that provides personalized insights to people living with diabetes into how food choices, insulin doses and daily routines impact their glucose levels. In this role, Yuan-Chi is primarily responsible for bringing machine learning based glucose analytics from research to production deployment using more than 25 million hours of real user data from Medtronic continuous glucose monitoring devices.

Yuan-Chi's holds a Ph.D. in Electrical Engineering and Computer Sciences from University of California, Berkeley and has held numerous technical and management roles in IBM Research prior to his work on Sugar.IQ. His expertise spans across data analytics, machine learning, big data, data integration, AI engineering and warehousing. Yuan-Chi Chang was also an IBM Graduate Fellowship recipient and interned at IBM Research before joining in 1999.

Why Yuan-Chi is interested in this field of work, in his own words
“I believe in innovations that matter. The Sugar.IQ project is a culmination of data science making an impact to diabetes patients through a real world application. The journey of building this app was composed of a series of obstacles overcame by strong collaboration across IBM Research, Watson Health and Medtronic Diabetes. I learned and benefited a great deal from working with dedicated colleagues to deliver the first cognitive diabetes solution in a HIPAA enabled environment. There is continuing research to investigate as more data sources become available to help patients manage diabetes better. I look forward to leaping progress ahead.” 
Behind the Data: Transforming Diabetes Care Through Artificial Intelligence
It’s no secret that the influx of data is driving the need for the application of AI technologies in health, and we're just beginning to scratch the surface of understanding its potential and promise to support the work of the healthcare industry.  

Take diabetes, for example. An estimated 425 million people globally have diabetes – with more than 30 million living in the United States.  In 2017, the   cost of treating diabetes patients in the U.S. reached a staggering $327 billion. Healthcare providers know the causes of diabetes and – once it is identified – it can be treated.

But how do we determine which AI innovations are actually showing real, measurable progress in a way that could improve a broad spectrum of diabetes care, costs and outcomes?

A new study, titled: “ Transforming Diabetes Care Through Artificial Intelligence: The Future Is Here ” tackles that exact question.  Published in the peer reviewed journal  Population Health Management,  researchers at IBM Watson Health conducted a literature review of 450 published studies which examined the various uses of AI technology in the treatment of Type 2 diabetes to find the areas of diabetes care most likely to be transformed by the technology. The research identified four areas that are showing the most real-world promise for the technology:

  • Predictive Population Risk Stratification: The most highly-cited area of AI research specific to diabetes, a total of 135 studies, were published from 2009-2018 and focused on the identification of diabetes subpopulations at a higher risk for complications, hospitalization and readmissions.
  • Clinical Decision Support: A total of 126 studies were published that focused on detection and monitoring of diabetes and comorbidities such as neuropathy, nephropathy, and wounds.
  • Retinal Screening: The use of AI technologies to detect diabetic retinopathy, maculopathy, exudates, and other abnormalities was the focus of 96 studies.
  • Patient Self-Managed Tools: 94 studies addressed the use of AI to improve glucose sensors, artificial pancreas and activity and dietary tracking devices for use in patient self-management of the disease.

In summary of the findings, the lead author explained: “The published studies suggest that a broad spectrum of market-ready AI approaches are being developed, tested, and deployed today in the prevention, detection, and treatment of diabetes… Because of AI’s ability to rapidly interpret and process enormous amounts of data into simple, actionable guidance, these published studies suggest that AI has significant potential to improve screening, diagnosis, and management of patients with diabetes."
Data + Clinical Evidence Highlights – Q3 2018
Watson Health AI Offerings & Capabilities
Manuscripts and Articles

ACM SIGKDD Conference on Knowledge Discovery and Data Mining , August 2018

International Conference on Pattern Recognition , August 2018
The Oncologist , September 2018

Population Health Management, September 2018

Abstracts and Posters

Medicaid Enterprise Systems Conference (MESC) , August 2018

Public Health Informatics Conference, August 2018

International Gynecologic Cancer Society Annual Meeting , September 2018

International Gynecologic Cancer Society Annual Meeting , September 2018

Watson Health Real-World Evidence

Manuscript and Articles

Pediatric Emergency Care , July 2018

The American Journal of Managed Care , July 2018

Psychiatric Services , July 2018

Dovepress , July 2018

Human Vaccines & Immunotherapeutics , August 2018

Rheumatology and Therapy , August 2018

Gynecologic Oncology , September 2018

Journal of Occupational and Environmental Medicine, September 2018

Abstracts and Posters

American Diabetes Association 78th Scientific Sessions , July 2018

International Society for Pharmacoepidemiology , August 2018

IBM Research

Manuscripts and Articles

Artificial Intelligence in Medicine , July 2018

Psychiatric Services , July 2018

Studies in Health Technology and Informatics, July 2018

Studies in Health Technology and Informatics, July 2018

Studies in Health Technology and Informatics , July 2018

Studies in Health Technology and Informatics , July 2018

Medical Image Analysis , September 2018
Coming Up…
Stay subscribed to keep up to date on how we’re helping our clients and partners around the globe accelerate innovation and tackle some of the world’s biggest health challenges with data, analytics and AI. We hope to see you at some of these industry events happening through the end of this year, including:

Contact Us:
For additional information, or to receive the full list of studies published in Q3 2018, please contact Kristi Bond at kristi.bond@us.ibm.com .
IBM Watson Health| 75 Binney Street, Cambridge, MA