New IBM Watson and Medtronic App Anticipates Low Blood Glucose Levels for People with Diabetes

"Glucose: Ball-and-Stick Model", Image by Siyavula Education

“Glucose: Ball-and-Stick Model”, Image by Siyavula Education

Can a new app jointly developed by IBM with its Watson AI technology in partnership with the medical device maker Medtronic provide a new form of  support for people with diabetes by safely avoiding low blood glucose (BG) levels (called hypoglycemia), in advance? If so, and assuming regulatory approval, this technology could potentially be a very significant boon to the care of this disease.

Basics of Managing Blood Glucose Levels

The daily management of diabetes involves a diverse mix of factors including, but not limited to, regulating insulin dosages, checking BG readings, measuring carbohydrate intakes at meals, gauging activity and exercise levels, and controlling stress levels. There is no perfect algorithm to do this as everyone with this medical condition is different from one another and their bodies react in individual ways in trying to balance all of this while striving to maintain healthy short and long-term control of BG levels.

Diabetes care today operates in a very data-driven environment. BG levels, expressed numerically, can be checked on hand-held meter and test strips using a single drop of blood or a continuous glucose monitoring system (CGM). The latter consists of a thumb drive-size sensor attached with temporary adhesive to the skin and a needle attached to this unit inserted just below the skin. This system provides patients with frequent real-time readings of their BG levels, and whether they are trending up or down, so they can adjust their medication accordingly. That is, for A grams of carbs and B amounts of physical activity and other contributing factors, C amount of insulin can be calculated and dispensed.

Insulin itself can be administered either manually by injection or by an insulin pump (also with a subcutaneously inserted needle). The later of these consists of two devices: The pump itself, a small enclosed device (about the size of a pager), with an infusion needle placed under the patient’s skin and a Bluetooth-enabled handheld device (that looks just like a smartphone), used to adjust the pump’s dosage and timing of insulin released. Some pump manufacturers are also bringing to market their latest generation of CGMs that integrate their data and command functions with their users’ smartphones.

(The links in the previous two paragraphs are to Wikipedia pages with detailed pages and photos on CGMs and insulin pumps. See also, this June 27, 2015 Subway Fold post entitled Medical Researchers are Developing a “Smart Insulin Patch” for another glucose sensing and insulin dispensing system under development.)

The trickiest part of all of these systems is maintaining levels of BG throughout each day that are within an acceptable range of values. High levels can result in a host of difficult symptoms. Hypoglycemic low levels, can quickly become serious, manifesting as dizziness, confusion and other symptoms, and can ultimately lead to unconsciousness in extreme cases if not treated immediately.

New App for Predicting and Preventing Low Blood Glucose Levels

Taking this challenge to an entirely new level, at last week’s annual Consumer Electronics Show (CES) held in Las Vegas, IBM and Medtronic jointly announced their new app to predict hypoglycemic events in advance. The app is built upon Watson’s significant strengths in artificial intelligence (AI) and machine learning to sift through and intuit patterns in large volumes of data, in this case generated from Medtronic’s user base for their CGMs and insulin pumps. This story was covered in a most interesting article posted in The Washington Post on January 6, 2016 entitled IBM Extends Health Care Bet With Under Armour, Medtronic by Jing Cao and Michelle Fay Cortez. I will summarize and annotate this report and then pose some of my own questions.

The announcement and demo of this new app on January 6, 2016 at CES showed the process by which a patient’s data can be collected from their Medtronic devices and then combined with additional information from their wearable activity trackers and food intake. Next, all of this information is processed through Watson in order to “provide feedback” for the patient to “manage their diabetes”.

Present and Future Plans for The App and This Approach

Making the announcement were Virginia Rometty, Chairman, President and CEO of IBM, and Omar Ishrak, Chairman and CEO of Medtronic. The introduction of this technology is expected in the summer of 2016. It still needs to be submitted to the US government’s regulatory review process.

Ms. Rometty said that the capability to predict low BG events, in some cases up to three hours before they occur, is a “breakthrough”. She described Watson as “cognitive computing”, using algorithms to generate “prescriptive and predictive analysis”. The company is currently making a major strategic move into finding and facilitating applications and partners for Watson in the health care industry. (The eight Subway Fold posts cover other various systems and developments using Watson.)

Hooman Hakami, Executive VP and President, of the Diabetes Group at Medtronic, described how his company is working to “anticipate” how the behavior of each person with Diabetes affects their blood glucose levels. With this information they can then “make choices to improve their health”. Here is the page from the company’s website about their partnership with IBM to work together on treating diabetes.

In the future, both companies are aiming to “give patients real-time information” on how their individual data is influencing their BG levels and “provide coaching” to assist them in making adjustments to keep their readings in a “healthy range”. In one scenario, patients might receive a text message that “they have an 85% chance of developing low blood sugar within an hour”. This will also include a recommendation to watch their readings and eat something to raise their BG back up to a safer level.

My Questions

  • Will this make patients more or less diligent in their daily care? Is there potential for patients to possibly assume less responsibility for their care if they sense that the management of their diabetes is running on a form of remote control? Alternatively, might this result in too much information for patients to manage?
  • What would be the possible results if this app is ever engineered to work in conjunction with the artificial pancreas project being led in by Ed Damiano and his group of developers in Boston?
  • If this app receives regulatory approval and gains wide acceptance among people with diabetes, what does this medical ecosystem look like in the future for patients, doctors, medical insurance providers, regulatory agencies, and medical system entrepreneurs? How might it positively or negatively affect the market for insulin pumps and CGMs?
  • Should IBM and Medtronic consider making their app available on and open-source basis to enable other individuals and groups of developers to improve it as well as develop additional new apps?
  • Whether and how will insurance policies for both patients and manufacturers, deal with any potential liability that may arise if the app causes some unforeseen adverse effects? Will medical insurance even cover, encourage or discourage the use of such an app?
  • Will the data generated by the app ever be used in any unforeseen ways that could affect patients’ privacy? Would patients using the new app have to relinquish all rights and interests to their own BG data?
  • What other medical conditions might benefit from a similar type of real-time data, feedback and recommendation system?

Medical Researchers are Developing a “Smart Insulin Patch”

“Spinning Top”, Image by Creativity103

April 9, 2018 Update: This post was originally uploaded on June 27, 2015. It has been updated with new information below.


In an innovative joint project at the University of North Carolina and at North Carolina State University, medical researchers are currently developing a “smart insulin patch” that can both measure blood glucose levels and then administer insulin to regulate it as needed for people with Type 1 diabetes. This is yet another approach at the core of much academic and commercial research and development at creating a “closed loop” system that senses and responds to changes in blood sugar.

Other ongoing research in this field is attempting to integrate continuous glucose sensors with insulin pumps, both of which are available on the market but not yet working together in a viable product with regulatory approval. Both of these approaches are efforts to create a biomedical system that can act as a fully functioning artificial pancreas for people with Type 1 diabetes.

The ongoing work on the smart insulin patch was covered in a fascinating article in the June 22, 2015 edition of The Washington Post entitled The ‘Smart’ Insulin Patch That Might One Day Replace Injections for Diabetic Patients by Brady Dennis. I will summarize, annotate and add a few questions of my own. (Two other recent Subway Fold posts on  October 3, 2014 and June 16, 2015, clickable here and here, respectively, have covered one project to upload glucose monitoring data to the mobile devices of friends and relatives, and another by a medical device manufacturer using social media to reach out to people using insulin pumps.)

This new smart insulin patch is a square shape as small as a penny and is word on the skin. One side of it contains numerous tiny “microneedles” that the face the skin and contain “both insulin and a glucose-sensing enzyme”. Thus, when an increase in blood glucose is detected, the patch can release insulin into the patient’s system “quickly and painlessly”. As a result, the necessity for the delivering insulin by traditional means of a syringe or insulin pump is eliminated.

To date, the development team has only tested the patch on mice. Early test results, published here in The Proceedings of the National Academy of Science (subscription required), showed that the patch worked on the test animals starting within 30 minutes of its application and then lasting for up to nine hours.

Dr. John Buse, one of the co-authors and the director of the UNC Diabetes Center, finds this “exciting”, but he also believes it will take years to determine if this will work in humans. A very informative and detailed news release with photos of the patch and the microneedles, entitled Smart Insulin Patch Could Replace Painful Injections for Diabetes, has recently posted on the UNC Diabetes Center website.

Using current technology requires people with Type 1 diabetes to check their blood glucose levels a number of times each day and then corresponding regulate their insulin to balance the effects of these up and down readings. Other researchers have endeavored to “closed the loop” between insulin pumps and continuous glucose monitors, but these systems still require close attention and adjustments by the patient

The smart insulin patch, if proven safe and viable, could one day dramatically change protocols for the care of Type 1 diabetes. It is an attempt to more directly emulate the human body’s own insulin regulatory system. As well, the microneedles in the patch are designed to be far less invasive and nearly painless than today’s use of injections, pumps and sensors, all of which require larger needles to pierce the skin. It is designed to directly “tap into the blood flowing through the capillaries” in order to become activated.

The researcher team has also found that they could “fine tune the patch” to attain blood glucose levels within an acceptable range. As a result, they are hopeful that, in the future, the patch could be adjusted to each individual patient’s system (including, among other things, weight and insulin sensitivity), and the duration of the patch’s effectiveness could be extended to several days.

My questions are as follows:

  • How exactly will the patch be personalized to meet the biological needs of each user? How will patients manage and regulate this from patch to patch? Is the goal to calibrate a single patch for the user or a series of patches as the user’s needs and environment changes?
  • Can the patches be customized and fabricated using today’s commercial 3D printing technology?
  • Will blood glucose levels still need to be checked regularly using current methods in order to assess and align the patch’s effectiveness and accuracy?
  • Can the patch’s data on blood glucose levels and insulin dosages be uploaded onto mobile devices in order to be monitored by the patient’s health professionals and family members?
  • Might the patch be used in conjunction with or even integrated into the Apple Watch as a medical app?
  • Can other medications that a person with diabetes is taking also be administered, monitored and regulated with the patch, perhaps making it even “smarter”?

April 9, 2018 Update: For a report on the latest research into non-invasive smart patches being used to measure blood glucose levels, a new article has just been posted today, April 9, 2018, on Nature.com entitled Non-invasive, Transdermal, Path-Selective and Specific Glucose Monitoring Via a Graphene-based Platform, by Luca Lipani, Bertrand G. R. Dupont, Floriant Doungmene, Frank Marken, Rex M. Tyrrell, Richard H. Guy & Adelina Ilie. Nature.com is a subscription-only site with the link provided here just to an abstract of the article. Nonetheless, it provides a most interesting introduction about this ongoing research. My question after seeing this is whether there is now, or will be in the future, any possibility that this technology and the insulin delivery research described in the main post above, will be integrated to form the basis of a closed-loop or artificial pancreas system that will both monitor blood glucose levels and deliver insulin in as needed response.

New Startups, Hacks and Conferences Focused Upon Health Data and Analytics

The intersection of digital technology, the Web and modern medicine seems to produce new innovative approaches to health care on a very steady basis. Three reports have appeared within the past ten days that I believe typify the imagination and dedication of the companies and individuals in this space. While the following articles barely scratch the surface, they nonetheless provide an informative sampling of some very interesting trends that likely would not have been possible until quite recently.

1. User Survey Data Mined to Provide Consumer Information on Prescription Drugs: A new company called Iodine has created a database based built upon 100,000+ surveys provided taken from people who have been prescribed medicines. Visitors to the site can use it to look up the consensus findings about the effectiveness, potential side effects, warnings, pricing and other practical information about a vast number of drugs. (Of course, consulting first with your doctor about them is always of primary importance.)

The full details of the Iodine’s origin, current operations*, investor support, use of Google Consumer Surveys and other data sources, and its potential benefits to patients and the pharmaceutical industry was the subject of a very engaging article published in the September 23, 2014 edition of The New York Times entitled To Gather Drug Data, a Health Start-Up Turns to Consumers by Steve Lohr. (See also another brief article entitled Iodine: A Platform to Help You Choose the Best Medicines for You by Ben Woods, posted on TheNextWeb.com on September 24, 2014.) I also highly recommend a click-through to Iodine’s site to view and test out their new approach to producing and presenting this specialized consumer information.

2. Hackers Modifying Medical Devices: A group of engineers have joined forces online to provide a useful hack to the continuous glucose monitor produced by a company called Dexcom. As reported in an article entitled Hackers Tinker With Medical Devices in the September 27, 2014 edition of The Wall Street Journal, by Kate Linebaugh (a subscription to WSJ.com is required for access), this hack is called NightScout. To briefly sum up this story, NightScout enables data from this device to be uploaded online to permit parents and other concerned individuals to remotely check the blood glucose levels of family members and friends who have Type 1 diabetes, from their smartphones. The Dexcom monitor currently on the market does not do this, although such a connection is planned for a subsequent release possibly next year.

The monitor itself consists of two parts: A small plastic pod which is worn by person with diabetes that transmits the blood glucose readings on a continuous basis to a handheld device within a 20-foot radius (which is nearly the same dimensions of a typical smartphone). This system is used to look for and alert the user to certain helpful patterns in the changes to their blood glucose levels and to record this data. In turn, the data is also quite helpful to the person’s medical providers.

This is indeed a very data-driven approach to treating Type 1 diabetes, which has always required close monitoring by the patient in an effort to maintain normal blood glucose levels. Doing so helps to avoid long-term complication and maintain good health.

Neither the manufacturer nor the FDA has approved NightScout, but they have not tried to stop it. Rather, they are closely watching its ongoing improvements by the NightScout online community and how this is affecting the quality of care for the users.

3. Industry Conference Presentation on Data-Driven Medical Technologies: An article entitled Can a Computer Replace Your Doctor? by Elizabeth Rosenthal in the September 20, 2014 edition of The New York Times, reported on other advances and growing interest by doctors driven by big data collection and analytics. These developments were the subject of a presentation called Health By Numbers at the recent 2014 Health Innovation Summit in San Francisco. This article opens with an account of a doctor asking his audience whether they would prefer an AI to an actual doctor.**

To briefly summarize this story, some of these systems and methodologies discussed, among others:

  • An iPhone app to diagnose ear infections
  • Home kits to check cholesterol levels
  • The above mentioned blood glucose monitoring devices
  • Wearable fitness trackers

Moreover, the attendees discussed many key issues about pursuing these lines of medical treatment and administration including high expectations and mixed outcomes, challenges in quantifying exactly what “health” means, that sometimes good data does not always equal a healthy patient, and how to most meaningfully process and analyze all of the available data. I highly recommend a click-through and full read of this very informative and thought-provoking piece.

My follow up questions concerning all three of these stories include:

  • Will the privacy patient and user data be adequately protected by current laws or do the rapid emergence and adaptation of these systems require new legislation and regulation to ensure patient privacy?
  • Whether and how the roles of doctors and other medical service personnel will be changed? If so, how will their academic training need to be revised?
  • What, if any, will be the impact on the costs, quality, policies and politics of medical care in the US and elsewhere?

____________________________
*   No stitches were involved as these concern business, not surgery.

** Compare and contrast to this September 1, 2014 post here entitled Possible Futures for Artificial Intelligence in Law Practice.