A technical blog dedicated to discussing future technologies to improve medical monitoring and patient management. If you have an interest in this area, I think you will not be disappointed. I have added a new dimension: periodic articles on medical usability, risk management, IEC 62366 and ANSI/AAMI HE 75 ... and all things related. If you want to know more about me, please look at my LinkedIn profile ... search for Gary Dorst.
An Indian team is close to developing an electrical device that can diagnose 15 different medical conditions and can monitor vital signs for around 72 hours.
Chennai-based American Megatrends India is developing a medical hand-held scanner that is worthy to be included in the television show Star Trek.
American Megatrends’ medical device is a wireless health monitoring tool that can monitor a battery of vital statistics that include blood pressure, heart rate, oxygen saturation, respiratory rate and temperature, as well as atrial fibulation, sleep apnea, stroke, diabetes, etc. The device can collect large volumes of data from ongoing measurement of health states through a combination of wireless sensors, imaging technologies, and portable, non-invasive techniques. The stream of data generated will be stored in the cloud, currently on AMI’s own servers, with plans afoot to work with major cloud operators such as Apple and Google.
Article speaks for itself. No commentary necessary.
The issue raised of particular interest was the high "false alarm" rate generated reported by the author that would lead medical professionals to disregard warnings generated by their computer systems. I wrote that I wanted to follow-up on the issue of false alarms.
The patent application (the application has been published, but a patent has not yet been granted) describes an invention intended to 1) perform continuous automated monitoring and 2) lower the rate of false alarms.
Here are the details of the patent application so that you can find it yourself if you wish:
The continuous monitoring process from a technical standpoint is not all that interesting or new. What is interesting is the process they propose to lower the false alarm rate and determine whether this process in turn will not lower the false negative rate.
Proposed Process of Lowering False Alarms
As mentioned in my earlier article, it appears that false alarms have been a significant issue for medical devices and technology. Systems that issue too many false alarms issue warnings that are often dismissed or ignored. Or waste the time and attention of caregivers who spend time and energy on responding to a false alarm. This patent application is intended to reduce the number of false alarms. However, as I mentioned earlier, can it do that by not increasing the number of false negatives, that is, failure to detect when there is a real event where an alarm should be going off.
Getting through all the details of the patent application and trying to make sense of what they're trying to convey, the following is what I believe is the essence of the invention:
Measurement a sensor indicates an adverse patient conditions and an alarm should be initiated.
Before the alarm is initiated, the system cross-checks against other measurements that are:
1) from another sensor measuring essentially the same physiological condition as the
sensor that detected the adverse condition, the measurement from the second sensor
would confirm the alarm condition or indicate that an alarm condition should not exist; or
2) from another sensor or sensors that take physiological measurements that would confirm
the alarm condition from the first sensor or indicate that an alarm condition should not
In this model at least two sensors must provide measurements that point to an alarm state.
Acceptable Model for Suppressing False Alarms and Not Increasing False Negatives?
Whatever you do in this domain of detecting adverse patient conditions, you don't want to lower your accuracy of detecting the adverse condition. That is, increase your false negative rate.
So is this one way of at least maintaining your currently level of detecting adverse events and lowering your false alarm rate? On the face of it, I don't know. But it does appear that it might be possible.
One of the conditions the inventors suggest that initiates false alarms are those times when patients move or turn over in their beds. This could disconnect a sensor or cause it to malfunction. A second sensor taking the identical measurement may not functioning normally and have a measurement from the patient indicating that nothing was wrong. The alarm would be suppressed ... although, if a sensor was disconnected, one would expect that there would be a disconnected sensor indicator would be turned on.
Under the conditions the inventors suggest, it would appear that cross checking measurements might reduce false positives without increasing false negatives. I would suggest that care should be given to insure that a rise in false negative rates do not increase. With array of new sensors and sensor technology becoming available, we're going to need to do a lot of research. Much of it would be computer simulations to identify those conditions were an adverse patient condition goes undetected or suppressed by cross-checking measurements.
For those who do not know, I am on numerous patents and patent applications (pending patents). Not only that I have written the description section of a few patent applications. So I have a reasonable sense of what is what is not patentable ... this is in spite of the fact that I'm an experimental, cognitive psychologist and we're not general known for our patents.
So, what is my take on the likelihood that this applications will be issued a patent? My sense is not likely. As far as I can tell there's nothing really new described in this application. The core of the invention, the method for reducing false alarms, is not new. Cross-checking, cross-verifying measurements to determine if the system should be in an alarm state is not new. As someone who has analyzed datasets for decades, one of first things that one does with a new dataset is to check for outliers and anomalies - these are similar alarm conditions. One of the ways to determine whether an outlier is real, is to cross check against other measures to determine if they're consistent with and predictive of the outlier. I do not see anything that is particularly new or passes what known in patent review process as the "obviousness test." For me cross checking measures does not reach the grade of patentability.
This was an opinion piece published 21 March 2015 in the New York Times written by Robert M. Wachter, Professor of Medicine, University of California, San Francisco and author of "The Digital Doctor: Hope, Hype, and Harm at the Dawn of Medicine’s Computer Age” also published in the New York Times.
I have commented on several quotes from the article.
1. "Even in preventing medical mistakes — a central rationale for computerization — technology has let us down. (My emphasis.) A recent study of more than one million medication errors reported to a national database between 2003 and 2010 found that 6 percent were related to the computerized prescribing system.
At my own hospital, in 2013 we gave a teenager a 39-fold overdose of a common antibiotic. The initial glitch was innocent enough: A doctor failed to recognize that a screen was set on “milligrams per kilogram” rather than just “milligrams.” But the jaw-dropping part of the error involved alerts that were ignored by both physician and pharmacist. The error caused a grand mal seizure that sent the boy to the I.C.U. and nearly killed him.
How could they do such a thing? It’s because providers receive tens of thousands of such alerts each month, a vast majority of them false alarms. (My emphasis.) In one month, the electronic monitors in our five intensive care units, which track things like heart rate and oxygen level, produced more than 2.5 million alerts. It’s little wonder that health care providers have grown numb to them."
Comments: Before I read the third paragraph, I was thinking How can you blame the computer when it provided you with an alert regarding the prescribing error that you made?
It is well known that systems that produce a high percentage of false alarms, that those alarms over time will be ignored or discounted. I consider this is a devastating indictment. We must do better.
I have been a human factors engineer and researcher for decades. One of the mantras of human factors is preventing errors. That's central to what we're about. But if the systems we help engineer generate false alarms at a rate that has our users ignoring the correct ones, then we have failed and failed miserably.
I think the problem of false alarms requires further research and commentary.
2. "... despite the problems, the evidence shows that care is better and safer with computers than without them."
Commentary: This is nice to read, but we as medical technologists need to do better. We really need to follow up on the repercussions of our technology we create when it's deployed and used in the field.
3. "Moreover, the digitization of health care promises, eventually, to be transformative. Patients who today sit in hospital beds will one day receive telemedicine-enabled care in their homes and workplaces."
Commentary: I agree. Of course that's a central theme of this blog.
4. "Big-data techniques will guide the treatment of individual patients, as well as the best ways to organize our systems of care. ... Some improvements will come with refinement of the software. Today’s health care technology has that Version 1.0 feel, and it is sure to get better.
... training students and physicians to focus on the patient despite the demands of the computers.
We also need far better collaboration between academic researchers and software developers to weed out bugs and reimagine how our work can be accomplished in a digital environment."
Commentary: Agreed again. But, I believe that technologist just can't dump these systems into the healthcare environments without significant follow-up research to insure that these systems provide or suggest the correct treatment programs and effectively monitor patients. Investment in systems like these will be cost effective and improve lives, but only if the necessary level of care and follow-up is performed.
5. "... Boeing’s top cockpit designers, who wouldn’t dream of green-lighting a new plane until they had spent thousands of hours watching pilots in simulators and on test flights. This principle of user-centered design is part of aviation’s DNA, yet has been woefully lacking in health care software design."
Commentary: All this is true. And as noted above that it would be a good idea to do more extensive research on medical systems before we deploy them to the field as well. That this is not done may be a regulatory issue that the FDA has not required the kind of rigorous research as performed in aircraft cockpit design. They should require more research in real or simulated environments. Right now, all that appears to be required is a single verification and single validation test before allowing commercialization. I think it would be valuable for regulators to require more research in real or simulated settings before allowing companies to commercialize their products.
Or, requiring more extensive follow-up research. Grant companies the right to sell their medical products on a probationary basis for (say) 1 year after receiving initial commercialization certification. During that year, the company must perform follow-up research on how their medical product performs in real environments. If there are no significant problems ... such as overly abundant number of false alarms ... then the product no longer on probation and would be considered fully certified for commercialization.
However, if significant problems emerge, the FDA could:
a) continue to keep the product in a probationary status pending correction of those problems and another year of follow-up research or
b) it could require the withdrawal of the product from sale. A product that had been withdrawn would have to go through the entire commercialization certification process just as if it were a new product before commercialization and sale would be allowed.
A final thought ... I think there's a reality in commercial aviation that is not true in medicine. If commercial aircraft killed and injured as many people as are killed and injured by medical practitioners, then the commercial aviation would come to a halt. People would refuse to fly because they perceive it to be too dangerous. But, if you're sick, then you have little choice but the clinic, ER or hospital.
I've been arguing for some time that remote monitoring can not only lower medical costs, but it show itself to be of benefit to the patient as well. Here's an article that not only shows that remote monitoring can be of benefit to the patient, but to the physician as well.
Remote monitoring can not only provide better and more data ... that can lead to better analysis and conclusions. It can provide that data to the physician before the patient comes in for a visit. Furthermore, if an adverse medical event occurs, that data is captured and available to the attending health care providers. Admittedly the patient would have needed to have been wearing the monitoring device at the time, but if the person was wearing the monitoring device that information would be available.
Here are a few quotes from the article that I found interesting ...
... if you spend $100 a month to monitor patients remotely – over a year it would cost much less then what you would pay if they have to come back to the hospital.
[T]here are two waves of activity. The more traditional top down wave extends the reach of hospitals with FDA approved medical devices that are deployed out in the home by providers by doctors to keep track of these patients.
There is also an increasing consumer wave where people are going out and buying the sensors and devices on their own and tracking their fitness and health and bringing that information to their healthcare providers.
=== I find this quote interesting in light of the Apple Watch and other similar devices ======
Some physicians, Kleinberg asserted, don’t need and don’t want that data from the patient and claim that they don't have a place to put the data and they don't have time to look at it.
=== Actually, machines can monitor this data on a continual basis. The machines can alert physicians as needed and provide summaries. Physicians need not review raw data. ======
"There's a push back to this consumer-up bottom-up wave. But over time I think we're going to see that the sensors and the data that’s coming from these devices is going to have more and more value and providers are going to put more faith in it," said Kleinberg. "They're going to look at it and make some sense of it and part of the way they are going to do that is if they have more confidence about that data."
=== I think the last sentence may be one of the most significant in the article. Confidence in the data and automated analysis will build and become mainstream. And I think that cost considerations will be a factor. =====
Announcement Title: Mayo Clinic To Develop Wireless Sensors To Treat Obesity
I found this quite interesting when I came across it. The sensors are far from being developed but I thought it worth posting the announcement link.
The goal is to produce the first wearable patch sensor – the size of a bandage – that is wireless, disposable, and can remotely monitor patient movements via smartphone. This new technology would simplify tracking with greater accuracy of patients and clinical trial subjects for whom a certain level of activity is prescribed to achieve their goals.
Before I dive into the issues regarding the possible means for connecting medical devices to the Internet, I would like to provide you with a little background on two relevant research programs I have lead. I was the principal investigator on two Federally supported research programs described below.
The first was a NIST Research grant to support the development of a secure and commercially viable wireless data communications technology. Much of that technology has been incorporated into today's smartphones, although not all of what we created has yet found its way into the current generation of smartphones. But with each iteration, more of what we created gets incorporated.
A central part of our program was to insure secure and private data communications. It would be secure from infiltration by malware and impenetrable by snoops ... including the NSA. The system worked by securing and controlling both ends of the communication. It was capable of sending a single file to over multiple communications channels simultaneously, the packets could be sent out of order using multiple forms of encryption including nonstandard or private encryption methods -- that are much harder to break. By securing and controlling both ends of the connection between devices, we could completely control what went in and out of the channel. Nothing would flow to the other end that was out of our view or control.
The second Federal grant was for a data security program. VoIP communications channels are lightly secured largely due to the requirements to insure that audio is clear and voices understandable. This fact makes VoIP channels particularly vulnerable vectors to use for an attack. There have been attempts to logically divide voice and data channels; however, there have been several demonstrations that this does not always work. Our research focused on methods to detect the presence of an intruder without disrupting or significantly lowering audio quality. And when we detected a possible intruder, we attacked this apparent intruder through a series of escalating techniques that could finally end with terminating the connection when it was clearly apparent that an intruder was using the VoIP connection to do something nefarious.
Architectures for the Internet of Things
The two architectures I would like to review are direct and mediated connections that could be used in the realm of the Internet of Things.
Direct and mediated connections are illustrated in the figure below.
The real difference between the two diagrams is the way the Apple Watch is connected to the Internet. On the left the Watch is directly connected to the Internet. When connected, it is an addressable device on the Internet. On the right, the Watch is connected to the Internet through the iPhone. The iPhone mediates the connection to the Internet through the iPhone. All the data traffic to and from the Watch goes through the iPhone.
A mediated connection through the device can be as simple and unmanaged as one through a router. However, with the appropriate software on the iPhone, the iPhone should be able to manage the connection with and security of the Watch.
In the case of the direct connection, management of the connection to the Internet including security must be done by the Watch itself. The Watch could be subject to a direct attack and must defend against such an attack by itself.
Best Architecture for Medical Devices?
In the diagram above, I'm treating the Watch as if it were a medical device ... and a medical device it could be. It would seem that the safest connection to the Internet would be a mediated connection. However, there are hybrid scenarios. For example, incoming communications including software updates could require a mediated connection. Encrypted uploads from the Watch to a centralized server system could use a direct connection.
This is a brief introduction into this topic. I'll have further explorations into this issue in future articles.
According to the article Apple considered including a number of medical monitoring devices/capabilities for their first generation Watch. For the first generation, those have been scrapped for reliability and regulatory reasons. Apparently Apple is still interested in adding more physiological sensors to the Watch, but if those capabilities appear, they'll be included in next generation Watches.
However, there was something that caught my interest from the article:
"Aside from catchall smartwatch devices, a number of standalone solutions for off-the-shelf medical style monitoring already exist in the form of products — usually wrist-worn — from smaller manufacturers and startups. For example, the W/Me band incorporates a specialized sensor to measure a user's autonomic nervous system for keeping track of stress levels, while the latest products from Fitbit tout all-day heart rate monitoring."
There are lots of other companies making sensors that would be useful for medical monitoring purposes. For Apple and the Watch there are many ways this can play out. Frankly none of these are mutually exclusive.
Apple can purchase the sensing technology to incorporate into Apple-produced sensors.
Apple can purchase the sensors and integrated them into the Watch
The third-party sensors can communicate with the Apple Watch over WiFi.
The data collected by the Apple Watch could be:
Analyzed and presented locally ... by the Watch
Uploaded to the iPhone were the iPhone would process the data and either communicate it back to the Watch for display or be displayed on the iPhone ... or both.
Uploaded to the iPhone that intern uploads it to a centralized system for processing. The results of that analysis could be communicated back for display on the iPhone or Watch. If so indicated an alert could be included if conditions warranted.
Again, none of these are mutually exclusive. Data could be processed and displayed on the Watch and communicated back to a centralized system.
A brief note ... the FDA has given approval the patients implanted with the Biotronik Eluna pacemaker can safely undergo full MRI body scans. Note, this approval does NOT say that this pacemaker is MRI-safe. Someone implanted with this pacemaker cannot be placed in an MRI without making the necessary changes.
The pacemaker is MRI-conditional ... meaning that it is safe for a patient with a Biotronik Eluna pacemaker with the ProMRI technology to undergo a full-body MRI scan under the condition that the settings on this pacemaker are properly set to their MRI conditional settings.
... sometimes I worry that announcements like these can be misinterpreted and could lead to something bad happening. I've seen an article regarding a Biotronik pacemaker that stated that the pacemaker was "MRI-safe" when it wasn't true. As of this date and as far as I know, there are no MRI-safe pacemakers. The one's where the FDA has approved MRI compatibility are all MRI-conditional.
Here are links to two articles announcing FDA's approval:
I had a chance to review the page-hits I received over the life of this blog and it turned out that my short posting regarding an article in the Washington Post that discussed virtual doctor visits was the one most requested. Frankly, I found this flabbergasting, because this blog was founded on the belief that remotely practiced medicine can be good medicine ... as good or potentially better than the medicine practiced in offices, clinics and hospitals. And I'm going to take it a step further with the idea that virtual doctors may be just for those who live in rural areas or even in difficult circumstances inner cities, virtual doctor visits may be the wave of the future ... and you'll be better for it.
Personally, I would prefer a virtual visit over the need go to the doctor's office, clinic or hospital.
While virtual doctor visits certainly seem to be on the upswing with increasing acceptance, the idea that a computerized physician could be your primary physician would seem to most like science fiction. And at this point in time, it is. However, computerized medicine doing the things that only physicians once performed has been the works for decades. In later posts, I'll explore this in greater detail.
Much of my writing on these topics will be in conjunction with my further explorations of the Apple Watch and its emerging capabilities.
Apple has been grappling with the design and capabilities of a smart watch for years. Apple CEO Tim Cook announced that Apple would produce a smart watch in September 2014. The initial rollout is scheduled for 25 April 2015.
Tim Cook has suggested that the Apple Watch would do more than provide its owner with the time and as a wearable means to communicate with your iPhone ... something that you would rather leave in your pocket or purse. He suggested that this device could also serve as a means to assist people with monitoring their health and fitness. But can this device that is strapped to your wrist really do that?
Research on Smart Watches and Their Owners
Before doing the deep dive into the Apple Watch, I want briefly discuss some of my experience with researching smart watches. I can't divulge all the details of that research because some of that work that I was part of a research team is proprietary. I can say a few things about smart watches, the variety of their capabilities and some of the opinions about them that people who have used them have provided.
The smart watches that we used in our research had capabilities that fell into two categories. The first were capabilities that allowed the owner to communicate with and control their smartphone. For example, a smart watch would allow an owner to control music or podcasts being played or allow the owner to make and receive calls through the smart watch. Communication between the two devices was over Bluetooth (IEEE 802.15.1) The second were independent capabilities this can include GPS map capabilities, collecting and displaying running or cycling distances and routes. And providing the date and time.
We found that owners of smart watches were initially excited and enthusiastic about owning a smart watch. However, over time that excitement and interest disappeared ... and disappeared to the point where most owners were considering ways to rid themselves of their smart watches. Based on our research, smart watches seemed like a good idea. But once initially-enthusiastic owners tried to incorporate smart watches into their lives, their response to them became negative.
The Apple Watch is almost upon us with great fanfare. Based on photographs and my read of the hardware and descriptions of the Apple Watch, it appears to be stylish that its predecessors ... an important quality. It appears that it will have many of the same capabilities as it's predecessors as well ... the ability to communicate with and control the owners iPhones (5 or later) - the smart watch will have Near Field Communication (NFC), Bluetooth (4.0), a speaker, microphone and a touch screen to enable communication and control - and a number of independent capabilities based on the following embedded sensors: accelerometer, gyroscope, heart rate sensor and barometer.
Beyond the heart rate sensor, what else might make the Apple Watch a wearable system to assist people with their health and fitness? I'm not sure, but what I found interesting about the Apple Watch, what makes it potential game changer in the realm of health and fitness is this: WiFi (802.11 b/g/n).
From all that I can tell, the inclusion of WiFi could be something that might make the Apple Watch something significant with respect to means for medical monitoring. WiFi is different from Bluetooth in that Bluetooth creates a dedicated one to one communications channel. A WiFi access point (AP) can support multiple, simultaneous connections. Is Apple working with other companies to create new body sensors that can communicate with the Apple Watch using WiFi? It's plausible and well worth watching.