Article: Establishing Trust in Wearable Medical Devices

Many of the topics covered in this article I have covered in this blog. Most recently, my discussion of signal detection and the Apple Watch (https://medicalremoteprogramming.blogspot.com/2019/12/signal-detection-and-apple-watch.html) that I suggest that you read after reading this article from Machine Design.

Here's the link to the article: https://www.machinedesign.com/medical-design/article/21122718/establishing-trust-in-healthcare-wearables?utm_source=MN+MD+Medical+Design&utm_medium=email&utm_campaign=CPS200206038&o_eid=7596G0176945B2B&rdx.ident%5Bpull%5D=omeda%7C7596G0176945B2B&oly_enc_id=7596G0176945B2B

Here are a few quotes from the article.

To say that we can get personal health insight from continuous monitoring presumes a “chain of trust.” In other words: 

• The interpretation of any data must not only be accurate but reliable. The challenge lies in handling “borderline” data. Any interpreting strategy or algorithm faces data sets that it finds ambiguous. For an algorithm to be reliable, users must be able to quantitatively understand its detection limits and error characteristics.

• The data and/or its interpretation must reliably reach the decision-maker for it to become actionable.

• The data must be correctly associated with historical records of the patient for it to have context.

• The data must be proven to be authentic to trigger any meaningful action.

However, using clinical equipment to capture vital signs that are representative of the wearable use cases is often difficult and sometimes inaccurate. To avoid a rash of false positives or false negatives, one must carefully select the population of test subjects and carefully develop the representative use cases. It’s also important to compare data from the patient’s own history or baseline, keeping in mind that this baseline isn’t static as the patient ages and undergoes other changes.

Careband: Keeping track of those with dementia

I was at an evening venture capitalist meeting on 13 November 2018. I'm not a venture capitalist but I have a few connections to this community and I periodically receive invitations to their meetings. Most of the time I pass on attending. I'm interested in science, mathematics and technology. VCs are interested in ways to make money. Nothing against them. We just live on different planes of existence.

However, I attended this meeting because I read the description of one of the companies doing a presentation, careband (http:www.careband.co).

careband

Careband provides a capability to track the location of people with dementia. This is a more difficult problem than you might imagine. In institutions, patients with dementia are known to wander away: from the institution, from their homes, from family members. The patients do not know where they are or how to return. Institutions who care for dementia patients frequently need to find their patients who have wandered away from the institution's grounds or to areas of the institution that caregivers do not expect that they would be able to wander. 

Thus there's a clear need to be able to keep contact track of dementia patients. To know where their location at all times and be notified when they've wandered off the grounds of the institution.  Here's a page from the careband.co website that summarizes the capabilities of their system.

The diagram above shows the elements of system for patients and customers/caregivers -- those responsible for caring for the dementia patient(s). Caregivers can see at a glance the current location of each patient. Each dementia patient wears a band about the size of a large wristwatch on the wrist that periodically sends a location related message to the network. All data is sent to careband's cloud server system. Patient location data is made accessible to the caregiver systems that are connected to the cloud server system.

The wrist bands connect to the Internet to the low-power communications system: LoraWAN. More information about this wireless data communications network is available here: https://lora-alliance.org/about-lorawan The LoraWAN network is a low-power, low-speed (0.3 kbps to 50 kbps) but long distance (up to 3 miles from an access point outside) and robust wireless communications system. 

The wristband also includes Bluetooth that is used to provide indoor location data. And an accelerometer has been included to provide information regarding whether the patient has moved his or her body during the reporting period. 

I am not familiar with all of the current capabilities of the careband.co system. However, I know that the wristband continually transmits to the cloud the following data:

• Patient ID data
• Transmission time 
• Location data
• Movement (whether or not the person has moved from the time of the last data transmission and the time of the current data transmission)
• Battery charge level

How careband.co is currently analyzing is something of which I am presently unsure, but there are a number of pieces of information that can be derived from this relatively small amount of data. Here's what's possible:

1. Current patient location
2. Map of patient's activity and the distance covered over time
3. Amount of time that the patient was moving
4. Alarm initiation: should the patient stray away from the institution, the system can automatically notify the caregivers. (Boundaries should be able to be drawn on the display.)
5. Trend and trend line analysis for patient activity time and distance covered. These could be indicators of the patient's cognitive health. Significant deviations from calculated trend lines could be indicators of a slip or improvement in a patient's cognitive and/or physical health.
6. Suggest that the patient has removed the band from his or her wrist (when the patient appears not to have moved during normal activity time) or that the patient maybe in distress or died.

There could be more information that can derived from the wristband data that I have yet to think of. As I come up with additional thoughts regarding this, I shall post them.

Upgrades to the wristband could include pulse oximetry and pulse rate data. Again, there are other capabilities that could be added that I have yet to think of.

Since the transmission speed is so low, careband.co will likely need to develop a data compression system to effectively communicate this data back to the cloud server system. 

Careband.co is one more interesting product for remote medical monitoring. It's not designed for remote patient management largely because most patients will normally be closely supervised. However, it could be an aid to enable people with dementia to live for a longer time in their own homes. The benefits to both the patient and to society are massive. Six months to a few years of being able to live in one's own home would improve both the quality of life for people with dementia and significantly, dramatically reduce the cost of care.

I shall continue to monitor careband.co's progress. Stay tuned.

Careband.co plans on making their products available through medical device distributors. Their products are not yet commercially available. They are about to manufacture the wristband. Their wristband has been approved by the FCC. FDA approval is not required.  If you are interested in purchasing their product, please contact them at care band.co.

I should mention that careband.co is looking for investors. If you're interested in what careband.co is selling, please contact them directly using the URL listed above.

International Medical Device Database

For anyone interested in medical device safety, you should bookmark this website: https://medicaldevices.icij.org

It has been created by the International Consortium of Investigative Journalists to:

"Explore more than 70,000 Recalls, Safety Alerts and Field Safety Notices of medical devices and their connections with their manufacturers."