AI

AI

Six guiding principles for designing connected medical devices that support embedded intelligence



Categories:

Head of Analytics at Cyient, an engineering design, networks and operations company, Bhoopathi Rapolu shares six guiding principles for the design of connected medical devices

connected medical device

According to IT research company Gartner, there will be more than 20 billion connected devices globally by 2020, with the Internet of Things (IoT) increasingly impacting on every aspect of both our professional and personal lives. Take healthcare for instance, the proliferation of connectivity among both medical and personal-health/fitness tracking devices is leading to an explosion in the amount of data generated. This, in turn, is opening up new possibilities for device manufacturers to embed artificial intelligence (AI) into their equipment. These devices collect terabytes of data every day – monitoring, for example, our heart rate, blood pressure, the number of steps we take and calories we burn – most of which goes unused. However, the application of advanced analytics and AI on healthcare data has far reaching implications on the industry overall.

As the number of connected medical devices and resultant data generated continues to grow exponentially, manufacturers are looking to new methods to process these huge volumes of information. Traditionally, this data has been processed in the Cloud, but as the volume has increased, so too has the challenge of shifting it all to a remote server, analysing it and returning the actionable information back to the device. Cloud computing is suitable for infrequent data transfer – much like the way the average consumer may use DropBox or Flickr, for instance, to upload files occasionally. It is not as suitable for real-time insight and data processing – that’s why new methodologies, such as edge computing, are coming to the fore.

The rise of edge computing

The relentless pace of technological development means that many devices now have the computational power to process more data themselves and adapt their performance accordingly. This is based on one of the multitude of sensors on a device that generate data, which is subsequently run through a complex series of algorithms to be processed. These algorithms can make predictions about the device and then recommendations to improve its performance; otherwise known as embedded intelligence.

Using edge computing, only the most insightful and actionable data is sent to the Cloud, thus freeing up a huge amount of capacity and improving efficiencies. Without having to process endless reams of largely unusable data, equipment manufacturers can use edge computing to crunch the most meaningful information and apply the intelligence accrued to enhance device development, resulting in better quality patient care.

Shifting to the edge

To take advantage of this shift, device manufacturers need to create the right conditions for their product development, by re-engineering their design processes. Here are my six guiding principles for designing connected medical devices that support embedded intelligence.

1. Be software-defined

Most manual functionality in medical devices – switches, buttons and dials, for example – are now being replaced with software. Why? Because software-defined devices require less maintenance, enabling routine checks and updates to be undertaken quickly for minimal outlay. Software updates, for instance, can be completed remotely to alter the device’s functionality or add new features.

2. Be autonomous

We can make systems autonomous by incorporating remote monitoring and self-learning capabilities. By introducing as much autonomy as possible to each subsystem, medical devices will be able to self-monitor and “self-heal” if they develop any problems, removing the need for any manual intervention by the user.

3. Improve efficiency

Improving the performance and efficiency of products in an aesthetic way has been one of key drivers for product designers for some time now. We’re now able to take it a step further by using the capabilities afforded by the IoT and AI. While the IoT allows us to generate the right data from the systems, AI can be used to make sense of that data and generate actionable insights. Incorporating these capabilities into the design process is the first step towards building intelligent medical equipment. With efficiency gains derived from IoT and AI-driven design modifications, manufacturers can extend the uptime on production, creating equipment that can, if necessary, quickly take a new shape or direction, and connect to the wider system.

4. Monitor and report

Every system and subsystem needs to have some form of monitoring while ‘in the field’, whether it be a heart monitor, MRI machine or fitness tracker. Monitoring enables each device or application to report back to the manufacturer on its performance levels, and helps them to redesign, or make any improvements or fixes where necessary. This also creates scope for interoperability between devices, which is critical to the further development of a wider medical IoT.

5. Enable remote control

While monitoring is one-way, remote control creates a two-way flow of information and recommended actions between manufacturers and their devices that enables them to act quickly if their products develop issues in the field, by deploying software to clear any bugs. Enabling remote control will require a sea change in the way that products are designed, shifting the emphasis from user feedback to tangible device performance statistics.

6. Optimise for new business opportunities

Ultimately, every manufacturer is seeking more business, and connected equipment can help unlock new opportunities. By paying more attention to product design, the data their devices generate may allow them to build new offerings such as remote service software, to sell data to selected third parties, or to combine data with other systems to create a more comprehensive, valuable package for other players in the industry to analyse and apply.

Design optimisation to this extent enables manufacturers to alter medical equipment through remote action and to provide the user with an experience that continues to improve as they use the device more. As a result of providing improved customer service, manufacturers can begin to identify new business opportunities based on individual needs.

Ultimately, the connected medical equipment of tomorrow will have embedded intelligence at its heart, enabling clinicians and healthcare staff to benefit from improved devices in the field and to provide better care for patients as a result. So it’s critical that equipment manufacturers look closely at their design processes to remain competitive in the market and to create the digital-first devices needed for 21st-century healthcare.

About the author

Big Data strategist, author and keynote speaker, Bhoopathi explores emerging IoT technology around the world to create solutions for industries like Aerospace, Rail Transportation, Medical, Communication and Utilities.

Related articles

Contribute

You're the expert! Write for The Engine or share your articles, papers and research

Add your content

Add your content

Keep informed

Sign up for Ignition, our regular, ideas-packed newsletter

Sign in with social media

or with a username