To what lengths will medical devices of the future go? It’s an explosive new application area, but with some staggering challenges.
We don't often print a feature on medical electronics. The area might seem one of those charming but slow-moving little backwaters with which the embedded world is so replete. In some senses, medical electronics has been not a distinct application area at all, but merely a subset of the test and measurement market. Medical electronic devices have mostly been measuring instruments that get splashed with saline solutions.
But as Vasanth, Oswal, and Bartolome point out in our cover story, all that is changing. The industry has begun moving along several different trajectories at once, and moving rapidly. Imaging systems are growing to include huge numbers of sensors, massive data storage capacities, and enormous amounts of processing power. At the other extreme, diagnostic devices are shrinking from the table-top to the implantable or even the ingestible—think a colonoscopy in a pill—forcing new levels of miniaturization, energy efficiency, and autonomous intelligence.
Designers are working on ICs that can conduct a full set of blood chemistry measurements within one chip, log the results, and disappear unmourned into the medical waste bin. And they're planning implantable systems that can draw energy from their host while continuously monitoring a body characteristic, transmitting results to an external relay point and thence through the cellular network to a remote center for analysis.
So a great deal is changing on the hardware front. Far from being a backwater, medical applications are attracting technology so advanced it is in many cases still in the research lab. Some of these devices can only work through a fusion of very different disciplines: for example MEMS, microfluidics, surface electrochemistry, nanopower computing, near-field wireless networking, and energy scavenging. These are disciplines that barely speak to each other.
But what does all this mean for the embedded software expert? Take that last point, for example. Software developers on an implantable blood chemistry analyzer may find themselves trying to extract requirements and theory of operation from a diverse set of hardware designers, chemists, and nanoscale fabricators who don't even speak each others' languages. Good luck on that.
There will be other interesting challenges. The general trend in embedded computing of late has been for the hardware to so far exceed the absolute computing needs of the application that choice of language, methodology, and quality of code didn't make much difference. But many of these medical devices will be trying to do a great deal of control and signal conditioning with vanishingly small amounts of energy and tiny memory space. That may force a return to a level of care in coding that many embedded designers have long since forgotten.
And then there is safety. With a human life potentially at stake in every application, the demands for code reliability and security will be unprecedented. Casual debugging will not answer in this space any longer. It's an explosive new application area, but with some staggering challenges.
Ron Wilson is the director of content/ media, EE Times Group Events and Embedded. You may reach him at firstname.lastname@example.org.