Medical devices are advancing to provide increasingly intelligent and relevant responses, bringing the potential for greater impact and better patient outcomes. Such responses are derived from analysis of patient signals made available thanks to advances in sensing and instrumentation technologies. However, given the complexity of the underlying physiologic and pathophysiologic processes, analysis of these signals is challenging on many levels. Data-driven methods for analysis are showing substantial promise towards these challenges, actuated both by the large-scale emergence of data in the medical domain and by progress in algorithms from the machine-learning and statistical-signal-processing domains. This chapter explores the platformlevel challenges with extending data-driven methods to resource-constrained (energy, area) wearable and implantable devices. Recent work in the area of heterogeneous microprocessor design and low-power algorithms is presented to illustrate approaches to addressing the challenges.
|Original language||English (US)|
|Title of host publication||Circuit Design Considerations for Implantable Devices|
|Number of pages||34|
|State||Published - Dec 31 2017|
All Science Journal Classification (ASJC) codes
- Biochemistry, Genetics and Molecular Biology(all)