Enhancing the Reliability of Closed-Loop Medical Systems with Real-Time Biosignal Modeling

Biosignal monitoring using wearable and implantable devices (WIMDs) is driving the advent of highly personalized medicine. However, such devices may suffer from the same faulty behavior as any electronic system and may furthermore be targeted by malicious actors seeking to do harm. Closed-loop medic...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of hardware and systems security Ročník 8; číslo 1; s. 12 - 24
Hlavní autoři: Mahmud, Shakil, Zareen, Farhath, Olney, Brooks, Karam, Robert
Médium: Journal Article
Jazyk:angličtina
Vydáno: Cham Springer International Publishing 01.03.2024
Springer Nature B.V
Témata:
Algorithms
Artificial intelligence
Biosensors
Bladder
Circuits and Systems
Closed loop systems
Closed loops
Component reliability
Computer Hardware
Control systems
Control theory
Controllers
Data acquisition
Electronic systems
Energy consumption
Engineering
Error correction & detection
Glucose
Information Systems Applications (incl.Internet)
Machine learning
Medical equipment
Neural networks
Nonlinear control
Nonlinear systems
Pacemakers
Pancreas
Patients
Physiology
Prediction models
Predictive control
Quality of life
Real time
Sensors
System reliability
Systems and Data Security
Target acquisition
Transplants & implants
Urogenital system
Wearable computers
Biosignal
Closed-loop system
Neural network
Implantable medical device
Nonlinear autoregressive
ISSN:2509-3428, 2509-3436
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Biosignal monitoring using wearable and implantable devices (WIMDs) is driving the advent of highly personalized medicine. However, such devices may suffer from the same faulty behavior as any electronic system and may furthermore be targeted by malicious actors seeking to do harm. Closed-loop medical control systems, which monitor biosignals for data acquisition, contain and interact with many other components, any of which may be maliciously targeted or suffer a naturally occurring fault. Any measure aiming to improve the security and reliability of these systems must also consider the interplay between each component. In this paper, we explore the vulnerability of closed-loop medical control systems considering both individual system components and the system as a whole and utilize a predictive model based on a nonlinear autoregressive neural network (NARNN) to detect and correct faulty behavior in real time. We present a case study using a human bladder pressure dataset from nine subjects undergoing acute urodynamics testing. Signals are corrupted to simulate faulty sensor readings or malicious attacks and then processed using a custom bladder event detection algorithm designed for use in a closed-loop neuromodulation system. Using the proposed technique, 100% of faulty measurements were detected and corrected, so the control algorithm induced no additional false positives. We present the circuit-level implementation of the NARNN suitable for on-chip machine learning (ML)/artificial intelligence (AI) applications. We synthesized and generated the layout of the NARNN architecture in SAED 32  nm technology. The implementation requires an area of 0.022 m m 2 and a total power consumption of 0.31  mW , which is suitable for WIMDs.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2509-3428
2509-3436
DOI:10.1007/s41635-023-00140-4