Page 269 - Handbook of Deep Learning in Biomedical Engineering Techniques and Applications

260 Chapter 9 Applications of deep learning in biomedical engineering

27. Bodyemachine interface

Automotive health-examining systems intend to monitor
health conditions by examining signals such as heart rate, blood
pressure, blood sugar, EEG, and ECG.
These automated frameworks can be classified into two types
according to their functionality. They are as follows:
1. Drug infusion system
2. Rehabilitation system [20]

28. Drug infusion system
Automated drug infusion system assists anesthesiologists and
clinicians to regulate the hemodynamic effects of the patients in
reaction to drugs. ANN-based adaptive predictive controller is
capable of learning and detecting irregular signs that vary over
time. Hence, DL is the most promising technique in drug infusion
system [21].

29. Rehabilitation system
DL techniques are applicable for monitoring rehabilitation ex-
ercise to recover after surgeries. The approach of activity recogni-
tion is utilized to analyze information from the embedded
devices [22].

30. Diseases diagnosis
Most of these applications in BBMI concern about the auto-
mated detection of irregularities in the rate or heartbeat rhythm
using deep neural networks. DL has also been applied in other
applications such as automated detection and diagnosis of
seizure and screening of depression or neonatal sleep-state
identification.
Different applications of BBMIs are as follows:
• Sleep patterns
• Epilepsy
• Attention deficit hyperactivity disorder (ADHD)
• Disorders of consciousness
• Depth of anesthesia
• Fatigue and mental workload
• Mood analysis
• Emotion detection