Title:Role of Oxidative Stress and Inflammation in Insomnia Sleep Disorder and Cardiovascular
Diseases: Herbal Antioxidants and Anti-inflammatory Coupled
with Insomnia Detection using Machine Learning
Volume: 28
Issue: 45
Author(s): Md. Belal Bin Heyat*, Faijan Akhtar, Arshiya Sultana, Saifullah Tumrani, Bibi Nushrina Teelhawod, Rashid Abbasi, Mohammad Amjad Kamal, Abdullah Y. Muaad, Dakun Lai*Kaishun Wu*
Affiliation:
- IoT Research Center, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, Guangdong
518060, China
- BMI-EP Laboratory, School of Electronic Science
and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan 610054, China
- IoT Research Center, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, Guangdong
518060, China
Keywords:
AI, detection, electrocardiogram, insomnia, oxidative stress, mitochondria, sleep disorder, ROS, diagnosis, nervous system, sleep.
Abstract: Insomnia is well-known as trouble in sleeping and enormously influences human life due to the shortage
of sleep. Reactive Oxygen Species (ROS) accrue in neurons during the waking state, and sleep has a defensive
role against oxidative damage and dissipates ROS in the brain. In contrast, insomnia is the source of inequity
between ROS generation and removal by an endogenous antioxidant defense system. The relationship between
insomnia, depression, and anxiety disorders damages the cardiovascular systems' immune mechanisms
and functions. Traditionally, polysomnography is used in the diagnosis of insomnia. This technique is complex,
with a long time overhead. In this work, we have proposed a novel machine learning-based automatic detection
system using the R-R intervals extracted from a single-lead electrocardiograph (ECG). Additionally, we aimed
to explore the role of oxidative stress and inflammation in sleeping disorders and cardiovascular diseases, antioxidants’
effects, and the psychopharmacological effect of herbal medicine. This work has been carried out in
steps, which include collecting the ECG signal for normal and insomnia subjects, analyzing the signal, and finally,
automatic classification. We used two approaches, including subjects (normal and insomnia), two sleep
stages, i.e., wake and rapid eye movement, and three Machine Learning (ML)-based classifiers to complete the
classification. A total number of 3000 ECG segments were collected from 18 subjects. Furthermore, using the
theranostics approach, the role of mitochondrial dysfunction causing oxidative stress and inflammatory response
in insomnia and cardiovascular diseases was explored. The data from various databases on the mechanism
of action of different herbal medicines in insomnia and cardiovascular diseases with antioxidant and antidepressant
activities were also retrieved. Random Forest (RF) classifier has shown the highest accuracy (subjects:
87.10% and sleep stage: 88.30%) compared to the Decision Tree (DT) and Support Vector Machine
(SVM). The results revealed that the suggested method could perform well in classifying the subjects and sleep
stages. Additionally, a random forest machine learning-based classifier could be helpful in the clinical discovery
of sleep complications, including insomnia. The evidence retrieved from the databases showed that herbal
medicine contains numerous phytochemical bioactives and has multimodal cellular mechanisms of action, viz.,
antioxidant, anti-inflammatory, vasorelaxant, detoxifier, antidepressant, anxiolytic, and cell-rejuvenator properties.
Other herbal medicines have a GABA-A receptor agonist effect. Hence, we recommend that the theranostics
approach has potential and can be adopted for future research to improve the quality of life of humans.
