Table 1.3 Impact of AI-mHealth communication system in healthcare.
| Source | Subject matter | Role of AI-Driven mHealth devices | Related performance measures |
| [12–14] | Medical big data analysis | Personalized clinical decision-making | A complex diagnosis process in multiple chronic illnesses became simplerSimilarities in illness patterns are analyzed effectively |
| [15] | Digital healthcare | Health Monitoring - Continuous Glucose Monitoring (CGM)CardioMEMS Heart Sensor with Wireless implantable Hemodynamic Monitoring (W-HM)Automated diagnostic algorithm | POCUS uses in heart diseasesCGM early detects hypoglycemic episodesW-HM results in 30% reduction in heart failure readmissions (hazard ratio 0.70, 95% confidence interval 0.60–0.84) |
| [16] | Atrial fibrillation detection | C statistic–based trained ANN using smart watch data | ANN predicts AF with 90.2% specificity and 98% sensitivity |
| [17] | Echocardiographic evaluation | Machine learning–based Associative memory classifier | Achieves 22% more accuracy in prediction than SVM. |
| [18, 19] | Transthoracic 3D Echocardiography (TTE) Left Heart Chamber Quantification | Automated Adaptive Analytics Algorithm | Achieves better correlation (r = 0.87 to 0.96) with manual 3D TTE |
| [20] | Echocardiogram Interpretation | CNN-based detection trained with 14 035 Echocardiogram images | CNN detects hypertrophic cardiomyopathy, cardiac amyloidosis, and pulmonary arterial hypertension with 95% accuracy. |
A body area network has wide applications in medical and non-medical fields. In the medical field, they are either used as wearable devices or implanted in a patient’s body or as a remote monitoring system to keep track of patient’s health based on the sensory nodes positioned in their bodies. This is very sensitive to older adults or patients with chronic diseases. Through biomedical sensors, motion detectors, and wireless communication, monitoring of every activity like glucose, blood pressure, and pulse rate is done. Figure 1.5 shows a typical body area network with wearable devices for health monitoring. All the required information is collected through the central hub and processed wirelessly to the healthcare provider or medical staff during emergencies. The end devices can also be wearable [22–24], which act as transducers to display human activities, temperature, and pressure.
Communication in the body sensor network is of two types.
1 (i) In-body communication uses RF signals between sensory nodes, which are implanted in our human body. The frequency at which the communication has to take place is defined by Medical Implantable Communication Service (MICS), and the range of frequency is 402–405 MHz
2 (ii) On-body communication is the communication between wearable sensory nodes, which consists of biosensors. Ultrawideband (UWB) can be used for on-body communication. IMS based, which is mainly used for industrial, medical, and scientific applications having a range of 2.4–2.485 GHz. Many electronic applications operate on this band.
Figure 1.5 Wearable devices in the health monitoring system (Adopted from [21]).
1.4.1 Features
Since the nodes are placed inside and outside the human body, it requires less power consumption as the devices are battery operated. So, it is essential that for the battery to work longer, power consumption should be less. As communication deals with bio-signals in the medical field, the Quality of Service (QoS) plays an important role. So, the user can detect proper information and treat accordingly.
As the network deals with information transmission related to vital parameters of human beings, the security of data is critical to avoid unauthorized accessibility. In the case of biosensors, the threshold value is set. So, if any parameter increases or decreases below the threshold value, then it generates an alarm, so fewer false alarms are required. Wireless Medical Telemetry Service (WMTS) and UWB are technologies that are used for body monitoring systems because of their low transmission power.
1.4.2 Communication Architecture of Wireless Body Area Networks
In this section, we discuss the architecture of WBAN, which is divided into the three-stage process to depict the working mechanism of WBAN as shown in Figure 1.6 [25].
Stage 1: Intra sensor communication
The communication among the sensors around the human body is considered in this stage. A personal server acts as a gateway, which is used by communication signals within the human body. Gateway transfers the data to the next stage of architecture.
Stage 2: Medium
This stage enables the data transfer between the personal server and user through an access point, which is considered as a central unit of the network, which can make decisions in case of emergencies.
Figure 1.6 Architecture of WBAN communication.
Stage 3: Beyond WBAN
Smartphones are used to interlink between the access point and medical server, in which patient historical data could be stored. The medical environment database is a very sensitive part of stage 3. Security against this stage is fulfilled to protect the personal history of the patients.
1.4.3 Role of AI in WBAN Architecture
Internal communication among the sensors and measured parameters from the human body are processed using deep learning algorithms. AI-based data processing models analyze massive amounts of data from the sensors and extract useful information from them. Figure 1.7 shows the role of AI in WBAN. The extracted features are used to diagnosis the disease, wherein the proposed model is trained with related data. CNNs are used for feature extraction; based on the inputs, CNN generates