Classification of Alzheimer's Disease Using RF Signals and Machine Learning

Abstract

Objectives: Alzheimer's disease is one of the most fastest growing and costly diseases in the world today. It affects the livelihood of not just patients, but those who take care of them, including care givers, nurses, and close family members. Current progression monitoring techniques are based on MRI and PET scans which are inconvenient for patients to use. In addition, more intelligent and efficient methods are needed to predict what the current stage of the disease is and strategies on how to slow down its progress over time. Technology or Method: In this paper, machine learning was used with S-parameter data obtained from 6 antennas that were placed around the head to noninvasively capture changes in the brain in the presence of Alzheimer's disease pathology. Measurements were conducted for 9 different human models that varied in head sizes. The data was processed in several machine learning algorithms. Each algorithm's prediction and accuracy score were generated and the results were compared to determine which machine learning algorithm could be used to efficiently classify different stages of Alzheimer's disease. Results: Results from the study showed that overall, the logistic regression model had the best accuracy of 98.97% and efficiency in differentiating between 4 different stages of Alzheimer's disease. Clinical or Biological Impact: The results obtained here provide a transformative approach to clinics and monitoring systems where machine learning can be integrated with noninvasive microwave medical sensors and systems to intelligently predict the stage of Alzheimer's disease in the brain.

Microwave Radiation and the Brain: Mechanisms, Current Status, and Future Prospects

“…Accordingly, establishing safety levels by standardizing the frequency, power, and exposure times of microwaves, along with their applications, is of the upmost importance. Some studies have reported that microwaves may affect our CNSs differently, with some indicating that microwaves are involved in the manifestation of CNS diseases [ 108 ], including Alzheimer’s disease [ 109 , 202 , 203 , 204 , 205 , 206 ]. ( Figure 6 ).…”

Review Of Models & Techniques For Identification Of Human Health Diseases

“…While absolute values for accuracy & precision were available, other metrics like delay, complexity and scalability were evaluated in terms of fuzzy range sets of Low (L), Medium, High (H), and Very High (VH), which were decided based on their internal configurations and performance across different scenarios. Based on this strategy, table 1 showcases parameters for these models, Based on this analysis, it can be observed that DF [43], TPA GAN [4], PCA NET [17], THS GAN [50], SSDP [24], MA Net [30], TSA CNN [26], and RL [42] showcase high accuracy, while DLN [40], Fuzzy GBDT [22], PD Res Net [21], GERF [39], PC SVM [41], SSDP [24], SALL [25], THS GAN [50], ACGA [23], TSA CNN [26], and RL [42] showcase high precision, which makes them useful for a wide variety of real-time clinical use cases.…”

“…The authors of this paper outline an automated deep learning-based movie-based PD detection system. Researchers describe a 3D convolutional neural networks (CNN) ability to categorize the severity of PD [26]. The severity of PD may be identified through non-medical transfer learning, according to research, despite the paucity of clinical data in this area.…”

“…TSA CNN [26], and RL [42] showcase high accuracy, whereas DLN [40], Fuzzy GBDT [22], PD Res Net [21], GERF [39], PC SVM [41], SSDP [24], SALL [25], THS GAN [50], ACGA [ In terms of complexity, CT [6], SVM [15], SSDP [24], and LR [27] are able to achieve higher performance. On the other hand, in terms of delay, UESR [5], JHCP MMP [13], SVM [15], and SVM [47] are able to display quicker performance, and hence may be utilized for high-speed clinical deployments.…”

Evaluation of Unobtrusive Microwave Sensors in Healthcare 4.0—Toward the Creation of Digital-Twin Model

“…The authors of [ 58 ] utilized a stepped monopole antenna for its microwave unobtrusive sensing [ 59 ] ability to detect and create image zones of the brain that are affected by Alzheimer’s disease, providing an improvement over PET scans, which rely on biomarkers. The antenna was fabricated using conductive textile material (Shieldex Zell) and flexible substrate material (RS-PRO Viscose Wool Felt) to provide adaptability in the placement of the antenna [ 60 ].…”