Machine Learning Techniques for Developing Remotely Monitored Central Nervous System Biomarkers Using Wearable Sensors: A Narrative Literature Review

Abstract

Background: Central nervous system (CNS) disorders benefit from ongoing monitoring to assess disease progression and treatment efficacy. Mobile health (mHealth) technologies offer a means for the remote and continuous symptom monitoring of patients. Machine Learning (ML) techniques can process and engineer mHealth data into a precise and multidimensional biomarker of disease activity. Objective: This narrative literature review aims to provide an overview of the current landscape of biomarker development using mHealth technologies and ML. Additionally, it proposes recommendations to ensure the accuracy, reliability, and interpretability of these biomarkers. Methods: This review extracted relevant publications from databases such as PubMed, IEEE, and CTTI. The ML methods employed across the selected publications were then extracted, aggregated, and reviewed. Results: This review synthesized and presented the diverse approaches of 66 publications that address creating mHealth-based biomarkers using ML. The reviewed publications provide a foundation for effective biomarker development and offer recommendations for creating representative, reproducible, and interpretable biomarkers for future clinical trials. Conclusion: mHealth-based and ML-derived biomarkers have great potential for the remote monitoring of CNS disorders. However, further research and standardization of study designs are needed to advance this field. With continued innovation, mHealth-based biomarkers hold promise for improving the monitoring of CNS disorders.

Exploring the Relationship between Behavioral and Neurological Impairments Due to Mild Cognitive Impairment: Correlation Study between Virtual Kiosk Test and EEG-SSVEP

“…To identify the best model for behavioral and neurological features, we compared the following six machine learning classifiers: Support Vector Machine (SVM), Linear Discriminant Analysis (LDA), Naive Bayes Classifier (NB), Gaussian Process Classifier (GPC), k-Nearest Neighbors classifier (KNN), and Random Forest (RF) [ 40 , 41 ]. For the feature selection process, an embedded method using SVM with a linear kernel and L2 regularization with C = 0.05 was adopted to filter features with lower importance relative to the average importance across all features [ 42 ].…”

Applications of Machine Learning (ML) and Mathematical Modeling (MM) in Healthcare with Special Focus on Cancer Prognosis and Anticancer Therapy: Current Status and Challenges

“…Sensors for mobility, pulse, respiration rate, body temperature, blood pressure, oxygen levels, and other biometrics are becoming a common feature of wearable technology [ 365 , 366 , 367 , 368 , 369 ]. In the future, wearable and sound sensor data will probably be utilized to find novel biomarkers, possibly by merging data from various types of devices [ 130 , 370 , 371 ]. The continuous monitoring of a person’s behavior and bodily functions via wearable and home gadgets, along with readouts from routine blood tests, are features of health management.…”

Smartwatch Versus Routine Tremor Documentation: Descriptive Comparison

“…Clinical assessment of tremor is limited by its subjectivity, making it challenging to detect subtle tremors (<0.05 g) [1]. The need for technology-based evaluations led to extensive research on sensor-based tremor assessments [2][3][4][5][6]. However, the benefits of smart consumer devices for clinical documentation remain unaddressed.…”