This study quantitatively evaluated whether and how machine learning (ML) models built by data from controlled conditions can fit real-world conditions. This study focused on feature-based models using wearable technology from real-world data collected from young adults, so as to provide insights into the models’ robustness and the specific challenges posed by diverse environmental noise. Feature-based models, particularly XGBoost and Decision Trees, demonstrated considerable resilience, maintaining higher accuracy and reliability across different noise levels. This investigation included an in-depth analysis of transfer learning, highlighting its potential and limitations in adapting models developed from standard datasets, like WESAD, to complex real-world scenarios. Moreover, this study analyzed the distributed feature importance across various physiological signals, such as electrodermal activity (EDA) and electrocardiography (ECG), considering their vulnerability to environmental factors. It was found that integrating multiple physiological data types could significantly enhance model robustness. The results underscored the need for a nuanced understanding of signal contributions to model efficacy, suggesting that feature-based models showed much promise in practical applications.

The resilience of machine learning models for anxiety detection through wearable technology was explored. The effectiveness of feature-based and end-to-end machine learning models for anxiety detection was evaluated under varying conditions of Gaussian noise. By adding synthetic Gaussian noise to a well-known open access affective states dataset collected with commercially available wearable devices (WESAD), a performance baseline was established using the original dataset. This was followed by an examination of the impact of noise on model accuracy to better understand model performance (F₁-score and Accuracy) changes as a function of noise. The results of the analysis revealed that with the increase in noise, the performance of feature-based models dropped from a high of 90% F1-score and 92% accuracy to 65% and 70%, respectively; while end-to-end models showed a decrease from an 85% F1-score and 87% accuracy to below 60% and 65%, respectively. This indicated a proportional decline in performance across both feature-based and end-to-end models as noise levels increased, challenging initial assumptions about model resilience. This analysis highlights the need for more robust algorithms capable of maintaining accuracy in noisy, real-world environments and emphasizes the importance of considering environmental factors in the development of wearable anxiety detection systems.

The field of anxiety detection and use of machine learning (ML) has experienced rapid growth necessitating an updated review of commonly used ML models and their performance, anxiety-inducing methodologies, data collection conditions, and dataset utilization. Feature-based ML models have been extensively employed due to their interpretability and simplicity. However, these models require manual feature engineering, which can be labor-intensive and potentially biased. End-to-end deep learning models have emerged as alternatives, capable of utilizing raw signal directly and handling large datasets. This review aims to provide a detailed exploration of anxiety detection using ML, including use of feature-based vs. end-to-end models, a taxonomy of stressors, performance benchmarks, challenges in deployment to real-world scenarios, and generalizability of findings, given limitations in sociodemographic diversity and heterogeneity in the use of validated anxiety measures. A total of 105 eligible papers were retrieved from the Scopus, IEEE Xplore, and PubMed databases. Stressors were categorized into six distinct types—social, mental, physical, emotional, driving, and daily-life stressors—to provide a better overview of methodologies used to elicit anxiety. Papers were organized according to the type of data collection—lab-based or real-world conditions—and characterized through the type of anxiety instrument used, population examined, and classification performance. This review underscores the need for further investigation into model architecture and their suitability for different types of data, limitations in population diversity and representation in existing studies, and advocating for a more nuanced and personalized approach to anxiety detection using machine learning.

This review provides a detailed exploration of the current state of anxiety detection using machine learning (ML), with a focus on both feature-based and end-to-end models. The field has experienced rapid growth, with a significant increase in academic output ne-cessitating an updated review of commonly used ML models and their performance, anxiety-inducing methodologies, data collection conditions, and dataset utilization. Feature-based ML models, such as Support Vector Machines, have been extensively employed due to their interpretability and simplicity. However, these models require manual feature engineering, which can be labor-intensive and potentially biased. End-to-end deep learning models have emerged as powerful alternatives, capable of utilizing raw signal directly and handling large datasets. Additionally, this review categorizes stressors into six distinct types – social, mental, physical, emotional, driving, and daily-life stressors – to provide a better overview of methodologies used to elicit anxiety. These are further explored based on whether data were collected under con-trolled in-lab conditions or real world in-the-wild conditions. This review underscores the need for further exploration into model architecture and their suitability for different types of data, advocating for a more nuanced and personalized approach to anxiety detection using machine learning.

This work is an outcome of ACCESS MatchPlus pilot program where a student works under the mentorship of a mentor and the researcher who presented a technical challenge and seeked assistance from the MATCHPlus program. The original research project explores the physiological data and applies the machine-learning algorithms to detect anxiety. It proposes a fundamentally new approach significantly enhancing algorithm accuracy. However, practical implementation remains challenging due to performance limitations. The focus of the collaboration under the ACCESS MatchPlus program was aimed to enhance runtime and model efficiency, making the models more applicable for practical use. The paper highlights the improved accuracy and efficiency of the anxiety detection models.