Exploring Unsupervised Machine Learning Classification Methods for Physiological Stress Detection

Patient-ventilator asynchrony classification in mechanically ventilated patients: Model-based or machine learning method?

BACKGROUND AND OBJECTIVE

Patient-ventilator asynchrony (PVA) is associated with poor clinical outcomes and remains under-monitored. Automated PVA detection would enable complete monitoring standard observational methods do not allow. While model-based and machine learning PVA approaches exist, they have variable performance and can miss specific PVA events. This study compares a model and rule-based algorithm with a machine learning PVA method by retrospectively validating both methods using an independent patient cohort.

METHODS

Hysteresis loop analysis (HLA) which is a rule-based method (RBM) and a tri-input convolutional neural network (TCNN) machine learning model are used to classify 7 different types of PVA, including: 1) flow asynchrony; 2) reverse triggering; 3) premature cycling; 4) double triggering; 5) delayed cycling; 6) ineffective efforts; and 7) auto triggering. Class activation mapping (CAM) heatmaps visualise sections of respiratory waveforms the TCNN model uses for decision making, improving result interpretability. Both PVA classification methods were used to classify incidence in an independent retrospective clinical cohort of 11 mechanically ventilated patients for validation and performance comparison.

RESULTS

Self-validation with the training dataset shows overall better HLA performance (accuracy, sensitivity, specificity: 97.5 %, 96.6 %, 98.1 %) compared to the TCNN model (accuracy, sensitivity, specificity: 89.5 %, 98.3 %, 83.9 %). In this study, the TCNN model demonstrates higher sensitivity in detecting PVA, but HLA was better at identifying non-PVA breathing cycles due to its rule-based nature. While the overall AI identified by both classification methods are very similar, the intra-patient distribution of each PVA type varies between HLA and TCNN.

CONCLUSION

The collective findings underscore the efficacy of both HLA and TCNN in PVA detection, indicating the potential for real-time continuous monitoring of PVA. While ML methods such as TCNN demonstrate good PVA identification performance, it is essential to ensure optimal model architecture and diversity in training data before widespread uptake as standard care. Moving forward, further validation and adoption of RBM methods, such as HLA, offers an effective approach to PVA detection while providing clear distinction into the underlying patterns of PVA, better aligning with clinical needs for transparency, explicability, adaptability and reliability of these emerging tools for clinical care.

A comprehensive review of machine learning algorithms and their application in geriatric medicine: present and future

The increasing access to health data worldwide is driving a resurgence in machine learning research, including data-hungry deep learning algorithms. More computationally efficient algorithms now offer unique opportunities to enhance diagnosis, risk stratification, and individualised approaches to patient management. Such opportunities are particularly relevant for the management of older patients, a group that is characterised by complex multimorbidity patterns and significant interindividual variability in homeostatic capacity, organ function, and response to treatment. Clinical tools that utilise machine learning algorithms to determine the optimal choice of treatment are slowly gaining the necessary approval from governing bodies and being implemented into healthcare, with significant implications for virtually all medical disciplines during the next phase of digital medicine. Beyond obtaining regulatory approval, a crucial element in implementing these tools is the trust and support of the people that use them. In this context, an increased understanding by clinicians of artificial intelligence and machine learning algorithms provides an appreciation of the possible benefits, risks, and uncertainties, and improves the chances for successful adoption. This review provides a broad taxonomy of machine learning algorithms, followed by a more detailed description of each algorithm class, their purpose and capabilities, and examples of their applications, particularly in geriatric medicine. Additional focus is given on the clinical implications and challenges involved in relying on devices with reduced interpretability and the progress made in counteracting the latter via the development of explainable machine learning.

Generalizable machine learning for stress monitoring from wearable devices: A systematic literature review

INTRODUCTION

Wearable sensors have shown promise as a non-intrusive method for collecting biomarkers that may correlate with levels of elevated stress. Stressors cause a variety of biological responses, and these physiological reactions can be measured using biomarkers including Heart Rate Variability (HRV), Electrodermal Activity (EDA) and Heart Rate (HR) that represent the stress response from the Hypothalamic-Pituitary-Adrenal (HPA) axis, the Autonomic Nervous System (ANS), and the immune system. While Cortisol response magnitude remains the gold standard indicator for stress assessment [1], recent advances in wearable technologies have resulted in the availability of a number of consumer devices capable of recording HRV, EDA and HR sensor biomarkers, amongst other signals. At the same time, researchers have been applying machine learning techniques to the recorded biomarkers in order to build models that may be able to predict elevated levels of stress.

OBJECTIVE

The aim of this review is to provide an overview of machine learning techniques utilized in prior research with a specific focus on model generalization when using these public datasets as training data. We also shed light on the challenges and opportunities that machine learning-enabled stress monitoring and detection face.

METHODS

This study reviewed published works contributing and/or using public datasets designed for detecting stress and their associated machine learning methods. The electronic databases of Google Scholar, Crossref, DOAJ and PubMed were searched for relevant articles and a total of 33 articles were identified and included in the final analysis. The reviewed works were synthesized into three categories of publicly available stress datasets, machine learning techniques applied using those, and future research directions. For the machine learning studies reviewed, we provide an analysis of their approach to results validation and model generalization. The quality assessment of the included studies was conducted in accordance with the IJMEDI checklist [2].

RESULTS

A number of public datasets were identified that are labeled for stress detection. These datasets were most commonly produced from sensor biomarker data recorded using the Empatica E4 device, a well-studied, medical-grade wrist-worn wearable that provides sensor biomarkers most notable to correlate with elevated levels of stress. Most of the reviewed datasets contain less than twenty-four hours of data, and the varied experimental conditions and labeling methodologies potentially limit their ability to generalize for unseen data. In addition, we discuss that previous works show shortcomings in areas such as their labeling protocols, lack of statistical power, validity of stress biomarkers, and model generalization ability.

CONCLUSION

Health tracking and monitoring using wearable devices is growing in popularity, while the generalization of existing machine learning models still requires further study, and research in this area will continue to provide improvements as newer and more substantial datasets become available.

Improved Stress Classification Using Automatic Feature Selection from Heart Rate and Respiratory Rate Time Signals

Time-series features are the characteristics of data periodically collected over time. The calculation of time-series features helps in understanding the underlying patterns and structure of the data, as well as in visualizing the data. The manual calculation and selection of time-series feature from a large temporal dataset are time-consuming. It requires researchers to consider several signal-processing algorithms and time-series analysis methods to identify and extract meaningful features from the given time-series data. These features are the core of a machine learning-based predictive model and are designed to describe the informative characteristics of the time-series signal. For accurate stress monitoring, it is essential that these features are not only informative but also well-distinguishable and interpretable by the classification models. Recently, a lot of work has been carried out on automating the extraction and selection of times-series features. In this paper, a correlation-based time-series feature selection algorithm is proposed and evaluated on the stress-predict dataset. The algorithm calculates a list of 1578 features of heart rate and respiratory rate signals (combined) using the tsfresh library. These features are then shortlisted to the more specific time-series features using Principal Component Analysis (PCA) and Pearson, Kendall, and Spearman correlation ranking techniques. A comparative study of conventional statistical features (like, mean, standard deviation, median, and mean absolute deviation) versus correlation-based selected features is performed using linear (logistic regression), ensemble (random forest), and clustering (k-nearest neighbours) predictive models. The correlation-based selected features achieved higher classification performance with an accuracy of 98.6% as compared to the conventional statistical feature’s 67.4%. The outcome of the proposed study suggests that it is vital to have better analytical features rather than conventional statistical features for accurate stress classification.

Applications of machine learning in metabolomics: Disease modeling and classification

Metabolomics research has recently gained popularity because it enables the study of biological traits at the biochemical level and, as a result, can directly reveal what occurs in a cell or a tissue based on health or disease status, complementing other omics such as genomics and transcriptomics. Like other high-throughput biological experiments, metabolomics produces vast volumes of complex data. The application of machine learning (ML) to analyze data, recognize patterns, and build models is expanding across multiple fields. In the same way, ML methods are utilized for the classification, regression, or clustering of highly complex metabolomic data. This review discusses how disease modeling and diagnosis can be enhanced via deep and comprehensive metabolomic profiling using ML. We discuss the general layout of a metabolic workflow and the fundamental ML techniques used to analyze metabolomic data, including support vector machines (SVM), decision trees, random forests (RF), neural networks (NN), and deep learning (DL). Finally, we present the advantages and disadvantages of various ML methods and provide suggestions for different metabolic data analysis scenarios.

Stress Monitoring Using Wearable Sensors: A Pilot Study and Stress-Predict Dataset

With the recent advancements in the field of wearable technologies, the opportunity to monitor stress continuously using different physiological variables has gained significant interest. The early detection of stress can help improve healthcare and minimizes the negative impact of long-term stress. This paper reports outcomes of a pilot study and associated stress-monitoring dataset, named the "Stress-Predict Dataset", created by collecting physiological signals from healthy subjects using wrist-worn watches with a photoplethysmogram (PPG) sensor. While wearing these watches, 35 healthy volunteers underwent a series of tasks (i.e., Stroop color test, Trier Social Stress Test and Hyperventilation Provocation Test), along with a rest period in-between each task. They also answered questionnaires designed to induce stress levels compatible with daily life. The changes in the blood volume pulse (BVP) and heart rate were recorded by the watch and were labelled as occurring during stress-inducing tasks or a rest period (no stress). Additionally, respiratory rate was estimated using the BVP signal. Statistical models and personalised adaptive reference ranges were used to determine the utility of the proposed stressors and the extracted variables (heart rate and respiratory rate). The analysis showed that the interview session was the most significant stress stimulus, causing a significant variation in heart rate of 27 (77%) participants and respiratory rate of 28 (80%) participants out of 35. The outcomes of this study contribute to the understanding the role of stressors and their association with physiological response and provide a dataset to help develop new wearable solutions for more reliable, valid, and sensitive physio-logical stress monitoring.