Prediction of state anxiety by machine learning applied to photoplethysmography data

Intelligent Detection Method of Atrial Fibrillation by CEPNCC-BiLSTM Based on Long-Term Photoplethysmography Data

Atrial fibrillation (AF) is the most prevalent arrhythmia characterized by intermittent and asymptomatic episodes. However, traditional detection methods often fail to capture the sporadic and intricate nature of AF, resulting in an increased risk of false-positive diagnoses. To address these challenges, this study proposes an intelligent AF detection and diagnosis method that integrates Complementary Ensemble Empirical Mode Decomposition, Power-Normalized Cepstral Coefficients, Bi-directional Long Short-term Memory (CEPNCC-BiLSTM), and photoelectric volumetric pulse wave technology to enhance accuracy in detecting AF. Compared to other approaches, the proposed method demonstrates faster preprocessing efficiency and higher sensitivity in detecting AF while effectively filtering out false alarms from photoplethysmography (PPG) recordings of non-AF patients. Considering the limitations of conventional AF detection evaluation systems that lack a comprehensive assessment of efficiency and accuracy, this study proposes the ET-score evaluation system based on F-measurement, which incorporates both computational speed and accuracy to provide a holistic assessment of overall performance. Evaluated with the ET-score, the CEPNCC-BiLSTM method outperforms EEMD-based improved Power-Normalized Cepstral Coefficients and Bi-directional Long Short-term Memory (EPNCC-BiLSTM), Support Vector Machine (SVM), EPNCC-SVM, and CEPNCC-SVM methods. Notably, this approach achieves an outstanding accuracy rate of up to 99.2% while processing PPG recordings within 5 s, highlighting its potential for long-term AF monitoring.

A novel approach to anxiety level prediction using small sets of judgment and survey variables

Anxiety, a condition characterized by intense fear and persistent worry, affects millions each year and, when severe, is distressing and functionally impairing. Numerous machine learning frameworks have been developed and tested to predict features of anxiety and anxiety traits. This study extended these approaches by using a small set of interpretable judgment variables (n = 15) and contextual variables (demographics, perceived loneliness, COVID-19 history) to (1) understand the relationships between these variables and (2) develop a framework to predict anxiety levels [derived from the State Trait Anxiety Inventory (STAI)]. This set of 15 judgment variables, including loss aversion and risk aversion, models biases in reward/aversion judgments extracted from an unsupervised, short (2-3 min) picture rating task (using the International Affective Picture System) that can be completed on a smartphone. The study cohort consisted of 3476 de-identified adult participants from across the United States who were recruited using an email survey database. Using a balanced Random Forest approach with these judgment and contextual variables, STAI-derived anxiety levels were predicted with up to 81% accuracy and 0.71 AUC ROC. Normalized Gini scores showed that the most important predictors (age, loneliness, household income, employment status) contributed a total of 29-31% of the cumulative relative importance and up to 61% was contributed by judgment variables. Mediation/moderation statistics revealed that the interactions between judgment and contextual variables appears to be important for accurately predicting anxiety levels. Median shifts in judgment variables described a behavioral profile for individuals with higher anxiety levels that was characterized by less resilience, more avoidance, and more indifference behavior. This study supports the hypothesis that distinct constellations of 15 interpretable judgment variables, along with contextual variables, could yield an efficient and highly scalable system for mental health assessment. These results contribute to our understanding of underlying psychological processes that are necessary to characterize what causes variance in anxiety conditions and its behaviors, which can impact treatment development and efficacy.

Assessing the Impact of Electrosuit Therapy on Cerebral Palsy: A Study on the Users' Satisfaction and Potential Efficacy

The aim of this study is to evaluate the effectiveness of electrosuit therapy in the clinical treatment of children with Cerebral Palsy, focusing on the effect of the therapy on spasticity and trunk control. Moreover, the compliance of caregivers with respect to the use of the tool was investigated. During the period ranging from 2019 to 2022, a total of 26 children (18 M and 8 F), clinically stable and affected by CP and attending the Neurorehabilitation Unit of the "Padre Pio Foundation and Rehabilitation Centers", were enrolled in this study. A subset of 12 patients bought or rented the device; thus, they received the administration of the EMS-based therapy for one month, whereas the others received only one-hour training to evaluate the feasibility (by the caregivers) and short-term effects. The Gross Motor Function Classification System was utilized to evaluate gross motor functions and to classify the study sample, while the MAS and the LSS were employed to assess the outcomes of the EMS-based therapy. Moreover, between 80% and 90% of the study sample were satisfied with the safety, ease of use, comfort, adjustment, and after-sales service. Following a single session of electrical stimulation with EMS, patients exhibited a statistically significant enhancement in trunk control. For those who continued this study, the subscale of the QUEST with the best score was adaptability (0.74 ± 0.85), followed by competence (0.67 ± 0.70) and self-esteem (0.59 ± 0.60). This study investigates the impact of the employment of the EMS on CP children's ability to maintain trunk control. Specifically, after undergoing a single EMS session, LSS showed a discernible improvement in children's trunk control. In addition, the QUEST and the PIADS questionnaires demonstrated a good acceptability and satisfaction of the garment by the patients and the caregivers.

Assessing Feasibility of Cognitive Impairment Testing Using Social Robotic Technology Augmented with Affective Computing and Emotional State Detection Systems

Social robots represent a valid opportunity to manage the diagnosis, treatment, care, and support of older people with dementia. The aim of this study is to validate the Mini-Mental State Examination (MMSE) test administered by the Pepper robot equipped with systems to detect psychophysical and emotional states in older patients. Our main result is that the Pepper robot is capable of administering the MMSE and that cognitive status is not a determinant in the effective use of a social robot. People with mild cognitive impairment appreciate the robot, as it interacts with them. Acceptability does not relate strictly to the user experience, but the willingness to interact with the robot is an important variable for engagement. We demonstrate the feasibility of a novel approach that, in the future, could lead to more natural human-machine interaction when delivering cognitive tests with the aid of a social robot and a Computational Psychophysiology Module (CPM).

A Deep Learning Approach for Atrial Fibrillation Classification Using Multi-Feature Time Series Data from ECG and PPG

Atrial fibrillation is a prevalent cardiac arrhythmia that poses significant health risks to patients. The use of non-invasive methods for AF detection, such as Electrocardiogram and Photoplethysmogram, has gained attention due to their accessibility and ease of use. However, there are challenges associated with ECG-based AF detection, and the significance of PPG signals in this context has been increasingly recognized. The limitations of ECG and the untapped potential of PPG are taken into account as this work attempts to classify AF and non-AF using PPG time series data and deep learning. In this work, we emploted a hybrid deep neural network comprising of 1D CNN and BiLSTM for the task of AF classification. We addressed the under-researched area of applying deep learning methods to transmissive PPG signals by proposing a novel approach. Our approach involved integrating ECG and PPG signals as multi-featured time series data and training deep learning models for AF classification. Our hybrid 1D CNN and BiLSTM model achieved an accuracy of 95% on test data in identifying atrial fibrillation, showcasing its strong performance and reliable predictive capabilities. Furthermore, we evaluated the performance of our model using additional metrics. The precision of our classification model was measured at 0.88, indicating its ability to accurately identify true positive cases of AF. The recall, or sensitivity, was measured at 0.85, illustrating the model's capacity to detect a high proportion of actual AF cases. Additionally, the F1 score, which combines both precision and recall, was calculated at 0.84, highlighting the overall effectiveness of our model in classifying AF and non-AF cases.

A Survey on Wearable Sensors for Mental Health Monitoring

Mental illness, whether it is medically diagnosed or undiagnosed, affects a large proportion of the population. It is one of the causes of extensive disability, and f not properly treated, it can lead to severe emotional, behavioral, and physical health problems. In most mental health research studies, the focus is on treatment, but fewer resources are focused on technical solutions to mental health issues. The present paper carried out a systematic review of available literature using PRISMA guidelines to address various monitoring solutions in mental health through the use of wearable sensors. Wearable sensors can offer several advantages over traditional methods of mental health assessment, including convenience, cost-effectiveness, and the ability to capture data in real-world settings. Their ability to collect data related to anxiety and stress levels, as well as panic attacks, is discussed. The available sensors on the market are described, as well as their success in providing data that can be correlated with the aforementioned health issues. The current wearable landscape is quite dynamic, and the current offerings have enough quality to deliver meaningful data targeted for machine learning algorithms. The results indicate that mental health monitoring is feasible.

Can Data-Driven Supervised Machine Learning Approaches Applied to Infrared Thermal Imaging Data Estimate Muscular Activity and Fatigue?

Surface electromyography (sEMG) is the acquisition, from the skin, of the electrical signal produced by muscle activation. Usually, sEMG is measured through electrodes with electrolytic gel, which often causes skin irritation. Capacitive contactless electrodes have been developed to overcome this limitation. However, contactless EMG devices are still sensitive to motion artifacts and often not comfortable for long monitoring. In this study, a non-invasive contactless method to estimate parameters indicative of muscular activity and fatigue, as they are assessed by EMG, through infrared thermal imaging (IRI) and cross-validated machine learning (ML) approaches is described. Particularly, 10 healthy participants underwent five series of bodyweight squats until exhaustion interspersed by 1 min of rest. During exercising, the vastus medialis activity and its temperature were measured through sEMG and IRI, respectively. The EMG average rectified value (ARV) and the median frequency of the power spectral density (MDF) of each series were estimated through several ML approaches applied to IRI features, obtaining good estimation performances (r = 0.886, p < 0.001 for ARV, and r = 0.661, p < 0.001 for MDF). Although EMG and IRI measure physiological processes of a different nature and are not interchangeable, these results suggest a potential link between skin temperature and muscle activity and fatigue, fostering the employment of contactless methods to deliver metrics of muscular activity in a non-invasive and comfortable manner in sports and clinical applications.

Emotion Recognition: Photoplethysmography and Electrocardiography in Comparison

Automatically recognizing negative emotions, such as anger or stress, and also positive ones, such as euphoria, can contribute to improving well-being. In real-life, emotion recognition is a difficult task since many of the technologies used for this purpose in both laboratory and clinic environments, such as electroencephalography (EEG) and electrocardiography (ECG), cannot realistically be used. Photoplethysmography (PPG) is a non-invasive technology that can be easily integrated into wearable sensors. This paper focuses on the comparison between PPG and ECG concerning their efficacy in detecting the psychophysical and affective states of the subjects. It has been confirmed that the levels of accuracy in the recognition of affective variables obtained by PPG technology are comparable to those achievable with the more traditional ECG technology. Moreover, the affective psychological condition of the participants (anxiety and mood levels) may influence the psychophysiological responses recorded during the experimental tests.

Machine Learning for Anxiety Detection Using Biosignals: A Review

Anxiety disorder (AD) is a major mental health illness. However, due to the many symptoms and confounding factors associated with AD, it is difficult to diagnose, and patients remain untreated for a long time. Therefore, researchers have become increasingly interested in non-invasive biosignals, such as electroencephalography (EEG), electrocardiogram (ECG), electrodermal response (EDA), and respiration (RSP). Applying machine learning to these signals enables clinicians to recognize patterns of anxiety and differentiate a sick patient from a healthy one. Further, models with multiple and diverse biosignals have been developed to improve accuracy and convenience. This paper reviews and summarizes studies published from 2012 to 2022 that applied different machine learning algorithms with various biosignals. In doing so, it offers perspectives on the strengths and weaknesses of current developments to guide future advancements in anxiety detection. Specifically, this literature review reveals promising measurement accuracies ranging from 55% to 98% for studies with sample sizes of 10 to 102 participants. On average, studies using only EEG seemed to obtain the best performance, but the most accurate results were obtained with EDA, RSP, and heart rate. Random forest and support vector machines were found to be widely used machine learning methods, and they lead to good results as long as feature selection has been performed. Neural networks are also extensively used and provide good accuracy, with the benefit that no feature selection is needed. This review also comments on the effective combinations of modalities and the success of different models for detecting anxiety.

Human state anxiety classification framework using EEG signals in response to exposure therapy

Human anxiety is a grave mental health concern that needs to be addressed in the appropriate manner in order to develop a healthy society. In this study, an objective human anxiety assessment framework is developed by using physiological signals of electroencephalography (EEG) and recorded in response to exposure therapy. The EEG signals of twenty-three subjects from an existing database called "A Database for Anxious States which is based on a Psychological Stimulation (DASPS)" are used for anxiety quantification into two and four levels. The EEG signals are pre-processed using appropriate noise filtering techniques to remove unwanted ocular and muscular artifacts. Channel selection is performed to select the significantly different electrodes using statistical analysis techniques for binary and four-level classification of human anxiety, respectively. Features are extracted from the data of selected EEG channels in the frequency domain. Frequency band selection is applied to select the appropriate combination of EEG frequency bands, which in this study are theta and beta bands. Feature selection is applied to the features of the selected EEG frequency bands. Finally, the selected subset of features from the appropriate frequency bands of the statistically significant EEG channels were classified using multiple machine learning algorithms. An accuracy of 94.90% and 92.74% is attained for two and four-level anxiety classification using a random forest classifier with 9 and 10 features, respectively. The proposed state anxiety classification framework outperforms the existing anxiety detection framework in terms of accuracy with a smaller number of features which reduces the computational complexity of the algorithm.

Diagnostic Features and Potential Applications of PPG Signal in Healthcare: A Systematic Review

Recent research indicates that Photoplethysmography (PPG) signals carry more information than oxygen saturation level (SpO2) and can be utilized for affordable, fast, and noninvasive healthcare applications. All these encourage the researchers to estimate its feasibility as an alternative to many expansive, time-wasting, and invasive methods. This systematic review discusses the current literature on diagnostic features of PPG signal and their applications that might present a potential venue to be adapted into many health and fitness aspects of human life. The research methodology is based on the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines 2020. To this aim, papers from 1981 to date are reviewed and categorized in terms of the healthcare application domain. Along with consolidated research areas, recent topics that are growing in popularity are also discovered. We also highlight the potential impact of using PPG signals on an individual's quality of life and public health. The state-of-the-art studies suggest that in the years to come PPG wearables will become pervasive in many fields of medical practices, and the main domains include cardiology, respiratory, neurology, and fitness. Main operation challenges, including performance and robustness obstacles, are identified.

Automated Affective Computing Based on Bio-Signals Analysis and Deep Learning Approach

Extensive possibilities of applications have rendered emotion recognition ineluctable and challenging in the fields of computer science as well as in human-machine interaction and affective computing. Fields that, in turn, are increasingly requiring real-time applications or interactions in everyday life scenarios. However, while extremely desirable, an accurate and automated emotion classification approach remains a challenging issue. To this end, this study presents an automated emotion recognition model based on easily accessible physiological signals and deep learning (DL) approaches. As a DL algorithm, a Feedforward Neural Network was employed in this study. The network outcome was further compared with canonical machine learning algorithms such as random forest (RF). The developed DL model relied on the combined use of wearables and contactless technologies, such as thermal infrared imaging. Such a model is able to classify the emotional state into four classes, derived from the linear combination of valence and arousal (referring to the circumplex model of affect’s four-quadrant structure) with an overall accuracy of 70% outperforming the 66% accuracy reached by the RF model. Considering the ecological and agile nature of the technique used the proposed model could lead to innovative applications in the affective computing field.

Trends in Daily Heart Rate Variability Fluctuations Are Associated with Longitudinal Changes in Stress and Somatisation in Police Officers

The emergence of wearable sensors that allow for unobtrusive monitoring of physiological and behavioural patterns introduces new opportunities to study the impact of stress in a real-world context. This study explores to what extent within-subject trends in daily Heart Rate Variability (HRV) and daily HRV fluctuations are associated with longitudinal changes in stress, depression, anxiety, and somatisation. Nine Dutch police officers collected daily nocturnal HRV data using an Oura ring during 15–55 weeks. Participants filled in the Four-Dimensional Symptoms Questionnaire every 5 weeks. A sample of 47 five-week observations was collected and analysed using multiple regression. After controlling for trends in total sleep time, moderate-to-vigorous physical activity and alcohol use, an increasing trend in the seven-day rolling standard deviation of the HRV (HRVsd) was associated with increases in stress and somatisation over 5 weeks. Furthermore, an increasing HRV trend buffered against the association between HRVsd trend and somatisation change, undoing this association when it was combined with increasing HRV. Depression and anxiety could not be related to trends in HRV or HRVsd, which was related to observed floor effects. These results show that monitoring trends in daily HRV via wearables holds promise for automated stress monitoring and providing personalised feedback.

Assessment of Non-Invasive Blood Pressure Prediction from PPG and rPPG Signals Using Deep Learning

Exploiting photoplethysmography signals (PPG) for non-invasive blood pressure (BP) measurement is interesting for various reasons. First, PPG can easily be measured using fingerclip sensors. Second, camera based approaches allow to derive remote PPG (rPPG) signals similar to PPG and therefore provide the opportunity for non-invasive measurements of BP. Various methods relying on machine learning techniques have recently been published. Performances are often reported as the mean average error (MAE) on the data which is problematic. This work aims to analyze the PPG- and rPPG based BP prediction error with respect to the underlying data distribution. First, we train established neural network (NN) architectures and derive an appropriate parameterization of input segments drawn from continuous PPG signals. Second, we use this parameterization to train NNs with a larger PPG dataset and carry out a systematic evaluation of the predicted blood pressure. The analysis revealed a strong systematic increase of the prediction error towards less frequent BP values across NN architectures. Moreover, we tested different train/test set split configurations which underpin the importance of a careful subject-aware dataset assignment to prevent overly optimistic results. Third, we use transfer learning to train the NNs for rPPG based BP prediction. The resulting performances are similar to the PPG-only case. Finally, we apply different personalization techniques and retrain our NNs with subject-specific data for both the PPG-only and rPPG case. Whilst the particular technique is less important, personalization reduces the prediction errors significantly.