A comprehensive review and analysis of supervised-learning and soft computing techniques for stress diagnosis in humans

Causal Effects of High Stress Assessed Via Interviews on Mental and Physical Health: Toward Computer Agent-Driven Stress Assessment

OBJECTIVES

This study investigated the causal effect of high stress assessment via an interview on the mental and physical health of workers 1 month later.

METHODS

Stress assessment interviews and feedback were conducted with 50 Japanese workers. In addition to the interviewer, two occupational health professionals assessed participants' stress based on recordings. The average treatment effect was estimated by propensity score matching.

RESULTS

High stress, according to the interview-based assessment, had a significant negative causal effect on self-reported well-being 1 month later (95% confidence interval: -3.02, -1.10). In addition, no effect of high stress on stress load, mental and physical symptoms, or burnout was observed.

CONCLUSIONS

This study provides important insights into the prognosis of individuals who were assessed through interviews to have high stress. The findings are expected to help automate stress assessments using computer agents.

Catatonia in patients with dementia: A descriptive study of clinical profiles and treatment response

BACKGROUND

Catatonia is a highly prevalent syndrome in patients presenting with major neurocognitive disorders (dementia). In this study, we aim to provide a comprehensive description of the clinical and therapeutic aspects of catatonia in patients with dementia.

METHOD

This descriptive study, conducted between September 2015 and June 2022, collected data from 25 patients diagnosed with dementia, out of 143 patients treated for catatonia in our specialized psychiatry department. We collected sociodemographic, clinical and treatment data for each patient.

RESULTS

Dementia patients constituted 17% of the catatonic cases. Predominantly female, the cohort had a mean age of 65. Diagnoses included Alzheimer's (4 patients, 17%) and Parkinson's (1 patient, 4%) diseases, Lewy body dementia (5 patients, 21%), vascular dementia (4 patients, 17%) and frontotemporal lobar degeneration (10 patients, 41%). The mean Bush-Francis Catatonia Rating Scale score upon admission was 20/69. Overall, complete remission of catatonia was achieved in 75% of patients (n=18), with only 13% (n=3) responding to lorazepam alone, while others required additional interventions such as electroconvulsive therapy (ECT) and/or amantadine. Vascular dementia was predominantly observed in cases resistant to treatment.

CONCLUSION

The findings indicate a frequent co-occurrence of catatonia and dementia, highlighting treatability yet suggesting a potential for resistance to lorazepam, which varies by dementia diagnosis. Investigating the mechanisms underlying this resistance and the variability in treatment response is crucial for developing more precise therapeutic strategies.

A fluorescent sensor array based on antibiotic-stabilized metal nanoclusters for the multiplex detection of bacteria

To address the need for facile, rapid detection of pathogens in water supplies, a fluorescent sensing array platform based on antibiotic-stabilized metal nanoclusters was developed for the multiplex detection of pathogens. Using five common antibiotics, eight different nanoclusters (NCs) were synthesized including ampicillin stabilized copper NCs, cefepime stabilized gold and copper NCs, kanamycin stabilized gold and copper NCs, lysozyme stabilized gold NCs, and vancomycin stabilized gold/silver and copper NCs. Based on the different interaction of each NC with the bacteria strains, unique patterns were generated. Various machine learning algorithms were employed for pattern discernment, among which the artificial neural networks proved to have the highest performance, with an accuracy of 100%. The developed prediction model performed well on an independent test dataset and on real samples gathered from drinking water, tap water and the Anzali Lagoon water, with prediction accuracy of 96.88% and 95.14%, respectively. This work demonstrates how generic antibiotics can be implemented for NC synthesis and used as recognition elements for pathogen detection. Furthermore, it displays how merging machine learning techniques can elevate sensitivity of analytical devices.

Effects of trace element dietary supplements on voice parameters and some physiological and psychological parameters related to stress

Trace elements, often used as dietary supplements, are widely accessible without prescription at pharmacies. Pronutri has pioneered Nutripuncture®, a methodology that utilizes orally consumed trace elements to elicit a physiological response akin to that of acupuncture. Pronutri has empirically observed that the user's voice becomes deeper following an exclusive ingestion procedure. Given that alterations in vocal characteristics are often linked to stress, the Pronutri researchers postulated that the pills have the capacity to promptly alleviate stress upon ingestion. Nevertheless, there is a lack of scientific substantiation about the impact of these supplements on voice (or stress) indicators. The aim of this research was to determine whether there is a consistent impact of trace element ingestion on vocal characteristics, namely the fundamental frequency of the voice, as well as other physiological and psychological stress measurements. In order to achieve this objective, we have devised a unique methodology to examine this hypothesis. This involves conducting a monocentric crossover, randomized, triple-blind, placebo-controlled trial with a sample size of 43 healthy individuals. This study demonstrates that compared to placebo tablets, consuming 10 metal traces containing tablets at once is enough to cause noticeable changes in the vocal spectrum in the direction of an improvement of the voice timbre "richness", and a decrease in the occurrence of spontaneous electrodermal activity, suggesting a stress reduction. However, there were no significant changes observed in the other parameters that were tested. These parameters include vocal measures such as voice frequency F0, standard deviation from this frequency, jitter, and shimmer. Additionally, physiological measures such as respiratory rate, oxygenation and heart rate variability parameters, as well as psychological measures such as self-assessment analogic scales of anxiety, stress, muscle tension, and nervous tension, did not show any significant changes. Ultimately, our research revealed that the ingestion of 10 trace elements pills may promptly elicit a targeted impact on both vocal spectrum and electrodermal activity. Despite the limited impact, these findings warrant more research to explore the long-term effects of trace elements on voice and stress reduction.

Detection of arousal and valence from facial expressions and physiological responses evoked by different types of stressors

Automatically detecting mental state such as stress from video images of the face could support evaluating stress responses in applicants for high risk jobs or contribute to timely stress detection in challenging operational settings (e.g., aircrew, command center operators). Challenges in automatically estimating mental state include the generalization of models across contexts and across participants. We here aim to create robust models by training them using data from different contexts and including physiological features. Fifty-one participants were exposed to different types of stressors (cognitive, social evaluative and startle) and baseline variants of the stressors. Video, electrocardiogram (ECG), electrodermal activity (EDA) and self-reports (arousal and valence) were recorded. Logistic regression models aimed to classify between high and low arousal and valence across participants, where "high" and "low" were defined relative to the center of the rating scale. Accuracy scores of different models were evaluated: models trained and tested within a specific context (either a baseline or stressor variant of a task), intermediate context (baseline and stressor variant of a task), or general context (all conditions together). Furthermore, for these different model variants, only the video data was included, only the physiological data, or both video and physiological data. We found that all (video, physiological and video-physio) models could successfully distinguish between high- and low-rated arousal and valence, though performance tended to be better for (1) arousal than valence, (2) specific context than intermediate and general contexts, (3) video-physio data than video or physiological data alone. Automatic feature selection resulted in inclusion of 3-20 features, where the models based on video-physio data usually included features from video, ECG and EDA. Still, performance of video-only models approached the performance of video-physio models. Arousal and valence ratings by three experienced human observers scores based on part of the video data did not match with self-reports. In sum, we showed that it is possible to automatically monitor arousal and valence even in relatively general contexts and better than humans can (in the given circumstances), and that non-contact video images of faces capture an important part of the information, which has practical advantages.

Old dog, new tricks? Exploring the potential functionalities of ChatGPT in supporting educational methods in social psychiatry

BACKGROUND

Artificial Intelligence is ever-expanding and large-language models are increasingly shaping teaching and learning experiences. ChatGPT is a prominent recent example of this technology and has generated much debate around the benefits and disadvantages of chatbots in educational domains.

AIM

This study seeks to demonstrate the possible use-cases of ChatGPT in supporting educational methods specific to social psychiatry.

METHODS

Through interactions with ChatGPT 3.5, we asked this technology to list six ways in which it could aid social psychiatry teaching. Subsequently, we requested that ChatGPT perform one of the tasks it identified in its responses.

FINDINGS

ChatGPT highlighted several roles it could fulfil in educational settings, including as an information provider, a tool for debates and discussions, a facilitator of self-directed learning and a content-creator for course materials. For the latter scenario, based on another prompt, ChatGPT generated a hypothetical case vignette for a topic relevant to social psychiatry.

CONCLUSIONS

Based on our experiences, ChatGPT can be an effective teaching tool, offering opportunities for active and case-based learning for students and instructors in social psychiatry. However, in their current form, chatbots have several limitations that must be considered, including misinformation and inherent biases, although these may only be temporary in nature as these technologies continue to advance. Accordingly, we argue that large-language models can support social psychiatry education with appropriate caution and encourage educators to become attuned to their potential through further detailed research in this area.

Machine learning model for aberrant driving behaviour prediction using heart rate variability: a pilot study involving highway bus drivers

Objectives. Current approaches via physiological features detecting aberrant driving behaviour (ADB), including speeding, abrupt steering, hard braking and aggressive acceleration, are developing. This study proposes using machine learning approaches incorporating heart rate variability (HRV) parameters to predict ADB occurrence. Methods. Naturalistic driving data of 10 highway bus drivers in Taiwan from their daily routes were collected for 4 consecutive days. Their driving behaviours and physiological data during a driving task were determined using a navigation mobile application and heart rate watch. Participants' self-reported data on sleep, driving-related experience, open-source data on weather and the traffic congestion level were obtained. Five machine learning models - logistic regression, random forest, naive Bayes, support vector machine and gated recurrent unit (GRU) - were employed to predict ADBs. Results. Most drivers with ADB had low sleep efficiency (≤80%), with significantly higher scores in driver behaviour questionnaire subcategories of lapses and errors and in the Karolinska sleepiness scale than those without ADBs. Moreover, HRV parameters were significantly different between baseline and pre-ADB event measurements. GRU had the highest accuracy (81.16-84.22%). Conclusions. Sleep deficit may be related to the increased fatigue level and ADB occurrence predicted from HRV-based models among bus drivers.

Reviewing methods of deep learning for diagnosing COVID-19, its variants and synergistic medicine combinations

The COVID-19 pandemic has necessitated the development of reliable diagnostic methods for accurately detecting the novel coronavirus and its variants. Deep learning (DL) techniques have shown promising potential as screening tools for COVID-19 detection. In this study, we explore the realistic development of DL-driven COVID-19 detection methods and focus on the fully automatic framework using available resources, which can effectively investigate various coronavirus variants through modalities. We conducted an exploration and comparison of several diagnostic techniques that are widely used and globally validated for the detection of COVID-19. Furthermore, we explore review-based studies that provide detailed information on synergistic medicine combinations for the treatment of COVID-19. We recommend DL methods that effectively reduce time, cost, and complexity, providing valuable guidance for utilizing available synergistic combinations in clinical and research settings. This study also highlights the implication of innovative diagnostic technical and instrumental strategies, exploring public datasets, and investigating synergistic medicines using optimised DL rules. By summarizing these findings, we aim to assist future researchers in their endeavours by providing a comprehensive overview of the implication of DL techniques in COVID-19 detection and treatment. Integrating DL methods with various diagnostic approaches holds great promise in improving the accuracy and efficiency of COVID-19 diagnostics, thus contributing to effective control and management of the ongoing pandemic.

Classification of Mental Stress Levels using EEG Connectivity and Convolutional Neural Networks

Classifying mental stress is important as it helps in identifying the type and severity of stress, which can inform the most appropriate treatment or intervention. In this study, we propose utilizing electroencephalography (EEG) signals with convolutional neural networks (CNNs) to classify four mental states: rest, control-alert, stress and stress mitigation. The mental stress state was induced using Stroop color word test (SCWT) with time constrains and was then mitigated using 16 Hz Binaural beat stimulation (BBs). We quantified the four mental states using the reaction time (RT) to stimuli, accuracy of target detection, subjective score, and functional connectivity images of EEG estimated by Phase Locking Value (PLV). Our results show that, the SCWT reduced the accuracy of target detection by 70% with (F= 24.56, p = .00001), and the BBs improved the accuracy by 28% (F= 4.54, p = .00470). The functional connectivity network showed different patterns between the frontal/occipital and parietal regions, under the four mental states. The proposed CNNs with PLV images differentiated between the four mental states with highest classification performance at beta frequency band with 80.95% accuracy, 80.36% sensitivity, 94.75% specificity, 83.63% precision and 81.96% F-score. The overall results suggest that 16 Hz BBs can be used as an effective method to mitigate stress and the proposed CNNs with EEG-PLV images as a promising method for classifying different mental states.

Deep learning-based assessment of knee septic arthritis using transformer features in sonographic modalities

PURPOSE

Septic arthritis is an infectious disease. Conventionally, the diagnosis of septic arthritis can only be based on the identification of causal pathogens taken from synovial fluid, synovium or blood samples. However, the cultures require several days for the isolation of pathogens. A rapid assessment performed through computer-aided diagnosis (CAD) would bring timely treatment.

METHODS

A total of 214 non-septic arthritis and 64 septic arthritis images generated by gray-scale (GS) and Power Doppler (PD) ultrasound modalities were collected for the experiment. A deep learning-based vision transformer (ViT) with pre-trained parameters were used for image feature extraction. The extracted features were then combined in machine learning classifiers with ten-fold cross validation in order to evaluate the abilities of septic arthritis classification.

RESULTS

Using a support vector machine, GS and PD features can achieve an accuracy rate of 86% and 91%, with the area under the receiver operating characteristic curves (AUCs) being 0.90 and 0.92, respectively. The best accuracy (92%) and best AUC (0.92) was obtained by combining both feature sets.

CONCLUSIONS

This is the first CAD system based on a deep learning approach for the diagnosis of septic arthritis as seen on knee ultrasound images. Using pre-trained ViT, both the accuracy and computation costs improved more than they had through convolutional neural networks. Additionally, automatically combining GS and PD generates a higher accuracy to better assist the physician's observations, thus providing a timely evaluation of septic arthritis.

Applications of artificial intelligence-machine learning for detection of stress: a critical overview

Psychological distress is a major contributor to human physiology and pathophysiology, and it has been linked to several conditions, such as auto-immune diseases, metabolic syndrome, sleep disorders, and suicidal thoughts and inclination. Therefore, early detection and management of chronic stress is crucial for the prevention of several diseases. Artificial intelligence (AI) and Machine Learning (ML) have promoted a paradigm shift in several areas of biomedicine including diagnosis, monitoring, and prognosis of disease. Here, our review aims to present some of the AI and ML applications for solving biomedical issues related to psychological stress. We provide several lines of evidence from previous studies highlighting that AI and ML have been able to predict stress and detect the brain normal states vs. abnormal states (notably, in post-traumatic stress disorder (PTSD)) with accuracy around 90%. Of note, AI/ML-driven technology applied to identify ubiquitously present stress exposure may not reach its full potential, unless future analytics focus on detecting prolonged distress through such technology instead of merely assessing stress exposure. Moving forward, we propose that a new subcategory of AI methods called Swarm Intelligence (SI) can be used towards detecting stress and PTSD. SI involves ensemble learning techniques to efficiently solve a complex problem, such as stress detection, and it offers particular strength in clinical settings, such as privacy preservation. We posit that AI and ML approaches will be beneficial for the medical and patient community when applied to predict and assess stress levels. Last, we encourage additional research to bring AI and ML into the standard clinical practice for diagnostics in the not-too-distant future.

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.

Early prediction of hemodialysis complications employing ensemble techniques

Background and objectives

Hemodialysis complications remain a critical threat among dialysis patients. They result in sudden termination of the session which impacts the efficiency of dialysis. As intra-dialytic complications are the result of the interplay of multiple factors, artificial intelligence can aid in their early prediction. This research aims to compare different machine learning tools for the early prediction of the most frequent hemodialysis complications with high performance, using the fewest predictors for easier practical implementation.

Methods

Fifty different variables were recorded during 6000 hemodialysis sessions performed in a regional dialysis unit in Egypt. The filter technique was used to extract the most relevant features. Then, five individual classifiers and three ensemble approaches were implemented to predict the occurrence of intra-dialytic complications. Different subsets of 25, 12 and 6 from the 50 collected features were tested.

Results

Random forest yielded the highest accuracy of 98% with the least training time using 12 features in a balanced dataset, while the gradient boosting allowed obtaining the highest F1-score of 94%, 92%, and 78% in the prediction of hypotension, hypertension, and dyspnea, respectively, in imbalanced datasets.

Conclusion

Applying different machine learning algorithms to big datasets can improve accuracy, reduce training time and model complexity allowing simple implementation in clinical practice. Our models can help nephrologists predict and possibly prevent dialysis complications.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12938-022-01044-0.

A Plain Bayesian Algorithm-Based Method for Predicting the Mental Health Status and Biomedical Diagnosis of University Students

The purpose of this study was to assess e-learning during Corona epidemic regarding advantages, limitations, and their recommendations for managing learning during the epidemic. Based on a case study, this study used qualitative research. Sixteen students from King Saud University's College of Education were invited to take part. These students receive their online lectures via the "Zoom" application. A 20-minute WhatsApp one-on-one semiorganized interview was likewise utilized. To guarantee the reliability, iCloud was utilized to record gatherings and meetings for direct record (adaptability, constancy, confirmability, and validity). Results were presented in three themes: advantages of employing distance education, limitations of usages, and recommendations for improvements. Analyzing the feedbacks collected from students by the four interviewers, important characteristics of distance education emerged. They were student-centered learning, which included: comfortable, self-directed learning, asynchronous learning, and flexibility. The most common limitations associated with distance education, in general, included inefficiency, that is, lack of student feedback, and lack of attentiveness. As for recommendations for improvements the most obvious characteristics that became evident in students' responses were teaching and assessment and quality enhancement.

Real-time mental stress detection using multimodality expressions with a deep learning framework

Mental stress is becoming increasingly widespread and gradually severe in modern society, threatening people’s physical and mental health. To avoid the adverse effects of stress on people, it is imperative to detect stress in time. Many studies have demonstrated the effectiveness of using objective indicators to detect stress. Over the past few years, a growing number of researchers have been trying to use deep learning technology to detect stress. However, these works usually use single-modality for stress detection and rarely combine stress-related information from multimodality. In this paper, a real-time deep learning framework is proposed to fuse ECG, voice, and facial expressions for acute stress detection. The framework extracts the stress-related information of the corresponding input through ResNet50 and I3D with the temporal attention module (TAM), where TAM can highlight the distinguishing temporal representation for facial expressions about stress. The matrix eigenvector-based approach is then used to fuse the multimodality information about stress. To validate the effectiveness of the framework, a well-established psychological experiment, the Montreal imaging stress task (MIST), was applied in this work. We collected multimodality data from 20 participants during MIST. The results demonstrate that the framework can combine stress-related information from multimodality to achieve 85.1% accuracy in distinguishing acute stress. It can serve as a tool for computer-aided stress detection.

Application of Machine Learning Techniques to Help in the Feature Selection Related to Hospital Readmissions of Suicidal Behavior

Suicide was the main source of death from external causes in Spain in 2020, with 3,941 cases. The importance of identifying those mental disorders that influenced hospital readmissions will allow us to manage the health care of suicidal behavior. The feature selection of each hospital in this region was carried out by applying Machine learning (ML) and traditional statistical methods. The results of the characteristics that best explain the readmissions of each hospital after assessment by the psychiatry specialist are presented. Adjustment disorder, alcohol abuse, depressive syndrome, personality disorder, and dysthymic disorder were selected for this region. The most influential methods or characteristics associated with suicide were benzodiazepine poisoning, suicidal ideation, medication poisoning, antipsychotic poisoning, and suicide and/or self-harm by jumping. Suicidal behavior is a concern in our society, so the results are relevant for hospital management and decision-making for its prevention.

Linc00261 Inhibited High-Grade Serous Ovarian Cancer Progression through miR-552-ATG10-EMT Axis

In recent years, long non-coding RNAs (lncRNAs) play an important role in a multitude of pathways across species; however, their functions are still unknown. In this study, we demonstrate that Linc00261 is downregulation in high-grade serous ovarian cancer (HGSOC) and can inhibit cell proliferation and migration of high-grade serous ovarian cancer cells. We further validate the targeting interactions among Linc00261, miR-552, and ATG10. Interestingly, they all play important roles for regulating epithelial-mesenchymal transition (EMT) progression. Collectively, these findings suggest that Linc00261, a mediator of EMT progression, can target oncogenic miR-552, elevating ATG10 expression, to prevent high-grade serous ovarian cancer tumorigenesis and may serve as a potential novel therapeutic target.

Autoencoded deep features for semi-automatic, weakly supervised physiological signal labelling

BACKGROUND AND AIMS

Machine Learning is transforming data processing in medical research and clinical practice. Missing data labels are a common limitation to training Machine Learning models. To overcome missing labels in a large dataset of microneurography recordings, a novel autoencoder based semi-supervised, iterative group-labelling methodology was developed.

METHODS

Autoencoders were systematically optimised to extract features from a dataset of 478621 signal excerpts from human microneurography recordings. Selected features were clusters with k-means and randomly selected representations of the corresponding original signals labelled as valid or non-valid muscle sympathetic nerve activity (MSNA) bursts in an iterative, purifying procedure by an expert rater. A deep neural network was trained based on the fully labelled dataset.

RESULTS

Three autoencoders, two based on fully connected neural networks and one based on convolutional neural network, were chosen for feature learning. Iterative clustering followed by labelling of complete clusters resulted in all 478621 signal peak excerpts being labelled as valid or non-valid within 13 iterations. Neural networks trained with the labelled dataset achieved, in a cross validation step with a testing dataset not included in training, on average 93.13% accuracy and 91% area under the receiver operating curve (AUC ROC).

DISCUSSION

The described labelling procedure enabled efficient labelling of a large dataset of physiological signal based on expert ratings. The procedure based on autoencoders may be broadly applicable to a wide range of datasets without labels that require expert input and may be utilised for Machine Learning applications if weak-labels were available.

Online Mindfulness Experience for Emotional Support to Healthcare staff in times of Covid-19

During the first confinement in Spain, between the months of March to June 2020, Information and Communication Technologies strategies were implemented in order to support health workers in the Wellbeing of Mental Health. Faced with so much uncertainty about the pandemic, an Online Mindfulness course. The objective of the course was to support healthcare professionals in Castilla y León in managing stress, anxiety and other emotional disturbances generated by coping with a situation as uncertain and unexpected as a pandemic, in order to manage emotions and thoughts that can lead to suicidal ideation. The motivations for the demand, reasons or motivations in which the health professionals of Castilla y León decided to participate in the mindfulness course in the first wave of Covid-19 in Spain are described. The descriptive and inferential statistical analysis of the customer satisfaction survey applied at the end of the mindfulness course, to the health professionals who participated in a satisfaction survey (CSQ-8: Client Satisfaction Questionnaire). Professional were asked to complete a survey based on (CSQ-8: Client Satisfaction Questionnaire) whose Cronbach's alpha = 0.917 is why the instrument used with N = 130 participants has high reliability. The 66% answered with a highly satisfied that they would return to the mindfulness online course. The 93% of the people who answered the satisfaction survey were women, of which they are professionals in the nursing area, with a participation of around 62%. In relation to the online system used in the Mindfulness intervention, 74% expressed that they fully agreed that it has been easy to use the online system for the mindfulness intervention. Health Professionals responded with 58% high satisfaction and 36% satisfaction, making a total of 94% on the help received in the online mindfulness courses to solve their problems. There is no difference between the age groups of the professionals who have preferred the Mindfulness online course (p = 0.672).

K-means panning - Developing a new standard in automated MSNA signal recognition with a weakly supervised learning approach

BACKGROUND

Accessibility of labelled datasets is often a key limitation for the application of Machine Learning in clinical research. A novel semi-automated weak-labelling approach based on unsupervised clustering was developed to classify a large dataset of microneurography signals and subsequently used to train a Neural Network to reproduce the labelling process.

METHODS

Clusters of microneurography signals were created with k-means and then labelled in terms of the validity of the signals contained in each cluster. Only purely positive or negative clusters were labelled, whereas clusters with mixed content were passed on to the next iteration of the algorithm to undergo another cycle of unsupervised clustering and labelling of the clusters. After several iterations of this process, only pure labelled clusters remained which were used to train a Deep Neural Network.

RESULTS

Overall, 334,548 individual signal peaks form the integrated data were extracted and more than 99.99% of the data was labelled in six iterations of this novel application of weak labelling with the help of a domain expert. A Deep Neural Network trained based on this dataset achieved consistent accuracies above 95%.

DISCUSSION

Data extraction and the novel iterative approach of labelling unsupervised clusters enabled creation of a large, labelled dataset combining unsupervised learning and expert ratings of signal-peaks on cluster basis in a time effective manner. Further research is needed to validate the methodology and employ it on other types of physiologic data for which it may enable efficient generation of large labelled datasets.

An Evaluation of Speech-Based Recognition of Emotional and Physiological Markers of Stress

Life in modern societies is fast-paced and full of stress-inducing demands. The development of stress monitoring methods is a growing area of research due to the personal and economic advantages that timely detection provides. Studies have shown that speech-based features can be utilised to robustly predict several physiological markers of stress, including emotional state, continuous heart rate, and the stress hormone, cortisol. In this contribution, we extend previous works by the authors, utilising three German language corpora including more than 100 subjects undergoing a Trier Social Stress Test protocol. We present cross-corpus and transfer learning results which explore the efficacy of the speech signal to predict three physiological markers of stress—sequentially measured saliva-based cortisol, continuous heart rate as beats per minute (BPM), and continuous respiration. For this, we extract several features from audio as well as video and apply various machine learning architectures, including a temporal context-based Long Short-Term Memory Recurrent Neural Network (LSTM-RNN). For the task of predicting cortisol levels from speech, deep learning improves on results obtained by conventional support vector regression—yielding a Spearman correlation coefficient (ρ) of 0.770 and 0.698 for cortisol measurements taken 10 and 20 min after the stress period for the two corpora applicable—showing that audio features alone are sufficient for predicting cortisol, with audiovisual fusion to an extent improving such results. We also obtain a Root Mean Square Error (RMSE) of 38 and 22 BPM for continuous heart rate prediction on the two corpora where this information is available, and a normalised RMSE (NRMSE) of 0.120 for respiration prediction (−10: 10). Both of these continuous physiological signals show to be highly effective markers of stress (based on cortisol grouping analysis), both when available as ground truth and when predicted using speech. This contribution opens up new avenues for future exploration of these signals as proxies for stress in naturalistic settings.

Machine Learning in Medical Emergencies: a Systematic Review and Analysis

Despite the increasing demand for artificial intelligence research in medicine, the functionalities of his methods in health emergency remain unclear. Therefore, the authors have conducted this systematic review and a global overview study which aims to identify, analyse, and evaluate the research available on different platforms, and its implementations in healthcare emergencies. The methodology applied for the identification and selection of the scientific studies and the different applications consist of two methods. On the one hand, the PRISMA methodology was carried out in Google Scholar, IEEE Xplore, PubMed ScienceDirect, and Scopus. On the other hand, a review of commercial applications found in the best-known commercial platforms (Android and iOS). A total of 20 studies were included in this review. Most of the included studies were of clinical decisions (n = 4, 20%) or medical services or emergency services (n = 4, 20%). Only 2 were focused on m-health (n = 2, 10%). On the other hand, 12 apps were chosen for full testing on different devices. These apps dealt with pre-hospital medical care (n = 3, 25%) or clinical decision support (n = 3, 25%). In total, half of these apps are based on machine learning based on natural language processing. Machine learning is increasingly applicable to healthcare and offers solutions to improve the efficiency and quality of healthcare. With the emergence of mobile health devices and applications that can use data and assess a patient's real-time health, machine learning is a growing trend in the healthcare industry.