A new movement artifact detector for photoplethysmographic signals

A Robust End-to-End IoT System for Supporting Workers in Mining Industries

The adoption of the Internet of Things (IoT) in the mining industry can dramatically enhance the safety of workers while simultaneously decreasing monitoring costs. By implementing an IoT solution consisting of a number of interconnected smart devices and sensors, mining industries can improve response times during emergencies and also reduce the number of accidents, resulting in an overall improvement of the social image of mines. Thus, in this paper, a robust end-to-end IoT system for supporting workers in harsh environments such as in mining industries is presented. The full IoT solution includes both edge devices worn by the workers in the field and a remote cloud IoT platform, which is responsible for storing and efficiently sharing the gathered data in accordance with regulations, ethics, and GDPR rules. Extended experiments conducted to validate the IoT components both in the laboratory and in the field proved the effectiveness of the proposed solution in monitoring the real-time status of workers in mines.

AI-Enabled Smart Wristband Providing Real-Time Vital Signs and Stress Monitoring

This work introduces the design, architecture, implementation, and testing of a low-cost and machine-learning-enabled device to be worn on the wrist. The suggested wearable device has been developed for use during emergency incidents of large passenger ship evacuations, and enables the real-time monitoring of the passengers' physiological state, and stress detection. Based on a properly preprocessed PPG signal, the device provides essential biometric data (pulse rate and oxygen saturation level) and an efficient unimodal machine learning pipeline. The stress detecting machine learning pipeline is based on ultra-short-term pulse rate variability, and has been successfully integrated into the microcontroller of the developed embedded device. As a result, the presented smart wristband is able to provide real-time stress detection. The stress detection system has been trained with the use of the publicly available WESAD dataset, and its performance has been tested through a two-stage process. Initially, evaluation of the lightweight machine learning pipeline on a previously unseen subset of the WESAD dataset was performed, reaching an accuracy score equal to 91%. Subsequently, external validation was conducted, through a dedicated laboratory study of 15 volunteers subjected to well-acknowledged cognitive stressors while wearing the smart wristband, which yielded an accuracy score equal to 76%.

A quality metric for heart rate variability from photoplethysmogram sensor data

Heart rate variability (HRV) measures the regularity between consecutive heartbeats driven by the balance between the sympathetic and parasympathetic branches of the autonomous nervous system. Wearable devices embedding photoplethysmogram (PPG) technology can be used to derive HRV, creating many opportunities for remote monitoring of this physiological parameter. However, uncontrolled conditions met in daily life pose several challenges related to disturbances that can deteriorate the PPG signal, making the calculation of HRV metrics untrustworthy and not reliable. In this work, we propose a HRV quality metric that is directly related to the HRV accuracy and can be used to distinguish between accurate and inaccurate HRV values. A parametric supervised approach estimates HRV accuracy using a model whose inputs are features extracted from the PPG signal and the output is the HRV error between HRV metrics obtained from the PPG and the ECG collected during an experimental protocol involving several activities. The estimated HRV accuracy of the model is used as an indication of the HRV quality.

Automatic unsupervised respiratory analysis of infant respiratory inductance plethysmography signals

Infants are at risk for potentially life-threatening postoperative apnea (POA). We developed an Automated Unsupervised Respiratory Event Analysis (AUREA) to classify breathing patterns obtained with dual belt respiratory inductance plethysmography and a reference using Expectation Maximization (EM). This work describes AUREA and evaluates its performance. AUREA computes six metrics and inputs them into a series of four binary k-means classifiers. Breathing patterns were characterized by normalized variance, nonperiodic power, instantaneous frequency and phase. Signals were classified sample by sample into one of 5 patterns: pause (PAU), movement (MVT), synchronous (SYB) and asynchronous (ASB) breathing, and unknown (UNK). MVT and UNK were combined as UNKNOWN. Twenty-one preprocessed records obtained from infants at risk for POA were analyzed. Performance was evaluated with a confusion matrix, overall accuracy, and pattern specific precision, recall, and F-score. Segments of identical patterns were evaluated for fragmentation and pattern matching with the EM reference. PAU exhibited very low normalized variance. MVT had high normalized nonperiodic power and low frequency. SYB and ASB had a median frequency of respectively, 0.76Hz and 0.71Hz, and a mode for phase of 4^o and 100^o. Overall accuracy was 0.80. AUREA confused patterns most often with UNKNOWN (25.5%). The pattern specific F-score was highest for SYB (0.88) and lowest for PAU (0.60). PAU had high precision (0.78) and low recall (0.49). Fragmentation was evident in pattern events <2s. In 75% of the EM pattern events >2s, 50% of the samples classified by AUREA had identical patterns. Frequency and phase for SYB and ASB were consistent with published values for synchronous and asynchronous breathing in infants. The low normalized variance in PAU, was consistent with published scoring rules for pediatric apnea. These findings support the use of AUREA to classify breathing patterns and warrant a future evaluation of clinically relevant respiratory events.

Assessing the Quality of Heart Rate Variability Estimated from Wrist and Finger PPG: A Novel Approach Based on Cross-Mapping Method

The non-invasiveness of photoplethysmographic (PPG) acquisition systems, together with their cost-effectiveness and easiness of connection with IoT technologies, is opening up to the possibility of their widespread use. For this reason, the study of the reliability of PPG and pulse rate variability (PRV) signal quality has become of great scientific, technological, and commercial interest. In this field, sensor location has been demonstrated to play a crucial role. The goal of this study was to investigate PPG and PRV signal quality acquired from two body locations: finger and wrist. We simultaneously acquired the PPG and electrocardiographic (ECG) signals from sixteen healthy subjects (aged 28.5 ± 3.5, seven females) who followed an experimental protocol of affective stimulation through visual stimuli. Statistical tests demonstrated that PPG signals acquired from the wrist and the finger presented different signal quality indexes (kurtosis and Shannon entropy), with higher values for the wrist-PPG. Then we propose to apply the cross-mapping (CM) approach as a new method to quantify the PRV signal quality. We found that the performance achieved using the two sites was significantly different in all the experimental sessions (p < 0.01), and the PRV dynamics acquired from the finger were the most similar to heart rate variability (HRV) dynamics.

Cardiorespiratory behavior of preterm infants receiving continuous positive airway pressure and high flow nasal cannula post extubation: randomized crossover study

BACKGROUND

Nasal continuous positive airway pressure (NCPAP) and high flow nasal cannula (HFNC) are modes of non-invasive respiratory support commonly used after extubation in extremely preterm infants. However, the cardiorespiratory physiology of these infants on each mode is unknown.

METHODS

Prospective, randomized crossover study in infants with birth weight ≤1250 g undergoing their first extubation attempt. NCPAP and HFNC were applied randomly for 45 min each, while ribcage and abdominal movements, electrocardiogram, oxygen saturation, and fraction of inspired oxygen (FiO₂) were recorded. Respiratory signals were analyzed using an automated method, and differences between NCPAP and HFNC features and changes in FiO₂ were analyzed.

RESULTS

A total of 30 infants with median [interquartile range] gestational age of 27 weeks [25.7, 27.9] and birth weight of 930 g [780, 1090] were studied. Infants were extubated at 5 days [2, 13] of life with 973 g [880, 1170] and three failed (10%). No differences in cardiorespiratory behavior were noted, except for longer respiratory pauses (9.2 s [5.0, 11.5] vs. 7.3 s [4.6, 9.3]; p = 0.04) and higher FiO₂ levels (p = 0.02) during HFNC compared to NCPAP.

CONCLUSIONS

In extremely preterm infants studied shortly after extubation, the use of HFNC was associated with longer respiratory pauses and higher FiO₂ requirements.

Undersampling and Bagging of Decision Trees in the Analysis of Cardiorespiratory Behavior for the Prediction of Extubation Readiness in Extremely Preterm Infants

Extremely preterm infants often require endotracheal intubation and mechanical ventilation during the first days of life. Due to the detrimental effects of prolonged invasive mechanical ventilation (IMV), clinicians aim to extubate infants as soon as they deem them ready.Unfortunately, existing strategies for prediction of extubation readiness vary across clinicians and institutions, and lead to high reintubation rates. We present an approach using Random Forest classifiers for the analysis of cardiorespiratory variability to predict extubation readiness. We address the issue of data imbalance by employing random undersampling of examples from the majority class before training each Decision Tree in a bag. By incorporating clinical domain knowledge, we further demonstrate that our classifier could have identified 71% of infants who failed extubation, while maintaining a success detection rate of 78%.

An optimal filter for short photoplethysmogram signals

A photoplethysmogram (PPG) contains a wealth of cardiovascular system information, and with the development of wearable technology, it has become the basic technique for evaluating cardiovascular health and detecting diseases. However, due to the varying environments in which wearable devices are used and, consequently, their varying susceptibility to noise interference, effective processing of PPG signals is challenging. Thus, the aim of this study was to determine the optimal filter and filter order to be used for PPG signal processing to make the systolic and diastolic waves more salient in the filtered PPG signal using the skewness quality index. Nine types of filters with 10 different orders were used to filter 219 (2.1s) short PPG signals. The signals were divided into three categories by PPG experts according to their noise levels: excellent, acceptable, or unfit. Results show that the Chebyshev II filter can improve the PPG signal quality more effectively than other types of filters and that the optimal order for the Chebyshev II filter is the 4^th order.

An Algorithm for Real-Time Pulse Waveform Segmentation and Artifact Detection in Photoplethysmograms

Photoplethysmography has been used in a wide range of medical devices for measuring oxygen saturation, cardiac output, assessing autonomic function, and detecting peripheral vascular disease. Artifacts can render the photoplethysmogram (PPG) useless. Thus, algorithms capable of identifying artifacts are critically important. However, the published PPG algorithms are limited in algorithm and study design. Therefore, the authors developed a novel embedded algorithm for real-time pulse waveform (PWF) segmentation and artifact detection based on a contour analysis in the time domain. This paper provides an overview about PWF and artifact classifications, presents the developed PWF analysis, and demonstrates the implementation on a 32-bit ARM core microcontroller. The PWF analysis was validated with data records from 63 subjects acquired in a sleep laboratory, ergometry laboratory, and intensive care unit in equal parts. The output of the algorithm was compared with harmonized experts' annotations of the PPG with a total duration of 31.5 h. The algorithm achieved a beat-to-beat comparison sensitivity of 99.6%, specificity of 90.5%, precision of 98.5%, and accuracy of 98.3%. The interrater agreement expressed as Cohen's kappa coefficient was 0.927 and as F-measure was 0.990. In conclusion, the PWF analysis seems to be a suitable method for PPG signal quality determination, real-time annotation, data compression, and calculation of additional pulse wave metrics such as amplitude, duration, and rise time.

Automated analysis of respiratory behavior for the prediction of apnea in infants following general anesthesia

Infants recovering from general anesthesia are at risk of postoperative apnea (POA), a potentially life threatening event. There is no accurate way to identify which infants will experience POA, and thus all infants with postmenstrual age <; 60 weeks are monitored for apnea in hospital postoperatively. Using a comprehensive, automated analysis of the postoperative breathing patterns, we identified the occurrence of respiratory pauses in 24 infants at age risk for POA. We determined the POA category for each infant by using K-medoids to cluster the duration of the longest respiratory pause. Two clusters were identified, corresponding to APNEA and NO-APNEA, with a threshold of 14.6 s, a value consistent with the clinically accepted threshold of 15 s. K-medoids derived POA labels were used to evaluate the predictive ability of demographic and anesthetic management variables. Weight and the intraoperative doses of atropine, propofol, and opioids discriminated between the APNEA and NO-APNEA groups. A linear Gaussian discriminant analysis classifier provided a very good classification with a probability of detection PD = 0.73 and a probability of false alarm PFA = 0.22. This approach provides a promising tool for the systematic, objective study of infants at risk of POA.

Scoring Tools for the Analysis of Infant Respiratory Inductive Plethysmography Signals

Infants recovering from anesthesia are at risk of life threatening Postoperative Apnea (POA). POA events are rare, and so the study of POA requires the analysis of long cardiorespiratory records. Manual scoring is the preferred method of analysis for these data, but it is limited by low intra- and inter-scorer repeatability. Furthermore, recommended scoring rules do not provide a comprehensive description of the respiratory patterns. This work describes a set of manual scoring tools that address these limitations. These tools include: (i) a set of definitions and scoring rules for 6 mutually exclusive, unique patterns that fully characterize infant respiratory inductive plethysmography (RIP) signals; (ii) RIPScore, a graphical, manual scoring software to apply these rules to infant data; (iii) a library of data segments representing each of the 6 patterns; (iv) a fully automated, interactive formal training protocol to standardize the analysis and establish intra- and inter-scorer repeatability; and (v) a quality control method to monitor scorer ongoing performance over time. To evaluate these tools, three scorers from varied backgrounds were recruited and trained to reach a performance level similar to that of an expert. These scorers used RIPScore to analyze data from infants at risk of POA in two separate, independent instances. Scorers performed with high accuracy and consistency, analyzed data efficiently, had very good intra- and inter-scorer repeatability, and exhibited only minor confusion between patterns. These results indicate that our tools represent an excellent method for the analysis of respiratory patterns in long data records. Although the tools were developed for the study of POA, their use extends to any study of respiratory patterns using RIP (e.g., sleep apnea, extubation readiness). Moreover, by establishing and monitoring scorer repeatability, our tools enable the analysis of large data sets by multiple scorers, which is essential for longitudinal and multicenter studies.