Signal quality and data fusion for false alarm reduction in the intensive care unit

Artificial Intelligence-Enhanced Neurocritical Care for Traumatic Brain Injury : Past, Present and Future

In neurointensive care units (NICUs), particularly in cases involving traumatic brain injury (TBI), swift and accurate decision-making is critical because of rapidly changing patient conditions and the risk of secondary brain injury. The use of artificial intelligence (AI) in NICU can enhance clinical decision support and provide valuable assistance in these complex scenarios. This article aims to provide a comprehensive review of the current status and future prospects of AI utilization in the NICU, along with the challenges that must be overcome to realize this. Presently, the primary application of AI in NICU is outcome prediction through the analysis of preadmission and high-resolution data during admission. Recent applications include augmented neuromonitoring via signal quality control and real-time event prediction. In addition, AI can integrate data gathered from various measures and support minimally invasive neuromonitoring to increase patient safety. However, despite the recent surge in AI adoption within the NICU, the majority of AI applications have been limited to simple classification tasks, thus leaving the true potential of AI largely untapped. Emerging AI technologies, such as generalist medical AI and digital twins, harbor immense potential for enhancing advanced neurocritical care through broader AI applications. If challenges such as acquiring high-quality data and ethical issues are overcome, these new AI technologies can be clinically utilized in the actual NICU environment. Emphasizing the need for continuous research and development to maximize the potential of AI in the NICU, we anticipate that this will further enhance the efficiency and accuracy of TBI treatment within the NICU.

Interdisciplinary collaboration in critical care alarm research: A bibliometric analysis

BACKGROUND

Alarm fatigue in nurses is a major patient safety concern in the intensive care unit. This is caused by exposure to high rates of false and non-actionable alarms. Despite decades of research, the problem persists, leading to stress, burnout, and patient harm resulting from true missed events. While engineering approaches to reduce false alarms have spurred hope, they appear to lack collaboration between nurses and engineers to produce real-world solutions. The aim of this bibliometric analysis was to examine the relevant literature to quantify the level of authorial collaboration between nurses, physicians, and engineers.

METHODS

We conducted a bibliometric analysis of articles on alarm fatigue and false alarm reduction strategies in critical care published between 2010 and 2022. Data were extracted at the article and author level. The percentages of author disciplines per publication were calculated by study design, journal subject area, and other article-level factors.

RESULTS

A total of 155 articles with 583 unique authors were identified. While 31.73 % (n = 185) of the unique authors had a nursing background, publications using an engineering study design (n = 46), e.g., model development, had a very low involvement of nursing authors (mean proportion at 1.09 %). Observational studies (n = 58) and interventional studies (n = 33) had a higher mean involvement of 52.27 % and 47.75 %, respectively. Articles published in nursing journals (n = 32) had the highest mean proportion of nursing authors (80.32 %), while those published in engineering journals (n = 46) had the lowest (9.00 %), with 6 (13.04 %) articles having one or more nurses as co-authors.

CONCLUSION

Minimal involvement of nursing expertise in alarm research utilizing engineering methodologies may be one reason for the lack of successful, real-world solutions to ameliorate alarm fatigue. Fostering a collaborative, interdisciplinary research culture can promote a common publication culture across fields and may yield sustainable implementation of technological solutions in healthcare.

Quantitative analysis of pulse arrival time and PPG morphological features based cuffless blood pressure estimation: a comparative study between diabetic and non-diabetic groups

Pulse arrival time (PAT) and PPG morphological features have attracted much interest in cuffless blood pressure (BP) estimation, but their effects are not clearly understood when vascular characteristics are affected by diseases such as diabetes. This work quantitatively analyzes the effect of diabetic disease on the PAT and PPG morphological features-based BP estimation. We selected 112 diabetic patients and 308 non-diabetic subjects from VitalDB, and extracted 16 features including PAT, PPG morphological features, and heart rate. BP estimation performance was statistically compared between groups using linear regression models with several feature sets, and the relative importance of each feature in the optimal feature set was extracted. As a result, the standard deviation of the error and mean absolute error of PAT-based BP estimation were significantly higher in the diabetic group than in the non-diabetic group (p < 0.01). A feature set containing PAT and PPG morphological features achieved the best performance in both groups. However, the relative importance of each feature for BP estimation differed notably between groups. The results indicate that different features are important depending on the vascular characteristics, which could help to construct different models to accommodate specific diseases.

An annotated ventricular tachycardia (VT) alarm database: Toward a uniform standard for optimizing automated VT identification in hospitalized patients

BACKGROUND

False ventricular tachycardia (VT) alarms are common during in-hospital electrocardiographic (ECG) monitoring. Prior research shows that the majority of false VT can be attributed to algorithm deficiencies.

PURPOSE

The purpose of this study was: (1) to describe the creation of a VT database annotated by ECG experts and (2) to determine true vs. false VT using a new VT algorithm created by our group.

METHODS

The VT algorithm was processed in 5320 consecutive ICU patients with 572,574 h of ECG and physiologic monitoring. A search algorithm identified potential VT, defined as: heart rate >100 beats/min, QRSs > 120 ms, and change in QRS morphology in >6 consecutive beats compared to the preceding native rhythm. Seven ECG channels, SpO₂ , and arterial blood pressure waveforms were processed and loaded into a web-based annotation software program. Five PhD-prepared nurse scientists performed the annotations.

RESULTS

Of the 5320 ICU patients, 858 (16.13%) had 22,325 VTs. After three levels of iterative annotations, a total of 11,970 (53.62%) were adjudicated as true, 6485 (29.05%) as false, and 3870 (17.33%) were unresolved. The unresolved VTs were concentrated in 17 patients (1.98%). Of the 3870 unresolved VTs, 85.7% (n = 3281) were confounded by ventricular paced rhythm, 10.8% (n = 414) by underlying BBB, and 3.5% (n = 133) had a combination of both.

CONCLUSIONS

The database described here represents the single largest human-annotated database to date. The database includes consecutive ICU patients, with true, false, and challenging VTs (unresolved) and could serve as a gold standard database to develop and test new VT algorithms.

Automatic signal quality assessment of raw trans-abdominal biopotential recordings for non-invasive fetal electrocardiography

Introduction: Wearable monitoring systems for non-invasive multi-channel fetal electrocardiography (fECG) can support fetal surveillance and diagnosis during pregnancy, thus enabling prompt treatment. In these embedded systems, power saving is the key to long-term monitoring. In this regard, the computational burden of signal processing methods implemented for the fECG extraction from the multi-channel trans-abdominal recordings plays a non-negligible role. In this work, a supervised machine-learning approach for the automatic selection of the most informative raw abdominal recordings in terms of fECG content, i.e., those potentially leading to good-quality, non-invasive fECG signals from a low number of channels, is presented and evaluated. Methods: For this purpose, several signal quality indexes from the scientific literature were adopted as features to train an ensemble tree classifier, which was asked to perform a binary classification between informative and non-informative abdominal channels. To reduce the dimensionality of the classification problem, and to improve the performance, a feature selection approach was also implemented for the identification of a subset of optimal features. 10336 5-s long signal segments derived from a real dataset of multi-channel trans-abdominal recordings acquired from 55 voluntary pregnant women between the 21st and the 27th week of gestation, with healthy fetuses, were adopted to train and test the classification approach in a stratified 10-time 10-fold cross-validation scheme. Abdominal recordings were firstly pre-processed and then labeled as informative or non-informative, according to the signal-to-noise ratio exhibited by the extracted fECG, thus producing a balanced dataset of bad and good quality abdominal channels. Results and Discussion: Classification performance revealed an accuracy above 86%, and more than 88% of those channels labeled as informative were correctly identified. Furthermore, by applying the proposed method to 50 annotated 24-channel recordings from the NInFEA dataset, a significant improvement was observed in fetal QRS detection when only the channels selected by the proposed approach were considered, compared with the use of all the available channels. As such, our findings support the hypothesis that performing a channel selection by looking directly at the raw abdominal signals, regardless of the fetal presentation, can produce a reliable measurement of fetal heart rate with a lower computational burden.

A signal quality assessment method for fetal QRS complexes detection

OBJECTIVE

Non-invasive fetal ECG (NI-FECG) provides a non-invasive method to monitor the health of the fetus. However, the NI-FECG is easily interfered by noise, which makes the signal quality decline, leading to the fetal heart rate (FHR) monitoring becoming a challenging task.

METHODS

In this work, an algorithm for dynamic evaluation of signal quality is proposed to improve the multi-channel FHR monitoring. The innovation of the method is to assess the signal quality in the process of multi-channel fetal QRS (FQRS) complexes detection. Specifically, the detected FQRS is used as quality unit. Each quality unit can be a true R peak (TR) or a false R peak (FR). It is the basic quality information in this work. The signal quality of each channel is estimated by estimating the correctness of the detection results. Further, the TRs of all channels can be fused to obtain more reliable fetal heart rate monitoring.

MAIN RESULTS

Analysis results demonstrate that the proposed algorithm is capable of selecting the good quality signal for FQRS detection achieving 97.40% PPV, 98.33% SE and 97.86% F₁.

SIGNIFICANCE

This work sheds light on the quality assessment of fetal monitoring signal.

Computational approaches to alleviate alarm fatigue in intensive care medicine: A systematic literature review

Patient monitoring technology has been used to guide therapy and alert staff when a vital sign leaves a predefined range in the intensive care unit (ICU) for decades. However, large amounts of technically false or clinically irrelevant alarms provoke alarm fatigue in staff leading to desensitisation towards critical alarms. With this systematic review, we are following the Preferred Reporting Items for Systematic Reviews (PRISMA) checklist in order to summarise scientific efforts that aimed to develop IT systems to reduce alarm fatigue in ICUs. 69 peer-reviewed publications were included. The majority of publications targeted the avoidance of technically false alarms, while the remainder focused on prediction of patient deterioration or alarm presentation. The investigated alarm types were mostly associated with heart rate or arrhythmia, followed by arterial blood pressure, oxygen saturation, and respiratory rate. Most publications focused on the development of software solutions, some on wearables, smartphones, or headmounted displays for delivering alarms to staff. The most commonly used statistical models were tree-based. In conclusion, we found strong evidence that alarm fatigue can be alleviated by IT-based solutions. However, future efforts should focus more on the avoidance of clinically non-actionable alarms which could be accelerated by improving the data availability.

Systematic Review Registration:https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42021233461, identifier: CRD42021233461.

Predicting arrhythmia, atrial fibrillation from electrocardiogram signals using Pivot Range Fitness Scale-Based Machine Learning Model

Purpose

Patients having ventricular arrhythmias and atrial fibrillation, that are early markers of stroke and sudden cardiac death, as well as benign subjects are all studied using the electrocardiogram (ECG). In order to identify cardiac anomalies, ECG signals analyse the heart's electrical activity and show output in the form of waveforms. Patients with these disorders must be identified as soon as possible. ECG signals can be difficult, time-consuming and subject to inter-observer variability when inspected manually.

Design/methodology/approach

There are various forms of arrhythmias that are difficult to distinguish in complicated non-linear ECG data. It may be beneficial to use computer-aided decision support systems (CAD). It is possible to classify arrhythmias in a rapid, accurate, repeatable and objective manner using the CAD, which use machine learning algorithms to identify the tiny changes in cardiac rhythms. Cardiac infractions can be classified and detected using this method. The authors want to categorize the arrhythmia with better accurate findings in even less computational time as the primary objective. Using signal and axis characteristics and their association n-grams as features, this paper makes a significant addition to the field. Using a benchmark dataset as input to multi-label multi-fold cross-validation, an experimental investigation was conducted.

Findings

This dataset was used as input for cross-validation on contemporary models and the resulting cross-validation metrics have been weighed against the performance metrics of other contemporary models. There have been few false alarms with the suggested model's high sensitivity and specificity.

Originality/value

The results of cross validation are significant. In terms of specificity, sensitivity, and decision accuracy, the proposed model outperforms other contemporary models.

Robustness of electrocardiogram signal quality indices

Electrocardiogram (ECG) signal quality indices (SQIs) are essential for improving diagnostic accuracy and reliability of ECG analysis systems. In various practical applications, the ECG signals are corrupted by different types of noise. These corrupted ECG signals often provide insufficient and incorrect information regarding a patient's health. To solve this problem, signal quality measurements should be made before an ECG signal is used for decision-making. This paper investigates the robustness of existing popular statistical signal quality indices (SSQIs): relative power of QRS complex (SQIp), skewness (SQIskew), signal-to-noise ratio (SQIsnr), higher order statistics SQI (SQIhos) and peakedness of kurtosis (SQIkur). We analysed the robustness of these SSQIs against different window sizes across diverse datasets. Results showed that the performance of SSQIs considerably fluctuates against varying datasets, whereas the impact of varying window sizes was minimal. This fluctuation occurred due to the use of a static threshold value for classifying noise-free ECG signals from the raw ECG signals. Another drawback of these SSQIs is the bias towards noise-free ECG signals, that limits their usefulness in clinical settings. In summary, the fixed threshold-based SSQIs cannot be used as a robust noise detection system. In order to solve this fixed threshold problem, other techniques can be developed using adaptive thresholds and machine-learning mechanisms.

Real-Time Arrhythmia Detection Using Hybrid Convolutional Neural Networks

Background Accurate detection of arrhythmic events in the intensive care units (ICU) is of paramount significance in providing timely care. However, traditional ICU monitors generate a high rate of false alarms causing alarm fatigue. In this work, we develop an algorithm to improve life threatening arrhythmia detection in the ICUs using a deep learning approach. Methods and Results This study involves a total of 953 independent life-threatening arrhythmia alarms generated from the ICU bedside monitors of 410 patients. Specifically, we used the ECG (4 channels), arterial blood pressure, and photoplethysmograph signals to accurately detect the onset and offset of various arrhythmias, without prior knowledge of the alarm type. We used a hybrid convolutional neural network based classifier that fuses traditional handcrafted features with features automatically learned using convolutional neural networks. Further, the proposed architecture remains flexible to be adapted to various arrhythmic conditions as well as multiple physiological signals. Our hybrid- convolutional neural network approach achieved superior performance compared with methods which only used convolutional neural network. We evaluated our algorithm using 5-fold cross-validation for 5 times and obtained an accuracy of 87.5%±0.5%, and a score of 81%±0.9%. Independent evaluation of our algorithm on the publicly available PhysioNet 2015 Challenge database resulted in overall classification accuracy and score of 93.9% and 84.3%, respectively, indicating its efficacy and generalizability. Conclusions Our method accurately detects multiple arrhythmic conditions. Suitable translation of our algorithm may significantly improve the quality of care in ICUs by reducing the burden of false alarms.

Application Scenarios for Artificial Intelligence in Nursing Care: Rapid Review

Background

Artificial intelligence (AI) holds the promise of supporting nurses’ clinical decision-making in complex care situations or conducting tasks that are remote from direct patient interaction, such as documentation processes. There has been an increase in the research and development of AI applications for nursing care, but there is a persistent lack of an extensive overview covering the evidence base for promising application scenarios.

Objective

This study synthesizes literature on application scenarios for AI in nursing care settings as well as highlights adjacent aspects in the ethical, legal, and social discourse surrounding the application of AI in nursing care.

Methods

Following a rapid review design, PubMed, CINAHL, Association for Computing Machinery Digital Library, Institute of Electrical and Electronics Engineers Xplore, Digital Bibliography & Library Project, and Association for Information Systems Library, as well as the libraries of leading AI conferences, were searched in June 2020. Publications of original quantitative and qualitative research, systematic reviews, discussion papers, and essays on the ethical, legal, and social implications published in English were included. Eligible studies were analyzed on the basis of predetermined selection criteria.

Results

The titles and abstracts of 7016 publications and 704 full texts were screened, and 292 publications were included. Hospitals were the most prominent study setting, followed by independent living at home; fewer application scenarios were identified for nursing homes or home care. Most studies used machine learning algorithms, whereas expert or hybrid systems were entailed in less than every 10th publication. The application context of focusing on image and signal processing with tracking, monitoring, or the classification of activity and health followed by care coordination and communication, as well as fall detection, was the main purpose of AI applications. Few studies have reported the effects of AI applications on clinical or organizational outcomes, lacking particularly in data gathered outside laboratory conditions. In addition to technological requirements, the reporting and inclusion of certain requirements capture more overarching topics, such as data privacy, safety, and technology acceptance. Ethical, legal, and social implications reflect the discourse on technology use in health care but have mostly not been discussed in meaningful and potentially encompassing detail.

Conclusions

The results highlight the potential for the application of AI systems in different nursing care settings. Considering the lack of findings on the effectiveness and application of AI systems in real-world scenarios, future research should reflect on a more nursing care–specific perspective toward objectives, outcomes, and benefits. We identify that, crucially, an advancement in technological-societal discourse that surrounds the ethical and legal implications of AI applications in nursing care is a necessary next step. Further, we outline the need for greater participation among all of the stakeholders involved.

Estimating Resting HRV during fMRI: A Comparison between Laboratory and Scanner Environment

Heart rate variability (HRV) is regularly assessed in neuroimaging studies as an indicator of autonomic, emotional or cognitive processes. In this study, we investigated the influence of a loud and cramped environment during magnetic resonance imaging (MRI) on resting HRV measures. We compared recordings during functional MRI sessions with recordings in our autonomic laboratory (LAB) in 101 healthy subjects. In the LAB, we recorded an electrocardiogram (ECG) and a photoplethysmogram (PPG) over 15 min. During resting state functional MRI, we acquired a PPG for 15 min. We assessed anxiety levels before the scanning in each subject. In 27 participants, we performed follow-up sessions to investigate a possible effect of habituation. We found a high intra-class correlation ranging between 0.775 and 0.996, indicating high consistency across conditions. We observed no systematic influence of the MRI environment on any HRV index when PPG signals were analyzed. However, SDNN and RMSSD were significantly higher when extracted from the PPG compared to the ECG. Although we found a significant correlation of anxiety and the decrease in HRV from LAB to MRI, a familiarization session did not change the HRV outcome. Our results suggest that psychological factors are less influential on the HRV outcome during MRI than the methodological choice of the cardiac signal to analyze.

Computer Assisted Patient Monitoring: Associated Patient, Clinical and ECG Characteristics and Strategy to Minimize False Alarms

This chapter is a review of studies that have examined false arrhythmia alarms during in-hospital electrocardiographic (ECG) monitoring in the intensive care unit. In addition, we describe an annotation effort being conducted at the UCSF School of Nursing, Center for Physiologic Research designed to improve algorithms for lethal arrhythmias (i.e., asystole, ventricular fibrillation, and ventricular tachycardia). Background: Alarm fatigue is a serious patient safety hazard among hospitalized patients. Data from the past five years, showed that alarm fatigue was responsible for over 650 deaths, which is likely lower than the actual number due to under-reporting. Arrhythmia alarms are a common source of false alarms and 90% are false. While clinical scientists have implemented a number of interventions to reduce these types of alarms (e.g., customized alarm settings; daily skin electrode changes; disposable vs. non-disposable lead wires; and education), only minor improvements have been made. This is likely as these interventions do not address the primary problem of false arrhythmia alarms, namely deficient and outdated arrhythmia algorithms. In this chapter we will describe a number of ECG features associated with false arrhythmia alarms. In addition, we briefly discuss an annotation effort our group has undertaken to improve lethal arrhythmia algorithms.

ECG quality assessment based on hand-crafted statistics and deep-learned S-transform spectrogram features

Background and Objective Electrocardiogram (ECG) quality assessment is significant for automatic diagnosis of cardiovascular disease and reducing the massive workload of reviewing continuous ECGs. Hence, how to design an appropriate algorithm for objectively evaluating the multi-lead ECG recordings is particularly important. Despite the deep learning methods performing well in many fields, as a data-driven method, it may not be entirely suitable for ECG analysis due to the difficulty in obtaining sufficient data and the low signal-to-noise ratio of ECG recordings. In this study, with the aim of providing an accurate and automatic ECG quality assessment scheme, we propose an innovative ECG quality assessment algorithm based on hand-crafted statistical features and deep-learned spectral features. Methods In this paper, a novel approach, combining the deep-learned Stockwell transform (S-Transform) spectrogram features and hand-crafted statistical features, is proposed for ECG quality assessment. Firstly, a double-input convolutional neural network (CNN) is established. Then, the S-Transform with a novel online augmentation scheme is performed on the multi-lead raw ECG signal received from one input layer to obtain proper time-frequency representation. After that, the CNN with three convolutional layers is employed to extract robust deep-learned features automatically. Simultaneously, the hand-crafted statistical features, including lead-fall, baseline drift, and R peak features, are calculated and fed into another input layer for feature fusion training. Finally, the deep-learned and hand-crafted features are concatenated and further fused by a fully connected layer for quality classification. Furthermore, a log-odds analysis scheme combining with a gradient-based method can localize the abnormal zone in time, frequency, and spatial domains. Results and Conclusion Our proposed method is evaluated on a publicly available database with 10-fold cross-validation. The experimental results demonstrate that the proposed assessment algorithm reached a mean accuracy of 93.09%, a mean F1-score of 0.8472, and a sensitivity of 0.9767. Moreover, comprehensive experiments indicate that the fusion of CNN features and statistical features has complementary advantages and ideal interpretability, achieving end-to-end multi-lead ECG assessment with satisfying performance.

Assessing Electrocardiogram and Respiratory Signal Quality of a Wearable Device (SensEcho): Semisupervised Machine Learning-Based Validation Study

Background

With the development and promotion of wearable devices and their mobile health (mHealth) apps, physiological signals have become a research hotspot. However, noise is complex in signals obtained from daily lives, making it difficult to analyze the signals automatically and resulting in a high false alarm rate. At present, screening out the high-quality segments of the signals from huge-volume data with few labels remains a problem. Signal quality assessment (SQA) is essential and is able to advance the valuable information mining of signals.

Objective

The aims of this study were to design an SQA algorithm based on the unsupervised isolation forest model to classify the signal quality into 3 grades: good, acceptable, and unacceptable; validate the algorithm on labeled data sets; and apply the algorithm on real-world data to evaluate its efficacy.

Methods

Data used in this study were collected by a wearable device (SensEcho) from healthy individuals and patients. The observation windows for electrocardiogram (ECG) and respiratory signals were 10 and 30 seconds, respectively. In the experimental procedure, the unlabeled training set was used to train the models. The validation and test sets were labeled according to preset criteria and used to evaluate the classification performance quantitatively. The validation set consisted of 3460 and 2086 windows of ECG and respiratory signals, respectively, whereas the test set was made up of 4686 and 3341 windows of signals, respectively. The algorithm was also compared with self-organizing maps (SOMs) and 4 classic supervised models (logistic regression, random forest, support vector machine, and extreme gradient boosting). One case validation was illustrated to show the application effect. The algorithm was then applied to 1144 cases of ECG signals collected from patients and the detected arrhythmia false alarms were calculated.

Results

The quantitative results showed that the ECG SQA model achieved 94.97% and 95.58% accuracy on the validation and test sets, respectively, whereas the respiratory SQA model achieved 81.06% and 86.20% accuracy on the validation and test sets, respectively. The algorithm was superior to SOM and achieved moderate performance when compared with the supervised models. The example case showed that the algorithm was able to correctly classify the signal quality even when there were complex pathological changes in the signals. The algorithm application results indicated that some specific types of arrhythmia false alarms such as tachycardia, atrial premature beat, and ventricular premature beat could be significantly reduced with the help of the algorithm.

Conclusions

This study verified the feasibility of applying the anomaly detection unsupervised model to SQA. The application scenarios include reducing the false alarm rate of the device and selecting signal segments that can be used for further research.

Comparison of Machine Learning Algorithms for the Quality Assessment of Wearable ECG Signals Via Lenovo H3 Devices

Purpose

Electrocardiogram (ECG) signals collected from wearable devices are easily corrupted with surrounding noise and artefacts, where the signal-to-noise ratio (SNR) of wearable ECG signals is significantly lower than that from hospital ECG machines. To meet the requirements for monitoring heart disease via wearable devices, eliminating useless or poor-quality ECG signals (e.g., lead-falls and low SNRs) can be solved by signal quality assessment algorithms.

Methods

To compensate for the deficiency of the existing ECG quality assessment system, a wearable ECG signal dataset from heart disease patients collected by Lenovo H3 devices was constructed. Then, this paper compares the performance of three machine learning algorithms, i.e., the traditional support vector machine (SVM), least-squares SVM (LS-SVM) and long short-term memory (LSTM) algorithms. Different non-morphological signal quality indices (i.e., the approximate entropy (ApEn), sample entropy (SaEn), fuzzy measure entropy (FMEn), Hurst exponent (HE), kurtosis (K) and power spectral density (PSD) features) extracted from the original ECG signals are fed into the three algorithms as input.

Results

The true positive rate, true negative rate, sensitivity and accuracy are used to evaluate the performance of each method, and the LSTM algorithm achieves the best results on these metrics (97.14%, 86.8%, 97.46% and 95.47%, respectively).

Conclusions

Among the three algorithms, the LSTM-based quality assessment method is the most suitable for the signals collected by the Lenovo H3 devices. The results also show that the combination of statistical features can effectively evaluate the quality of ECG signals.

Automated False Alarm Reduction in a Real-Life Intensive Care Setting Using Motion Detection

BACKGROUND

Contemporary monitoring systems are sensitive to motion artifacts and cause an excess of false alarms. This results in alarm fatigue and hazardous alarm desensitization. To reduce the number of false alarms, we developed and validated a novel algorithm to classify alarms, based on automatic motion detection in videos.

METHODS

We considered alarms generated by the following continuously measured parameters: arterial oxygen saturation, systolic blood pressure, mean blood pressure, heart rate, and mean intracranial pressure. The movements of the patient and in his/her surroundings were monitored by a camera situated at the ceiling. Using the algorithm, alarms were classified into RED (true), ORANGE (possibly false), and GREEN alarms (false, i.e., artifact). Alarms were reclassified by blinded clinicians. The performance was evaluated using confusion matrices.

RESULTS

A total of 2349 alarms from 45 patients were reclassified. For RED alarms, sensitivity was high (87.0%) and specificity was low (29.6%) for all parameters. As the sensitivities and specificities for RED and GREEN alarms are interrelated, the opposite was observed for GREEN alarms, i.e., low sensitivity (30.2%) and high specificity (87.2%). As RED alarms should not be missed, even at the expense of false positives, the performance was acceptable. The low sensitivity for GREEN alarms is acceptable, as it is not harmful to tag a GREEN alarm as RED/ORANGE. It still contributes to alarm reduction. However, a 12.8% false-positive rate for GREEN alarms is critical.

CONCLUSIONS

The proposed system is a step forward toward alarm reduction; however, implementation of additional layers, such as signal curve analysis, multiple parameter correlation analysis and/or more sophisticated video-based analytics are needed for improvement.

Generalizability of SuperAlarm via Cross-Institutional Performance Evaluation

Bedside patient monitors are ubiquitous tools in modern critical care units to provide timely patient status. However, current systems suffer from high volume of false alarms leading to alarm fatigue, one of top technical hazards in clinical settings. Many studies are racing to develop improved algorithms towards precision patient monitoring, while little has been done to investigate the aspect of algorithm generalizability across different health institutions. Our group has been developing an evolving framework termed SuperAlarm that extracts multivariate patterns in data streams (monitor alarms, electronic health records and physiologic waveforms) of modern health enterprise to predict patient deterioration and has demonstrated great potential in mitigating alarm fatigue. In this study, we further investigate the generalizability of SuperAlarm by designing a comprehensive approach to achieve performance comparison in predicting in-hospital code blue (CB) events across two health institutions. SuperAlarm model trained with alarm data in one institution is tested on both internal and external test sets. Results show comparable performance with sensitivity up to 80% within one-hour window of events and over 90% in reduction of false alarms in both institutions. Cross-institutional performance agreement can be further improved by predicting a more stringent CB subtype (cardiopulmonary arrest), with internal sensitivity lying within 95% confident interval of external one up to 8-hour before event onset. The cross-institutional performance comparison offers first-hand knowledge on both advantages and challenges in generalizing a prediction algorithm across different institutions, which hold key information to guide the design of model training and deployment strategy.

Actionable Ventricular Tachycardia During In-Hospital ECG Monitoring and Its Impact on Alarm Fatigue

BACKGROUND

Ventricular tachycardia (V-tach) is the most common lethal arrhythmia, yet 90% of alarms are false and contribute to alarm fatigue. We hypothesize that some true V-tach also causes alarm fatigue because current criteria are too sensitive (i.e., ≥6 beats ≥100 beats/min [bpm]).

PURPOSE

This study was designed to determine (1) the proportion of clinically actionable true V-tach events; (2) whether true actionable versus nonactionable V-tach differs in terms of heart rate and/or duration (seconds); and (3) if actionable V-tach is associated with adverse outcomes.

METHODS

This was a secondary analysis in 460 intensive care unit (ICU) patients. Electronic health records were examined to determine if a V-tach event was actionable or nonactionable. Actionable V-tach was defined if a clinical action(s) was taken within 15 minutes of its occurrence (i.e., new and/or change of medication, defibrillation, and/or laboratory test). Maximal heart rate and duration for each V-tach event were measured from bedside monitor electrocardiography. Adverse patient outcomes included a code blue event and/or death.

RESULTS

In 460 ICU patients, 50 (11%) had 151 true V-tach events (range 1-20). Of the 50 patients, 40 (80%) had only nonactionable V-tach (97 events); 3 (6%) had both actionable and nonactionable V-tach (32 events); and 7 patients (14%) had only actionable V-tach (23 events). There were differences in duration comparing actionable versus nonactionable V-tach (mean 56.19 ± 116.87 seconds vs. 4.28 ± 4.09 seconds; P = 0.001) and maximal heart rate (188.81 ± 116.83 bpm vs. 150.79 ± 28.26 bpm; P = 0.001). Of the 50 patients, 3 (6%) had a code blue, 2 died, and all were in the actionable V-tach group.

CONCLUSIONS

In our sample, <1% experienced a code blue following true V-tach. Heart rate and duration for actionable V-tach were much faster and longer than that for nonactionable V-tach. Current default settings typically used for electrocardiographic monitoring (i.e., ≥6 beats ≥100 bpm) appear to be too conservative and can lead to crisis/red level nuisance alarms that contribute to alarm fatigue. A prospective study designed to test whether adjusting default settings to these higher levels is safe for patients is needed.

Daily Electrocardiogram Electrode Change and the Effect on Frequency of Nuisance Alarms

BACKGROUND

In 2018, The Joint Commission identified false telemetry alarms as a significant technology hazard placing patients at risk of injury. Reasons include poor skin preparation when applying electrodes and improper placement of electrodes.

OBJECTIVES

The purpose of this quality improvement project was to determine if changing electrocardiogram electrodes daily would decrease the frequency of nuisance alarms.

METHODS

Study design was quantitative/comparative on all patients receiving telemetry monitoring on a 36-bed adult inpatient cardiac telemetry unit. Data collection occurred for 14 days before the intervention and 14 days during the intervention of daily electrode change. Comparison analysis determined if frequency of alarms decreased after the intervention with daily electrode change.

RESULTS

Postintervention data showed a 74.15% reduction in telemetry alarms following implementation of a daily electrode change.

DISCUSSION

Daily electrocardiogram electrode changes may be an effective strategy for reducing nuisance alarms on telemetry units. Outcomes can be used in conjunction with existing evidence to drive current practice.

Reduction of false alarms in the intensive care unit using an optimized machine learning based approach

This work attempts to reduce the number of false alarms generated by bedside monitors in the intensive care unit (ICU), as a majority of current alarms are false. In this study, we applied methods that can be categorized into three stages: signal processing, feature extraction, and optimized machine learning. At the stage of signal processing, we ensured that the heartbeats were properly annotated. During feature extraction, besides extracting features that are relevant to the arrhythmic alarms, we also extracted a set of signal quality indices (SQIs), which we used to distinguish noise/artifact from normal physiological signals. When applying a machine learning algorithm (Random Forest), we performed feature selection in order to reduce the complexity of the models and improve the efficiency of the algorithm. The dataset used is from Reducing False Arrhythmia Alarms in the ICU: the PhysioNet/Computing in Cardiology Challenge 2015. Using the performance metric "score" from the Challenge, we achieved a score of 83.08 in the real-time category on the hidden test set, which is the highest in all published work.

Signal quality measure for pulsatile physiological signals using morphological features: Applications in reliability measure for pulse oximetry

Pulse oximetry is a noninvasive and low-cost physiological monitor that measures blood oxygen levels. While the noninvasive nature of pulse oximetry is advantageous, the estimates of oxygen saturation generated by these devices are prone to motion artifacts and ambient noise, reducing the reliability of such estimations. Clinicians combat this by assessing the quality of oxygen saturation estimation by visual inspection of the photoplethysmograph (PPG), which represents changes in pulsatile blood volume and is also generated by the pulse oximeter. In this paper, we propose six morphological features that can be used to determine the quality of the PPG signal and generate a signal quality index. Unlike many similar studies, this approach uses machine learning and does not require a separate signal, such as ECG, for reference. Multiple algorithms were tested against 46 30-min PPG segments of patients with cardiovascular and respiratory conditions, including atrial fibrillation, hypoxia, acute heart failure, pneumonia, ARDS, and pulmonary embolism. These signals were independently annotated for signal quality by two clinicians, with the union of their annotations used as the ground-truth. Similar to any physiological signal recorded in a clinical setting, the utilized dataset is also unbalanced in favor of good quality segments. The experiments showed that a cost-sensitive Support Vector Machine (SVM) outperformed other tested methods and was robust to the unbalanced nature of the data. Though the proposed algorithm was tested on PPG signals, the methodology remains agnostic to the dataset used, and may be applied to any type of pulsatile physiological signal.

A novel diversity method for smartphone camera-based heart rhythm signals in the presence of motion and noise artifacts

The advent of smartphones has advanced the use of embedded sensors to acquire various physiological information. For example, smartphone camera sensors and accelerometers can provide heart rhythm signals to the subjects, while microphones can give respiratory signals. However, the acquired smartphone-based physiological signals are more vulnerable to motion and noise artifacts (MNAs) compared to using medical devices, since subjects need to hold the smartphone with proper contact to the smartphone camera and lens stably and tightly for a duration of time without any movement in the hand or finger. This results in more MNA than traditional methods, such as placing a finger inside a tightly enclosed pulse oximeter to get PPG signals, which provides stable contact between the sensor and the subject's finger. Moreover, a smartphone lens does not block ambient light in an effective way, while pulse oximeters are designed to block the ambient light effectively. In this paper, we propose a novel diversity method for smartphone signals that reduces the effect of MNAs during heart rhythm signal detection by 1) acquiring two heterogeneous signals from a color intensity signal and a fingertip movement signal, and 2) selecting the less MNA-corrupted signal of the two signals. The proposed method has advantages in that 1) diversity gain can be obtained from the two heterogeneous signals when one signal is clean while the other signal is corrupted, and 2) acquisition of the two heterogeneous signals does not double the acquisition procedure but maintains a single acquisition procedure, since two heterogeneous signals can be obtained from a single smartphone camera recording. In our diversity method, we propose to choose the better signal based on the signal quality indices (SQIs), i.e., standard deviation of instantaneous heart rate (STD-HR), root mean square of the successive differences of peak-to-peak time intervals (RMSSD-T), and standard deviation of peak values (STD-PV). As a performance metric evaluating the proposed diversity method, the ratio of usable period is considered. Experimental results show that our diversity method increases the usable period 19.53% and 6.25% compared to the color intensity or the fingertip movement signals only, respectively.

Decision Tree Predictive Learner-Based Approach for False Alarm Detection in ICU

In this work, a novel method has been proposed for false alarm detection in Intensive Care Unit (ICU) during arrhythmia. To detect false alarm, various inputs are used such as electrocardiogram (ECG) signals, atrial blood pressure (ABP), photoplethysmogram signals (PLETH) and respiration (RESP). The inputs are given to decision tree predictive learner (DTPL) based classifier for thedetection of false alarm. The proposed method has an accuracy of 97% for prediction of false alarm in ICU. Theresult of the proposed method is promising which suggest that it can be used effectively for false alarm detection in ICUs. To the best of our knowledge, there is no such assumption based classification approach.

Hemodynamic Instability and Cardiovascular Events After Traumatic Brain Injury Predict Outcome After Artifact Removal With Deep Belief Network Analysis

BACKGROUND

Hemodynamic instability and cardiovascular events heavily affect the prognosis of traumatic brain injury. Physiological signals are monitored to detect these events. However, the signals are often riddled with faulty readings, which jeopardize the reliability of the clinical parameters obtained from the signals. A machine-learning model for the elimination of artifactual events shows promising results for improving signal quality. However, the actual impact of the improvements on the performance of the clinical parameters after the elimination of the artifacts is not well studied.

MATERIALS AND METHODS

The arterial blood pressure of 99 subjects with traumatic brain injury was continuously measured for 5 consecutive days, beginning on the day of admission. The machine-learning deep belief network was constructed to automatically identify and remove false incidences of hypotension, hypertension, bradycardia, tachycardia, and alterations in cerebral perfusion pressure (CPP).

RESULTS

The prevalences of hypotension and tachycardia were significantly reduced by 47.5% and 13.1%, respectively, after suppressing false incidents (P=0.01). Hypotension was particularly effective at predicting outcome favorability and mortality after artifact elimination (P=0.015 and 0.027, respectively). In addition, increased CPP was also statistically significant in predicting outcomes (P=0.02).

CONCLUSIONS

The prevalence of false incidents due to signal artifacts can be significantly reduced using machine-learning. Some clinical events, such as hypotension and alterations in CPP, gain particularly high predictive capacity for patient outcomes after artifacts are eliminated from physiological signals.

An open source benchmarked toolbox for cardiovascular waveform and interval analysis

OBJECTIVE

This work aims to validate a set of data processing methods for variability metrics, which hold promise as potential indicators for autonomic function, prediction of adverse cardiovascular outcomes, psychophysiological status, and general wellness. Although the investigation of heart rate variability (HRV) has been prevalent for several decades, the methods used for preprocessing, windowing, and choosing appropriate parameters lacks consensus among academic and clinical investigators. Moreover, many of the important steps are omitted from publications, preventing reproducibility.

APPROACH

To address this, we have compiled a comprehensive and open-source modular toolbox for calculating HRV metrics and other related variability indices, on both raw cardiovascular time series and RR intervals. The software, known as the PhysioNet Cardiovascular Signal Toolbox, is implemented in the MATLAB programming language, with standard (open) input and output formats, and requires no external libraries. The functioning of our software is compared with other widely used and referenced HRV toolboxes to identify important differences.

MAIN RESULTS

Our findings demonstrate how modest differences in the approach to HRV analysis can lead to divergent results, a factor that might have contributed to the lack of repeatability of studies and clinical applicability of HRV metrics.

SIGNIFICANCE

Existing HRV toolboxes do not include standardized preprocessing, signal quality indices (for noisy segment removal), and abnormal rhythm detection and are therefore likely to lead to significant errors in the presence of moderate to high noise or arrhythmias. We therefore describe the inclusion of validated tools to address these issues. We also make recommendations for default values and testing/reporting.

SQI Quality Evaluation Mechanism of Single-Lead ECG Signal Based on Simple Heuristic Fusion and Fuzzy Comprehensive Evaluation

For both the acquisition of mobile electrocardiogram (ECG) devices and early warning and diagnosis of clinical work, high-quality ECG signals is particularly important. We describe an effective system which could be deployed as a stand-alone signal quality assessment algorithm for vetting the quality of ECG signals. The proposed ECG quality assessment method is based on the simple heuristic fusion and fuzzy comprehensive evaluation of the SQIs. This method includes two modules, i.e., the quantification and extraction of Signal Quality Indexes (SQIs) for different features, intelligent assessment and classification. First, simple heuristic fusion is executed to extract SQIs and determine the following SQIs: R peak detection match qSQI, QRS wave power spectrum distribution pSQI, kurtosis kSQI, and baseline relative power basSQI. Then, combined with Cauchy distribution, rectangular distribution and trapezoidal distribution, the membership function of SQIs was quantified, and the fuzzy vector was established. The bounded operator was selected for fuzzy synthesis, and the weighted membership function was used to perform the assessment and classification. The performance of the proposed method was tested on the database from Physionet ECG database, with an accuracy (Acc) of 97.67%, sensitivity (Se) of 96.33% and specificity (Sp) of 98.33% on the training set. Testing against the test datasets resulted in scores of 94.67, 90.33, and 93.00%, respectively. There's no gold standard exists for determining the quality of ECGs. However, the proposed algorithm discriminates between high- and poor-quality ECGs, which could aid in ECG acquisition for mobile ECG devices, early clinical diagnosis and early warning.

Faster clinical response to the onset of adverse events: A wearable metacognitive attention aid for nurse triage of clinical alarms

Objective

This study evaluates the potential for improving patient safety by introducing a metacognitive attention aid that enables clinicians to more easily access and use existing alarm/alert information. It is hypothesized that this introduction will enable clinicians to easily triage alarm/alert events and quickly recognize emergent opportunities to adapt care delivery. The resulting faster response to clinically important alarms/alerts has the potential to prevent adverse events and reduce healthcare costs.

Materials and methods

A randomized within-subjects single-factor clinical experiment was conducted in a high-fidelity 20-bed simulated acute care hospital unit. Sixteen registered nurses, four at a time, cared for five simulated patients each. A two-part highly realistic clinical scenario was used that included representative: tasking; information; and alarms/alerts. The treatment condition introduced an integrated wearable attention aid that leveraged metacognition methods from proven military systems. The primary metric was time for nurses to respond to important alarms/alerts.

Results

Use of the wearable attention aid resulted in a median relative within-subject improvement for individual nurses of 118% (W = 183, p = 0.006). The top quarter of relative improvement was 3,303% faster (mean; 17.76 minutes reduced to 1.33). For all unit sessions, there was an overall 148% median faster response time to important alarms (8.12 minutes reduced to 3.27; U = 2.401, p = 0.016), with 153% median improvement in consistency across nurses (F = 11.670, p = 0.001).

Discussion and conclusion

Existing device-centric alarm/alert notification solutions can require too much time and effort for nurses to access and understand. As a result, nurses may ignore alarms/alerts as they focus on other important work. There has been extensive research on reducing alarm frequency in healthcare. However, alarm safety remains a top problem. Empirical observations reported here highlight the potential of improving patient safety by supporting the meta-work of checking alarms.

A Review of Signal Processing Techniques for Electrocardiogram Signal Quality Assessment

Electrocardiogram (ECG) signal quality assessment (SQA) plays a vital role in significantly improving the diagnostic accuracy and reliability of unsupervised ECG analysis systems. In practice, the ECG signal is often corrupted with different kinds of noises and artifacts. Therefore, numerous SQA methods were presented based on the ECG signal and/or noise features and the machine learning classifiers and/or heuristic decision rules. This paper presents an overview of current state-of-the-art SQA methods and highlights the practical limitations of the existing SQA methods. Based upon past and our studies, it is noticed that a lightweight ECG noise analysis framework is highly demanded for real-time detection, localization, and classification of single and combined ECG noises within the context of wearable ECG monitoring devices which are often resource constrained.

Benchmarking heart rate variability toolboxes

BACKGROUND

Heart rate variability (HRV) metrics hold promise as potential indicators for autonomic function, prediction of adverse cardiovascular outcomes, psychophysiological status, and general wellness. Although the investigation of HRV has been prevalent for several decades, the methods used for preprocessing, windowing, and choosing appropriate parameters lack consensus among academic and clinical investigators.

METHODS

A comprehensive and open-source modular program is presented for calculating HRV implemented in Matlab with evidence-based algorithms and output formats. We compare our software with another widely used HRV toolbox written in C and available through PhysioNet.org.

RESULTS

Our findings show substantially similar results when using high quality electrocardiograms (ECG) free from arrhythmias.

CONCLUSIONS

Our software shows equivalent performance alongside an established predecessor and includes validated tools for performing preprocessing, signal quality, and arrhythmia detection to help provide standardization and repeatability in the field, leading to fewer errors in the presence of noise or arrhythmias.

A novel algorithm for reducing false arrhythmia alarms in intensive care units

Alarm fatigue in intensive care units (ICU) is one of the top healthcare issues in the US. False alarms in ICU will decrease the quality of care and staff response time over the alarms. Normally, false alarm will cause desensitization of the clinical staff which leads to warnings and misleading, if the triggered alarm is true. In this study, we have proposed a multi-model ensemble approach to reduce the false alarm rate in monitoring systems. We have used 750 patient records from PhysioNet database. At First arrhythmia based features from electrocardiogram (ECG), arterial blood pressure (ABP) and photoplethysmogram (PPG) features were extracted from the records. Next, the dataset has been separated into two subsets on the basis of available features information. The first dataset (DS1) is the combination of ECG physiological, ABP and PPG features. Their correlation coefficient and p-values criteria have been applied for relevant alarm-wise feature-set selection, and random forest classifier was used for model development and validation. The threshold based approach was used on second dataset (DS2) which is the combination of arrhythmia, ABP and PPG features. The developed ensemble model is able to achieve sensitivity 83.33-100 % (average 95.56 %) being true alarms and suppress false alarms rate 66.67-89% (average 77.25%). The predictability of classifier shows the advantage to deal with unbalanced set of information, therefore overall model performance has reached to 83.96% accuracy.

Is the Sequence of SuperAlarm Triggers More Predictive Than Sequence of the Currently Utilized Patient Monitor Alarms?

OBJECTIVE

Our previous studies have shown that "code blue" events can be predicted by SuperAlarm patterns that are multivariate combinations of monitor alarms and laboratory test results cooccurring frequently preceding the events but rarely among control patients. Deploying these patterns to the monitor data streams can generate SuperAlarm sequences. The objective of this study is to test the hypothesis that SuperAlarm sequences may contain more predictive sequential patterns than monitor alarms sequences.

METHODS

Monitor alarms and laboratory test results are extracted from a total of 254 adult coded and 2213 control patients. The training dataset is composed of subsequences that are sampled from complete sequences and then further represented as fixed-dimensional vectors by the term frequency inverse document frequency method. The information gain technique and weighted support vector machine are adopted to select the most relevant features and train a classifier to differentiate sequences between coded patients and control patients. Performances are assessed based on an independent dataset using three metrics: sensitivity of lead time (Sen L @T), alarm frequency reduction rate (AFRR), and work-up to detection ratio (WDR).

RESULTS

The performance of 12-h-long sequences of SuperAlarm can yield a Sen L@2 of 93.33%, an AFRR of 87.28%, and a WDR of 3.01. At an AFRR = 87.28%, Sen L@2 for raw alarm sequences and discretized alarm sequences are 73.33% and 70.19%, respectively. At a WDR = 3.01, Sen L@2 are 49.88% and 43.33%.

CONCLUSION AND SIGNIFICANCE

The results demonstrate that SuperAlarm sequences indeed outperform monitor alarm sequences and suggest that one can focus on sequential patterns from SuperAlarm sequences to develop more precise patient monitoring solutions.

Reducing false arrhythmia alarm rates using robust heart rate estimation and cost-sensitive support vector machines

To lessen the rate of false critical arrhythmia alarms, we used robust heart rate estimation and cost-sensitive support vector machines. The PhysioNet MIMIC II database and the 2015 PhysioNet/CinC Challenge public database were used as the training dataset; the 2015 Challenge hidden dataset was for testing. Each record had an alarm labeled with asystole, extreme bradycardia, extreme tachycardia, ventricular tachycardia or ventricular flutter/fibrillation. Before alarm onsets, 300 s multimodal data was provided, including electrocardiogram, arterial blood pressure and/or photoplethysmogram. A signal quality modified Kalman filter achieved robust heart rate estimation. Based on this, we extracted heart rate variability features and statistical ECG features. Next, we applied a genetic algorithm (GA) to select the optimal feature combination. Finally, considering the high cost of classifying a true arrhythmia as false, we selected cost-sensitive support vector machines (CSSVMs) to classify alarms. Evaluation on the test dataset showed the overall true positive rate was 95%, and the true negative rate was 85%.

Using Lempel-Ziv Complexity to Assess ECG Signal Quality

The poor quality of wireless electrocardiography (ECG) recordings can lead to misdiagnosis and waste of medical resources. This study presents an interpretation of Lempel–Ziv (LZ) complexity in terms of ECG quality assessment, and verifies its performance on real ECG signals. Firstly, LZ complexities for typical signals, namely high-frequency (HF) noise, low-frequency (LF) noise, power-line (PL) noise, impulse (IM) noise, clean artificial ECG signals, and ECG signals with various types of noise added (ECG plus HF, LF, PL, and IM noise, respectively) were analyzed. Then, the effects of noise, signal length, and signal-to-noise ratio (SNR) on the LZ complexity of ECG signals were analyzed. The simulation results show that LZ complexity for HF noise was obviously different from those for PL and LF noise. The LZ value can be used to determine the presence of HF noise. ECG plus HF noise had the highest LZ values. Other types of noise had low LZ values. Signal lengths of over 40 s had only a small effect on LZ values. The LZ values for ECG plus all types of noise increased monotonically with decreasing SNR except for LF and PL noise. For the test of real ECG signals plus three types of noise, namely muscle artefacts (MAs), baseline wander (BW), and electrode motion (EM) artefacts, LZ complexity varied obviously with increasing MA but not for BW and EM noise. This study demonstrates that LZ complexity is sensitive to noise level (especially for HF noise) and can thus be a valuable reference index for the assessment of ECG signal quality.

Detection of false arrhythmia alarms with emphasis on ventricular tachycardia

Our approach to detecting false arrhythmia alarms in the intensive care unit breaks down into several tasks. It involves beat detection on different signals: electrocardiogram, photoplethysmogram and arterial blood pressure. The quality of each channel has to be estimated in order to evaluate the reliability of obtained beat detections. The information about the heart rate from the different channels must be integrated in order to find a final conclusion. Some alarm types require particular detectors as is the case of ventricular fibrillation. To identify false ventricular tachycardia alarms we needed to classify heart beats as normal/ventricular. For that purpose we introduce a new feature, QRS polarity type. This feature was important in order to reduce misclassification of ventricular beats: there was an improvement in the ventricular tachycardia alarm true positive rate from 69% to 81%. However, the true negative rate was reduced from 95% to 69% and our global challenge score (real-time event) dropped from 79.02 to 74.28. Our challenge algorithm achieved the third best score in the 2015 PhysioNet/CinC challenge event 1 (real time).

Assessing ECG signal quality indices to discriminate ECGs with artefacts from pathologically different arrhythmic ECGs

False and non-actionable alarms in critical care can be reduced by developing algorithms which assess the trueness of an arrhythmia alarm from a bedside monitor. Computational approaches that automatically identify artefacts in ECG signals are an important branch of physiological signal processing which tries to address this issue. Signal quality indices (SQIs) derived considering differences between artefacts which occur in ECG signals and normal QRS morphology have the potential to discriminate pathologically different arrhythmic ECG segments as artefacts. Using ECG signals from the PhysioNet/Computing in Cardiology Challenge 2015 training set, we studied previously reported ECG SQIs in the scientific literature to differentiate ECG segments with artefacts from arrhythmic ECG segments. We found that the ability of SQIs to discriminate between ECG artefacts and arrhythmic ECG varies based on arrhythmia type since the pathology of each arrhythmic ECG waveform is different. Therefore, to reduce the risk of SQIs classifying arrhythmic events as noise it is important to validate and test SQIs with databases that include arrhythmias. Arrhythmia specific SQIs may also minimize the risk of misclassifying arrhythmic events as noise.

Life-threatening false alarm rejection in ICU: using the rule-based and multi-channel information fusion method

False alarm (FA) rates as high as 86% have been reported in intensive care unit monitors. High FA rates decrease quality of care by slowing staff response times while increasing patient burdens and stresses. In this study, we proposed a rule-based and multi-channel information fusion method for accurately classifying the true or false alarms for five life-threatening arrhythmias: asystole (ASY), extreme bradycardia (EBR), extreme tachycardia (ETC), ventricular tachycardia (VTA) and ventricular flutter/fibrillation (VFB). The proposed method consisted of five steps: (1) signal pre-processing, (2) feature detection and validation, (3) true/false alarm determination for each channel, (4) 'real-time' true/false alarm determination and (5) 'retrospective' true/false alarm determination (if needed). Up to four signal channels, that is, two electrocardiogram signals, one arterial blood pressure and/or one photoplethysmogram signal were included in the analysis. Two events were set for the method validation: event 1 for 'real-time' and event 2 for 'retrospective' alarm classification. The results showed that 100% true positive ratio (i.e. sensitivity) on the training set were obtained for ASY, EBR, ETC and VFB types, and 94% for VTA type, accompanied by the corresponding true negative ratio (i.e. specificity) results of 93%, 81%, 78%, 85% and 50% respectively, resulting in the score values of 96.50, 90.70, 88.89, 92.31 and 64.90, as well as with a final score of 80.57 for event 1 and 79.12 for event 2. For the test set, the proposed method obtained the score of 88.73 for ASY, 77.78 for EBR, 89.92 for ETC, 67.74 for VFB and 61.04 for VTA types, with the final score of 71.68 for event 1 and 75.91 for event 2.

False arrhythmia alarms reduction in the intensive care unit: a multimodal approach

The purpose of this study was to develop algorithms to lower the incidence of false arrhythmia alarms in the ICU using information from independent sources, namely electrocardiogram (ECG), arterial blood pressure (ABP) and photoplethysmogram (PPG). Our approach relies on robust adaptive signal processing techniques in order to extract accurate heart rate (HR) values from the different waveforms. Based on the quality of available signals, heart rate was either estimated from pulsatile waveforms using an adaptive frequency tracking algorithm or computed from ECGs using an adaptive mathematical morphology approach. Furthermore, we developed a supplementary measure based on the spectral purity of the ECGs to determine whether a ventricular tachycardia or flutter/fibrillation arrhythmia has taken place. Finally, alarm veracity was determined based on a set of decision rules on HR and spectral purity values. The proposed method was evaluated on the PhysioNet/CinC Challenge 2015 database, which is composed of 1250 life-threatening alarm recordings, each categorized into either bradycardia, tachycardia, asystole, ventricular tachycardia or ventricular flutter/fibrillation arrhythmia. This resulted in overall true positive rates of 95%/99% and overall true negative rates of 76%/80% on the real-time and retrospective subsets of the test dataset, respectively.