False alarm reduction in critical care

The influence of patient characteristics on the alarm rate in intensive care units: a retrospective cohort study

Intensive care units (ICU) are often overflooded with alarms from monitoring devices which constitutes a hazard to both staff and patients. To date, the suggested solutions to excessive monitoring alarms have remained on a research level. We aimed to identify patient characteristics that affect the ICU alarm rate with the goal of proposing a straightforward solution that can easily be implemented in ICUs. Alarm logs from eight adult ICUs of a tertiary care university-hospital in Berlin, Germany were retrospectively collected between September 2019 and March 2021. Adult patients admitted to the ICU with at least 24 h of continuous alarm logs were included in the study. The sum of alarms per patient per day was calculated. The median was 119. A total of 26,890 observations from 3205 patients were included. 23 variables were extracted from patients' electronic health records (EHR) and a multivariable logistic regression was performed to evaluate the association of patient characteristics and alarm rates. Invasive blood pressure monitoring (adjusted odds ratio (aOR) 4.68, 95%CI 4.15-5.29, p < 0.001), invasive mechanical ventilation (aOR 1.24, 95%CI 1.16-1.32, p < 0.001), heart failure (aOR 1.26, 95%CI 1.19-1.35, p < 0.001), chronic renal failure (aOR 1.18, 95%CI 1.10-1.27, p < 0.001), hypertension (aOR 1.19, 95%CI 1.13-1.26, p < 0.001), high RASS (aOR 1.22, 95%CI 1.18-1.25, p < 0.001) and scheduled surgical admission (aOR 1.22, 95%CI 1.13-1.32, p < 0.001) were significantly associated with a high alarm rate. Our study suggests that patient-specific alarm management should be integrated in the clinical routine of ICUs. To reduce the overall alarm load, particular attention regarding alarm management should be paid to patients with invasive blood pressure monitoring, invasive mechanical ventilation, heart failure, chronic renal failure, hypertension, high RASS or scheduled surgical admission since they are more likely to have a high contribution to noise pollution, alarm fatigue and hence compromised patient safety in ICUs.

Training Convolutional Neural Networks on Simulated Photoplethysmography Data: Application to Bradycardia and Tachycardia Detection

Objective: To develop a method for detection of bradycardia and ventricular tachycardia using the photoplethysmogram (PPG).

Approach: The detector is based on a dual-branch convolutional neural network (CNN), whose input is the scalograms of the continuous wavelet transform computed in 5-s segments. Training and validation of the CNN is accomplished using simulated PPG signals generated from RR interval series extracted from public ECG databases. Manually annotated real PPG signals from the PhysioNet/CinC 2015 Challenge Database are used for performance evaluation. The performance is compared to that of a pulse-based reference detector.

Results: The sensitivity/specificity were found to be 98.1%/97.9 and 76.6%/96.8% for the CNN-based detector, respectively, whereas the corresponding results for the pulse-based detector were 94.7%/99.8 and 67.1%/93.8%, respectively.

Significance: The proposed detector may be useful for continuous, long-term monitoring of bradycardia and tachycardia using wearable devices, e.g., wrist-worn devices, especially in situations where sensitivity is favored over specificity. The study demonstrates that simulated PPG signals are suitable for training and validation of a CNN.

Critical Care Nurses' Perceptions of Clinical Alarm Management on Nursing Practice

The alarm management of physiological monitoring systems is a key responsibility of critical care nurses. However, the high numbers of false and nonactionable (true but clinically irrelevant) alarms cause distractions to healthcare professionals, interruptions to nursing workflow, and ignoring of crucial tasks. Therefore, understanding how nurses manage large amounts of alarms in their daily work could provide a direction to design interventions to prevent adverse patient care effects. A qualitative design with focus group interviews was conducted with 37 nurses in Taiwan. Content analysis was performed to analyze the interview data, and four main themes were derived: (1) the foundation stone of critical care nursing practice; (2) a trajectory adaptation of alarms management; (3) adverse impacts on the quality of care and patient safety; and (4) a hope for multimodal learning alternatives and wireless technology. Nurses manage alarm parameter settings influenced not only by their knowledge and skills of patient care, but also in accordance with the three dimensions of technology, human, and organization evaluation framework. Customized alarm management training alternatives, patient-centered care values, and application of wireless technology are the suggested approaches to enhance nursing care and minimize the risk of adverse events.

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.

Robust R-Peak Detection in Low-Quality Holter ECGs using 1D Convolutional Neural Network

OBJECTIVE

Noise and low quality of ECG signals acquired from Holter or wearable devices deteriorate the accuracy and robustness of R-peak detection algorithms. This paper presents a generic and robust system for R-peak detection in Holter ECG signals. While many proposed algorithms have successfully addressed the problem of ECG R-peak detection, there is still a notable gap in the performance of these detectors on such low-quality ECG records.

METHODS

In this study, a novel implementation of the 1D Convolutional Neural Network (CNN) is used integrated with a verification model to reduce the number of false alarms. This CNN architecture consists of an encoder block and a corresponding decoder block followed by a sample-wise classification layer to construct the 1D segmentation map of R-peaks from the input ECG signal. Once the proposed model has been trained, it can solely be used to detect R-peaks possibly in a single channel ECG data stream quickly and accurately, or alternatively, such a solution can be conveniently employed for real-time monitoring on a lightweight portable device.

RESULTS

The model is tested on two open-access ECG databases: The China Physiological Signal Challenge (2020) database (CPSC-DB) with more than one million beats, and the commonly used MIT-BIH Arrhythmia Database (MIT-DB). Experimental results demonstrate that the proposed systematic approach achieves 99.30% F1-score, 99.69% recall, and 98.91% precision in CPSC-DB, which is the best R-peak detection performance ever achieved. Results also demonstrate similar or better performance than most competing algorithms on MIT-DB with 99.83% F1-score, 99.85% recall, and 99.82% precision.

SIGNIFICANCE

Compared to all competing methods, the proposed approach can reduce the false-positives and false-negatives in Holter ECG signals by more than 54% and 82%, respectively.

CONCLUSION

Finally, the simple and invariant nature of the parameters leads to a highly generic system and therefore applicable to any ECG dataset.

Towards better heartbeat segmentation with deep learning classification

The confidence of medical equipment is intimately related to false alarms. The higher the number of false events occurs, the less truthful is the equipment. In this sense, reducing (or suppressing) false positive alarms is hugely desirable. In this work, we propose a feasible and real-time approach that works as a validation method for a heartbeat segmentation third-party algorithm. The approach is based on convolutional neural networks (CNNs), which may be embedded in dedicated hardware. Our proposal aims to detect the pattern of a single heartbeat and classifies them into two classes: a heartbeat and not a heartbeat. For this, a seven-layer convolution network is employed for both data representation and classification. We evaluate our approach in two well-settled databases in the literature on the raw heartbeat signal. The first database is a conventional on-the-person database called MIT-BIH, and the second is one less uncontrolled off-the-person type database known as CYBHi. To evaluate the feasibility and the performance of the proposed approach, we use as a baseline the Pam-Tompkins algorithm, which is a well-known method in the literature and still used in the industry. We compare the baseline against the proposed approach: a CNN model validating the heartbeats detected by a third-party algorithm. In this work, the third-party algorithm is the same as the baseline for comparison purposes. The results support the feasibility of our approach showing that our method can enhance the positive prediction of the Pan-Tompkins algorithm from \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$97.84\%$$\end{document}97.84%/\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$90.28\%$$\end{document}90.28% to \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$100.00\%$$\end{document}100.00%/\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$96.77\%$$\end{document}96.77% by slightly decreasing the sensitivity from \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$95.79\%$$\end{document}95.79%/\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$96.95\%$$\end{document}96.95% to \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$92.98\%/$$\end{document}92.98%/\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$95.71\%$$\end{document}95.71% on the MIT-BIH/CYBHi databases.

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.

Diagnostic Quality Assessment of Ocular Fundus Photographs: Efficacy of Structure-Preserving ScatNet Features

Various ophthalmic procedures critically depend on high-quality images. For instance, efficiency of teleophthalmology, a framework to bring advanced eye care to remote regions, is determined by the capability of assessing diagnostic quality of ocular fundus photographs (FPs), and rejecting poor-quality ones at the source. In this context, we study algorithmic methods of classifying high- and low-quality FPs. Crucially, diagnostic quality (DQ) - determined by clinically, but not necessarily perceptually, significant structures - is not synonymous with perceptual appeal. Yet, traditional methods handpick features individually (or in small subsets) to meet certain ad hoc perceptual requirements. In contrast, we investigate the efficacy of a comprehensive set of structure-preserving features, systematically generated by a deep scattering network (ScatNet). Specifically, we consider three advanced machine learning classifiers, train each using ScatNet as well as traditional features separately, and demonstrate that the former ensure significantly superior performance for each classifier under multiple criteria including classification accuracy.

Predictive Monitoring of Critical Cardiorespiratory Alarms in Neonates Under Intensive Care

We aimed at reducing alarm fatigue in neonatal intensive care units by developing a model using machine learning for the early prediction of critical cardiorespiratory alarms. During this study in over 34,000 patient monitoring hours in 55 infants 278,000 advisory (yellow) and 70,000 critical (red) alarms occurred. Vital signs including the heart rate, breathing rate, and oxygen saturation were obtained at a sampling frequency of 1 Hz while heart rate variability was calculated by processing the ECG - both were used for feature development and for predicting alarms. Yellow alarms that were followed by at least one red alarm within a short post-alarm window constituted the case-cohort while the remaining yellow alarms constituted the control cohort. For analysis, the case and control cohorts, stratified by proportion, were split into training (80%) and test sets (20%). Classifiers based on decision trees were used to predict, at the moment the yellow alarm occurred, whether a red alarm(s) would shortly follow. The best performing classifier used data from the 2-min window before the occurrence of the yellow alarm and could predict 26% of the red alarms in advance (18.4s, median), at the expense of 7% additional red alarms. These results indicate that based on predictive monitoring of critical alarms, nurses can be provided a longer window of opportunity for preemptive clinical action. Further, such as algorithm can be safely implemented as alarms that are not algorithmically predicted can still be generated upon the usual breach of the threshold, as in current clinical practice.

Simultaneous multiple features tracking of beats: A representation learning approach to reduce false alarm rates in ICUs

The high rate of false alarms is a key challenge related to patient care in intensive care units (ICUs) that can result in delayed responses of the medical staff. Several rule-based and machine learning-based techniques have been developed to address this problem. However, the majority of these methods rely on the availability of different physiological signals such as different electrocardiogram (ECG) leads, arterial blood pressure (ABP), and photoplethysmogram (PPG), where each signal is analyzed by an independent processing unit and the results are fed to an algorithm to determine an alarm. That calls for novel methods that can accurately detect the cardiac events by only accessing one signal (e.g., ECG) with a low level of computation and sensors requirement. We propose a novel and robust representation learning framework for ECG analysis that only rely on a single lead ECG signal and yet achieves considerably better performance compared to the state-of-the-art works in this domain, without relying on an expert knowledge. We evaluate the performance of this method using the "2015 Physionet computing in cardiology challenge" dataset. To the best of our knowledge, the best previously reported performance is based on both expert knowledge and machine learning where all available signals of ECG, ABP and PPG are utilized. Our proposed method reaches the performance of 97.3%, 95.5 %, and 90.8 % in terms of sensitivity, specificity, and the challenge's score, respectively for the detection of five arrhythmias when only one single ECG lead signals is used without any expert knowledge.

A Feature Selection Method Based on Shapley Value to False Alarm Reduction in ICUs A Genetic-Algorithm Approach

High false alarm rate in intensive care units (ICUs) has been identified as one of the most critical medical challenges in recent years. This often results in overwhelming the clinical staff by numerous false or unurgent alarms and decreasing the quality of care through enhancing the probability of missing true alarms as well as causing delirium, stress, sleep deprivation and depressed immune systems for patients. One major cause of false alarms in clinical practice is that the collected signals from different devices are processed individually to trigger an alarm, while there exists a considerable chance that the signal collected from one device is corrupted by noise or motion artifacts. In this paper, we propose a low-computational complexity yet accurate game-theoretic feature selection method which is based on a genetic algorithm that identifies the most informative biomarkers across the signals collected from various monitoring devices and can considerably reduce the rate of false alarms ¹.

An algorithm strategy for precise patient monitoring in a connected healthcare enterprise

This perspective paper describes the building elements for realizing a precise patient monitoring algorithm to fundamentally address the alarm fatigue problem. Alarm fatigue is well recognized but no solution has been widely successful. Physiologic patient monitors are responsible for the lion's share of alarms at the bedside, most of which are either false or non-actionable. Algorithms on patient monitors lack precision because they fail to leverage multivariate relationship among variables monitored, to integrate rich patient clinical information from electronic health record system, and to utilize temporal patterns in data streams. Therefore, a solution to patient monitor alarm fatigue is to open the black-box of patient monitors to integrate physiologic data with clinical data from EHR under a four-element algorithm strategy to be described in this paper. This strategy will be presented in this paper in the context of its current status as described in our prior publications.

Intensive Care Unit Telemedicine in the Era of Big Data, Artificial Intelligence, and Computer Clinical Decision Support Systems

This article examines the history of the telemedicine intensive care unit (tele-ICU), the current state of clinical decision support systems (CDSS) in the tele-ICU, applications of machine learning (ML) algorithms to critical care, and opportunities to integrate ML with tele-ICU CDSS. The enormous quantities of data generated by tele-ICU systems is a major driver in the development of the large, comprehensive, heterogeneous, and granular data sets necessary to develop generalizable ML CDSS algorithms, and deidentification of these data sets expands opportunities for ML CDSS research.

A novel method to quantify arterial pulse waveform morphology: attractor reconstruction for physiologists and clinicians

Current arterial pulse monitoring systems capture data at high frequencies (100-1000 Hz). However, they typically report averaged or low frequency summary data such as heart rate and systolic, mean and diastolic blood pressure. In doing so, a potential wealth of information contained in the high-fidelity waveform data is discarded, data which has long been known to contain useful information on cardiovascular performance. Here we summarise a new mathematical method, attractor reconstruction, which enables the quantification of arterial waveform shape and variability in real-time. The method can handle long streams of non-stationary data and does not require preprocessing of the raw physiological data by the end user. Whilst the detailed mathematical proofs have been described elsewhere (Aston et al 2008 Physiol. Meas. 39), the authors were motivated to write a summary of the method and its potential utility for biomedical researchers, physiologists and clinician readers. Here we illustrate how this new method may supplement and potentially enhance the sensitivity of detecting cardiovascular disturbances, to aid with biomedical research and clinical decision making.

Representation Learning Approaches to Detect False Arrhythmia Alarms from ECG Dynamics

The high rate of intensive care unit false arrhythmia alarms can lead to disruption of care and slow response time due to desensitization of clinical staff. We study the use of machine learning models to detect false ventricular tachycardia (v-tach) alarms using ECG waveform recordings. We propose using a Supervised Denoising Autoencoder (SDAE) to detect false alarms using a low-dimensional representation of ECG dynamics learned by minimizing a combined reconstruction and classification loss. We evaluate our algorithms on the PhysioNet Challenge 2015 dataset, containing over 500 records (over 300 training and 200 testing) with v-tach alarms. Our results indicate that using the SDAE on Fast Fourier Transformed (FFT) ECG at a beat-by-beat level outperforms several competitive baselines on the task of v-tach false alarm classification. We show that it is important to exploit the underlying known physiological structure using beat-by-beat frequency distribution from multiple cardiac cycles of the ECG waveforms to obtain competitive results and improve over previous entries from the 2015 PhysioNet Challenge.

Game Theoretic Approach for Systematic Feature Selection; Application in False Alarm Detection in Intensive Care Units

Intensive Care Units (ICUs) are equipped with many sophisticated sensors and monitoring devices to provide the highest quality of care for critically ill patients. However, these devices might generate false alarms that reduce standard of care and result in desensitization of caregivers to alarms. Therefore, reducing the number of false alarms is of great importance. Many approaches such as signal processing and machine learning, and designing more accurate sensors have been developed for this purpose. However, the significant intrinsic correlation among the extracted features from different sensors has been mostly overlooked. A majority of current data mining techniques fail to capture such correlation among the collected signals from different sensors that limits their alarm recognition capabilities. Here, we propose a novel information-theoretic predictive modeling technique based on the idea of coalition game theory to enhance the accuracy of false alarm detection in ICUs by accounting for the synergistic power of signal attributes in the feature selection stage. This approach brings together techniques from information theory and game theory to account for inter-features mutual information in determining the most correlated predictors with respect to false alarm by calculating Banzhaf power of each feature. The numerical results show that the proposed method can enhance classification accuracy and improve the area under the ROC (receiver operating characteristic) curve compared to other feature selection techniques, when integrated in classifiers such as Bayes-Net that consider inter-features dependencies.

Implementation and Operational Analysis of an Interactive Intensive Care Unit within a Smart Health Context

In the context of hospital management and operation, Intensive Care Units (ICU) are one of the most challenging in terms of time responsiveness and criticality, in which adequate resource management and signal processing play a key role in overall system performance. In this work, a context aware Intensive Care Unit is implemented and analyzed to provide scalable signal acquisition capabilities, as well as to provide tracking and access control. Wireless channel analysis is performed by means of hybrid optimized 3D Ray Launching deterministic simulation to assess potential interference impact as well as to provide required coverage/capacity thresholds for employed transceivers. Wireless system operation within the ICU scenario, considering conventional transceiver operation, is feasible in terms of quality of service for the complete scenario. Extensive measurements of overall interference levels have also been carried out, enabling subsequent adequate coverage/capacity estimations, for a set of Zigbee based nodes. Real system operation has been tested, with ad-hoc designed Zigbee wireless motes, employing lightweight communication protocols to minimize energy and bandwidth usage. An ICU information gathering application and software architecture for Visitor Access Control has been implemented, providing monitoring of the Boxes external doors and the identification of visitors via a RFID system. The results enable a solution to provide ICU access control and tracking capabilities previously not exploited, providing a step forward in the implementation of a Smart Health framework.

Measurement of Physiological Monitor Alarm Accuracy and Clinical Relevance in Intensive Care Units

BACKGROUND

Alarm fatigue threatens patient safety by delaying or reducing clinician response to alarms, which can lead to missed critical events. Interventions to reduce alarms without jeopardizing patient safety target either inaccurate or clinically irrelevant alarms, so assessment of alarm accuracy and clinical relevance may enhance the rigor of alarm intervention studies done in clinical units.

OBJECTIVES

To (1) examine approaches used to measure accuracy and/or clinical relevance of physiological monitor alarms in intensive care units and (2) compare the proportions of inaccurate and clinically irrelevant alarms.

METHODS

An integrative review was used to systematically search the literature and synthesize resulting articles.

RESULTS

Twelve studies explicitly measuring alarm accuracy and/or clinical relevance on a clinical unit were identified. In the most rigorous studies, alarms were annotated retrospectively by obtaining alarm data and parameter waveforms rather than being annotated in real time. More than half of arrhythmia alarms in recent studies were inaccurate. However, contextual data were needed to determine alarms' clinical relevance. Proportions of clinically irrelevant alarms were high, but definitions of clinically irrelevant alarms often included inaccurate alarms.

CONCLUSIONS

Future studies testing interventions on clinical units should include alarm accuracy and/or clinical relevance as outcome measures. Arrhythmia alarm accuracy should improve with advances in technology. Clinical interventions should focus on reducing clinically irrelevant alarms, with careful consideration of how clinical relevance is defined and measured.

Non-invasive Fetal ECG Signal Quality Assessment for Multichannel Heart Rate Estimation

OBJECTIVE

The noninvasive fetal ECG (NI-FECG) from abdominal recordings offers novel prospects for prenatal monitoring. However, NI-FECG signals are corrupted by various nonstationary noise sources, making the processing of abdominal recordings a challenging task. In this paper, we present an online approach that dynamically assess the quality of NI-FECG to improve fetal heart rate (FHR) estimation.

METHODS

Using a naive Bayes classifier, state-of-the-art and novel signal quality indices (SQIs), and an existing adaptive Kalman filter, FHR estimation was improved. For the purpose of training and validating the proposed methods, a large annotated private clinical dataset was used.

RESULTS

The suggested classification scheme demonstrated an accuracy of Krippendorff's alpha in determining the overall quality of NI-FECG signals. The proposed Kalman filter outperformed alternative methods for FHR estimation achieving accuracy.

CONCLUSION

The proposed algorithm was able to reliably reflect changes of signal quality and can be used in improving FHR estimation.

SIGNIFICANCE

NI-ECG signal quality estimation and multichannel information fusion are largely unexplored topics. Based on previous works, multichannel FHR estimation is a field that could strongly benefit from such methods. The developed SQI algorithms as well as resulting classifier were made available under a GNU GPL open-source license and contributed to the FECGSYN toolbox.

Reducing false alarms in the ICU by quantifying self-similarity of multimodal biosignals

False arrhythmia alarms pose a major threat to the quality of care in today's ICU. Thus, the PhysioNet/Computing in Cardiology Challenge 2015 aimed at reducing false alarms by exploiting multimodal cardiac signals recorded by a patient monitor. False alarms for asystole, extreme bradycardia, extreme tachycardia, ventricular flutter/fibrillation as well as ventricular tachycardia were to be reduced using two electrocardiogram channels, up to two cardiac signals of mechanical origin as well as a respiratory signal. In this paper, an approach combining multimodal rhythmicity estimation and machine learning is presented. Using standard short-time autocorrelation and robust beat-to-beat interval estimation, the signal's self-similarity is analyzed. In particular, beat intervals as well as quality measures are derived which are further quantified using basic mathematical operations (min, mean, max, etc). Moreover, methods from the realm of image processing, 2D Fourier transformation combined with principal component analysis, are employed for dimensionality reduction. Several machine learning approaches are evaluated including linear discriminant analysis and random forest. Using an alarm-independent reduction strategy, an overall false alarm reduction with a score of 65.52 in terms of the real-time scoring system of the challenge is achieved on a hidden dataset. Employing an alarm-specific strategy, an overall real-time score of 78.20 at a true positive rate of 95% and a true negative rate of 78% is achieved. While the results for some categories still need improvement, false alarms for extreme tachycardia are suppressed with 100% sensitivity and specificity.