A contrastive learning approach for ICU false arrhythmia alarm reduction

Forecasting Treatment Outcomes Over Time Using Alternating Deep Sequential Models

Medical decision making often relies on accurately forecasting future patient trajectories. Conventional approaches for patient progression modeling often do not explicitly model treatments when predicting patient trajectories and outcomes. In this paper, we propose Alternating Transformer (AL-Transformer) to jointly model treatment and clinical outcomes over time as alternating sequential models. We leverage causal convolution in the self-attention mechanism of AL-Transformer to incorporate local spatial information in the sequence, thus enhancing the model's ability to capture local contextual information of the sequence. Additionally, to predict the sparse treatment, a constraint learned by a convolutional neural network (CNN) is used to constrain the sparse treatment output. Experimental results on two datasets from patients with sepsis and respiratory failure extracted from the Medical Information Mart for Intensive Care (MIMIC) database demonstrate the effectiveness of the proposed approach, outperforming existing state-of-the-art methods.

Performance comparison of 6 in-hospital patient monitoring systems in the detection and alarm of ventricular cardiac arrhythmias

Background

Patient monitoring devices are critical for alerting of potential cardiac arrhythmias during hospitalization; however, there are concerns of alarm fatigue due to high false alarm rates.

Objective

The purpose of this study was to evaluate the sensitivity and false alarm rate of hospital-based continuous electrocardiographic (ECG) monitoring technologies.

Methods

Six commonly used multiparameter bedside monitoring systems available in the United States were evaluated: B125M (GE HealthCare), ePM10 and iPM12 (Mindray), Efficia and IntelliVue (Philips), and Life Scope (Nihon Kohden). Sensitivity was tested using ECG recordings containing 57 true ventricular tachycardia (VT) events. False-positive rate testing used 205 patient-hours of ECG recordings containing no cardiac arrhythmias. Signals from ECG recordings were fed to devices simultaneously; high-severity arrhythmia alarms were tracked. Sensitivity to true VT events and false-positive rates were determined. Differences were assessed using Fisher exact tests (sensitivity) and Z-tests (false-positive rates).

Results

B125M raised 56 total alarms for 57 annotated VT events and had the highest sensitivity (98%; P <.05), followed by iPM12 (84%), Life Scope (81%), Efficia (79%), ePM10 (77%), and IntelliVue (75%). B125M raised 20 false alarms, which was significantly lower (P <.0001) than iPM12 (284), Life Scope (292), IntelliVue (304), ePM10 (324), and Efficia (493). The most common false alarm was VT, followed by nonsustained VT.

Conclusion

We found significant performance differences among multiparameter bedside ECG monitoring systems using previously collected recordings. B125M had the highest sensitivity in detecting true VT events and lowest false alarm rate. These results can assist in minimizing alarm fatigue and optimizing patient safety by careful selection of in-hospital continuous monitoring technology.

A customised down-sampling machine learning approach for sepsis prediction

OBJECTIVE

Sepsis is a life-threatening condition in the ICU and requires treatment in time. Despite the accuracy of existing sepsis prediction models, insufficient focus on reducing alarms could worsen alarm fatigue and desensitisation in ICUs, potentially compromising patient safety. In this retrospective study, we aim to develop an accurate, robust, and readily deployable method in ICUs, only based on the vital signs and laboratory tests.

METHODS

Our method consists of a customised down-sampling process and a specific dynamic sliding window and XGBoost to offer sepsis prediction. The down-sampling process was applied to the retrospective data for training the XGBoost model. During the testing stage, the dynamic sliding window and the trained XGBoost were used to predict sepsis on the retrospective datasets, PhysioNet and FHC.

RESULTS

With the filtered data from PhysioNet, our method achieved 80.74% accuracy (77.90% sensitivity and 84.42% specificity) and 83.95% (84.82% sensitivity and 82.00% specificity) on the test set of PhysioNet-A and PhysioNet-B, respectively. The AUC score was 0.89 for both datasets. On the FHC dataset, our method achieved 92.38% accuracy (88.37% sensitivity and 95.16% specificity) and 0.98 AUC score on the test set of FHC.

CONCLUSION

Our results indicate that the down-sampling process and the dynamic sliding window with XGBoost brought robust and accurate performance to give sepsis prediction under various hospital settings. The localisation and robustness of our method can assist in sepsis diagnosis in different ICU settings.

In-Distribution and Out-of-Distribution Self-Supervised ECG Representation Learning for Arrhythmia Detection

This paper presents a systematic investigation into the effectiveness of Self-Supervised Learning (SSL) methods for Electrocardiogram (ECG) arrhythmia detection. We begin by conducting a novel analysis of the data distributions on three popular ECG-based arrhythmia datasets: PTB-XL, Chapman, and Ribeiro. To the best of our knowledge, our study is the first to quantitatively explore and characterize these distributions in the area. We then perform a comprehensive set of experiments using different augmentations and parameters to evaluate the effectiveness of various SSL methods, namely SimCRL, BYOL, and SwAV, for ECG representation learning, where we observe the best performance achieved by SwAV. Furthermore, our analysis shows that SSL methods achieve highly competitive results to those achieved by supervised state-of-the-art methods. To further assess the performance of these methods on both In-Distribution (ID) and Out-of-Distribution (OOD) ECG data, we conduct cross-dataset training and testing experiments. Our comprehensive experiments show almost identical results when comparing ID and OOD schemes, indicating that SSL techniques can learn highly effective representations that generalize well across different OOD datasets. This finding can have major implications for ECG-based arrhythmia detection. Lastly, to further analyze our results, we perform detailed per-disease studies on the performance of the SSL methods on the three datasets.

Standard practices in cardiac monitoring: training needs of intensive care unit nurses

BACKGROUND

Enforcing practice standards for cardiac monitoring in intensive care units (ICUs) has been shown to reduce misdiagnoses and inappropriate interventions. Continuous professional development (CPD) programs are committed to aligning clinical practices with recommended standards. The crucial initial phase in CPD development involves assessing the training needs of the targeted population.

OBJECTIVE

To assess the training needs of ICU nurses in cardiac monitoring. The overarching goal was to formulate a focused Continuous Professional Development (CPD) program geared towards implementing standard practices in cardiac monitoring.

METHODS

This study employed a generic qualitative approach with a descriptive design, utilizing interviews and focus groups from July to September 2018. Involving 16 ICU nurses. Content analysis was employed, encompassing transcription, fluctuant and iterative reading, unitization, categorization, coding, description, and interpretation.

RESULTS

All nurses recognized cardiac monitoring's importance in the ICU but reported barriers to its effective implementation which were related to factors that could addressed by a CPD as insufficient knowledge and skills. Training needs were identified in both clinical and technical aspects, with recommendations for practical and theoretical activities and e-learning strategies. Barriers related to organizational aspects (equipment and communication within the healthcare team) were also mentioned.

CONCLUSION

ICU nurses presented clear and specific training needs related to cardiac monitoring as knowledge, skills, and competencies. Other organizational aspects were also reported as barriers. Addressing these learning needs through targeted CPD aligned with organizational initiatives can contribute to enhancing the quality of cardiac monitoring practices in ICUs.