Figure - available via license: CC BY
Content may be subject to copyright.
Source publication
Background:
Chest pain is one of the most common complaints among patients presenting to the emergency department (ED). Causes of chest pain can be benign or life threatening, making accurate risk stratification a critical issue in the ED. In addition to the use of established clinical scores, prior studies have attempted to create predictive mode...
Contexts in source publication
Context 1
... analyses of HRV and HRnV parameters are tabulated in Table 2. In this clinical case study, N was set as 3, thus HR 2 V, HR 2 V 1 , HR 3 V, HR 3 V 1 and HR 3 V 2 parameters were calculated. ...Context 2
... since HRnV is a novel representation of beat-to-beat variations in ECG, many technical issues need to be addressed in future research. For instance, as shown in Table 2, SampEn became larger when the available number of data points was less than 200 [19], suggesting that additional research is required to investigate its applicability to short ECG records. Moreover, parameters NN50n and pNN50n are newly introduced in HRnV representation only. ...Similar publications
Aim: In this study, we aimed to evaluate the ability of the CHA2DS2-VASc-HSF score to predict short-term prognosis in acute coronary syndrome (ACS) patients. Material and Methods: A total of 167 patients who underwent coronary angiography were included in this retrospective study. The patients were divided into two groups according to CHA2DS2-VASc-...
Citations
... entropy) describes the level of apparent disorder within a system. Low signal complexity predicts unfavorable outcome in a variety of diseases and is assumed to reflect increased rigidity of the cardio/cerebrovascular feedback/regulating system leading to (or reflecting) autoregulation failure [9][10][11][12] This, in turn, leaves the brain susceptible to secondary injury. Physiological systems are regulated by multiple, interacting, mechanisms leading to dynamically changing biosignals across different temporal scales. ...
Background: Signal complexity (i.e. entropy) describes the level of order within a system. Low physiological signal complexity predicts unfavorable outcome in a variety of diseases and is assumed to reflect increased rigidity of the cardio/cerebrovascular system leading to (or reflecting) autoregulation failure. Aneurysmal subarachnoid hemorrhage (aSAH) is followed by a cascade of complex systemic and cerebral sequelae. In aSAH, the value of entropy has not been established yet.
Methods: aSAH patients from 2 prospective cohorts (Zurich—derivation cohort, Aachen—validation cohort) were included. Multiscale Entropy (MSE) was estimated for arterial blood pressure, intracranial pressure, heart rate, and their derivatives, and compared to dichotomized (1–4 vs. 5–8) or ordinal outcome (GOSE—extended Glasgow Outcome Scale) at 12 months using uni- and multivariable (adjusted for age, World Federation of Neurological Surgeons grade, modified Fisher (mFisher) grade, delayed cerebral infarction), and ordinal methods (proportional odds logistic regression/sliding dichotomy). The multivariable logistic regression models were validated internally using bootstrapping and externally by assessing the calibration and discrimination.
Results: A total of 330 (derivation: 241, validation: 89) aSAH patients were analyzed. Decreasing MSE was associated with a higher likelihood of unfavorable outcome independent of covariates and analysis method. The multivariable adjusted logistic regression models were well calibrated and only showed a slight decrease in discrimination when assessed in the validation cohort. The ordinal analysis revealed its effect to be linear. MSE remained valid when adjusting the outcome definition against the initial severity.
Conclusions: MSE metrics and thereby complexity of physiological signals are independent, internally and externally valid predictors of 12-month outcome. Incorporating high-frequency physiological data as part of clinical outcome prediction may enable precise, individualized outcome prediction. The results of this study warrant further investigation into the cause of the resulting complexity as well as its association to important and potentially preventable complications including vasospasm and delayed cerebral ischemia.
... The multiscale entropy (MSE) metrics (Costa et al., 2002) calculate SampEn on multiscale coarse-gained series derived from RRI to reflect the nonlinear behavior of the heart on multiple time scales. To generalize the averaging multiscale approach, N. Liu et al. (2020) proposed heart rate n-variability (HRnV) that utilizes sliding and stridden summation windows over RRI to obtain new RRI-like intervals denoted as and . Using these novel RRI representations, new HRnV metrics can be calculated with conventional HRV analysis metrics, providing an entire family of new metrics, and potentially additional insights into the dynamics and long-term dependencies of the original RRI, making HRnV complementary to the conventional HRV analysis. ...
... Research has shown that HRnV improves the accuracy of triage for patients with chest pain (N. Liu et al., 2020) and sepsis (N. Liu et al., 2021). ...
... With wearable IoT devices becoming more common, model inputs such as ECGs, vital signs, and potentially EHR will also become more readily accessible. With these rich information sources, there is significant potential for applying advanced AI and ML (121,122) and novel physiological measures (123) for remote continuous monitoring. However, such IoT systems are nascent and require further validation in larger datasets and real-world contexts. ...
Introduction: The literature on the use of AI in prehospital emergency care (PEC) settings is scattered and diverse, making it difficult to understand the current state of the field. In this scoping review, we aim to provide a descriptive analysis of the current literature and to visualise and identify knowledge and methodological gaps using an evidence map.
Methods: We conducted a scoping review from inception until 14 December 2021 on MEDLINE, Embase, Scopus, IEEE Xplore, ACM Digital Library, and Cochrane Central Register of Controlled Trials (CENTRAL). We included peer-reviewed, original studies that applied AI to prehospital data, including applications for cardiopulmonary resuscitation (CPR), automated external defibrillation (AED), out-of-hospital cardiac arrest, and emergency medical service (EMS) infrastructure like stations and ambulances.
Results: The search yielded 4350 articles, of which 106 met the inclusion criteria. Most studies were retrospective (n=88, 83.0%), with only one (0.9%) randomised controlled trial. Studies were mostly internally validated (n=96, 90.6%), and only ten studies (9.4%) reported on calibration metrics. While the most studied AI applications were Triage/Prognostication (n=52, 49.1%) and CPR/AED optimisation (n=26, 24.5%), a few studies reported unique use cases of AI such as patient-trial matching for research and Internet-of-Things (IoT) wearables for continuous monitoring. Out of 49 studies that identified a comparator, 39 reported AI performance superior to either clinicians or non-AI status quo algorithms. The minority of studies utilised multimodal inputs (n=37, 34.9%), with few models using text (n=8), audio (n=5), images (n=1), or videos (n=0) as inputs.
Conclusion: AI in PEC is a growing field and several promising use cases have been reported, including prognostication, demand prediction, resource optimisation, and IoT continuous monitoring systems. Prospective, externally validated studies are needed before applications can progress beyond the proof-of-concept stage to real-world clinical settings.
... Heart rate n-variability (HRnV), constructs new signals based on the R-to-R peak intervals (RRI) used in the conventional HRV analysis. It was more recently invented as a novel tool to augment the number of calculated parameters from the same segment of signals, with the potential to enhance the prognostic information provided by traditional HRV parameters (26,27). ...
... HRnV is a novel complementary method to the conventional HRV analysis (26). HRnV constructs new signals based on the RRI used in the conventional HRV analysis, called RRnIs. ...
... The variables were determined after reviewing known predictors in the literature, as well as availability of these data at ED triage and then at consultation. Collinearities (squared Pearson's correlation coefficient bigger than 0.85) were removed before conducting multivariable regression, due to known correlations among HRV and HRnV parameters (26). We described performance of the model using area under curve (AUC) analysis, with corresponding 95% CIs. ...
Background:
We aim to investigate the utility of heart rate variability (HRV) and heart rate n-variability (HRnV) in addition to vital signs and blood biomarkers, among febrile young infants at risk of serious bacterial infections (SBIs).
Methods:
We performed a prospective observational study between December 2017 and November 2021 in a tertiary paediatric emergency department (ED). We included febrile infants <90 days old with a temperature ≥38 ℃. We obtained HRV and HRnV parameters via a single lead electrocardiogram. HRV measures beat-to-beat (R-R) oscillation and reflects autonomic nervous system (ANS) regulation. HRnV includes overlapping and non-overlapping R-R intervals and provides additional physiological information. We defined SBIs as meningitis, bacteraemia and urinary tract infections (UTIs). We performed area under curve (AUC) analysis to assess predictive performance.
Results:
We recruited 330 and analysed 312 infants. The median age was 35.5 days (interquartile range 13.0-61.0); 74/312 infants (23.7%) had SBIs with the most common being UTIs (66/72, 91.7%); 2 infants had co-infections. No patients died and 32/312 (10.3%) received fluid resuscitation. Adding HRV and HRnV to demographics and vital signs at ED triage successively improved the AUC from 0.765 [95% confidence interval (CI): 0.705-0.825] to 0.776 (95% CI: 0.718-0.835) and 0.807 (95% CI: 0.752-0.861) respectively. The final model including demographics, vital signs, HRV, HRnV and blood biomarkers had an AUC of 0.874 (95% CI: 0.828-0.921).
Conclusions:
Addition of HRV and HRnV to current assessment tools improved the prediction of SBIs among febrile infants at ED triage. We intend to validate our findings and translate them into tools for clinical care in the ED.
... This growth has caused ED crowding 2 and delays in care delivery 3 , resulting in increased morbidity and mortality 4 . Prediction models [5][6][7][8][9] provide opportunities for identifying high-risk patients and prioritizing limited medical resources. ED prediction models center on risk stratification, which is a complex clinical judgment based on factors such as patient's likely acute course, availability of medical resources, and local practices 10 . ...
The demand for emergency department (ED) services is increasing across the globe, particularly during the current COVID-19 pandemic. Clinical triage and risk assessment have become increasingly challenging due to the shortage of medical resources and the strain on hospital infrastructure caused by the pandemic. As a result of the widespread use of electronic health records (EHRs), we now have access to a vast amount of clinical data, which allows us to develop prediction models and decision support systems to address these challenges. To date, there is no widely accepted clinical prediction benchmark related to the ED based on large-scale public EHRs. An open-source benchmark data platform would streamline research workflows by eliminating cumbersome data preprocessing, and facilitate comparisons among different studies and methodologies. Based on the Medical Information Mart for Intensive Care IV Emergency Department (MIMIC-IV-ED) database, we created a benchmark dataset and proposed three clinical prediction benchmarks. This study provides future researchers with insights, suggestions, and protocols for managing data and developing predictive tools for emergency care.
... This growth has caused ED crowding 2 and delays in care delivery 3 , resulting in higher morbidity and mortality 4 . ED triage models [5][6][7][8] provided opportunities for identifying high-risk patients with the prioritization of limited medical resources. Risk stratification is a complex clinical judgment 9 based on the tacit understanding of the patient's likely acute course, availability of medical resources, and local practices. ...
There is a continuously growing demand for emergency department (ED) services across the world, especially under the COVID-19 pandemic. Risk triaging plays a crucial role in prioritizing limited medical resources for patients who need them most. Recently the pervasive use of Electronic Health Records (EHR) has generated a large volume of stored data, accompanied by vast opportunities for the development of predictive models which could improve emergency care. However, there is an absence of widely accepted ED benchmarks based on large-scale public EHR, which new researchers could easily access. Success in filling in this gap could enable researchers to start studies on ED more quickly and conveniently without verbose data preprocessing and facilitate comparisons among different studies and methodologies. In this paper, based on the Medical Information Mart for Intensive Care IV Emergency Department (MIMIC-IV-ED) database, we proposed a public ED benchmark suite and obtained a benchmark dataset containing over 500,000 ED visits episodes from 2011 to 2019. Three ED-based prediction tasks (hospitalization, critical outcomes, and 72-hour ED revisit) were introduced, where various popular methodologies, from machine learning methods to clinical scoring systems, were implemented. The results of their performance were evaluated and compared. Our codes are open-source so that anyone with access to MIMIC-IV-ED could follow the same steps of data processing, build the benchmarks, and reproduce the experiments. This study provided insights, suggestions, as well as protocols for future researchers to process the raw data and quickly build up models for emergency care.
... The multiscale entropy (MSE) metrics [30] calculate SampEn on multiscale coarse-gained series derived from RRI to reflect the nonlinear behavior of the heart on multiple time scales. To generalize the averaging multiscale approach, Liu et al. [31] proposed heart rate n-variability (HRnV) that utilizes sliding and stridden summation windows over RRI to obtain new RRI-like intervals denoted and . Using these novel RRI representations, new HRnV metrics can be calculated with conventional HRV analysis metrics, providing an entire family of new metrics, and potentially additional insights into the dynamics and long-term dependencies of the original RRI. ...
... Using these novel RRI representations, new HRnV metrics can be calculated with conventional HRV analysis metrics, providing an entire family of new metrics, and potentially additional insights into the dynamics and long-term dependencies of the original RRI. For example, research has shown that HRnV improves the accuracy of triage for patients with chest pain [31] and sepsis [32]. ...
... Moreover, with the exception of two open-source toolboxes, none of the available tools provide equivalent results, making comparisons between research impossible [38]. Since HRnV shares some common processing methods with conventional HRV analysis [31], it is natural to develop a HRnV platform based on existing benchmarked software. We therefore developed an open-source HRnV software, HRnV-Calc, based on the PhysioNet Cardiovascular Signal Toolbox (PCST) [38]. ...
Objective: Heart rate variability (HRV) has been proven to be an important indicator of physiological status for numerous applications. Despite the progress and active developments made in HRV metric research over the last few decades, the representation of the heartbeat sequence upon which HRV is based has received relatively little attention. The recently introduced heart rate n-variability (HRnV) offers an alternative to R-to-R peak interval representations which complements conventional HRV analysis by considering HRV behavior on varying scales. Although HRnV has been shown to improve triage in pilot studies, there is currently no open and standard software to support future research of HRnV and its broader clinical applications. We aimed to develop an open, reliable, and easy to use software package implementing HRnV for further research and improvements of HRnV. This package has been designed to facilitate collaborative investigations between clinicians and researchers to study HRnV in various contexts and applications. Approach: We developed an open-source software, HRnV-Calc, based on the PhysioNet Cardiovascular Signal Toolbox (PCST), which features comprehensive graphical user interfaces (GUIs) for HRnV and HRV analysis. Main results: While preserving the core functionalities and performance of PCST, HRnV-Calc enables step-by-step manual inspection and configuration of HRV and HRnV analysis, so that results can be debugged, easily interpreted, and integrated to downstream applications. Significance: The open-source HRnV-Calc software, an accessible and standardized HRV and HRnV analysis platform, enhances the scope of HRV assessment and is designed to assist in future improvements and applications of HRnV and related research.
... Fourthly, we did not capture other clinical features, such as heart rate variability (HRV). The HRV has been regarded as a promising predictor that is recognized to have a significant relationship between the autonomic nervous system and cardiovascular mortality [30,[33][34][35]. Due to the complicated estimation, time consuming procedure, and unsuitability with non-sinus rhythm [35], HRV has not been widely used clinically, especially in the developing country, and thus, was not included in the present study. ...
Background
Currently, the risk stratification of critically ill patient with chest pain is a challenge. We aimed to use machine learning approach to predict the critical care outcomes in patients with chest pain, and simultaneously compare its performance with HEART, GRACE, and TIMI scores.
Methods
This was a retrospective, case-control study in patients with acute non-traumatic chest pain who presented to the emergency department (ED) between January 2017 and December 2019. The outcomes included cardiac arrest, transfer to ICU, and death during treatment in ED. In the randomly sampled training set (70%), a LASSO regression model was developed, and presented with nomogram. The performance was measured in both training set (70% participants) and testing set (30% participants), and findings were compared with the three widely used scores.
Results
We proposed a LASSO regression model incorporating mode of arrival, reperfusion therapy, Killip class, systolic BP, serum creatinine, creatine kinase-MB, and brain natriuretic peptide as independent predictors of critical care outcomes in patients with chest pain. Our model significantly outperformed the HEART, GRACE, TIMI score with AUC of 0.953 (95%CI: 0.922–0.984), 0.754 (95%CI: 0.675–0.832), 0.747 (95%CI: 0.664–0.829), 0.735 (95%CI: 0.655–0.815), respectively. Consistently, our model demonstrated better outcomes regarding the metrics of accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1 score. Similarly, the decision curve analysis elucidated a greater net benefit of our model over the full ranges of clinical thresholds.
Conclusion
We present an accurate model for predicting the critical care outcomes in patients with chest pain, and provide substantial support to its application as a decision-making tool in ED.
... In our previous work [20], we invented novel heart rate n-variability (HRnV) parameters to provide enhanced prognostic information to complement traditional HRV parameters. The proposed HRnV has two measures-HR n V and HR n V m . ...
... For each of the traditional HRV, HR n V, and HR n V m measures, time domain, frequency domain, and nonlinear analysis will yield its respective set of parameters. An application of the novel HRnV variables demonstrated improved predictive ability for major adverse cardiac events among patients with chest pain presenting at the ED [20]. ...
... Conventional HRV analysis evaluates consecutive single RRIs in ECGs. Novel HRnV measures (HR n V and HR n V m ) analyse consecutive combined RRIs (RR n I and RR n I m ) [20]. ...
Sepsis is a potentially life-threatening condition that requires prompt recognition and treatment. Recently, heart rate variability (HRV), a measure of the cardiac autonomic regulation derived from short electrocardiogram tracings, has been found to correlate with sepsis mortality. This paper presents using novel heart rate n-variability (HRnV) measures for sepsis mortality risk prediction and comparing against current mortality prediction scores. This study was a retrospective cohort study on patients presenting to the emergency department of a tertiary hospital in Singapore between September 2014 to April 2017. Patients were included if they were above 21 years old and were suspected of having sepsis by their attending physician. The primary outcome was 30-day in-hospital mortality. Stepwise multivariable logistic regression model was built to predict the outcome, and the results based on 10-fold cross-validation were presented using receiver operating curve analysis. The final predictive model comprised 21 variables, including four vital signs, two HRV parameters, and 15 HRnV parameters. The area under the curve of the model was 0.77 (95% confidence interval 0.70–0.84), outperforming several established clinical scores. The HRnV measures may have the potential to allow for a rapid, objective, and accurate means of patient risk stratification for sepsis severity and mortality. Our exploration of the use of wealthy inherent information obtained from novel HRnV measures could also create a new perspective for data scientists to develop innovative approaches for ECG analysis and risk monitoring.
... Although physicians can generally ascertain the severity of a patient's acute condition Like the Emergency Severity Index, 31 some triage scores may achieve better performance in risk estimation but require some subjective variables. Some recent studies [32][33][34] highlighted the role of data-driven, objective clinical decision tools to help physicians rethink and reassess the triage process in the ED. Because our SERP scores only comprise objective elements, they can be easily computed by trained medical assistants or integrated into an existing hospital EHR, without the need for professional medical personnel. ...
Importance
Triage in the emergency department (ED) is a complex clinical judgment based on the tacit understanding of the patient’s likelihood of survival, availability of medical resources, and local practices. Although a scoring tool could be valuable in risk stratification, currently available scores have demonstrated limitations.
Objectives
To develop an interpretable machine learning tool based on a parsimonious list of variables available at ED triage; provide a simple, early, and accurate estimate of patients’ risk of death; and evaluate the tool’s predictive accuracy compared with several established clinical scores.
Design, Setting, and Participants
This single-site, retrospective cohort study assessed all ED patients between January 1, 2009, and December 31, 2016, who were subsequently admitted to a tertiary hospital in Singapore. The Score for Emergency Risk Prediction (SERP) tool was derived using a machine learning framework. To estimate mortality outcomes after emergency admissions, SERP was compared with several triage systems, including Patient Acuity Category Scale, Modified Early Warning Score, National Early Warning Score, Cardiac Arrest Risk Triage, Rapid Acute Physiology Score, and Rapid Emergency Medicine Score. The initial analyses were completed in October 2020, and additional analyses were conducted in May 2021.
Main Outcomes and Measures
Three SERP scores, namely SERP-2d, SERP-7d, and SERP-30d, were developed using the primary outcomes of interest of 2-, 7-, and 30-day mortality, respectively. Secondary outcomes included 3-day mortality and inpatient mortality. The SERP’s predictive power was measured using the area under the curve in the receiver operating characteristic analysis.
Results
The study included 224 666 ED episodes in the model training cohort (mean [SD] patient age, 63.60 [16.90] years; 113 426 [50.5%] female), 56 167 episodes in the validation cohort (mean [SD] patient age, 63.58 [16.87] years; 28 427 [50.6%] female), and 42 676 episodes in the testing cohort (mean [SD] patient age, 64.85 [16.80] years; 21 556 [50.5%] female). The mortality rates in the training cohort were 0.8% at 2 days, 2.2% at 7 days, and 5.9% at 30 days. In the testing cohort, the areas under the curve of SERP-30d were 0.821 (95% CI, 0.796-0.847) for 2-day mortality, 0.826 (95% CI, 0.811-0.841) for 7-day mortality, and 0.823 (95% CI, 0.814-0.832) for 30-day mortality and outperformed several benchmark scores.
Conclusions and Relevance
In this retrospective cohort study, SERP had better prediction performance than existing triage scores while maintaining easy implementation and ease of ascertainment in the ED. It has the potential to be widely applied and validated in different circumstances and health care settings.
