Prediction Of Cardiac Arrest Research Articles

Cardiovascular disease prediction using hyperparameters-tuned LSTM considering COVID-19 with experimental validation

<abstract> <p>Heart disease, globally recognized as a leading cause of death, has seen its impact magnified by the emergence of COVID-19. The heightened demand for early detection and diagnosis of heart disease has forced the development of innovative, intelligent systems. This research offers a novel approach by leveraging extended short-term memory networks (LSTM) and including COVID-19 as a significant parameter in cardiac arrest analysis. A comparative study is conducted between LSTM and other prevalent techniques, such as support vector machines (SVM), linear regression (LR), and artificial neural networks (ANN), focusing on accuracy and other prognostic criteria for heart disease. We aim to develop an intelligent system powered by LSTM to predict heart disease, thereby assisting healthcare professionals in making well-informed decisions about heart disease management, stroke prevention, and patient monitoring. Additionally, hyperparameter tuning has been performed to optimize the LSTM model's performance in cardiac arrest prediction. The results underscore that LSTM, especially when trained with COVID-19 as an input parameter, surpasses other established techniques in prediction accuracy. The proposed model underwent experimental testing, showcasing its proficiency in predicting cardiovascular disease.</p> </abstract>

Evaluation of optimal scene time interval for out-of-hospital cardiac arrest using a deep neural network

AimThis study aims to develop a cardiac arrest prediction model using deep learning (CAPD) algorithm and to validate the developed algorithm by evaluating the change in out-of-hospital cardiac arrest patient prognosis according to the increase in scene time interval (STI). MethodsWe conducted a retrospective cohort study using smart advanced life support trial data collected by the National Emergency Center from January 2016 to December 2019. The smart advanced life support data were randomly partitioned into derivation and validation datasets. The performance of the CAPD model using the patient's age, sex, event witness, bystander cardiopulmonary resuscitation (CPR), administration of epinephrine, initial shockable rhythm, prehospital defibrillation, provision of advanced life support, response time interval, and STI as prediction variables for prediction of a patient's prognosis was compared with conventional machine learning methods. After fixing other values of the input data, the changes in prognosis of the patient with respect to the increase in STI was observed. ResultsA total of 16,992 patients were included in this study. The area under the receiver operating characteristic curve values for predicting prehospital return of spontaneous circulation (ROSC) and favorable neurological outcomes were 0.828 (95% confidence interval 0.826–0.830) and 0.907 (0.914–0.910), respectively. Our algorithm significantly outperformed other artificial intelligence algorithms and conventional methods. The neurological recovery rate was predicted to decrease to 1/3 of that at the beginning of cardiopulmonary resuscitation when the STI was 28 min, and the prehospital ROSC was predicted to decrease to 1/2 of its initial level when the STI was 30 min. ConclusionThe CAPD exhibits potential and effectiveness in identifying patients with ROSC and favorable neurological outcomes for prehospital resuscitation.

Prediction of Sudden Cardiac Arrest After Alcohol Septal Ablation for Hypertrophic Obstructive Cardiomyopathy: ASA-SCARRE Risk Score

This study aimed to derive a new score, the Alcohol Septal Ablation-Sudden Cardiac ARREst (ASA-SCARRE) risk score, that can be easily used to evaluate the risk of sudden cardiac arrest events (sudden cardiac death, resuscitation, or appropriate implantable cardioverter-defibrillator discharge) after alcohol septal ablation (ASA) in patients with hypertrophic obstructive cardiomyopathy. We analyzed 1,834 patients from the Euro-ASA registry (49% men, mean age 57 ± 14years) who were followed up for 5.0 ± 4.3years (9,202 patient-years) after ASA. A total of 65 patients (3.5%) experienced sudden cardiac arrest events, translating to 0.72 events per 100 patient-years. The independent predictors of sudden cardiac arrest events were septum thickness before ASA (hazard ratio 1.09 per 1mm, 95% confidence interval 1.04 to 1.14, p <0.001) and left ventricular outflow tract (LVOT) gradient at the last clinical checkup (hazard ratio 1.01 per 1mm Hg, 95% confidence interval 1.01 to 1.02, p=0.002). The following ASA-SCARRE risk scores were derived and independently predicted long-term risk of sudden cardiac arrest events: "0" for both LVOT gradient <30mmHg and baseline septum thickness <20mm; "1" for LVOT gradient ≥30mm Hg or baseline septum thickness ≥20mm; and "2" for both LVOT gradient ≥30mm Hg and baseline septum thickness ≥20mm. The C statistic of the ASA-SCARRE risk score was 0.684 (SE 0.030). In conclusion, the ASA-SCARRE risk score may be a useful and easily available clinical tool to predict risk of sudden cardiac arrest events after ASA in patients with hypertrophic obstructive cardiomyopathy.

Attempting cardiac arrest prediction using artificial intelligence on vital signs from Electronic Health Records

This work attempts to determine whether it is possible to predict the occurrence of in-hospital Cardiac Arrest (CA) using vital signs routinely recorded in a hospital's Electronic Health Record (EHR) system. The goal is to give caregivers advance notice of the possibility so they can intervene before its occurrence or prepare for immediate response in case it occurs. The work concentrates on three different aspects: which prediction model, which vital signs, and what time window produce the most accurate prediction. A number of experiments were conducted using six artificial intelligence algorithms and vital sign recordings ranging from 1 to 12 h. The work demonstrates that Random Forest produces the best prediction accuracy, reaching higher than 80%. Accuracy improves by more than 10% when prediction is done using vital sign data from the immediately preceding 60 min. Additionally, performance improves by only 3% when the observation range is increased from 1 h to 12 h.

Improved inpatient deterioration detection in general wards by using time-series vital signs

Although in-hospital cardiac arrest is uncommon, it has a high mortality rate. Risk identification of at-risk patients is critical for post-cardiac arrest survival rates. Early warning scoring systems are generally used to identify hospitalized patients at risk of deterioration. However, these systems often require clinical data that are not always regularly measured. We developed a more accurate, machine learning-based model to predict clinical deterioration. The time series early warning score (TEWS) used only heart rate, systolic blood pressure, and respiratory data, which are regularly measured in general wards. We tested the performance of the TEWS in two tasks performed with data from the electronic medical records of 16,865 adult admissions and compared the results with those of other classifications. The TEWS detected more deteriorations with the same level of specificity as the different algorithms did when inputting vital signs data from 48 h before an event. Our framework improved in-hospital cardiac arrest prediction and demonstrated that previously obtained vital signs data can be used to identify at-risk patients in real-time. This model may be an alternative method for detecting patient deterioration.

Early Changes in Near-Infrared Spectroscopy Are Associated With Cardiac Arrest in Children With Congenital Heart Disease.

BackgroundThe association of near-infrared spectroscopy (NIRS) with various outcomes after pediatric cardiac surgery has been studied extensively. However, the role of NIRS in the prediction of cardiac arrest (CA) in children with heart disease has yet to be evaluated. We sought to determine if a model utilizing regional cerebral oximetry (rSO2c) and somatic oximetry (rSO2s) could predict CA in children admitted to a single-center pediatric cardiac intensive care unit (CICU).MethodsWe retrospectively reviewed 160 index CA events for patients admitted to our pediatric CICU between November 2010 and January 2019. We selected 711 control patients who did not have a cardiac arrest. Hourly data was collected from the electronic health record (EHR). We previously created a machine-learning algorithm to predict the risk of CA using EHR data. Univariable analysis was done on these variables, which we then used to create a multivariable logistic regression model. The outputs from the model were presented by odds ratio (OR) and 95% confidence interval (CI).ResultsWe created a multivariable model to evaluate the association of CA using five variables: arterial saturation (SpO2)- rSO2c difference, SpO2-rSO2s difference, heart rate, diastolic blood pressure, and vasoactive inotrope score. While the SpO2-rSO2c difference was not a significant contributor to the multivariable model, the SpO2-rSO2s difference was. The average SpO2-rSO2s difference cutoff with the best prognostic accuracy for CA was 29% [CI 26–31%]. In the multivariable model, a 10% increase in the SpO2-rSO2s difference was independently associated with increased odds of CA [OR 1.40 (1.18, 1.67), P < 0.001] at 1 h before CA. Our model predicted CA with an AUROC of 0.83 at 1 h before CA.ConclusionIn this single-center case-control study of children admitted to a pediatric CICU, we created a multivariable model utilizing hourly data from the EHR to predict CA. At 1 h before the event, for every 10% increase in the SpO2-rSO2s difference, the odds of cardiac arrest increased by 40%. These findings are important as the field explores ways to capitalize on the wealth of data at our disposal to improve patient care.

Machine Learning-Based Cardiac Arrest Prediction for Early Warning System

The early warning system detects early and responds quickly to emergencies in high-risk patients, such as cardiac arrest in hospitalized patients. However, traditional early warning systems have the problem of frequent false alarms due to low positive predictive value and sensitivity. We conducted early prediction research on cardiac arrest using time-series data such as biosignal and laboratory data. To derive the data attributes that affect the occurrence of cardiac arrest, we performed a correlation analysis between the occurrence of cardiac arrest and the biosignal data and laboratory data. To improve the positive predictive value and sensitivity of early cardiac arrest prediction, we evaluated the performance according to the length of the time series of measured biosignal data, laboratory data, and patient data range. We propose a machine learning and deep learning algorithm: the decision tree, random forest, logistic regression, long short-term memory (LSTM), gated recurrent unit (GRU) model, and the LSTM–GRU hybrid model. We evaluated cardiac arrest prediction models. In the case of our proposed LSTM model, the positive predictive value was 85.92% and the sensitivity was 89.70%.

Real-Time Prediction of Mortality, Cardiac Arrest, and Thromboembolic Complications in Hospitalized Patients With COVID-19

BackgroundCOVID-19 infection carries significant morbidity and mortality. Current risk prediction for complications in COVID-19 is limited, and existing approaches fail to account for the dynamic course of the disease. ObjectivesThe purpose of this study was to develop and validate the COVID-HEART predictor, a novel continuously updating risk-prediction technology to forecast adverse events in hospitalized patients with COVID-19. MethodsRetrospective registry data from patients with severe acute respiratory syndrome coronavirus 2 infection admitted to 5 hospitals were used to train COVID-HEART to predict all-cause mortality/cardiac arrest (AM/CA) and imaging-confirmed thromboembolic events (TEs) (n = 2,550 and n = 1,854, respectively). To assess COVID-HEART’s performance in the face of rapidly changing clinical treatment guidelines, an additional 1,100 and 796 patients, admitted after the completion of development data collection, were used for testing. Leave-hospital-out validation was performed. ResultsOver 20 iterations of temporally divided testing, the mean area under the receiver operating characteristic curve were 0.917 (95% confidence interval [CI]: 0.916-0.919) and 0.757 (95% CI: 0.751-0.763) for prediction of AM/CA and TE, respectively. The interquartile ranges of median early warning times were 14 to 21 hours for AM/CA and 12 to 60 hours for TE. The mean area under the receiver operating characteristic curve for the left-out hospitals were 0.956 (95% CI: 0.936-0.976) and 0.781 (95% CI: 0.642-0.919) for prediction of AM/CA and TE, respectively. ConclusionsThe continuously updating, fully interpretable COVID-HEART predictor accurately predicts AM/CA and TE within multiple time windows in hospitalized COVID-19 patients. In its current implementation, the predictor can facilitate practical, meaningful changes in patient triage and resource allocation by providing real-time risk scores for these outcomes. The potential utility of the predictor extends to COVID-19 patients after hospitalization and beyond COVID-19.

Sudden cardiac arrest prediction and resuscitation network: improving the quality of care (PARQ)

Sudden cardiac arrest prediction and resuscitation network: improving the quality of care (PARQ) PARQ aims to create a network of researchers across Europe whose overall aim is to reduce the societal burden of sudden cardiac arrest (SCA). To reach this aim, PARQ will conduct studies that focus on two dimensions: (1) prevention of SCA through the discovery of its inherited, acquired, and environmental causes, and their interaction, and improved recognition of individuals at risk; and (2) improvement of survival chances after SCA through the development and implementation of resuscitation treatments in the community.

Prediction of Sudden Cardiac Arrest in the General Population: Review of Traditional and Emerging Risk Factors.

Sudden cardiac death (SCD) is the most common and devastating outcome of sudden cardiac arrest (SCA), defined as an abrupt and unexpected cessation of cardiovascular function leading to circulatory collapse. The incidence of SCD is relatively infrequent for individuals in the general population, in the range of 0.03%-0.10% per year. Yet, the absolute number of cases around the world is high because of the sheer size of the population at risk, making SCA/SCD a major global health issue. On the basis of conservative estimates, there are at least 2 million cases of SCA occurring worldwide on a yearly basis. As such, identification of risk factors associated with SCA in the general population is an important objective from a clinical and public health standpoint. This review will provide an in-depth discussion of established and emerging factors predictive of SCA/SCD in the general population beyond coronary artery disease and impaired left ventricular ejection fraction. Contemporary studies on the association of age, sex, race, socioeconomic status, and the emerging contribution of diabetes and obesity to SCD risk beyond their role as atherosclerotic risk factors are reviewed. In addition, the role of biomarkers, particularly electrocardiographic ones, on SCA/SCD risk prediction in the general population are discussed. Finally, the use of machine learning as a tool to facilitate SCA/SCD risk prediction is examined.

Prediction of Sudden Cardiac Death Manifesting With Documented Ventricular Fibrillation or Pulseless Ventricular Tachycardia.

This study aimed to develop a novel clinical prediction algorithm for avertable sudden cardiac death. Sudden cardiac death manifests as ventricular fibrillation (VF)/ ventricular tachycardia (VT) potentially treatable with defibrillation, or nonshockable rhythms (pulseless electrical activity/asystole) with low likelihood of survival. There are no available clinical risk scores for targeted prediction of VF/VT. Subjects with out-of-hospital sudden cardiac arrest presenting with documented VF or pulseless VT (33% of total cases) were ascertained prospectively from the Portland, Oregon, metro area with population ≈1 million residents (n=1,374, 2002-2019). Comparisons of lifetime clinical records were conducted with a control group (n=1,600) with ≈70% coronary disease prevalence. Prediction models were constructed from a training dataset using backwards stepwise logistic regression and applied to an internal validation dataset. Receiver operating characteristic curves (Cstatistic) were used to evaluate model discrimination. External validation was performed in a separate, geographically distinct population (Ventura County, California, population ≈850,000, 2015-2020). A clinical algorithm (VFRisk) constructed with 13 clinical, electrocardiogram, and echocardiographic variableshad very good discrimination in the training dataset (C statistic=0.808; [95% CI: 0.774-0.842]) and was successfully validated in internal (C statistic=0.776 [95% CI: 0.725-0.827]) and external (C statistic=0.782 [95% CI: 0.718-0.846]) datasets. The algorithm substantially outperformed the left ventricular ejection fraction (LVEF)≤35% (Cstatistic=0.638) and performed well across the LVEF spectrum. An algorithm for prediction of sudden cardiac arrest manifesting with VF/VT was successfully constructed using widely available clinical and noninvasive markers. These findings have potential to enhance primaryprevention, especially in patients with mid-range or preserved LVEF.

How technology can save lives in cardiac arrest.

Technology is being increasingly implemented in the fields of cardiac arrest and cardiopulmonary resuscitation. In this review, we describe how recent technological advances have been implemented in the chain of survival and their impact on outcomes after cardiac arrest. Breakthrough technologies that are likely to make an impact in the future are also presented. Technology is present in every link of the chain of survival, from prediction, prevention, and rapid recognition of cardiac arrest to early cardiopulmonary resuscitation and defibrillation. Mobile phone systems to notify citizen first responders of nearby out-of-hospital cardiac arrest have been implemented in numerous countries with improvement in bystanders' interventions and outcomes. Drones delivering automated external defibrillators and artificial intelligence to support the dispatcher in recognising cardiac arrest are already being used in real-life out-of-hospital cardiac arrest. Wearables, smart speakers, surveillance cameras, and artificial intelligence technologies are being developed and studied to prevent and recognize out-of-hospital and in-hospital cardiac arrest. This review highlights the importance of technology applied to every single step of the chain of survival to improve outcomes in cardiac arrest. Further research is needed to understand the best role of different technologies in the chain of survival and how these may ultimately improve outcomes.

Prediction of Sudden Cardiac Arrest after Alcohol Septal Ablation for Hypertrophic Obstructive Cardiomyopathy (ASA-SCARRE Risk Score)

Prediction of Sudden Cardiac Arrest after Alcohol Septal Ablation for Hypertrophic Obstructive Cardiomyopathy (ASA-SCARRE Risk Score)

Explainable and efficient deep early warning system for cardiac arrest prediction from electronic health records.

Cardiac arrest (CA) is a fatal acute event. The development of new CA early warning system based on time series of vital signs from electronic health records (EHR) has great potential to reduce CA damage. In this process, recursive architecture-based deep learning, as a powerful tool for time series data processing, enables automatically extract features from various monitoring clinical parameters and to further improve the performance for acute critical illness prediction. However, the unexplainable nature and excessive time caused by black box structure with poor parallelism are the limitations of its development, especially in the CA clinical application with strict requirement of emergency treatment and low hidden dangers. In this study, we present an explainable and efficient deep early warning system for CA prediction, which features are captured by an efficient temporal convolutional network (TCN) on EHR clinical parameters sequence and explained by deep Taylor decomposition (DTD) theoretical framework. To demonstrate the feasibility of our method and further evaluate its performance, prediction and explanation experiments were performed. Experimental results show that our method achieves superior CA prediction accuracy compared with standard national early warning score (NEWS), in terms of overall AUROC (0.850 Vs. 0.476) and F1-Score (0.750 Vs. 0.450). Furthermore, our method improves the interpretability and efficiency of deep learning-based CA early warning system. It provides the relevance of prediction results for each clinical parameter and about 1.7 times speed enhancement for system calculation compared with the long short-term memory network.

Artificial Intelligence in Predicting Cardiac Arrest: Scoping Review.

BackgroundCardiac arrest is a life-threatening cessation of activity in the heart. Early prediction of cardiac arrest is important, as it allows for the necessary measures to be taken to prevent or intervene during the onset. Artificial intelligence (AI) technologies and big data have been increasingly used to enhance the ability to predict and prepare for the patients at risk.ObjectiveThis study aims to explore the use of AI technology in predicting cardiac arrest as reported in the literature.MethodsA scoping review was conducted in line with the guidelines of the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) extension for scoping reviews. Scopus, ScienceDirect, Embase, the Institute of Electrical and Electronics Engineers, and Google Scholar were searched to identify relevant studies. Backward reference list checks of the included studies were also conducted. Study selection and data extraction were independently conducted by 2 reviewers. Data extracted from the included studies were synthesized narratively.ResultsOut of 697 citations retrieved, 41 studies were included in the review, and 6 were added after backward citation checking. The included studies reported the use of AI in the prediction of cardiac arrest. Of the 47 studies, we were able to classify the approaches taken by the studies into 3 different categories: 26 (55%) studies predicted cardiac arrest by analyzing specific parameters or variables of the patients, whereas 16 (34%) studies developed an AI-based warning system. The remaining 11% (5/47) of studies focused on distinguishing patients at high risk of cardiac arrest from patients who were not at risk. Two studies focused on the pediatric population, and the rest focused on adults (45/47, 96%). Most of the studies used data sets with a size of <10,000 samples (32/47, 68%). Machine learning models were the most prominent branch of AI used in the prediction of cardiac arrest in the studies (38/47, 81%), and the most used algorithm was the neural network (23/47, 49%). K-fold cross-validation was the most used algorithm evaluation tool reported in the studies (24/47, 51%).ConclusionsAI is extensively used to predict cardiac arrest in different patient settings. Technology is expected to play an integral role in improving cardiac medicine. There is a need for more reviews to learn the obstacles to the implementation of AI technologies in clinical settings. Moreover, research focusing on how to best provide clinicians with support to understand, adapt, and implement this technology in their practice is also necessary.

Prediction of cardiac arrest in critically ill patients based on bedside vital signs monitoring

PurposeCardiac arrest (CA) is the most serious death-related event in critically ill patients and the early detection of CA is beneficial to reduce mortality according to clinical research. This study aims to develop and verify a real-time, interpretable machine learning model, namely cardiac arrest prediction index (CAPI), to predict CA of critically ill patients based on bedside vital signs monitoring. MethodsA total of 1,860 patients were analyzed retrospectively from the Medical Information Mart for Intensive Care III (MIMIC-III) database. Based on vital signs, we extracted a total of 43 features for building machine learning model. Extreme Gradient Boosting (XGBoost) was used to develop a real-time prediction model. Three-fold cross validation determined the consistency of model accuracy. SHAP value was used to capture the overall and real-time interpretability of the model. ResultsOn the test set, CAPI predicted 95% of CA events, 80% of which were identified more than 25 min in advance, resulting in an area under the receiver operating characteristic curve (AUROC) of 0.94. The sensitivity, specificity, area under the precision-recall curve (AUPRC) and F1-score were 0.86, 0.85, 0.12 and 0.05, respectively. ConclusionCAPI can help predict patients with CA in the vital signs monitoring at bedside. Compared with previous studies, CAPI can give more timely notifications to doctors for CA events. However, current performance was at the cost of alarm fatigue. Future research is still needed to achieve better clinical application.

Usefulness of cardiac magnetic resonance images for prediction of sudden cardiac arrest in patients with mitral valve prolapse: a multicenter retrospective cohort study

BackgroundAn association has been identified between mitral valve prolapse (MVP) and sudden cardiac arrest (SCA), and ventricular arrhythmias (VA). This study aimed to elucidate predictive factors for SCA or VA in MVP patients.MethodsMVP patients who underwent cardiac magnetic resonance (CMR) were retrospectively included. Patients with other structural heart disease or causes of aborted SCA were excluded. Clinical characteristics (sex, age, body mass index, histories of diabetes, hypertension, and dyslipidemia) and electrocardiographic (PR interval, QRS duration, corrected QT interval, inverted T wave in the inferior leads, bundle branch block, and atrial fibrillation), echocardiographic [mitral regurgitation grade, prolapsing mitral leaflet, and right ventricular systolic pressure (RVSP)], and CMR [left atrial volume index, both ventricular ejection fractions, both ventricular end-diastolic and systolic volume indexes, prolapse distance, mitral annular disjunction, systolic curling motion, presence of late gadolinium enhancement (LGE), LGE volume and proportion] parameters were analyzed.ResultsOf the 85 patients [age, 54.0 (41.0–65.0) years; 46 men], seven experienced SCA or VA. Younger age and wide QRS complex were observed more often in the SCA/VA group than in the no-SCA/VA group. The SCA/VA group exhibited lower RVSP, more systolic curling motion and LGE, greater LGE volume, and higher LGE proportion. The presence of LGE [hazard ratio (HR), 19.8; 95% confidence interval (CI) 2.65–148.15; P = 0.004], LGE volume (HR 1.08; 95% CI 1.02–1.14; P = 0.006) and LGE proportion (HR 1.32; 95% CI 1.08–1.60; P = 0.006) were independently associated with higher risk of SCA or VA in MVP patients together with systolic curling motion in each model.ConclusionsThe presence of systolic curling motion, high LGE volume and proportion, and the presence of LGE on CMR were independent predictive factors for SCA or VA in MVP patients.

Prediction of In-Hospital Cardiac Arrest Using Shallow and Deep Learning.

Sudden cardiac arrest can leave serious brain damage or lead to death, so it is very important to predict before a cardiac arrest occurs. However, early warning score systems including the National Early Warning Score, are associated with low sensitivity and false positives. We applied shallow and deep learning to predict cardiac arrest to overcome these limitations. We evaluated the performance of the Synthetic Minority Oversampling Technique Ratio. We evaluated the performance using a Decision Tree, a Random Forest, Logistic Regression, Long Short-Term Memory model, Gated Recurrent Unit model, and LSTM–GRU hybrid models. Our proposed Logistic Regression demonstrated a higher positive predictive value and sensitivity than traditional early warning systems.

A predictive framework in healthcare: Case study on cardiac arrest prediction

Data-driven healthcare uses predictive analytics to enhance decision-making and personalized healthcare. Developing prognostic models is one of the applications of predictive analytics in medical environments. Various studies have used machine learning techniques for this purpose. However, there is no specific standard for choosing prediction models for different medical purposes. In this paper, the ISAF framework was proposed for choosing appropriate prediction models with regard to the properties of the classification methods. As one of the case study applications, a prognostic model for predicting cardiac arrests in sepsis patients was developed step by step through the ISAF framework. Finally, a new modified stacking model produced the best results. We predict 85 % of heart arrest cases one hour before the incidence (sensitivity> = 0.85) and 73 % of arrest cases 25 h before the occurrence (sensitivity> = 0.73). The results indicated that the proposed prognostic model has significantly improved the prediction results compared to the two standard systems of APACHE II and MEWS. Furthermore, compared to previous research, the proposed model has extended the prediction interval and improved the performance criteria.

Laboratory-derived early warning score for the prediction of in-hospital mortality, intensive care unit admission, medical emergency team activation and cardiac arrest in general medical wards.

General medical wards admit a varied cohort of patients from the emergency department, some of whom deteriorate during their hospital stay. Currently, we use vital signs based warning scores to predict patients at risk of imminent deterioration, but there is now a growing body of literature that commonly available laboratory results may also help to identify those at risk. To assess whether a laboratory-based admission score can predict in hospital mortality, intensive care unit (ICU) admission, medical emergency team (MET) activation or cardiac arrest in a cohort of Australian general medical patients admitted through the emergency department (ED). We performed a retrospective observational study of all general medical admissions to hospital through the ED in 2015. Admission pathology was used to calculate a risk score. In-patient outcomes of death, ICU transfer, MET call activation or cardiac arrest were collected from hospital records. We studied 2942 admissions derived from 2521 patients, with a median age of 81 years. There were 143 in-patient deaths, 82 ICU admissions, 277 MET calls and 14 cardiac arrest calls. The laboratory-based admission score had an area under the receiver operating characteristic curve (AUC-ROC) of 0.76 (95% confidence interval (CI): 0.72-0.80) for inpatient death, an AUC-ROC of 0.79 (95% CI: 0.66-0.93) for inpatient cardiac arrest, an AUC-ROC of 0.64 (95% CI: 0.58-0.70) for ICU transfer and an AUC-ROC of 0.59 (95% CI: 0.55-0.62) for MET call activation. When patients aged over 75 were analysed separately, the AUC-ROC for prediction of in-patient death was 0.74 (95% CI: 0.70-0.78) and increased to 0.86 (95% CI: 0.73-0.98) for the prediction of in-patient cardiac arrest. A simple laboratory-derived score obtained at patient admission is a fair to good predictor of subsequent in-patient death or cardiac arrest in general medical patients and in the older patient cohort. Prospective interventional studies are required to ascertain the clinical utility of this admission score.