An intelligent warning model for early prediction of cardiac arrest in sepsis patients

doi:10.1016/j.cmpb.2019.06.010

Computer Methods and Programs in Biomedicine

Volume 178, September 2019, Pages 47-58

https://doi.org/10.1016/j.cmpb.2019.06.010 Get rights and content

Highlights

•
The effectiveness of a wide range of classical and ensemble machine learning techniques in predicting cardiac arrest were evaluated through a systematic approach.
•
Patient's time series dynamics of vital signs was investigated as a new factor for predicting cardiac arrest.
•
Cardiac arrest incidence was predicted in several time intervals.
•
The proposed model generated better results compared with APACHE II and MEWS.

Abstract

Background

Sepsis-associated cardiac arrest is a common issue with the low survival rate. Early prediction of cardiac arrest can provide the time required for intervening and preventing its onset in order to reduce mortality. Several studies have been conducted to predict cardiac arrest using machine learning. However, no previous research has used machine learning for predicting cardiac arrest in adult sepsis patients. Moreover, the potential of some techniques, including ensemble algorithms, has not yet been addressed in improving the prediction outcomes. It is required to find methods for generating high-performance predictions with sufficient time lapse before the arrest. In this regard, various variables and parameters should also been examined.

Objective

The aim was to use machine learning in order to propose a cardiac arrest prediction model for adult patients with sepsis. It is required to predict the arrest several hours before the incidence with high efficiency. The other goal was to investigate the effect of the time series dynamics of vital signs on the prediction of cardiac arrest.

Method

30 h clinical data of every sepsis patients were extracted from Mimic III database (79 cases, 4532 controls). Three datasets (multivariate, time series and combined) were created. Various machine learning models for six time groups were trained on these datasets. The models included classical techniques (SVM, decision tree, logistic regression, KNN, GaussianNB) and ensemble methods (gradient Boosting, XGBoost, random forest, balanced bagging classifier and stacking). Proper solutions were proposed to address the challenges of missing values, imbalanced classes of data and irregularity of time series.

Results

The best results were obtained using a stacking algorithm and multivariate dataset (accuracy = 0.76, precision = 0.19, sensitivity = 0.77, f1-score = 0.31, AUC= 0.82). The proposed model predicts the arrest incidence of up to six hours earlier with the accuracy and sensitivity over 70%.

Conclusion

We illustrated that machine learning techniques, especially ensemble algorithms have high potentials to be used in prognostic systems for sepsis patients. The proposed model, in comparison with the exiting warning systems including APACHE II and MEWS, significantly improved the evaluation criteria. According to the results, the time series dynamics of vital signs are of great importance in the prediction of cardiac arrest incidence in sepsis patients.

Introduction

Sepsis is a leading cause of death in general intensive care units (ICU) [1]. Its incidence is rising with a reported rate in the USA of 436 severe cases/100,000 persons in 2012 and an overall mortality of 17.5% [2]. Many sepsis cases result in cardiac arrest (CA) with poor outcome. Patients with sepsis are less likely to achieve return of spontaneous circulation (ROSC) or survive to hospital discharge following in hospital cardiac arrest [3].

Many cardiac arteries may be preventable. Since cardiopulmonary resuscitation in sepsis patients is challenging and usually unsuccessful, more research is required to prevent CA in these patients. Medical experts believe that early cardiac interventions can reduce mortality if CA is predicted before it happens. Considering the importance of this issue, several studies have been conducted to predict the risk of CA. Traditional studies used standard statistical methods aimed at identifying group-level differences and often used a limited number of variables for prediction. Today, modern technologies provide a wealth of physiological data and clinical parameters that require robust and inexpensive computing tools to process.

Machine learning, a subset of artificial intelligence, helps to automatically analyze complex data and produces significant results. Javan et al. [4] reviewed the use of machine learning algorithms in predicting cardiac arrest. According to this review paper, machine learning techniques (MLT) have high potential to be used as physician's assistants for early prediction of cardiac arrest. Compared to traditional methods of prediction such as regression, machine learning techniques provide better performance in many cases. However, the potential of some techniques, including ensemble algorithms, has not yet been addressed in improving the prediction outcomes. It is also necessary to find methods for generating high-performance predictions with sufficient time lapse before the arrest. On the other hand, in recent years, some studies have analyzed the time series of vital signs to produce early warning systems [[5], [6], [7], [8], [9]–10]. Physiological systems generate complex dynamics in their output signals, reflecting the state of the body's control systems. It should be investigated how the dynamics of these signals affects the prediction outcomes.

Considering the above motivations, an exploratory study was conducted to evaluate the efficiency of different classification algorithms in early prediction of cardiac arrest in adult sepsis patients. Our purpose was to maximize the prediction performance and make predictions as early as possible. Another goal of this study was to investigate whether the time series dynamics of vital signs has an effect on improving the efficiency of cardiac arrest prediction in sepsis patients.

Regarding the research goals, we extracted 30 h clinical data of adult sepsis patients recorded in Mimic III database. Three datasets (multivariate, time series and combined) were created using the extracted data. Some preprocessing tasks were performed to address the challenges of missing values, outliers, imbalanced classes of data and irregularity of the time series. Various machine learning techniques including classical models and ensemble methods were trained on the three datasets to predict CA occurrence in six time groups. We used sensitivity, precision and f1-score as the main criteria to evaluate the models. The best model in 1-hour group was used to predict the CA incidence in the other time groups.

The remainder of the paper is organized as follows. In Section 2, we describe the background and related works of CA prediction using machine learning. Section 3 details the proposed method. Section 4 presents the models and results achieved. Section 5 provides comparisons and discusses the obtained results. Finally, Section 6 concludes this paper and presents limitations and recommendations for future works.

Section snippets

Machine learning

In this study, since we had labeled records, the supervised learning approach was used. Several classification models, including classical methods (support vector machine (SVM), decision tree (DT), logistic regression (LR), k-nearest neighbor (KNN), GaussianNB), and ensemble methods (gradient boosting, XGBoost, random forest (RF), balanced bagging classifier and stacking) were used to classify the sepsis patients into two groups of normal and cardiac arrest. Ensemble methods combine various

Data

In this study, clinical data from the MIMIC-III database [20] were used for analysis and modeling. MIMIC-III is a large, freely-available database comprising de-identified health-related data associated with over 40,000 patients who stayed in critical care units of the Beth Israel Deaconess Medical Center between 2001 and 2012. Only a small fraction of patients were associated with their ECG waveforms in MIMIC database. As a result, we did not use ECG signals for analytic tasks.

The purpose of

Modelling and results

In this study, different models for six time classes were trained on three different data sets:

•
The first dataset contains multivariate features including demographics and the last values of vital signs and laboratory test results.
•
The second dataset involved trend features extracted from time series of patient's vital signs.
•
The third dataset consisted of a combination of multivariate and trend features.

As previously mentioned, classification models are divided into six different groups in terms

Discussion

In this research, various models were induced to predict the cardiac arrest incidence. As previously mentioned, increasing the amount of sensitivity will reduce the amount of precision and vice versa. Our goal was to make a trade-off between the sensitivity and precision values, so that the majority of CA cases were detected, while the number of false alarms was reduced. Although identifying all cases of cardiac arrest is important, but false alarms increase the workload of the hospital staff,

Conclusion

In this study, we showed that machine learning techniques, especially ensemble algorithms, have high potential to be used in prognostic systems for sepsis patients. The main contributions of this paper were as follows:

•
Evaluating the effectiveness of a wide range of machine learning algorithms in predicting CA, including classical models and ensemble methods.
•
Investigating the effect of time series dynamics of vital signs on CA prediction.
•
Predicting CA incidence in different time intervals.

There

Conflicts of interest

None.

References (23)

D. Leoni et al.
Cardiac arrest among patients with infections: causes, clinical practice and research implications
Clin. Microbiol. Infect.
(2017)
J. Stoller
Epidemiology of severe sepsis: 2008-2012
J. Crit. Care
(2016)
R.W. Morgan
Sepsis-associated in-hospital cardiac arrest: epidemiology, pathophysiology, and potential therapies
J. Crit. Care
(2017)
S.L. Javan et al.
Toward analyzing and synthesizing previous research in early prediction of cardiac arrest using machine learning based on a multi-layered integrative framework
J. Biomed. Informat.
(2018)
L. Mayaud
Dynamic data during hypotensive episode improves mortality predictions among patients with sepsis and hypotension
Crit. Care Med.
(2013)
J. Wiens et al.
Patient risk stratification for hospital-associated c. diff as a time-series classification task
H.L. Li-wei
Tracking progression of patient state of health in critical care using inferred shared dynamics in physiological time series
H.L. Li-wei
Discovering shared dynamics in physiological signals: application to patient monitoring in ICU
T.G. Buchman
Nonlinear dynamics, complex systems, and the pathobiology of critical illness
Current Opin. Crit. Care
(2004)
J.R. Moorman
Cardiovascular oscillations at the bedside: early diagnosis of neonatal sepsis using heart rate characteristics monitoring
Physiol. Measur.
(2011)

F. Portela

A Pervasive Intelligent System for Scoring MEWS and TISS-28 in Intensive Care

Cited by (54)

Hybrid stacking ensemble algorithm and simulated annealing optimization for stability evaluation of underground entry-type excavations
2024, Underground Space (new)
The stability of underground entry-type excavations (UETEs) is of paramount importance for ensuring the safety of mining operations. As more engineering cases are accumulated, machine learning (ML) has demonstrated great potential for the stability evaluation of UETEs. In this study, a hybrid stacking ensemble method aggregating support vector machine (SVM), k-nearest neighbor (KNN), decision tree (DT), random forest (RF), multilayer perceptron neural network (MLPNN) and extreme gradient boosting (XGBoost) algorithms was proposed to assess the stability of UETEs. Firstly, a total of 399 historical cases with two indicators were collected from seven mines. Subsequently, to pursue better evaluation performance, the hyperparameters of base learners (SVM, KNN, DT, RF, MLPNN and XGBoost) and meta learner (MLPNN) were tuned by combining a five-fold cross validation (CV) and simulated annealing (SA) approach. Based on the optimal hyperparameters configuration, the stacking ensemble models were constructed using the training set (75% of the data). Finally, the performance of the proposed approach was evaluated by two global metrics (accuracy and Cohen’s Kappa) and three within-class metrics (macro average of the precision, recall and F₁-score) on the test set (25% of the data). In addition, the evaluation results were compared with six base learners optimized by SA. The hybrid stacking ensemble algorithm achieved better comprehensive performance with the accuracy, Kappa coefficient, macro average of the precision, recall and F₁-score were 0.92, 0.851, 0.885, 0.88 and 0.883, respectively. The rock mass rating (RMR) had the most important influence on evaluation results. Moreover, the critical span graph (CSG) was updated based on the proposed model, representing a significant improvement compared with the previous studies. This study can provide valuable guidance for stability analysis and risk management of UETEs. However, it is necessary to consider more indicators and collect more extensive and balanced dataset to validate the model in future.
Corticosteroid sensitivity detection in sepsis patients using a personalized data mining approach: A clinical investigation
2024, Computer Methods and Programs in Biomedicine
Sepsis is a life-threatening disease with high mortality, incidence, and morbidity. Corticosteroids (CS) are a recommended treatment for sepsis, but some patients respond negatively to CS therapy. Early prediction of corticosteroid responsiveness can help intervene and reduce mortality. In this study, we aim to develop a data mining methodology for predicting CS responsiveness of septic patients.
We used data from a randomized controlled trial called APROCCHSS, which recruited 1241 septis patients to study the effectiveness of corticotherapy. We conducted a thorough study of multiple machine learning models to select the most efficient prediction model, called “signature”. We evaluated the performance of the signature using precision, sensitivity, and specificity values.
We found that Logistic Regression was the best model with an AUC of 72%. We conducted further experiments to examine the impact of additional features and the model's generalizability to different groups of patients. We also performed a statistical analysis to analyze the effect of the treatment at the individual level and on the population as a whole.
Our data mining methodology can accurately predict cortico-sensitivity or resistance in septis patients. The signature has been deployed into the Assistance Publique – Hôpitaux de Paris (APHP) information system as a web service, taking patient information as input and providing a prediction of cortico-sensitivity or resistance. Early prediction of corticosteroid responsiveness can help clinicians intervene promptly and improve patient outcomes.
Analysis of machine learning and deep learning prediction models for sepsis and neonatal sepsis: A systematic review
2023, ICT Express
Sepsis and Neonatal sepsis are major challenges in global healthcare because they cause life-threatening organ dysfunction in intensive care adult and pediatric patients due to downregulated host response to a particular infection. Early clinical identification of sepsis is difficult, and failure to provide prompt treatment can often lead to crucial stages and increase the rates of fatality. Thus an intense study is needed to determine and categorize sepsis in its initial stage. The complexity of varying clinical statistics makes it difficult to attain a precise definition in pediatrics. The advanced Machine Learning (ML) and Deep Learning (DL) technologies in the implementation of protocols show promising real-time models for predicting sepsis at the primary stage and thereby reducing the mortality rate. This review article contemplates the complete list of procedures through which sepsis and neonatal sepsis are speculated by ML and DL and concentrates specifically on data available in the adult emergency care unit as well as the neonatal intensive care unit. The survey process was carried out by searching terms related to ML and DL merged with topics concerning sepsis and neonatal sepsis. The literature analysis was carried out from Scopus, Web of Science, and PubMed databases for the period from 2015 to 2022. The assessment of the risk of bias was carried out for the eleven selected papers using the Prediction Model Risk of Bias Assessment Tool (PROBAST). The eleven papers were selected from different medical care units based on the performance measure AUROC, which ranges from 0.68 to 0.95. Five papers involving ML/DL models reduce the bias and lessen risk occurrence. Five papers generate an increase in bias but can be applied to new data. One paper works with above twenty-five features has high-risk probability but predicts patients within 5–6 h in the future. This survey portrays the role of prediction models that supports the researchers and clinicians for better decision-making and antibiotic administration at an earlier stage.
Use of Artificial Intelligence in Improving Outcomes in Heart Disease: A Scientific Statement From the American Heart Association
2024, Circulation
Development of a patient health monitoring system based on the internet of things with a module for predicting vital signs
2024, Indonesian Journal of Electrical Engineering and Computer Science
Knowledge Graph Embeddings for ICU readmission prediction
2023, BMC Medical Informatics and Decision Making

View all citing articles on Scopus

View full text

An intelligent warning model for early prediction of cardiac arrest in sepsis patients

Highlights

Abstract

Background

Objective

Method

Results

Conclusion

Introduction

Section snippets

Machine learning

Data

Modelling and results

Discussion

Conclusion

Conflicts of interest

Clin. Microbiol. Infect.

J. Crit. Care

J. Crit. Care

Toward analyzing and synthesizing previous research in early prediction of cardiac arrest using machine learning based on a multi-layered integrative framework

J. Biomed. Informat.

Dynamic data during hypotensive episode improves mortality predictions among patients with sepsis and hypotension

Crit. Care Med.

Patient risk stratification for hospital-associated c. diff as a time-series classification task

Tracking progression of patient state of health in critical care using inferred shared dynamics in physiological time series

Discovering shared dynamics in physiological signals: application to patient monitoring in ICU

Nonlinear dynamics, complex systems, and the pathobiology of critical illness

Current Opin. Crit. Care

Cardiovascular oscillations at the bedside: early diagnosis of neonatal sepsis using heart rate characteristics monitoring

Physiol. Measur.

A Pervasive Intelligent System for Scoring MEWS and TISS-28 in Intensive Care