Machine Learning Models for Survival and Neurological Outcome Prediction of Out-of-Hospital Cardiac Arrest Patients

Post-Cardiac arrest outcome prediction using machine learning: A systematic review and meta-analysis

BACKGROUND

Early and reliable prognostication in post-cardiac arrest patients remains challenging, with various factors linked to return of spontaneous circulation (ROSC), survival, and neurological results. Machine learning and deep learning models show promise in improving these predictions. This systematic review and meta-analysis evaluates how effective these approaches are in predicting clinical outcomes at different time points using structured data.

METHODS

This study followed PRISMA guidelines, involving a comprehensive search across PubMed, Scopus, and Web of Science databases until March 2024. Studies aimed at predicting ROSC, survival (or mortality), and neurological outcomes after cardiac arrest through the application of machine learning or deep learning techniques with structured data were included. Data extraction followed the guidelines of the CHARMS checklist, and the bias risk was evaluated using PROBAST tool. Models reporting the AUC metric with 95 % confidence intervals were incorporated into the quantitative synthesis and meta-analysis.

RESULTS

After extracting 2,753 initial records, 41 studies met the inclusion criteria, yielding 97 machine learning and 16 deep learning models. The pooled AUC for predicting favorable neurological outcomes (CPC 1 or 2) at hospital discharge was 0.871 (95 % CI: 0.813 - 0.928) for machine learning models and 0.877 (95 % CI: 0.831-0.924) across deep learning algorithms. For survival prediction, this value was found to be 0.837 (95 % CI: 0.757-0.916). Considerable heterogeneity and high risk of bias were observed, mainly attributable to inadequate management of missing data and the absence of calibration plots. Most studies focused on pre-hospital factors, with age, sex, and initial arrest rhythm being the most frequent features.

CONCLUSION

Predictive models utilizing AI-based approaches, including machine and deep learning models exhibit enhanced effectiveness compared to previous regression algorithms, but significant heterogeneity and high risk of bias limit their dependability. Evaluating state-of-the-art deep learning models tailored for tabular data and their clinical generalizability can enhance outcome prediction after cardiac arrest.

Transnational learning and teaching activities: Smart Healthcare Engineering

The new maintenance engineers become self-taught and learn from daily dedication, from solving repetitive problems, from exchanging experiences with a colleague, from reading a recommended book and little else. Their own experience has been the main reference for maintenance professionals who have not given up and have become experts. And within the maintenance activities, sanitary engineering plays a very important role. Through the Smart Healthcare Engineering project we have facilitated a close connection between 3 universities and 3 hospitals from 3 countries (Spain, Turkey and Romania), which benefit from each other's experience, transferring the know-how available in a single country. The study involves 7 students from each university, meaning that 21 students have worked and studied together for 2 weeks in Spain in the field of healthcare engineering. The chosen hospital was Dr. Negrin Hospital from Gran Canaria. Results at the organizational level include the modernization of content and the provision of resources for healthcare engineering training, the introduction of innovative educational concepts in healthcare engineering and the integration of blended learning methodologies in practical teaching and training activities. A tighter connection and transnational collaboration were established between European hospitals and universities in healthcare engineering, together with unrestricted access to routinely updated information. The specific results for each participant indicated their capacity to engage in the intricate processes of repair and maintenance within a practical context, making real-time judgments on-site.

Role of artificial intelligence in predicting neurological outcomes in postcardiac resuscitation

Being an extremely high mortality rate condition, cardiac arrest cases have rightfully been evaluated via various studies and scoring factors for effective resuscitative practices and neurological outcomes postresuscitation. This narrative review aims to explore the role of artificial intelligence (AI) in predicting neurological outcomes postcardiac resuscitation. The methodology involved a detailed review of all relevant recent studies of AI, different machine learning algorithms, prediction tools, and assessing their benefit in predicting neurological outcomes in postcardiac resuscitation cases as compared to more traditional prognostic scoring systems and tools. Previously, outcome determining clinical, blood, and radiological factors were prone to other influencing factors like limited accuracy and time constraints. Studies conducted also emphasized that to predict poor neurological outcomes, a more multimodal approach helped adjust for confounding factors, interpret diverse datasets, and provide a reliable prognosis, which only demonstrates the need for AI to help overcome challenges faced. Advanced machine learning algorithms like artificial neural networks (ANN) using supervised learning by AI have improved the accuracy of prognostic models outperforming conventional models. Several real-world cases of effective AI-powered algorithm models have been cited here. Studies comparing machine learning tools like XGBoost, AI Watson, hyperspectral imaging, ChatGPT-4, and AI-based gradient boosting have noted their beneficial uses. AI could help reduce workload, healthcare costs, and help personalize care, process vast genetic and lifestyle data and help reduce side effects from treatments. Limitations of AI have been covered extensively in this article, including data quality, bias, privacy issues, and transparency. Our objectives should be to use more diverse data sources, use interpretable data output giving process explanation, validation method, and implement policies to safeguard patient data. Despite the limitations, the advancements already made by AI and its potential in predicting neurological outcomes in postcardiac resuscitation cases has been quite promising and boosts a continually improving system, albeit requiring close human supervision with training and improving models, with plans to educate clinicians, the public and sharing collected data.

Application of multi-feature-based machine learning models to predict neurological outcomes of cardiac arrest

Cardiac arrest (CA) is a major disease burden worldwide and has a poor prognosis. Early prediction of CA outcomes helps optimize the therapeutic regimen and improve patients' neurological function. As the current guidelines recommend, many factors can be used to evaluate the neurological outcomes of CA patients. Machine learning (ML) has strong analytical abilities and fast computing speed; thus, it plays an irreplaceable role in prediction model development. An increasing number of researchers are using ML algorithms to incorporate demographics, arrest characteristics, clinical variables, biomarkers, physical examination findings, electroencephalograms, imaging, and other factors with predictive value to construct multi-feature prediction models for neurological outcomes of CA survivors. In this review, we explore the current application of ML models using multiple features to predict the neurological outcomes of CA patients. Although the outcome prediction model is still in development, it has strong potential to become a powerful tool in clinical practice.

Applications and Performance of Machine Learning Algorithms in Emergency Medical Services: A Scoping Review

OBJECTIVE

The aim of this study was to summarize the literature on the applications of machine learning (ML) and their performance in Emergency Medical Services (EMS).

METHODS

Four relevant electronic databases were searched (from inception through January 2024) for all original studies that employed EMS-guided ML algorithms to enhance the clinical and operational performance of EMS. Two reviewers screened the retrieved studies and extracted relevant data from the included studies. The characteristics of included studies, employed ML algorithms, and their performance were quantitively described across primary domains and subdomains.

RESULTS

This review included a total of 164 studies published from 2005 through 2024. Of those, 125 were clinical domain focused and 39 were operational. The characteristics of ML algorithms such as sample size, number and type of input features, and performance varied between and within domains and subdomains of applications. Clinical applications of ML algorithms involved triage or diagnosis classification (n = 62), treatment prediction (n = 12), or clinical outcome prediction (n = 50), mainly for out-of-hospital cardiac arrest/OHCA (n = 62), cardiovascular diseases/CVDs (n = 19), and trauma (n = 24). The performance of these ML algorithms varied, with a median area under the receiver operating characteristic curve (AUC) of 85.6%, accuracy of 88.1%, sensitivity of 86.05%, and specificity of 86.5%. Within the operational studies, the operational task of most ML algorithms was ambulance allocation (n = 21), followed by ambulance detection (n = 5), ambulance deployment (n = 5), route optimization (n = 5), and quality assurance (n = 3). The performance of all operational ML algorithms varied and had a median AUC of 96.1%, accuracy of 90.0%, sensitivity of 94.4%, and specificity of 87.7%. Generally, neural network and ensemble algorithms, to some degree, out-performed other ML algorithms.

CONCLUSION

Triaging and managing different prehospital medical conditions and augmenting ambulance performance can be improved by ML algorithms. Future reports should focus on a specific clinical condition or operational task to improve the precision of the performance metrics of ML models.

Prediction of neurologic outcome after out-of-hospital cardiac arrest: An interpretable approach with machine learning

Out-of-hospital cardiac arrest (OHCA) is a critical condition with low survival rates. In patients with a return of spontaneous circulation, brain injury is a leading cause of death. In this study, we propose an interpretable machine learning approach for predicting neurologic outcome after OHCA, using information available at the time of hospital admission.

METHODS

The study population were 55 615 OHCA cases registered in the Swedish Cardiopulmonary Resuscitation Registry between 2010 and 2020. The dataset was split to training and validation sets (for model development) and test set (for evaluation of the final model). We used an XGBoost algorithm with stratified, repeated 10-fold cross-validation along with Optuna framework for hyperparameters tuning. The final model was trained on 10 features selected based on the importance scores and evaluated on the test set in terms of discrimination, calibration and bias-variance tradeoff. We used SHapley Additive exPlanations to address the 'black-box' model and align with eXplainable artificial intelligence.

RESULTS

The final model achieved: area under the receiver operating characteristic value 0.964 (95% confidence interval (CI) [0.960-0.968]), sensitivity 0.606 (95% CI [0.573-0.634]), specificity 0.975 (95% CI [0.972-0.978]), positive predictive value (PPV) 0.664 (95% CI [0.625-0.696]), negative predictive value (NPV) 0.969 (95% CI [0.966-0.972]), macro F1 0.803 (95% CI [0.788-0.816]), and showed a very good calibration. SHAP features with the highest impact on the model's output were:'ROSC on arrival to hospital', 'Initial rhythm asystole' and 'Conscious on arrival to hospital'.

CONCLUSIONS

The XGBoost machine learning model with 10 features available at the time of hospital admission showed good performance for predicting neurologic outcome after OHCA, with no apparent signs of overfitting.

Machine Learning and Clinical Predictors of Mortality in Cardiac Arrest Patients: A Comprehensive Analysis

BACKGROUND Cardiac arrest (CA) is a global public health challenge. This study explored the predictors of mortality and their interactions utilizing machine learning algorithms and their related mortality odds among patients following CA. MATERIAL AND METHODS The study retrospectively investigated 161 medical records of CA patients admitted to the Intensive Care Unit (ICU). The random forest classifier algorithm was used to assess the parameters of mortality. The best classification trees were chosen from a set of 100 trees proposed by the algorithm. Conditional mortality odds were investigated with the use of logistic regression models featuring interactions between variables. RESULTS In the logistic regression model, male sex was associated with 5.68-fold higher mortality odds. The mortality odds among the asystole/pulseless electrical activity (PEA) patients were modulated by body mass index (BMI) and among ventricular fibrillation/pulseless ventricular tachycardia (VF/pVT) patients were by serum albumin concentration (decrease by 2.85-fold with 1 g/dl increase). Procalcitonin (PCT) concentration, age, high-sensitivity C-reactive protein (hsCRP), albumin, and potassium were the most influential parameters for mortality prediction with the use of the random forest classifier. Nutritional status-associated parameters (serum albumin concentration, BMI, and Nutritional Risk Score 2002 [NRS-2002]) may be useful in predicting mortality in patients with CA, especially in patients with PCT >0.17 ng/ml, as showed by the decision tree chosen from the random forest classifier based on goodness of fit (AUC score). CONCLUSIONS Mortality in patients following CA is modulated by many co-existing factors. The conclusions refer to sets of conditions rather than universal truths. For individual factors, the 5 most important classifiers of mortality (in descending order of importance) were PCT, age, hsCRP, albumin, and potassium.

Explainable Deep Learning Model for Predicting Serious Adverse Events in Hospitalized Geriatric Patients Within 72 Hours

Background

The global aging population presents a significant challenge, with older adults experiencing declining physical and cognitive abilities and increased vulnerability to chronic diseases and adverse health outcomes. This study aims to develop an interpretable deep learning (DL) model to predict adverse events in geriatric patients within 72 hours of hospitalization.

Methods

The study used retrospective data (2017-2020) from a major medical center in Taiwan. It included non-trauma geriatric patients who visited the emergency department and were admitted to the general ward. Data preprocessing involved collecting prognostic factors like vital signs, lab results, medical history, and clinical management. A deep feedforward neural network was developed, and performance was evaluated using accuracy, sensitivity, specificity, positive predictive value (PPV), and area under the receiver operating characteristic curve (AUC). Model interpretation utilized the Shapley Additive Explanation (SHAP) technique.

Results

The analysis included 127,268 patients, with 2.6% experiencing imminent intensive care unit transfer, respiratory failure, or death during hospitalization. The DL model achieved AUCs of 0.86 and 0.84 in the validation and test sets, respectively, outperforming the Sequential Organ Failure Assessment (SOFA) score. Sensitivity and specificity values ranged from 0.79 to 0.81. The SHAP technique provided insights into feature importance and interactions.

Conclusion

The developed DL model demonstrated high accuracy in predicting serious adverse events in geriatric patients within 72 hours of hospitalization. It outperformed the SOFA score and provided valuable insights into the model's decision-making process.

Artificial Intelligence and Machine Learning Applications in Sudden Cardiac Arrest Prediction and Management: A Comprehensive Review

PURPOSE OF REVIEW

This literature review aims to provide a comprehensive overview of the recent advances in prediction models and the deployment of AI and ML in the prediction of cardiopulmonary resuscitation (CPR) success. The objectives are to understand the role of AI and ML in healthcare, specifically in medical diagnosis, statistics, and precision medicine, and to explore their applications in predicting and managing sudden cardiac arrest outcomes, especially in the context of prehospital emergency care.

RECENT FINDINGS

The role of AI and ML in healthcare is expanding, with applications evident in medical diagnosis, statistics, and precision medicine. Deep learning is gaining prominence in radiomics and population health for disease risk prediction. There's a significant focus on the integration of AI and ML in prehospital emergency care, particularly in using ML algorithms for predicting outcomes in COVID-19 patients and enhancing the recognition of out-of-hospital cardiac arrest (OHCA). Furthermore, the combination of AI with automated external defibrillators (AEDs) shows potential in better detecting shockable rhythms during cardiac arrest incidents. AI and ML hold immense promise in revolutionizing the prediction and management of sudden cardiac arrest, hinting at improved survival rates and more efficient healthcare interventions in the future. Sudden cardiac arrest (SCA) continues to be a major global cause of death, with survival rates remaining low despite advanced first responder systems. The ongoing challenge is the prediction and prevention of SCA. However, with the rise in the adoption of AI and ML tools in clinical electrophysiology in recent times, there is optimism about addressing these challenges more effectively.

Bayesian network predicted variables for good neurological outcomes in patients with out-of-hospital cardiac arrest

Out-of-hospital cardiac arrest (OHCA) is linked to a poor prognosis and remains a public health concern. Several studies have predicted good neurological outcomes of OHCA. In this study, we used the Bayesian network to identify variables closely associated with good neurological survival outcomes in patients with OHCA. This was a retrospective observational study using the Japan Association for Acute Medicine OHCA registry. Fifteen explanatory variables were used, and the outcome was one-month survival with Glasgow-Pittsburgh cerebral performance category (CPC) 1-2. The 2014-2018 dataset was used as training data. The variables selected were identified and a sensitivity analysis was performed. The 2019 dataset was used for the validation analysis. Four variables were identified, including the motor response component of the Glasgow Coma Scale (GCS M), initial rhythm, age, and absence of epinephrine. Estimated probabilities were increased in the following order: GCS M score: 2-6; epinephrine: non-administered; initial rhythm: spontaneous rhythm and shockable; and age: <58 and 59-70 years. The validation showed a sensitivity of 75.4% and a specificity of 95.4%. We identified GCS M score of 2-6, initial rhythm (spontaneous rhythm and shockable), younger age, and absence of epinephrine as variables associated with one-month survival with CPC 1-2. These variables may help clinicians in the decision-making process while treating patients with OHCA.

A Machine Learning Prediction Model for Non-cardiogenic Out-of-hospital Cardiac Arrest with Initial Non-shockable Rhythm

Objectives

The purpose of this study was to develop and validate a machine learning prediction model for the prognosis of non-cardiogenic out-of-hospital cardiac arrest (OHCA) with an initial non-shockable rhythm.

Design

Data were obtained from a nationwide OHCA registry in Japan. Overall, 222,056 patients with OHCA and an initial non-shockable rhythm were identified from the registry in 2016 and 2017. Patients aged <18 years and OHCA caused by cardiogenic origin, cancer, and external factors were excluded. Finally, 58,854 participants were included.

Methods

Patients were classified into the training dataset (n=29,304, data from 2016) and the test dataset (n=29,550, data from 2017). The training dataset was used to train and develop the machine learning model, and the test dataset was used for internal validation. We selected XGBoost as the machine learning classifier. The primary outcome was the poor prognosis defined as cerebral performance category of 3-5 at 1 month. Eleven prehospital variables were selected as outcome predictors.

Results

In validation, the machine learning model predicted the primary outcome with an accuracy of 90.8% [95% confidence interval (CI): 90.5-91.2], a sensitivity of 91.4% [CI: 90.7-91.4], a specificity of 74.1% [CI: 69.2-78.6], and an area under the receiver operating characteristic value of 0.89 [0.87-0.92]. The important features for model development were the prehospital return of spontaneous circulation, prehospital adrenaline administration, and initial electrical rhythm.

Conclusions

We developed a favorable machine learning model to predict the prognosis of non-cardiogenic OHCA with an initial non-shockable rhythm in the early stage of resuscitation.

Machine learning models for predicting in-hospital mortality in patient with sepsis: Analysis of vital sign dynamics

Purpose

To build machine learning models for predicting the risk of in-hospital death in patients with sepsis within 48 h, using only dynamic changes in the patient's vital signs.

Methods

This retrospective observational cohort study enrolled septic patients from five emergency departments (ED) in Taiwan. We adopted seven variables, i.e., age, sex, systolic blood pressure, diastolic blood pressure, heart rate, respiratory rate, and body temperature.

Results

Among all 353,253 visits, after excluding 159,607 visits (45%), the study group consisted of 193,646 ED visits. With a leading time of 6 h, the convolutional neural networks (CNNs), long short-term memory (LSTM), and random forest (RF) had accuracy rates of 0.905, 0.817, and 0.835, respectively, and the area under the receiver operating characteristic curve (AUC) was 0.840, 0.761, and 0.770, respectively. With a leading time of 48 h, the CNN, LSTM, and RF achieved accuracy rates of 0.828, 0759, and 0.805, respectively, and an AUC of 0.811, 0.734, and 0.776, respectively.

Conclusion

By analyzing dynamic vital sign data, machine learning models can predict mortality in septic patients within 6 to 48 h of admission. The performance of the testing models is more accurate if the lead time is closer to the event.

Utilizing community level factors to improve prediction of out of hospital cardiac arrest outcome using machine learning

OBJECTIVES

To evaluate the impact of community level information on the predictability of out-of-hospital cardiac arrest (OHCA) survival.

METHODS

We used the Cardiac Arrest Registry to Enhance Survival (CARES) to geocode 9,595 Chicago incidents from 2014 to 2019 into community areas. Community variables including crime, healthcare, and economic factors from public data were merged with CARES. The merged data were used to develop ML models for OHCA survival. Models were evaluated using Area Under the Receiver Operating Characteristic curve (AUROC) and features were analyzed using SHapley Additive exPansion (SHAP) values.

RESULTS

Baseline results using CARES data achieved an AUROC of 84%. The final model utilizing community variables increased the AUROC to 88%. A SHAP analysis between high and low performing community area clusters showed the high performing cluster is positively impacted by good health related features and good community safety features positively impact the low performing cluster.

CONCLUSION

Utilizing community variables helps predict neurologic outcomes with better performance than only CARES data. Future studies will use this model to perform simulations to identify interventions to improve OHCA survival.