Artificial neural networks improve early outcome prediction and risk classification in out-of-hospital cardiac arrest patients admitted to intensive care

Key Concepts in Machine Learning and Clinical Applications in the Cardiac Intensive Care Unit

PURPOSE OF REVIEW

Artificial Intelligence (AI) technology will significantly alter critical care cardiology, from our understanding of diseases to the way in which we communicate with patients and colleagues. We summarize the potential applications of AI in the cardiac intensive care unit (CICU) by reviewing current evidence, future developments and possible challenges.

RECENT FINDINGS

Machine Learning (ML) methods have been leveraged to improve interpretation and discover novel uses for diagnostic tests such as the ECG and echocardiograms. ML-based dynamic risk stratification and prognostication may help optimize triaging and CICU discharge procedures. Latent class analysis and K-means clustering may reveal underlying disease sub-phenotypes within heterogeneous conditions such as cardiogenic shock and decompensated heart failure. AI technology may help enhance routine clinical care, facilitate medical education and training, and unlock individualized therapies for patients in the CICU. However, robust regulation and improved clinician understanding of AI is essential to overcome important practical and ethical challenges.

Application of artificial intelligence in the health management of chronic disease: bibliometric analysis

Background

With the rising global burden of chronic diseases, traditional health management models are encountering significant challenges. The integration of artificial intelligence (AI) into chronic disease management has enhanced patient care efficiency, optimized treatment strategies, and reduced healthcare costs, providing innovative solutions in this field. However, current research remains fragmented and lacks systematic, comprehensive analysis.

Objective

This study conducts a bibliometric analysis of AI applications in chronic disease health management, aiming to identify research trends, highlight key areas, and provide valuable insights into the current state of the field. Hoping our findings will serve as a useful reference for guiding further research and fostering the effective application of AI in healthcare.

Methods

The Web of Science Core Collection database was utilized as the source. All relevant publications from inception to August 2024 were retrieved. The external characteristics of the publications were summarized using HistCite. Keyword co-occurrences among countries, authors, and institutions were analyzed with Vosviewer, while CiteSpace was employed to assess keyword frequencies and trends.

Results

A total of 341 publications were retrieved, originating from 775 institutions across 55 countries, and published in 175 journals by 2,128 authors. A notable surge in publications occurred between 2013 and 2024, accounting for 95.31% (325/341) of the total output. The United States and the Journal of Medical Internet Research were the leading contributors in this field. Our analysis of the 341 publications revealed four primary research clusters: diagnosis, care, telemedicine, and technology. Recent trends indicate that mobile health technologies and machine learning have emerged as key focal points in the application of artificial intelligence in the field of chronic disease management.

Conclusion

Despite significant advancements in the application of AI in chronic disease management, several critical challenges persist. These include improving research quality, fostering greater international and inter-institutional collaboration, standardizing data-sharing practices, and addressing ethical and legal concerns. Future research should prioritize strengthening global partnerships to facilitate cross-disciplinary and cross-regional knowledge exchange, optimizing AI technologies for more precise and effective chronic disease management, and ensuring their seamless integration into clinical practice.

Using artificial intelligence to optimize anti-seizure treatment and EEG-guided decisions in severe brain injury

Electroencephalography (EEG) is invaluable in the management of acute neurological emergencies. Characteristic EEG changes have been identified in diverse neurologic conditions including stroke, trauma, and anoxia, and the increased utilization of continuous EEG (cEEG) has identified potentially harmful activity even in patients without overt clinical signs or neurologic diagnoses. Manual annotation by expert neurophysiologists is a major resource limitation in investigating the prognostic and therapeutic implications of these EEG patterns and in expanding EEG use to a broader set of patients who are likely to benefit. Artificial intelligence (AI) has already demonstrated clinical success in guiding cEEG allocation for patients at risk for seizures, and its potential uses in neurocritical care are expanding alongside improvements in AI itself. We review both current clinical uses of AI for EEG-guided management as well as ongoing research directions in automated seizure and ischemia detection, neurologic prognostication, and guidance of medical and surgical treatment.

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.

A Machine Learning-Based Decision Support System for the Prognostication of Neurological Outcomes in Successfully Resuscitated Out-of-Hospital Cardiac Arrest Patients

Background/Objectives: This study uses machine learning and multicenter registry data for analyzing the determinants of a favorable neurological outcome in patients with out-of-hospital cardiac arrest (OHCA) and developing decision support systems for various subgroups. Methods: The data came from the Korean Cardiac Arrest Research Consortium registry, with 2679 patients who underwent OHCA aged 18 or above with the return of spontaneous circulation (ROSC). The dependent variable was a favorable neurological outcome (Cerebral Performance Category score 1-2), and 68 independent variables were included, e.g., first monitored rhythm, in-hospital cardiopulmonary resuscitation (CPR) duration and post-ROSC pH. A random forest was used for identifying the major determinants of the favorable neurological outcome and developing decision support systems for the various subgroups stratified by the major variables. Results: Based on the random forest variable importance, the major determinants of the OHCA patient outcomes were the in-hospital CPR duration (0.0824), in-hospital electrocardiogram on emergency room arrival (0.0692), post-ROSC pH (0.0579), prehospital ROSC before emergency room arrival (0.0565), coronary angiography (0.0527), age (0.0415), first monitored rhythm (EMS) (0.0402), first monitored rhythm (community) (0.0401), early coronary angiography within 24 h (0.0304) and time from scene arrival to CPR stop (0.0301). It was also found that the patients could be divided into six subgroups in terms of their prehospital ROSC and first monitored rhythm (EMS), and that a decision tree could be developed as a decision support system for each subgroup to find the effective cut-off points regarding the in-hospital CPR duration, post-ROSC pH, age and hemoglobin. Conclusions: We identified the major determinants of favorable neurological outcomes in successfully resuscitated patients who underwent OHCA using machine learning. This study demonstrates the strengths of a random forest as an effective decision support system for each stratified subgroup (prehospital ROSC and first monitored rhythm by EMS) to find its own optimal cut-off points for the major in-hospital variables (in-hospital CPR duration, post-ROSC pH, age and hemoglobin).

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 of artificial intelligence in emergency and critical care diagnostics: a systematic review and meta-analysis

Introduction

Artificial intelligence has come to be the highlight in almost all fields of science. It uses various models and algorithms to detect patterns and specific findings to diagnose a disease with utmost accuracy. With the increasing need for accurate and precise diagnosis of disease, employing artificial intelligence models and concepts in healthcare setup can be beneficial.

Methodology

The search engines and databases employed in this study are PubMed, ScienceDirect and Medline. Studies published between 1st January 2013 to 1st February 2023 were included in this analysis. The selected articles were screened preliminarily using the Rayyan web tool, after which investigators screened the selected articles individually. The risk of bias for the selected studies was assessed using QUADAS-2 tool specially designed to test bias among studies related to diagnostic test reviews.

Results

In this review, 17 studies were included from a total of 12,173 studies. These studies were analysed for their sensitivity, accuracy, positive predictive value, specificity and negative predictive value in diagnosing barrette's neoplasia, cardiac arrest, esophageal adenocarcinoma, sepsis and gastrointestinal stromal tumors. All the studies reported heterogeneity with p-value <0.05 at confidence interval 95%.

Conclusion

The existing evidential data suggests that artificial intelligence can be highly helpful in the field of diagnosis providing maximum precision and early detection. This helps to prevent disease progression and also helps to provide treatment at the earliest. Employing artificial intelligence in diagnosis will define the advancement of health care environment and also be beneficial in every aspect concerned with treatment to illnesses.

Artificial Intelligence and Heart-Brain Connections: A Narrative Review on Algorithms Utilization in Clinical Practice

Cardiovascular and neurological diseases are a major cause of mortality and morbidity worldwide. Such diseases require careful monitoring to effectively manage their progression. Artificial intelligence (AI) offers valuable tools for this purpose through its ability to analyse data and identify predictive patterns. This review evaluated the application of AI in cardiac and neurological diseases for their clinical impact on the general population. We reviewed studies on the application of AI in the neurological and cardiological fields. Our search was performed on the PubMed, Web of Science, Embase and Cochrane library databases. Of the initial 5862 studies, 23 studies met the inclusion criteria. The studies showed that the most commonly used algorithms in these clinical fields are Random Forest and Artificial Neural Network, followed by logistic regression and Support-Vector Machines. In addition, an ECG-AI algorithm based on convolutional neural networks has been developed and has been widely used in several studies for the detection of atrial fibrillation with good accuracy. AI has great potential to support physicians in interpretation, diagnosis, risk assessment and disease management.

Prediction of outcomes after cardiac arrest by a generative artificial intelligence model

Aims

To investigate the prognostic accuracy of a non-medical generative artificial intelligence model (Chat Generative Pre-Trained Transformer 4 - ChatGPT-4) as a novel aspect in predicting death and poor neurological outcome at hospital discharge based on real-life data from cardiac arrest patients.

Methods

This prospective cohort study investigates the prognostic performance of ChatGPT-4 to predict outcomes at hospital discharge of adult cardiac arrest patients admitted to intensive care at a large Swiss tertiary academic medical center (COMMUNICATE/PROPHETIC cohort study). We prompted ChatGPT-4 with sixteen prognostic parameters derived from established post-cardiac arrest scores for each patient. We compared the prognostic performance of ChatGPT-4 regarding the area under the curve (AUC), sensitivity, specificity, positive and negative predictive values, and likelihood ratios of three cardiac arrest scores (Out-of-Hospital Cardiac Arrest [OHCA], Cardiac Arrest Hospital Prognosis [CAHP], and PROgnostication using LOGistic regression model for Unselected adult cardiac arrest patients in the Early stages [PROLOGUE score]) for in-hospital mortality and poor neurological outcome.

Results

Mortality at hospital discharge was 43% (n = 309/713), 54% of patients (n = 387/713) had a poor neurological outcome. ChatGPT-4 showed good discrimination regarding in-hospital mortality with an AUC of 0.85, similar to the OHCA, CAHP, and PROLOGUE (AUCs of 0.82, 0.83, and 0.84, respectively) scores. For poor neurological outcome, ChatGPT-4 showed a similar prediction to the post-cardiac arrest scores (AUC 0.83).

Conclusions

ChatGPT-4 showed a similar performance in predicting mortality and poor neurological outcome compared to validated post-cardiac arrest scores. However, more research is needed regarding illogical answers for potential incorporation of an LLM in the multimodal outcome prognostication after cardiac arrest.

Artificial Intelligence and Machine Learning Applications in Critically Ill Brain Injured Patients

The utilization of Artificial Intelligence (AI) and Machine Learning (ML) is paving the way for significant strides in patient diagnosis, treatment, and prognostication in neurocritical care. These technologies offer the potential to unravel complex patterns within vast datasets ranging from vast clinical data and EEG (electroencephalogram) readings to advanced cerebral imaging facilitating a more nuanced understanding of patient conditions. Despite their promise, the implementation of AI and ML faces substantial hurdles. Historical biases within training data, the challenge of interpreting multifaceted data streams, and the "black box" nature of ML algorithms present barriers to widespread clinical adoption. Moreover, ethical considerations around data privacy and the need for transparent, explainable models remain paramount to ensure trust and efficacy in clinical decision-making.This article reflects on the emergence of AI and ML as integral tools in neurocritical care, discussing their roles from the perspective of both their scientific promise and the associated challenges. We underscore the importance of extensive validation in diverse clinical settings to ensure the generalizability of ML models, particularly considering their potential to inform critical medical decisions such as withdrawal of life-sustaining therapies. Advancement in computational capabilities is essential for implementing ML in clinical settings, allowing for real-time analysis and decision support at the point of care. As AI and ML are poised to become commonplace in clinical practice, it is incumbent upon health care professionals to understand and oversee these technologies, ensuring they adhere to the highest safety standards and contribute to the realization of personalized medicine. This engagement will be pivotal in integrating AI and ML into patient care, optimizing outcomes in neurocritical care through informed and data-driven decision-making.

Prediction of risk factors for linezolid-induced thrombocytopenia based on neural network model

Background: Based on real-world medical data, the artificial neural network model was used to predict the risk factors of linezolid-induced thrombocytopenia to provide a reference for better clinical use of this drug and achieve the timely prevention of adverse reactions. Methods: The artificial neural network algorithm was used to construct the prediction model of the risk factors of linezolid-induced thrombocytopenia and further evaluate the effectiveness of the artificial neural network model compared with the traditional Logistic regression model. Results: A total of 1,837 patients receiving linezolid treatment in a hospital in Xi 'an, Shaanxi Province from 1 January 2011 to 1 January 2021 were recruited. According to the exclusion criteria, 1,273 cases that did not meet the requirements of the study were excluded. A total of 564 valid cases were included in the study, with 89 (15.78%) having thrombocytopenia. The prediction accuracy of the artificial neural network model was 96.32%, and the AUROC was 0.944, which was significantly higher than that of the Logistic regression model, which was 86.14%, and the AUROC was 0.796. In the artificial neural network model, urea, platelet baseline value and serum albumin were among the top three important risk factors. Conclusion: The predictive performance of the artificial neural network model is better than that of the traditional Logistic regression model, and it can well predict the risk factors of linezolid-induced thrombocytopenia.

Joint Modeling of Social Determinants and Clinical Factors to Define Subphenotypes in Out-of-Hospital Cardiac Arrest Survival: Cluster Analysis

Background

Machine learning clustering offers an unbiased approach to better understand the interactions of complex social and clinical variables via integrative subphenotypes, an approach not studied in out-of-hospital cardiac arrest (OHCA).

Objective

We conducted a cluster analysis for a cohort of OHCA survivors to examine the association of clinical and social factors for mortality at 1 year.

Methods

We used a retrospective observational OHCA cohort identified from Medicare claims data, including area-level social determinants of health (SDOH) features and hospital-level data sets. We applied k-means clustering algorithms to identify subphenotypes of beneficiaries who had survived an OHCA and examined associations of outcomes by subphenotype.

Results

We identified 27,028 unique beneficiaries who survived to discharge after OHCA. We derived 4 distinct subphenotypes. Subphenotype 1 included a distribution of more urban, female, and Black beneficiaries with the least robust area-level SDOH measures and the highest 1-year mortality (2375/4417, 53.8%). Subphenotype 2 was characterized by a greater distribution of male, White beneficiaries and had the strongest zip code-level SDOH measures, with 1-year mortality at 49.9% (4577/9165). Subphenotype 3 had the highest rates of cardiac catheterization at 34.7% (1342/3866) and the greatest distribution with a driving distance to the index OHCA hospital from their primary residence >16.1 km at 85.4% (8179/9580); more were also discharged to a skilled nursing facility after index hospitalization. Subphenotype 4 had moderate median household income at US $51,659.50 (IQR US $41,295 to $67,081) and moderate to high median unemployment at 5.5% (IQR 4.2%-7.1%), with the lowest 1-year mortality (1207/3866, 31.2%). Joint modeling of these features demonstrated an increased hazard of death for subphenotypes 1 to 3 but not for subphenotype 4 when compared to reference.

Conclusions

We identified 4 distinct subphenotypes with differences in outcomes by clinical and area-level SDOH features for OHCA. Further work is needed to determine if individual or other SDOH domains are specifically tied to long-term survival after OHCA.

Trend of Outcome Metrics in Recent Out-of-Hospital-Cardiac-Arrest Research: A Narrative Review of Clinical Trials

Cardiopulmonary resuscitation (CPR) research traditionally focuses on survival. In 2018, the International Liaison Committee on Resuscitation (ILCOR) proposed more patient-centered outcomes. Our narrative review assessed clinical trials after 2018 to identify the trends of outcome metrics in the field OHCA research. We performed a search of the PubMed database from 1 January 2019 to 22 September 2023. Prospective clinical trials involving adult humans were eligible. Studies that did not report any patient-related outcomes or were not available in full-text or English language were excluded. The articles were assessed for demographic information and primary and secondary outcomes. We included 89 studies for analysis. For the primary outcome, 31 (35%) studies assessed neurocognitive functions, and 27 (30%) used survival. For secondary outcomes, neurocognitive function was present in 20 (22%) studies, and survival was present in 10 (11%) studies. Twenty-six (29%) studies used both survival and neurocognitive function. Since the publication of the COSCA guidelines in 2018, there has been an increased focus on neurologic outcomes. Although survival outcomes are used frequently, we observed a trend toward fewer studies with ROSC as a primary outcome. There were no quality-of-life assessments, suggesting a need for more studies with patient-centered outcomes that can inform the guidelines for cardiac-arrest management.

Artificial intelligence in anesthesiology

Artificial intelligence (AI) is rapidly evolving and gaining attention in the medical world. Our aim is to provide readers with insights into this quickly changing medical landscape and the role of clinicians in the middle of this popular technology. In this review, our aim is to explain some of the increasingly frequently used AI terminology explicitly for physicians. Next, we give a summation, an overview of currently existing applications, future possibilities for AI in the medical field of anesthesiology and thoroughly highlight possible problems that could arise from implementing this technology in daily practice. Therefore, we conducted a literature search, including all types of articles published between the first of January 2010 and the 1st of May 2023, written in English, and having a free full text available. We searched Pubmed, Medline, and Embase using “artificial intelligence”, “machine learning”, “deep learning”, “neural networks” and “anesthesiology” as MESH terms. To structure these findings, we divided the results into five categories: preoperatively, perioperatively, postoperatively, AI in the intensive care unit and finally, AI used for teaching purposes. In the first category, we found AI applications for airway assessment, risk prediction, and logistic support. Secondly, we made a summation of AI applications used during the operation. AI can predict hypotensive events, delivering automated anesthesia, reducing false alarms, and aiding in the analysis of ultrasound anatomy in locoregional anesthesia and echocardiography. Thirdly, namely postoperatively, AI can be applied in predicting acute kidney injury, pulmonary complications, postoperative cognitive dysfunction and can help to diagnose postoperative pain in children. At the intensive care unit, AI tools discriminate acute respiratory distress syndrome (ARDS) from pulmonary oedema in pleural ultrasound, predict mortality and sepsis more accurately, and predict survival rates in severe Coronavirus-19 (COVID-19). Finally, AI has been described in training residents in spinal ultrasound, simulation, and plexus block anatomy. Several concerns must be addressed regarding the use of AI. Firstly, this software does not explain its decision process (i.e., the ‘black box problem’). Secondly, to develop AI models and decision support systems, we need big and accurate datasets, unfortunately with potential unknown bias. Thirdly, we need an ethical and legal framework before implementing this technology. At the end of this paper, we discuss whether this technology will be able to replace the clinician one day. This paper adds value to already existing literature because it not only offers a summation of existing literature on AI applications in anesthesiology but also gives clear definitions of AI itself and critically assesses implementation of this technology.

Guidelines for Neuroprognostication in Comatose Adult Survivors of Cardiac Arrest

BACKGROUND

Among cardiac arrest survivors, about half remain comatose 72 h following return of spontaneous circulation (ROSC). Prognostication of poor neurological outcome in this population may result in withdrawal of life-sustaining therapy and death. The objective of this article is to provide recommendations on the reliability of select clinical predictors that serve as the basis of neuroprognostication and provide guidance to clinicians counseling surrogates of comatose cardiac arrest survivors.

METHODS

A narrative systematic review was completed using Grading of Recommendations Assessment, Development and Evaluation (GRADE) methodology. Candidate predictors, which included clinical variables and prediction models, were selected based on clinical relevance and the presence of an appropriate body of evidence. The Population, Intervention, Comparator, Outcome, Timing, Setting (PICOTS) question was framed as follows: "When counseling surrogates of comatose adult survivors of cardiac arrest, should [predictor, with time of assessment if appropriate] be considered a reliable predictor of poor functional outcome assessed at 3 months or later?" Additional full-text screening criteria were used to exclude small and lower-quality studies. Following construction of the evidence profile and summary of findings, recommendations were based on four GRADE criteria: quality of evidence, balance of desirable and undesirable consequences, values and preferences, and resource use. In addition, good practice recommendations addressed essential principles of neuroprognostication that could not be framed in PICOTS format.

RESULTS

Eleven candidate clinical variables and three prediction models were selected based on clinical relevance and the presence of an appropriate body of literature. A total of 72 articles met our eligibility criteria to guide recommendations. Good practice recommendations include waiting 72 h following ROSC/rewarming prior to neuroprognostication, avoiding sedation or other confounders, the use of multimodal assessment, and an extended period of observation for awakening in patients with an indeterminate prognosis, if consistent with goals of care. The bilateral absence of pupillary light response > 72 h from ROSC and the bilateral absence of N20 response on somatosensory evoked potential testing were identified as reliable predictors. Computed tomography or magnetic resonance imaging of the brain > 48 h from ROSC and electroencephalography > 72 h from ROSC were identified as moderately reliable predictors.

CONCLUSIONS

These guidelines provide recommendations on the reliability of predictors of poor outcome in the context of counseling surrogates of comatose survivors of cardiac arrest and suggest broad principles of neuroprognostication. Few predictors were considered reliable or moderately reliable based on the available body of evidence.

The Aspects of Running Artificial Intelligence in Emergency Care; a Scoping Review

Introduction

Artificial Inteligence (AI) application in emergency medicine is subject to ethical and legal inconsistencies. The purposes of this study were to map the extent of AI applications in emergency medicine, to identify ethical issues related to the use of AI, and to propose an ethical framework for its use.

Methods

A comprehensive literature collection was compiled through electronic databases/internet search engines (PubMed, Web of Science Platform, MEDLINE, Scopus, Google Scholar/Academia, and ERIC) and reference lists. We considered studies published between 1 January 2014 and 6 October 2022. Articles that did not self-classify as studies of an AI intervention, those that were not relevant to Emergency Departments (EDs), and articles that did not report outcomes or evaluations were excluded. Descriptive and thematic analyses of data extracted from the included articles were conducted.

Results

A total of 137 out of the 2175 citations in the original database were eligible for full-text evaluation. Of these articles, 47 were included in the scoping review and considered for theme extraction. This review covers seven main areas of AI techniques in emergency medicine: Machine Learning (ML) Algorithms (10.64%), prehospital emergency management (12.76%), triage, patient acuity and disposition of patients (19.15%), disease and condition prediction (23.40%), emergency department management (17.03%), the future impact of AI on Emergency Medical Services (EMS) (8.51%), and ethical issues (8.51%).

Conclusion

There has been a rapid increase in AI research in emergency medicine in recent years. Several studies have demonstrated the potential of AI in diverse contexts, particularly when improving patient outcomes through predictive modelling. According to the synthesis of studies in our review, AI-based decision-making lacks transparency. This feature makes AI decision-making opaque.

Artificial Intelligence in Resuscitation: A Scoping Review

INTRODUCTION

Cardiac arrest is a significant cause of premature mortality and severe disability. Despite the death rate steadily decreasing over the previous decade, only 22% of survivors achieve good clinical status and only 25% of patients survive until their discharge from the hospital. The objective of this scoping review was to review relevant AI modalities and the main potential applications of AI in resuscitation.

METHODS

We conducted the literature search for related studies in PubMed, EMBASE, and Google Scholar. We included peer-reviewed publications and articles in the press, pooling and characterizing the data by their model types, goals, and benefits.

RESULTS

After identifying 268 original studies, we chose 59 original studies (reporting 1,817,419 patients) to include in the qualitative synthesis. AI-based methods appear to be superior to traditional methods in achieving high-level performance.

CONCLUSION

AI might be useful in predicting cardiac arrest, heart rhythm disorders, and post-cardiac arrest outcomes, as well as in the delivery of drone-delivered defibrillators and notification of dispatchers. AI-powered technologies could be valuable assistants to continuously track patient conditions. Healthcare professionals should assist in the research and development of AI-powered technologies as well as their implementation into clinical practice.

Artificial neural network-boosted Cardiac Arrest Survival Post-Resuscitation In-hospital (CASPRI) score accurately predicts outcome in cardiac arrest patients treated with targeted temperature management

Existing prognostic models to predict the neurological recovery in patients with cardiac arrest receiving targeted temperature management (TTM) either exhibit moderate accuracy or are too complicated for clinical application. This necessitates the development of a simple and generalizable prediction model to inform clinical decision-making for patients receiving TTM. The present study explores the predictive validity of the Cardiac Arrest Survival Post-resuscitation In-hospital (CASPRI) score in cardiac arrest patients receiving TTM, regardless of cardiac event location, and uses artificial neural network (ANN) algorithms to boost the prediction performance. This retrospective observational study evaluated the prognostic relevance of the CASPRI score and applied ANN to develop outcome prediction models in a cohort of 570 patients with cardiac arrest and treated with TTM between 2014 and 2019 in a nationwide multicenter registry in Taiwan. In univariate logistic regression analysis, the CASPRI score was significantly associated with neurological outcome, with the area under the receiver operating characteristics curve (AUC) of 0.811. The generated ANN model, based on 10 items of the CASPRI score, achieved a training AUC of 0.976 and validation AUC of 0.921, with the accuracy, precision, sensitivity, and specificity of 89.2%, 91.6%, 87.6%, and 91.2%, respectively, for the validation set. CASPRI score has prognostic relevance in patients who received TTM after cardiac arrest. The generated ANN-boosted, CASPRI-based model exhibited good performance for predicting TTM neurological outcome, thus, we propose its clinical application to improve outcome prediction, facilitate decision-making, and formulate individualized therapeutic plans for patients receiving TTM.

Remote Health Monitoring in Clinical Trial using Machine Learning Techniques: A Conceptual Framework

Monitoring any process is crucial and very necessary, this is to ensure that standard protocols and procedures are strictly adhered to, monitoring clinical trials is not an exception. It is one of the most crucial processes that should be monitored because human subjects are involved. In trying to monitor clinical trial, information and communication technology techniques can be deployed to facilitate the process and hence improve accuracy. This research formulates a new conceptual framework for monitoring clinical trial using Support Vector Machine and Artificial Neural Network classifiers with physiological datasets from a wearable device. The proposed framework prototype consists of data collection module, data transmission module, and data analysis and prediction module. The data analytic and prediction module is the core section of the proposed framework tailored with data analysis. These datasets are preprocessed and transformed and then used to train and test the system, through different experimental analysis including bagging Support Vector Machine (SVM) and Artificial Neural Network (ANN). The outcome of the analysis presents classification into three different categories, such as fit, unfit, and undecided participants. These various classifications are used to determine if a participant should be allowed to continue in the trial or not. This research provides a framework that is useful in monitoring clinical trial remotely, thereby informing the decision-making process of the research team.

A Knowledge Distillation Ensemble Framework for Predicting Short- and Long-Term Hospitalization Outcomes From Electronic Health Records Data

The ability to perform accurate prognosis is crucial for proactive clinical decision making, informed resource management and personalised care. Existing outcome prediction models suffer from a low recall of infrequent positive outcomes. We present a highly-scalable and robust machine learning framework to automatically predict adversity represented by mortality and ICU admission and readmission from time-series of vital signs and laboratory results obtained within the first 24 hours of hospital admission. The stacked ensemble platform comprises two components: a) an unsupervised LSTM Autoencoder that learns an optimal representation of the time-series, using it to differentiate the less frequent patterns which conclude with an adverse event from the majority patterns that do not, and b) a gradient boosting model, which relies on the constructed representation to refine prediction by incorporating static features. The model is used to assess a patient's risk of adversity and provides visual justifications of its prediction. Results of three case studies show that the model outperforms existing platforms in ICU and general ward settings, achieving average Precision-Recall Areas Under the Curve (PR-AUCs) of 0.891 (95% CI: 0.878-0.939) for mortality and 0.908 (95% CI: 0.870-0.935) in predicting ICU admission and readmission.

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

Background

Out-of-hospital cardiac arrest (OHCA) is a major health problem worldwide, and neurologic injury remains the leading cause of morbidity and mortality among survivors of OHCA. The purpose of this study was to investigate whether a machine learning algorithm could detect complex dependencies between clinical variables in emergency departments in OHCA survivors and perform reliable predictions of favorable neurologic outcomes.

Methods

This study included adults (≥18 years of age) with a sustained return of spontaneous circulation after successful resuscitation from OHCA between 1 January 2004 and 31 December 2014. We applied three machine learning algorithms, including logistic regression (LR), support vector machine (SVM), and extreme gradient boosting (XGB). The primary outcome was a favorable neurological outcome at hospital discharge, defined as a Glasgow-Pittsburgh cerebral performance category of 1 to 2. The secondary outcome was a 30-day survival rate and survival-to-discharge rate.

Results

The final analysis included 1071 participants from the study period. For neurologic outcome prediction, the area under the receiver operating curve (AUC) was 0.819, 0.771, and 0.956 in LR, SVM, and XGB, respectively. The sensitivity and specificity were 0.875 and 0.751 in LR, 0.687 and 0.793 in SVM, and 0.875 and 0.904 in XGB. The AUC was 0.766 and 0.732 in LR, 0.749 and 0.725 in SVM, and 0.866 and 0.831 in XGB, for survival-to-discharge and 30-day survival, respectively.

Conclusions

Prognostic models trained with ML technique showed appropriate calibration and high discrimination for survival and neurologic outcome of OHCA without using prehospital data, with XGB exhibiting the best performance.

Predicting Survived Events in Nontraumatic Out-of-Hospital Cardiac Arrest: A Comparison Study on Machine Learning and Regression Models

BACKGROUND

Prediction of early outcomes of nontraumatic out-of-hospital cardiac arrest (OHCA) by emergency physicians is inaccurate.

OBJECTIVE

Our aim was to develop and validate practical machine learning (ML)-based models to predict early outcomes of nontraumatic OHCA for use in the emergency department (ED). We compared their discrimination and calibration performances with the traditional logistic regression (LR) approach.

METHODS

Between October 1, 2017 and March 31, 2020, prehospital resuscitation was performed on 17,166 OHCA patients. There were 8157 patients 18 years or older with nontraumatic OHCA who received continued resuscitation in the ED included for analysis. Eleven demographic and resuscitation predictor variables were extracted to predict survived events, defined as any sustained return of spontaneous circulation until in-hospital transfer of care. Prediction models based on random forest (RF), multilayer perceptron (MLP), and LR were created with hyperparameter optimization. Model performances on internal and external validation were compared using discrimination and calibration statistics.

RESULTS

The three models showed similar discrimination performances with c-statistics values of 0.712 (95% confidence interval [CI] 0.711-0.713) for LR, 0.714 (95% CI 0.712-0.717) for RF, and 0.712 (95% CI 0.710-0.713) for MLP models on external validation. For calibration, MLP model had a better performance (slope of calibration regression line = 1.10, intercept = -0.09) than LR (slope = 1.17, intercept = -0.11) and RF (slope = 1.16, intercept= -0.10).

CONCLUSIONS

Two practical ML-based and one regression-based clinical prediction models of nontraumatic OHCA for survived events were developed and validated. The ML-based models did not outperform LR in discrimination, but the MLP model showed a better calibration performance.

Using Metabolic and Biochemical Indicators to Predict Diabetic Retinopathy by Back-Propagation Artificial Neural Network

PURPOSE

Timely diagnosis of diabetic retinopathy (DR) can significantly improve the prognosis of patients. In this study, we established a prediction model by analyzing the relationship between diabetic retinopathy and related metabolic and biochemical indicators.

METHODS

A total of 427 type 2 diabetes mellitus (T2DM) patients were selected from the datadryad website data. Logistic regression (MLR) was used to input layer variables of the model were screened. Then, Tan-Sigmoid was selected as the transfer function of the hidden layer node, and the linear function was used as the output layer function to establish the back propagation artificial neural network (BP-ANN) model. The model was applied to 183 patients with type 2 diabetes mellitus (T2DM) in our hospital to predict DR.

RESULTS

A total of 167 patients (39.2%) with DR were obtained from the Datadryad database. Input variables were screened by MLR model, and it was concluded that the age, sex, albumin and creatinine, diabetes course were independently associated with the occurrence of DR. The above variables were used to establish BP-ANN model. The area under receiver operating characteristic curve (AUC) was significantly higher than that of MLR model (0.88 vs 0.74, P<0.05), the probability threshold of the model was 0.3. Type 2 diabetes mellitus (T2DM) were selected in our hospital, including 92 patients with DR (50.2%). The above BP-ANN model was used to predict the incidence of DR, and the AUC area was significantly higher than that of the MLR model (0.77 vs 0.70, P<0.05), the probability threshold was 0.7.

CONCLUSION

We established the BP-ANN model and applied it to diagnose DR. Taking diabetic course, age, sex, albumin and creatinine as the inputs of BP-ANN, the existence of DR could be well predicted. Meanwhile, the generalization ability of the model could be improved by selecting different probability thresholds in different ROC curves.

Year in Review 2020: Noteworthy Literature in Cardiothoracic Anesthesiology

The year 2020 was marred by the emergence of a deadly pandemic that disrupted every aspect of life. Despite the disruption, notable research accomplishments in the practice of cardiothoracic anesthesiology occurred in 2020 with an emphasis on optimizing care, improving outcomes, and expanding what is possible for patients undergoing cardiac surgery. This year's edition of Noteworthy Literature Review will focus on specific themes in cardiac anesthesiology that include preoperative anemia, predictors of acute kidney injury following cardiac surgery, pain management modalities, anticoagulation strategies after transcatheter aortic valve replacement, mechanical circulatory support, and future directions in research.

Plasma proenkephalin A 119-159 and dipeptidyl peptidase 3 on admission after cardiac arrest help predict long-term neurological outcome

BACKGROUND

A large proportion of adult survivors of cardiac arrest have a poor neurological outcome. Guidelines recommend multimodal neuro-prognostication no earlier than 72-96 h after cardiac arrest. There is great interest in earlier prognostic markers, including very early markers at admission. The novel blood biomarkers proenkephalin A 119-159 (penKid), bioactive adrenomedullin (bio-ADM) and circulating dipeptidyl peptidase 3 (cDPP3) have not been previously investigated for the early prognosis of cardiac arrest survivors.

METHODS

This multicentre observational study included adult survivors of cardiac arrest admitted to intensive care at four Swedish intensive care units (ICUs) during 2016. Blood samples were collected at ICU admission and batch analysed. The association between admission plasma penKid, bio-ADM and cDPP3 and poor long-term neurological outcome, according to the Cerebral Performance Category (CPC) scale, was assessed by binary logistic regression. Their prognostic performance was assessed using the area under the receiver operating characteristic curve (AUC).

RESULTS

A total of 190 patients were included, of which 136 patients had suffered out-of-hospital and 54 patients in-hospital cardiac arrest. Poor long-term neurological outcome was associated with elevated admission plasma concentrations of penKid and cDPP3, but not with bio-ADM. The association for penKid, but not for cDPP3, remained after adjusting for clinical cardiac arrest variables with prognostic value (time to return of spontaneous circulation (ROSC), initial rhythm, admission Glasgow coma scale (GCS) motor score and absence of pupillary reflexes). The prognostic performance of above mentioned clinical cardiac arrest variables alone was very good with an AUC of 0.90 (95% confidence interval, CI, 0.86-0.95), but improved further with the addition of penKid resulting in an AUC of 0.93 (95% CI 0.89-0.97, p < 0.026). Plasma penKid and cDPP3 alone provided moderate long-term prognostic information with AUCs of 0.70 and 0.71, respectively.

CONCLUSION

After cardiac arrest, admission plasma levels of penKid and cDPP3, but not bio-ADM, predicted long-term neurological outcome. When added to clinical cardiac arrest variables, penKid further improved prognostic performance.

Clinical Application of Machine Learning-Based Artificial Intelligence in the Diagnosis, Prediction, and Classification of Cardiovascular Diseases

With the rapid development of artificial intelligence (AI) and machine learning (ML), as well as the arrival of the big data era, technological innovations have occurred in the field of cardiovascular medicine. First, the diagnosis of cardiovascular diseases (CVDs) is highly dependent on assistive examinations, the interpretation of which is time consuming and often limited by the knowledge level and clinical experience of doctors; however, AI could be used to automatically interpret the images obtained in auxiliary examinations. Second, some of the predictions of the incidence and prognosis of CVDs are limited in clinical practice by the use of traditional prediction models, but there may be occasions when AI-based prediction models perform well by using ML algorithms. Third, AI has been used to assist precise classification of CVDs by integrating a variety of medical data from patients, which helps better characterize the subgroups of heterogeneous diseases. To help clinicians better understand the applications of AI in CVDs, this review summarizes studies relating to AI-based diagnosis, prediction, and classification of CVDs. Finally, we discuss the challenges of applying AI to cardiovascular medicine.

Prediction of Neurologically Intact Survival in Cardiac Arrest Patients without Pre-Hospital Return of Spontaneous Circulation: Machine Learning Approach

Current multimodal approaches for the prognostication of out-of-hospital cardiac arrest (OHCA) are based mainly on the prediction of poor neurological outcomes; however, it is challenging to identify patients expected to have a favorable outcome, especially before the return of spontaneous circulation (ROSC). We developed and validated a machine learning-based system to predict good outcome in OHCA patients before ROSC. This prospective, multicenter, registry-based study analyzed non-traumatic OHCA data collected between October 2015 and June 2017. We used information available before ROSC as predictor variables, and the primary outcome was neurologically intact survival at discharge, defined as cerebral performance category 1 or 2. The developed models’ robustness were evaluated and compared with various score metrics to confirm their performance. The model using a voting classifier had the best performance in predicting good neurological outcome (area under the curve = 0.926). We confirmed that the six top-weighted variables predicting neurological outcomes, such as several duration variables after the instant of OHCA and several electrocardiogram variables in the voting classifier model, showed significant differences between the two neurological outcome groups. These findings demonstrate the potential utility of a machine learning model to predict good neurological outcome of OHCA patients before ROSC.

Predicting neurological outcome after out-of-hospital cardiac arrest with cumulative information; development and internal validation of an artificial neural network algorithm

Background

Prognostication of neurological outcome in patients who remain comatose after cardiac arrest resuscitation is complex. Clinical variables, as well as biomarkers of brain injury, cardiac injury, and systemic inflammation, all yield some prognostic value. We hypothesised that cumulative information obtained during the first three days of intensive care could produce a reliable model for predicting neurological outcome following out-of-hospital cardiac arrest (OHCA) using artificial neural network (ANN) with and without biomarkers.

Methods

We performed a post hoc analysis of 932 patients from the Target Temperature Management trial. We focused on comatose patients at 24, 48, and 72 h post-cardiac arrest and excluded patients who were awake or deceased at these time points. 80% of the patients were allocated for model development (training set) and 20% for internal validation (test set). To investigate the prognostic potential of different levels of biomarkers (clinically available and research-grade), patients’ background information, and intensive care observation and treatment, we created three models for each time point: (1) clinical variables, (2) adding clinically accessible biomarkers, e.g., neuron-specific enolase (NSE) and (3) adding research-grade biomarkers, e.g., neurofilament light (NFL). Patient outcome was the dichotomised Cerebral Performance Category (CPC) at six months; a good outcome was defined as CPC 1–2 whilst a poor outcome was defined as CPC 3–5. The area under the receiver operating characteristic curve (AUROC) was calculated for all test sets.

Results

AUROC remained below 90% when using only clinical variables throughout the first three days in the ICU. Adding clinically accessible biomarkers such as NSE, AUROC increased from 82 to 94% (p < 0.01). The prognostic accuracy remained excellent from day 1 to day 3 with an AUROC at approximately 95% when adding research-grade biomarkers. The models which included NSE after 72 h and NFL on any of the three days had a low risk of false-positive predictions while retaining a low number of false-negative predictions.

Conclusions

In this exploratory study, ANNs provided good to excellent prognostic accuracy in predicting neurological outcome in comatose patients post OHCA. The models which included NSE after 72 h and NFL on all days showed promising prognostic performance.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13054-021-03505-9.

The Recent Progress and Applications of Digital Technologies in Healthcare: A Review

BACKGROUND

The implementation of medical digital technologies can provide better accessibility and flexibility of healthcare for the public. It encompasses the availability of open information on the health, treatment, complications, and recent progress on biomedical research. At present, even in low-income countries, diagnostic and medical services are becoming more accessible and available. However, many issues related to digital health technologies remain unmet, including the reliability, safety, testing, and ethical aspects.

PURPOSE

The aim of the review is to discuss and analyze the recent progress on the application of big data, artificial intelligence, telemedicine, block-chain platforms, smart devices in healthcare, and medical education. Basic Design. The publication search was carried out using Google Scholar, PubMed, Web of Sciences, Medline, Wiley Online Library, and CrossRef databases. The review highlights the applications of artificial intelligence, "big data," telemedicine and block-chain technologies, and smart devices (internet of things) for solving the real problems in healthcare and medical education. Major Findings. We identified 252 papers related to the digital health area. However, the number of papers discussed in the review was limited to 152 due to the exclusion criteria. The literature search demonstrated that digital health technologies became highly sought due to recent pandemics, including COVID-19. The disastrous dissemination of COVID-19 through all continents triggered the need for fast and effective solutions to localize, manage, and treat the viral infection. In this regard, the use of telemedicine and other e-health technologies might help to lessen the pressure on healthcare systems. Summary. Digital platforms can help optimize diagnosis, consulting, and treatment of patients. However, due to the lack of official regulations and recommendations, the stakeholders, including private and governmental organizations, are facing the problem with adequate validation and approbation of novel digital health technologies. In this regard, proper scientific research is required before a digital product is deployed for the healthcare sector.