Artificial Intelligence in Critical Care Medicine

Intracranial pressure monitoring in adult patients with traumatic brain injury: challenges and innovations

Intracranial pressure monitoring enables the detection and treatment of intracranial hypertension, a potentially lethal insult after traumatic brain injury. Despite its widespread use, robust evidence supporting intracranial pressure monitoring and treatment remains sparse. International studies have shown large variations between centres regarding the indications for intracranial pressure monitoring and treatment of intracranial hypertension. Experts have reviewed these two aspects and, by consensus, provided practical approaches for monitoring and treatment. Advances have occurred in methods for non-invasive estimation of intracranial pressure although, for now, a reliable way to non-invasively and continuously measure intracranial pressure remains aspirational. Analysis of the intracranial pressure signal can provide information on brain compliance (ie, the ability of the cranium to tolerate volume changes) and on cerebral autoregulation (ie, the ability of cerebral blood vessels to react to changes in blood pressure). The information derived from the intracranial pressure signal might allow for more individualised patient management. Machine learning and artificial intelligence approaches are being increasingly applied to intracranial pressure monitoring, but many obstacles need to be overcome before their use in clinical practice could be attempted. Robust clinical trials are needed to support indications for intracranial pressure monitoring and treatment. Progress in non-invasive assessment of intracranial pressure and in signal analysis (for targeted treatment) will also be crucial.

Early sepsis mortality prediction model based on interpretable machine learning approach: development and validation study

Sepsis triggers a harmful immune response due to infection, causing high mortality. Predicting sepsis outcomes early is vital. Despite machine learning's (ML) use in medical research, local validation within the Medical Information Mart for Intensive Care IV (MIMIC-IV) database is lacking. We aimed to devise a prognostic model, leveraging MIMIC-IV data, to predict sepsis mortality and validate it in a Chinese teaching hospital. MIMIC-IV provided patient data, split into training and internal validation sets. Four ML models logistic regression (LR), support vector machine (SVM), deep neural networks (DNN), and extreme gradient boosting (XGBoost) were employed. Shapley additive interpretation offered early and interpretable mortality predictions. Area under the ROC curve (AUROC) gaged predictive performance. Results were cross verified in a Chinese teaching hospital. The study included 27,134 sepsis patients from MIMIC-IV and 487 from China. After comparing, 52 clinical indicators were selected for ML model development. All models exhibited excellent discriminative ability. XGBoost surpassed others, with AUROC of 0.873 internally and 0.844 externally. XGBoost outperformed other ML models (LR: 0.829; SVM: 0.830; DNN: 0.837) and clinical scores (Simplified Acute Physiology Score II: 0.728; Sequential Organ Failure Assessment: 0.728; Oxford Acute Severity of Illness Score: 0.738; Glasgow Coma Scale: 0.691). XGBoost's hospital mortality prediction achieved AUROC 0.873, sensitivity 0.818, accuracy 0.777, specificity 0.768, and F1 score 0.551. We crafted an interpretable model for sepsis death risk prediction. ML algorithms surpassed traditional scores for sepsis mortality forecast. Validation in a Chinese teaching hospital echoed these findings.

Artificial intelligence and machine learning: Definition of terms and current concepts in critical care research

With increasing computing power, artificial intelligence (AI) and machine learning (ML) have prospered, which facilitate the analysis of large datasets, especially those found in critical care. It is important to define these terminologies, to inform a standardized approach to critical care research. This manuscript hopes to clarify these terms with examples from medical literature. Three major components that are required for a successful ML implementation: (i) reliable dataset, (ii) ML algorithm, and (iii) unbiased model evaluation, are discussed. A reliable dataset can be structured or unstructured with limited noise, outliers, and missing values. ML, a subset of AI, is typically focused on supervised or unsupervised learning tasks in which the output is based on inputs and derived from iterative pattern recognition algorithms, while AI is the overall ability of a machine to "think" or mimic human behavior; and to analyze data free from human influence. Even with successful implementation, advanced AI and ML algorithms have faced challenges in adoption into practice, mainly due to their lack of interpretability, which hinders trust, buy-in, and engagement from clinicians. Consequently, traditional algorithms, such as linear and logistic regression, that may have reduced predictive power but are highly interpretable, continue to be widely used.

Role of artificial intelligence in critical care nutrition support and research

Nutrition plays a key role in the comprehensive care of critically ill patients. Determining optimal nutrition strategy, however, remains a subject of intense debate. Artificial intelligence (AI) applications are becoming increasingly common in medicine, and specifically in critical care, driven by the data-rich environment of intensive care units. In this review, we will examine the evidence regarding the application of AI in critical care nutrition. As of now, the use of AI in critical care nutrition is relatively limited, with its primary emphasis on malnutrition screening and tolerance of enteral nutrition. Despite the current scarcity of evidence, the potential for AI for more personalized nutrition management for critically ill patients is substantial. This stems from the ability of AI to integrate multiple data streams reflecting patients' changing needs while addressing inherent heterogeneity. The application of AI in critical care nutrition holds promise for optimizing patient outcomes through tailored and adaptive nutrition interventions. A successful implementation of AI, however, necessitates a multidisciplinary approach, coupled with careful consideration of challenges related to data management, financial aspects, and patient privacy.

A common data model for the standardization of intensive care unit medication features

Objective

Common data models provide a standard means of describing data for artificial intelligence (AI) applications, but this process has never been undertaken for medications used in the intensive care unit (ICU). We sought to develop a common data model (CDM) for ICU medications to standardize the medication features needed to support future ICU AI efforts.

Materials and Methods

A 9-member, multi-professional team of ICU clinicians and AI experts conducted a 5-round modified Delphi process employing conference calls, web-based communication, and electronic surveys to define the most important medication features for AI efforts. Candidate ICU medication features were generated through group discussion and then independently scored by each team member based on relevance to ICU clinical decision-making and feasibility for collection and coding. A key consideration was to ensure the final ontology both distinguished unique medications and met Findable, Accessible, Interoperable, and Reusable (FAIR) guiding principles.

Results

Using a list of 889 ICU medications, the team initially generated 106 different medication features, and 71 were ranked as being core features for the CDM. Through this process, 106 medication features were assigned to 2 key feature domains: drug product-related (n = 43) and clinical practice-related (n = 63). Each feature included a standardized definition and suggested response values housed in the electronic data library. This CDM for ICU medications is available online.

Conclusion

The CDM for ICU medications represents an important first step for the research community focused on exploring how AI can improve patient outcomes and will require ongoing engagement and refinement.

Extracorporeal organ support for critically ill patients: Overcoming the past, achieving the maximum at present, and redefining the future

Extracorporeal organ support (ECOS) has made remarkable progress over the last few years. Renal replacement therapy, introduced a few decades ago, was the first available application of ECOS. The subsequent evolution of ECOS enabled the enhanced support to many other organs, including the heart [veno-arterial extracorporeal membrane oxygenation (ECMO), slow continuous ultrafiltration], the lungs (veno-venous ECMO, extracorporeal carbon dioxide removal), and the liver (blood purification techniques for the detoxification of liver toxins). Moreover, additional indications of these methods, including the suppression of excessive inflammatory response occurring in severe disorders such as sepsis, coronavirus disease 2019, pancreatitis, and trauma (blood purification techniques for the removal of exotoxins, endotoxins, or cytokines), have arisen. Multiple organ support therapy is crucial since a vast majority of critically ill patients present not with a single but with multiple organ failure (MOF), whereas, traditional therapeutic approaches (mechanical ventilation for acute respiratory failure, antibiotics for sepsis, and inotropes for cardiac dysfunction) have reached the maximum efficacy and cannot be improved further. However, several issues remain to be clarified, such as the complexity and cost of ECOS systems, standardization of indications, therapeutic protocols and initiation time, choice of the patients who will benefit most from these interventions, while evidence from randomized controlled trials supporting their use is still limited. Nevertheless, these methods are currently a part of routine clinical practice in intensive care units. This editorial presents the past, present, and future considerations, as well as perspectives regarding these therapies. Our better understanding of these methods, the pathophysiology of MOF, the crosstalk between native organs resulting in MOF, and the crosstalk between native organs and artificial organ support systems when applied sequentially or simultaneously, will lead to the multiplication of their effects and the minimization of complications arising from their use.

Advanced neuromonitoring powered by ICM+ and its place in the Brand New AI World, reflections at the 20th anniversary boundary

Introduction

Adoption of the ICM+® brain monitoring software by clinical research centres worldwide has been continuously growing over the past 20 years. This has necessitated ongoing updates to accommodate evolving neuromonitoring research needs, including recent explosion of artificial intelligence (AI).

Research question

We sought to provide an update on the current features of the software. In particular, we aimed to highlight the new options of integrating AI models.

Material and methods

We reviewed all currently available ICM+ analytical areas and discussed potential AI based extensions in each. We tested a proof-of-concept integration of an AI model and evaluated its performance for real-time data processing.

Results

ICM+ current analytical tools serve both real-time (bed-side) and offline (file based) analysis, including the calculation engine, Signal Calculator, Custom Statistics, Batch tools, ScriptLab and charting. The ICM+ Python plugin engine allows to execute custom Python scripts and take advantage of complex AI frameworks. For the proof-of-concept, we used a neural network convolutional model with 207,000 trainable parameters that classifies morphology of intracranial pressure (ICP) pulse waveform into 5 pulse categories (normal to pathological plus artefactual). When evaluated within ICM+ plugin script on a Windows 10 laptop the classification of a 5 min ICP waveform segment took only 0.19s with a 2.3s of initial, one-off, model loading time required.

Conclusions

Modernised ICM+ analytical tools, reviewed in this manuscript, include integration of custom AI models allowing them to be shared and run in real-time, facilitating rapid prototyping and validating of new AI ideas at the bed-side.

Artificial Intelligence in the Intensive Care Unit: Current Evidence on an Inevitable Future Tool

Artificial intelligence (AI) is a technique that attempts to replicate human intelligence, analytical behavior, and decision-making ability. This includes machine learning, which involves the use of algorithms and statistical techniques to enhance the computer's ability to make decisions more accurately. Due to AI's ability to analyze, comprehend, and interpret considerable volumes of data, it has been increasingly used in the field of healthcare. In critical care medicine, where most of the patient load requires timely interventions due to the perilous nature of the condition, AI's ability to monitor, analyze, and predict unfavorable outcomes is an invaluable asset. It can significantly improve timely interventions and prevent unfavorable outcomes, which, otherwise, is not always achievable owing to the constrained human ability to multitask with optimum efficiency. AI has been implicated in intensive care units over the past many years. In addition to its advantageous applications, this article discusses its disadvantages, prospects, and the changes needed to train future critical care professionals. A comprehensive search of electronic databases was performed using relevant keywords. Data from articles pertinent to the topic was assimilated into this review article.

Centralized Multipatient Dashboards' Impact on Intensive Care Unit Clinician Performance and Satisfaction: A Systematic Review

BACKGROUND

 Intensive care unit (ICU) clinicians encounter frequent challenges with managing vast amounts of fragmented data while caring for multiple critically ill patients simultaneously. This may lead to increased provider cognitive load that may jeopardize patient safety.

OBJECTIVES

 This systematic review assesses the impact of centralized multipatient dashboards on ICU clinician performance, perceptions regarding the use of these tools, and patient outcomes.

METHODS

 A literature search was conducted on February 9, 2023, using the EBSCO CINAHL, Cochrane Central Register of Controlled Trials, Embase, IEEE Xplore, MEDLINE, Scopus, and Web of Science Core Collection databases. Eligible studies that included ICU clinicians as participants and tested the effect of dashboards designed for use by multiple users to manage multiple patients on user performance and/or satisfaction compared with the standard practice. We narratively synthesized eligible studies following the SWiM (Synthesis Without Meta-analysis) guidelines. Studies were grouped based on dashboard type and outcomes assessed.

RESULTS

 The search yielded a total of 2,407 studies. Five studies met inclusion criteria and were included. Among these, three studies evaluated interactive displays in the ICU, one study assessed two dashboards in the pediatric ICU (PICU), and one study examined centralized monitor in the PICU. Most studies reported several positive outcomes, including reductions in data gathering time before rounds, a decrease in misrepresentations during multidisciplinary rounds, improved daily documentation compliance, faster decision-making, and user satisfaction. One study did not report any significant association.

CONCLUSION

 The multipatient dashboards were associated with improved ICU clinician performance and were positively perceived in most of the included studies. The risk of bias was high, and the certainty of evidence was very low, due to inconsistencies, imprecision, indirectness in the outcome measure, and methodological limitations. Designing and evaluating multipatient tools using robust research methodologies is an important focus for future research.

Building a house without foundations? A 24-country qualitative interview study on artificial intelligence in intensive care medicine

OBJECTIVES

To explore the views of intensive care professionals in high-income countries (HICs) and lower-to-middle-income countries (LMICs) regarding the use and implementation of artificial intelligence (AI) technologies in intensive care units (ICUs).

METHODS

Individual semi-structured qualitative interviews were conducted between December 2021 and August 2022 with 59 intensive care professionals from 24 countries. Transcripts were analysed using conventional content analysis.

RESULTS

Participants had generally positive views about the potential use of AI in ICUs but also reported some well-known concerns about the use of AI in clinical practice and important technical and non-technical barriers to the implementation of AI. Important differences existed between ICUs regarding their current readiness to implement AI. However, these differences were not primarily between HICs and LMICs, but between a small number of ICUs in large tertiary hospitals in HICs, which were reported to have the necessary digital infrastructure for AI, and nearly all other ICUs in both HICs and LMICs, which were reported to neither have the technical capability to capture the necessary data or use AI, nor the staff with the right knowledge and skills to use the technology.

CONCLUSION

Pouring massive amounts of resources into developing AI without first building the necessary digital infrastructure foundation needed for AI is unethical. Real-world implementation and routine use of AI in the vast majority of ICUs in both HICs and LMICs included in our study is unlikely to occur any time soon. ICUs should not be using AI until certain preconditions are met.

Use of artificial intelligence in critical care: opportunities and obstacles

BACKGROUND

Perhaps nowhere else in the healthcare system than in the intensive care unit environment are the challenges to create useful models with direct time-critical clinical applications more relevant and the obstacles to achieving those goals more massive. Machine learning-based artificial intelligence (AI) techniques to define states and predict future events are commonplace activities of modern life. However, their penetration into acute care medicine has been slow, stuttering and uneven. Major obstacles to widespread effective application of AI approaches to the real-time care of the critically ill patient exist and need to be addressed.

MAIN BODY

Clinical decision support systems (CDSSs) in acute and critical care environments support clinicians, not replace them at the bedside. As will be discussed in this review, the reasons are many and include the immaturity of AI-based systems to have situational awareness, the fundamental bias in many large databases that do not reflect the target population of patient being treated making fairness an important issue to address and technical barriers to the timely access to valid data and its display in a fashion useful for clinical workflow. The inherent "black-box" nature of many predictive algorithms and CDSS makes trustworthiness and acceptance by the medical community difficult. Logistically, collating and curating in real-time multidimensional data streams of various sources needed to inform the algorithms and ultimately display relevant clinical decisions support format that adapt to individual patient responses and signatures represent the efferent limb of these systems and is often ignored during initial validation efforts. Similarly, legal and commercial barriers to the access to many existing clinical databases limit studies to address fairness and generalizability of predictive models and management tools.

CONCLUSIONS

AI-based CDSS are evolving and are here to stay. It is our obligation to be good shepherds of their use and further development.

[Functional requirements of patient data management systems in intensive care medicine]

BACKGROUND

As part of the German government's digitization initiative, the paper-based documentation that is still present in many intensive care units is to be replaced by digital patient data management systems (PDMS). In order to simplify the implementation of such systems, standards for basic functionalities that should be part of basic configurations of PDMS would be of great value.

PURPOSE

This paper describes functional requirements for PDMS in several categories.

METHODS

Criteria for standardized data documentation were defined by the authors and derived functional requirements were classified into two priority categories.

RESULTS

Overall, general technical requirements, functionalities for intensive care patient care, and additional functionalities for PDMS were defined and prioritized.

DISCUSSION

Using this paper as a starting point for a discussion about basic functionalities of PDMS, it is planned to develop and obtain consensus on definitive standards with representatives from medical societies, medical informatics and PDMS manufacture.

Unsupervised machine learning analysis to identify patterns of ICU medication use for fluid overload prediction

INTRODUCTION

Intravenous (IV) medications are a fundamental cause of fluid overload (FO) in the intensive care unit (ICU); however, the association between IV medication use (including volume), administration timing, and FO occurrence remains unclear.

METHODS

This retrospective cohort study included consecutive adults admitted to an ICU ≥72 hours with available fluid balance data. FO was defined as a positive fluid balance ≥7% of admission body weight within 72 hours of ICU admission. After reviewing medication administration record (MAR) data in three-hour periods, IV medication exposure was categorized into clusters using principal component analysis (PCA) and Restricted Boltzmann Machine (RBM). Medication regimens of patients with and without FO were compared within clusters to assess for temporal clusters associated with FO using the Wilcoxon rank sum test. Exploratory analyses of the medication cluster most associated with FO for medications frequently appearing and used in the first 24 hours was conducted.

RESULTS

FO occurred in 127/927 (13.7%) of the patients enrolled. Patients received a median (IQR) of 31 (13-65) discrete IV medication administrations over the 72-hour period. Across all 47,803 IV medication administrations, ten unique IV medication clusters were identified with 121-130 medications in each cluster. Among the ten clusters, cluster 7 had the greatest association with FO; the mean number of cluster 7 medications received was significantly greater in patients in the FO cohort compared to patients who did not experience FO (25.6 vs.10.9. p<0.0001). 51 of the 127 medications in cluster 7 (40.2%) appeared in > 5 separate 3-hour periods during the 72-hour study window. The most common cluster 7 medications included continuous infusions, antibiotics, and sedatives/analgesics. Addition of cluster 7 medications to a prediction model with APACHE II score and receipt of diuretics improved the ability for the model to predict fluid overload (AUROC 5.65, p =0.0004).

CONCLUSIONS

Using ML approaches, a unique IV medication cluster was strongly associated with FO. Incorporation of this cluster improved the ability to predict development of fluid overload in ICU patients compared with traditional prediction models. This method may be further developed into real-time clinical applications to improve early detection of adverse outcomes.

The intervention of artificial intelligence to improve the weaning outcomes of patients with mechanical ventilation: Practical applications in the medical intensive care unit and the COVID-19 intensive care unit: A retrospective study

Patients admitted to intensive care units (ICU) and receiving mechanical ventilation (MV) may experience ventilator-associated adverse events and have prolonged ICU length of stay (LOS). We conducted a survey on adult patients in the medical ICU requiring MV. Utilizing big data and artificial intelligence (AI)/machine learning, we developed a predictive model to determine the optimal timing for weaning success, defined as no reintubation within 48 hours. An interdisciplinary team integrated AI into our MV weaning protocol. The study was divided into 2 parts. The first part compared outcomes before AI (May 1 to Nov 30, 2019) and after AI (May 1 to Nov 30, 2020) implementation in the medical ICU. The second part took place during the COVID-19 pandemic, where patients were divided into control (without AI assistance) and intervention (with AI assistance) groups from Aug 1, 2022, to Apr 30, 2023, and we compared their short-term outcomes. In the first part of the study, the intervention group (with AI, n = 1107) showed a shorter mean MV time (144.3 hours vs 158.7 hours, P = .077), ICU LOS (8.3 days vs 8.8 days, P = .194), and hospital LOS (22.2 days vs 25.7 days, P = .001) compared to the pre-intervention group (without AI, n = 1298). In the second part of the study, the intervention group (with AI, n = 88) exhibited a shorter mean MV time (244.2 hours vs 426.0 hours, P = .011), ICU LOS (11.0 days vs 18.7 days, P = .001), and hospital LOS (23.5 days vs 40.4 days, P < .001) compared to the control group (without AI, n = 43). The integration of AI into the weaning protocol led to improvements in the quality and outcomes of MV patients.

Development and Validation of an Interpretable Conformal Predictor to Predict Sepsis Mortality Risk: Retrospective Cohort Study

BACKGROUND

Early and reliable identification of patients with sepsis who are at high risk of mortality is important to improve clinical outcomes. However, 3 major barriers to artificial intelligence (AI) models, including the lack of interpretability, the difficulty in generalizability, and the risk of automation bias, hinder the widespread adoption of AI models for use in clinical practice.

OBJECTIVE

This study aimed to develop and validate (internally and externally) a conformal predictor of sepsis mortality risk in patients who are critically ill, leveraging AI-assisted prediction modeling. The proposed approach enables explaining the model output and assessing its confidence level.

METHODS

We retrospectively extracted data on adult patients with sepsis from a database collected in a teaching hospital at Beth Israel Deaconess Medical Center for model training and internal validation. A large multicenter critical care database from the Philips eICU Research Institute was used for external validation. A total of 103 clinical features were extracted from the first day after admission. We developed an AI model using gradient-boosting machines to predict the mortality risk of sepsis and used Mondrian conformal prediction to estimate the prediction uncertainty. The Shapley additive explanation method was used to explain the model.

RESULTS

A total of 16,746 (80%) patients from Beth Israel Deaconess Medical Center were used to train the model. When tested on the internal validation population of 4187 (20%) patients, the model achieved an area under the receiver operating characteristic curve of 0.858 (95% CI 0.845-0.871), which was reduced to 0.800 (95% CI 0.789-0.811) when externally validated on 10,362 patients from the Philips eICU database. At a specified confidence level of 90% for the internal validation cohort the percentage of error predictions (n=438) out of all predictions (n=4187) was 10.5%, with 1229 (29.4%) predictions requiring clinician review. In contrast, the AI model without conformal prediction made 1449 (34.6%) errors. When externally validated, more predictions (n=4004, 38.6%) were flagged for clinician review due to interdatabase heterogeneity. Nevertheless, the model still produced significantly lower error rates compared to the point predictions by AI (n=1221, 11.8% vs n=4540, 43.8%). The most important predictors identified in this predictive model were Acute Physiology Score III, age, urine output, vasopressors, and pulmonary infection. Clinically relevant risk factors contributing to a single patient were also examined to show how the risk arose.

CONCLUSIONS

By combining model explanation and conformal prediction, AI-based systems can be better translated into medical practice for clinical decision-making.

Advances and Challenges in Sepsis Management: Modern Tools and Future Directions

Sepsis, a critical condition marked by systemic inflammation, profoundly impacts both innate and adaptive immunity, often resulting in lymphopenia. This immune alteration can spare regulatory T cells (Tregs) but significantly affects other lymphocyte subsets, leading to diminished effector functions, altered cytokine profiles, and metabolic changes. The complexity of sepsis stems not only from its pathophysiology but also from the heterogeneity of patient responses, posing significant challenges in developing universally effective therapies. This review emphasizes the importance of phenotyping in sepsis to enhance patient-specific diagnostic and therapeutic strategies. Phenotyping immune cells, which categorizes patients based on clinical and immunological characteristics, is pivotal for tailoring treatment approaches. Flow cytometry emerges as a crucial tool in this endeavor, offering rapid, low cost and detailed analysis of immune cell populations and their functional states. Indeed, this technology facilitates the understanding of immune dysfunctions in sepsis and contributes to the identification of novel biomarkers. Our review underscores the potential of integrating flow cytometry with omics data, machine learning and clinical observations to refine sepsis management, highlighting the shift towards personalized medicine in critical care. This approach could lead to more precise interventions, improving outcomes in this heterogeneously affected patient population.

Predicting Acute Brain Injury in Venoarterial Extracorporeal Membrane Oxygenation Patients with Tree-Based Machine Learning: Analysis of the Extracorporeal Life Support Organization Registry

Objective

To determine if machine learning (ML) can predict acute brain injury (ABI) and identify modifiable risk factors for ABI in venoarterial extracorporeal membrane oxygenation (VA-ECMO) patients.

Design

Retrospective cohort study of the Extracorporeal Life Support Organization (ELSO) Registry (2009-2021).

Setting

International, multicenter registry study of 676 ECMO centers.

Patients

Adults (≥18 years) supported with VA-ECMO or extracorporeal cardiopulmonary resuscitation (ECPR).

Interventions

None.

Measurements and Main Results

Our primary outcome was ABI: central nervous system (CNS) ischemia, intracranial hemorrhage (ICH), brain death, and seizures. We utilized Random Forest, CatBoost, LightGBM and XGBoost ML algorithms (10-fold leave-one-out cross-validation) to predict and identify features most important for ABI. We extracted 65 total features: demographics, pre-ECMO/on-ECMO laboratory values, and pre-ECMO/on-ECMO settings.Of 35,855 VA-ECMO (non-ECPR) patients (median age=57.8 years, 66% male), 7.7% (n=2,769) experienced ABI. In VA-ECMO (non-ECPR), the area under the receiver-operator characteristics curves (AUC-ROC) to predict ABI, CNS ischemia, and ICH was 0.67, 0.67, and 0.62, respectively. The true positive, true negative, false positive, false negative, positive, and negative predictive values were 33%, 88%, 12%, 67%, 18%, and 94%, respectively for ABI. Longer ECMO duration, higher 24h ECMO pump flow, and higher on-ECMO PaO2 were associated with ABI.Of 10,775 ECPR patients (median age=57.1 years, 68% male), 16.5% (n=1,787) experienced ABI. The AUC-ROC for ABI, CNS ischemia, and ICH was 0.72, 0.73, and 0.69, respectively. The true positive, true negative, false positive, false negative, positive, and negative predictive values were 61%, 70%, 30%, 39%, 29% and 90%, respectively, for ABI. Longer ECMO duration, younger age, and higher 24h ECMO pump flow were associated with ABI.

Conclusions

This is the largest study predicting neurological complications on sufficiently powered international ECMO cohorts. Longer ECMO duration and higher 24h pump flow were associated with ABI in both non-ECPR and ECPR VA-ECMO.

Analysis of comprehensive biomolecules in critically ill patients via bioinformatics technologies

Each patient with a critical illness such as sepsis and severe trauma has a different genetic background, comorbidities, age, and sex. Moreover, pathophysiology changes dynamically over time even in the same patient. Therefore, individualized treatment is necessary to account for heterogeneity in patient backgrounds. Recently, the analysis of comprehensive biomolecular information using clinical specimens has revealed novel molecular pathological classifications called subtypes. In addition, comprehensive biomolecular information using clinical specimens has enabled reverse translational research, which is a data-driven approach to the identification of drug target molecules. The development of these methods is expected to visualize the heterogeneity of patient backgrounds and lead to personalized therapy.

Supervised machine learning model to predict mortality in patients undergoing venovenous extracorporeal membrane oxygenation from a nationwide multicentre registry

BACKGROUND

Existing models have performed poorly when predicting mortality for patients undergoing venovenous extracorporeal membrane oxygenation (VV-ECMO). This study aimed to develop and validate a machine learning (ML)-based prediction model to predict 90-day mortality in patients undergoing VV-ECMO.

METHODS

This study included 368 patients with acute respiratory failure undergoing VV-ECMO from 16 tertiary hospitals across South Korea between 2012 and 2015. The primary outcome was the 90-day mortality after ECMO initiation. The inputs included all available features (n=51) and those from the electronic health record (EHR) systems without preprocessing (n=40). The discriminatory strengths of ML models were evaluated in both internal and external validation sets. The models were compared with conventional models, such as respiratory ECMO survival prediction (RESP) and predicting death for severe acute respiratory distress syndrome on VV-ECMO (PRESERVE).

RESULTS

Extreme gradient boosting (XGB) (areas under the receiver operating characteristic curve, AUROC 0.82, 95% CI (0.73 to 0.89)) and light gradient boosting (AUROC 0.81 (95% CI 0.71 to 0.88)) models achieved the highest performance using EHR's and all other available features. The developed models had higher AUROCs (95% CI 0.76 to 0.82) than those of RESP (AUROC 0.66 (95% CI 0.56 to 0.76)) and PRESERVE (AUROC 0.71 (95% CI 0.61 to 0.81)). Additionally, we achieved an AUROC (0.75) for 90-day mortality in external validation in the case of the XGB model, which was higher than that of RESP (0.70) and PRESERVE (0.67) in the same validation dataset.

CONCLUSIONS

ML prediction models outperformed previous mortality risk models. This model may be used to identify patients who are unlikely to benefit from VV-ECMO therapy during patient selection.

Utilizing Machine Learning to Predict Neurological Injury in Venovenous Extracorporeal Membrane Oxygenation Patients: An Extracorporeal Life Support Organization Registry Analysis

Background

Venovenous extracorporeal membrane oxygenation (VV-ECMO) is associated with acute brain injury (ABI), including central nervous system (CNS) ischemia (defined as ischemic stroke or hypoxic-ischemic brain injury) and intracranial hemorrhage (ICH). There is limited data on prediction models for ABI and neurological outcomes in VV-ECMO.

Research Question

Can machine learning (ML) accurately predict ABI and identify modifiable factors of ABI in VV-ECMO?

Study Design and Methods

We analyzed adult (≥18 years) VV-ECMO patients in the Extracorporeal Life Support Organization Registry (2009-2021) from 676 centers. ABI was defined as CNS ischemia, ICH, brain death, and seizures. Overall, 65 total variables were extracted including clinical characteristics and pre-ECMO and on-ECMO variables. Random Forest, CatBoost, LightGBM, and XGBoost ML algorithms (10-fold leave-one-out cross-validation) were used to predict ABI. Feature Importance Scores were used to pinpoint variables most important for predicting ABI.

Results

Of 37,473 VV-ECMO patients (median age=48.1 years, 63% male), 2,644 (7.1%) experienced ABI: 610 (2%) and 1,591 (4%) experienced CNS ischemia and ICH, respectively. The median ECMO duration was 10 days (interquartile range=5-20 days). The area under the receiver-operating characteristics curves to predict ABI, CNS ischemia, and ICH were 0.67, 0.63, and 0.70, respectively. The accuracy, positive predictive, and negative predictive values for ABI were 79%, 15%, and 95%, respectively. ML identified pre-ECMO cardiac arrest as the most important risk factor for ABI while ECMO duration and bridge to transplantation as an indication for ECMO were associated with lower risk of ABI.

Interpretation

This is the first study to use machine learning to predict ABI in a large cohort of VV-ECMO patients. Performance was sub-optimal due to the low reported prevalence of ABI with lack of standardization of neuromonitoring/imaging protocols and data granularity in the ELSO Registry. Standardized neurological monitoring and imaging protocols may improve machine learning performance to predict ABI.

Research Priorities in Critical Care Cardiology: JACC Expert Panel

Over the last several decades, the cardiac intensive care unit (CICU) has seen a substantial evolution in the patient population, comorbidities, and diagnoses. However, the generation of high-quality evidence to manage these complex and critically ill patients has been slow. Given the scarcity of clinical trials focused on critical care cardiology (CCC), CICU clinicians are often left to extrapolate from studies that either exclude or poorly represent the patient population admitted to CICUs. The lack of high-quality evidence and limited guidance from society guidelines has led to significant variation in practice patterns for many of the most common CICU diagnoses. Several barriers, both common to critical care research and unique to CCC, have impeded progress. In this multinational perspective, we describe key areas of priority for CCC research, current challenges for investigation in the CICU, and essential elements of a path forward for the field.

Systems of Care Delivery and Optimization in the Intensive Care Unit

As the volume and complexity of patients requiring intensive care grows, so do the barriers and challenges to the delivery of that care. This article summarizes these challenges, outlines strategies used to overcome them, and presents new developments and concepts within the care of the ICU patient.

A Delphi Process to Identify Relevant Outcomes That May Be Associated With a Predictive Analytic Tool to Detect Hemodynamic Deterioration in the Intensive Care Unit

Background The critical care literature has seen an increase in the development and validation of tools using artificial intelligence for early detection of patient events or disease onset in the intensive care unit (ICU). The hemodynamic stability index (HSI) was found to have an AUC of 0.82 in predicting the need for hemodynamic intervention in the ICU. Future studies using this tool may benefit from targeting those outcomes that are more relevant to clinicians and most achievable. Methods A three-round Delphi study was conducted with a panel of 10 critical care physicians and three nurses in the United States to identify outcomes that may be most relevant and achievable with the HSI when evaluated for use in the ICU. To achieve criteria for relevance, at least 65% of panelists had to rate an outcome as a 4 or 5 on a 5-point scale. Results Nineteen of 24 outcomes that may be associated with the HSI achieved consensus for relevance. The Kemeny-Young approach was used to develop a matrix depicting the distribution of outcomes considering both relevance and achievability. "Reduces time spent in hemodynamic instability" and "reduces times to recognition of hemodynamic instability" were the highest-ranking outcomes considering both relevance and achievability. Conclusion This Delphi study was a feasible method to identify relevant outcomes that may be associated with an appropriate predictive analytic tool in the ICU. These findings can provide insight to researchers looking to study such tools to impact outcomes relevant to critical care practitioners. Future studies should test these tools in the ICU that target the most clinically relevant and achievable outcomes, such as time spent hemodynamically unstable or time until actionable nursing assessment or treatment.

Causal inference using observational intensive care unit data: a scoping review and recommendations for future practice

This scoping review focuses on the essential role of models for causal inference in shaping actionable artificial intelligence (AI) designed to aid clinicians in decision-making. The objective was to identify and evaluate the reporting quality of studies introducing models for causal inference in intensive care units (ICUs), and to provide recommendations to improve the future landscape of research practices in this domain. To achieve this, we searched various databases including Embase, MEDLINE ALL, Web of Science Core Collection, Google Scholar, medRxiv, bioRxiv, arXiv, and the ACM Digital Library. Studies involving models for causal inference addressing time-varying treatments in the adult ICU were reviewed. Data extraction encompassed the study settings and methodologies applied. Furthermore, we assessed reporting quality of target trial components (i.e., eligibility criteria, treatment strategies, follow-up period, outcome, and analysis plan) and main causal assumptions (i.e., conditional exchangeability, positivity, and consistency). Among the 2184 titles screened, 79 studies met the inclusion criteria. The methodologies used were G methods (61%) and reinforcement learning methods (39%). Studies considered both static (51%) and dynamic treatment regimes (49%). Only 30 (38%) of the studies reported all five target trial components, and only seven (9%) studies mentioned all three causal assumptions. To achieve actionable AI in the ICU, we advocate careful consideration of the causal question of interest, describing this research question as a target trial emulation, usage of appropriate causal inference methods, and acknowledgement (and examination of potential violations of) the causal assumptions.

Machine learning vs. traditional regression analysis for fluid overload prediction in the ICU

Fluid overload, while common in the ICU and associated with serious sequelae, is hard to predict and may be influenced by ICU medication use. Machine learning (ML) approaches may offer advantages over traditional regression techniques to predict it. We compared the ability of traditional regression techniques and different ML-based modeling approaches to identify clinically meaningful fluid overload predictors. This was a retrospective, observational cohort study of adult patients admitted to an ICU ≥ 72 h between 10/1/2015 and 10/31/2020 with available fluid balance data. Models to predict fluid overload (a positive fluid balance ≥ 10% of the admission body weight) in the 48-72 h after ICU admission were created. Potential patient and medication fluid overload predictor variables (n = 28) were collected at either baseline or 24 h after ICU admission. The optimal traditional logistic regression model was created using backward selection. Supervised, classification-based ML models were trained and optimized, including a meta-modeling approach. Area under the receiver operating characteristic (AUROC), positive predictive value (PPV), and negative predictive value (NPV) were compared between the traditional and ML fluid prediction models. A total of 49 of the 391 (12.5%) patients developed fluid overload. Among the ML models, the XGBoost model had the highest performance (AUROC 0.78, PPV 0.27, NPV 0.94) for fluid overload prediction. The XGBoost model performed similarly to the final traditional logistic regression model (AUROC 0.70; PPV 0.20, NPV 0.94). Feature importance analysis revealed severity of illness scores and medication-related data were the most important predictors of fluid overload. In the context of our study, ML and traditional models appear to perform similarly to predict fluid overload in the ICU. Baseline severity of illness and ICU medication regimen complexity are important predictors of fluid overload.

The application of artificial intelligence in the management of sepsis

Sepsis is a complex and heterogeneous syndrome that remains a serious challenge to healthcare worldwide. Patients afflicted by severe sepsis or septic shock are customarily placed under intensive care unit (ICU) supervision, where a multitude of apparatus is poised to produce high-granularity data. This reservoir of high-quality data forms the cornerstone for the integration of AI into clinical practice. However, existing reviews currently lack the inclusion of the latest advancements. This review examines the evolving integration of artificial intelligence (AI) in sepsis management. Applications of artificial intelligence include early detection, subtyping analysis, precise treatment and prognosis assessment. AI-driven early warning systems provide enhanced recognition and intervention capabilities, while profiling analyzes elucidate distinct sepsis manifestations for targeted therapy. Precision medicine harnesses the potential of artificial intelligence for pathogen identification, antibiotic selection, and fluid optimization. In conclusion, the seamless amalgamation of artificial intelligence into the domain of sepsis management heralds a transformative shift, ushering in novel prospects to elevate diagnostic precision, therapeutic efficacy, and prognostic acumen. As AI technologies develop, their impact on shaping the future of sepsis care warrants ongoing research and thoughtful implementation.

Artificial intelligence and machine learning in prehospital emergency care: A scoping review

Our scoping review provides a comprehensive analysis of the landscape of artificial intelligence (AI) applications in prehospital emergency care (PEC). It contributes to the field by highlighting the most studied AI applications and identifying the most common methodological approaches across 106 included studies. The findings indicate a promising future for AI in PEC, with many unique use cases, such as prognostication, demand prediction, resource optimization, and the Internet of Things continuous monitoring systems. Comparisons with other approaches showed AI outperforming clinicians and non-AI algorithms in most cases. However, most studies were internally validated and retrospective, highlighting the need for rigorous prospective validation of AI applications before implementation in clinical settings. We identified knowledge and methodological gaps using an evidence map, offering a roadmap for future investigators. We also discussed the significance of explainable AI for establishing trust in AI systems among clinicians and facilitating real-world validation of AI models.

Clinical support system for triage based on federated learning for the Korea triage and acuity scale

Background and aims

This study developed a clinical support system based on federated learning to predict the need for a revised Korea Triage Acuity Scale (KTAS) to facilitate triage.

Methods

This was a retrospective study that used data from 11,952,887 patients in the Korean National Emergency Department Information System (NEDIS) from 2016 to 2018 for model development. Separate cohorts were created based on the emergency medical center level in the NEDIS: regional emergency medical center (REMC), local emergency medical center (LEMC), and local emergency medical institution (LEMI). External and temporal validation used data from emergency department (ED) of the study site from 2019 to 2021. Patient features obtained during the triage process and the initial KTAS scores were used to develop the prediction model. Federated learning was used to rectify the disparity in data quality between EDs. The patient's demographic information, vital signs in triage, mental status, arrival information, and initial KTAS were included in the input feature.

Results

3,626,154 patients' visits were included in the regional emergency medical center cohort; 8,278,081 patients' visits were included in the local emergency medical center cohort; and 48,652 patients' visits were included in the local emergency medical institution cohort. The study site cohort, which is used for external and temporal validation, included 135,780 patients visits. Among the patients in the REMC and study site cohorts, KTAS level 3 patients accounted for the highest proportion at 42.4% and 45.1%, respectively, whereas in the LEMC and LEMI cohorts, KTAS level 4 patients accounted for the highest proportion. The area under the receiver operating characteristic curve for the prediction model was 0.786, 0.750, and 0.770 in the external and temporal validation. Patients with revised KTAS scores had a higher admission rate and ED mortality rate than those with unaltered KTAS scores.

Conclusions

This novel system might accurately predict the likelihood of KTAS acuity revision and support clinician-based triage.

Integrating a Virtual ICU with Cardiac and Cardiovascular ICUs: Managing the Needs of a Complex and High-Acuity Specialty ICU Cohort

A long-standing shortage of critical care intensivists and nurses, exacerbated by the coronavirus disease (COVID-19) pandemic, has led to an accelerated adoption of tele-critical care in the United States (US). Due to their complex and high-acuity nature, cardiac, cardiovascular, and cardiothoracic intensive care units (ICUs) have generally been limited in their ability to leverage tele-critical care resources. In early 2020, Houston Methodist Hospital (HMH) launched its tele-critical care program called Virtual ICU, or vICU, to improve its ICU staffing efficiency while providing high-quality, continuous access to in-person and virtual intensivists and critical care nurses. This article provides a roadmap with prescriptive specifications for planning, launching, and integrating vICU services within cardiac and cardiovascular ICUs-one of the first such integrations among the leading academic US hospitals. The success of integrating vICU depends upon the (1) recruitment of intensivists and RNs with expertise in managing cardiac and cardiovascular patients on the vICU staff as well as concerted efforts to promote mutual trust and confidence between in-person and virtual providers, (2) consultations with the bedside clinicians to secure their buy-in on the merits of vICU resources, and (3) collaborative approaches to improve workflow protocols and communications. Integration of vICU has resulted in the reduction of monthly night-call requirements for the in-person intensivists and an increase in work satisfaction. Data also show that support of the vICU is associated with a significant reduction in the rate of Code Blue events (denoting a situation where a patient requires immediate resuscitation, typically due to a cardiac or respiratory arrest). As the providers become more comfortable with the advances in artificial intelligence and big data-driven technology, the Cardiac ICU Cohort continues to improve methods to predict and track patient trends in the ICUs.

Research Hotspots and Trends of Deep Learning in Critical Care Medicine: A Bibliometric and Visualized Study

Background

Interest in the application of deep learning (DL) in critical care medicine (CCM) is growing rapidly. However, comprehensive bibliometric research that analyze and measure the global literature is still lacking.

Objective

The present study aimed to systematically evaluate the research hotspots and trends of DL in CCM worldwide based on the output of publications, cooperative relationships of research, citations, and the co-occurrence of keywords.

Methods

A total of 1708 articles in all were obtained from Web of Science. Bibliometric analysis was performed by Bibliometrix package in R software (4.2.2), Microsoft Excel 2019, VOSviewer (1.6.18), and CiteSpace (5.8.R3).

Results

The annual publications increased steeply in the past five years, accounting for 95.67% (1634/1708) of all the included literature. China and USA contributed to approximately 71.66% (1244/1708) of all publications. Seven of the top ten most productive organizations rank in the top 100 universities globally. Hot spots in research on the application of DL in CCM have focused on classifying disease phenotypes, predicting early signs of clinical deterioration, and forecasting disease progression, prognosis, and death. Convolutional neural networks, long and short-term memory networks, recurrent neural networks, transformer models, and attention mechanisms were all commonly used DL technologies.

Conclusion

Hot spots in research on the application of DL in CCM have focused on classifying disease phenotypes, predicting early signs of clinical deterioration, and forecasting disease progression, prognosis, and death. Extensive collaborative research to improve the maturity and robustness of the model remains necessary to make DL-based model applications sufficiently compelling for conventional CCM practice.

Expectations of Anesthesiology and Intensive Care Professionals Toward Artificial Intelligence: Observational Study

BACKGROUND

Artificial intelligence (AI) applications offer numerous opportunities to improve health care. To be used in the intensive care unit, AI must meet the needs of staff, and potential barriers must be addressed through joint action by all stakeholders. It is thus critical to assess the needs and concerns of anesthesiologists and intensive care physicians related to AI in health care throughout Europe.

OBJECTIVE

This Europe-wide, cross-sectional observational study investigates how potential users of AI systems in anesthesiology and intensive care assess the opportunities and risks of the new technology. The web-based questionnaire was based on the established analytic model of acceptance of innovations by Rogers to record 5 stages of innovation acceptance.

METHODS

The questionnaire was sent twice in 2 months (March 11, 2021, and November 5, 2021) through the European Society of Anaesthesiology and Intensive Care (ESAIC) member email distribution list. A total of 9294 ESAIC members were reached, of whom 728 filled out the questionnaire (response rate 728/9294, 8%). Due to missing data, 27 questionnaires were excluded. The analyses were conducted with 701 participants.

RESULTS

A total of 701 questionnaires (female: n=299, 42%) were analyzed. Overall, 265 (37.8%) of the participants have been in contact with AI and evaluated the benefits of this technology higher (mean 3.22, SD 0.39) than participants who stated no previous contact (mean 3.01, SD 0.48). Physicians see the most benefits of AI application in early warning systems (335/701, 48% strongly agreed, and 358/701, 51% agreed). Major potential disadvantages were technical problems (236/701, 34% strongly agreed, and 410/701, 58% agreed) and handling difficulties (126/701, 18% strongly agreed, and 462/701, 66% agreed), both of which could be addressed by Europe-wide digitalization and education. In addition, the lack of a secure legal basis for the research and use of medical AI in the European Union leads doctors to expect problems with legal liability (186/701, 27% strongly agreed, and 374/701, 53% agreed) and data protection (148/701, 21% strongly agreed, and 343/701, 49% agreed).

CONCLUSIONS

Anesthesiologists and intensive care personnel are open to AI applications in their professional field and expect numerous benefits for staff and patients. Regional differences in the digitalization of the private sector are not reflected in the acceptance of AI among health care professionals. Physicians anticipate technical difficulties and lack a stable legal basis for the use of AI. Training for medical staff could increase the benefits of AI in professional medicine. Therefore, we suggest that the development and implementation of AI in health care require a solid technical, legal, and ethical basis, as well as adequate education and training of users.

Non-Invasive Mapping of Cerebral Autoregulation Using Near-Infrared Spectroscopy: A Study Protocol

The ability of cerebral vessels to maintain a fairly constant cerebral blood flow is referred to as cerebral autoregulation (CA). Using near-infrared spectroscopy (NIRS) paired with arterial blood pressure (ABP) monitoring, continuous CA can be assessed non-invasively. Recent advances in NIRS technology can help improve the understanding of continuously assessed CA in humans with high spatial and temporal resolutions. We describe a study protocol for creating a new wearable and portable imaging system that derives CA maps of the entire brain with high sampling rates at each point. The first objective is to evaluate the CA mapping system's performance during various perturbations using a block-trial design in 50 healthy volunteers. The second objective is to explore the impact of age and sex on regional disparities in CA using static recording and perturbation testing in 200 healthy volunteers. Using entirely non-invasive NIRS and ABP systems, we hope to prove the feasibility of deriving CA maps of the entire brain with high spatial and temporal resolutions. The development of this imaging system could potentially revolutionize the way we monitor brain physiology in humans since it would allow for an entirely non-invasive continuous assessment of regional differences in CA and improve our understanding of the impact of the aging process on cerebral vessel function.

Difficult diagnosis in the ICU: making the right call but beware uncertainty and bias

Dealing with an uncertain or missed diagnosis is commonplace in the intensive care unit setting. Affected patients are subject to a potential decrease in quality of care and a greater risk of a poor outcome. The diagnostic process is a complex task that starts with information gathering, followed by integration and interpretation of data, hypothesis generation and, finally, confirmation of a (hopefully correct) diagnosis. This may be particularly challenging in the patient who is critically ill where a good history may not be forthcoming and/or clinical, laboratory and imaging features are non-specific. The aim of this narrative review is to analyse and describe common causes of diagnostic error in the intensive care unit, highlighting the multiple types of cognitive bias, and to suggest a diagnostic framework. To inform this review, we performed a literature search to identify relevant articles, particularly those pertinent to unclear diagnoses in patients who are critically ill. Clinicians should be cognisant as to how they formulate diagnoses and utilise debiasing strategies. Multidisciplinary teamwork and more time spent with the patient, supported by effective and efficient use of electronic healthcare records and decision support resources, is likely to improve the quality of the diagnostic process, patient care and outcomes.

Explainable Machine Learning to Predict Successful Weaning of Mechanical Ventilation in Critically Ill Patients Requiring Hemodialysis

Lungs and kidneys are two vital and frequently injured organs among critically ill patients. In this study, we attempt to develop a weaning prediction model for patients with both respiratory and renal failure using an explainable machine learning (XML) approach. We used the eICU collaborative research database, which contained data from 335 ICUs across the United States. Four ML models, including XGBoost, GBM, AdaBoost, and RF, were used, with weaning prediction and feature windows, both at 48 h. The model's explanations were presented at the domain, feature, and individual levels by leveraging various techniques, including cumulative feature importance, the partial dependence plot (PDP), the Shapley additive explanations (SHAP) plot, and local explanation with the local interpretable model-agnostic explanations (LIME). We enrolled 1789 critically ill ventilated patients requiring hemodialysis, and 42.8% (765/1789) of them were weaned successfully from mechanical ventilation. The accuracies in XGBoost and GBM were better than those in the other models. The discriminative characteristics of six key features used to predict weaning were demonstrated through the application of the SHAP and PDP plots. By utilizing LIME, we were able to provide an explanation of the predicted probabilities and the associated reasoning for successful weaning on an individual level. In conclusion, we used an XML approach to establish a weaning prediction model in critically ill ventilated patients requiring hemodialysis.

Evolution of Hybrid Intelligence and Its Application in Evidence-Based Medicine: A Review

Modern medicine, both in clinical practice and research, has become more and more based on data, which is changing equally in type and quality with the advent and development of healthcare digitalization. The first part of the present paper aims to present the steps through which data, and subsequently clinical and research practice, have evolved from paper-based to digital, proposing a possible future of this digitalization in terms of potential applications and integration of digital tools in medical practice. Noting that digitalization is no more a possible future, but a concrete reality, there is a strong need for a new definition of evidence-based medicine, which must take into account the progressive integration of artificial intelligence (AI) in all decision-making processes. So, leaving behind the traditional research concept of human intelligence versus AI, poorly adaptable to real-world clinical practice, a Human and AI hybrid model, seen as a deep integration of AI and human thinking, is proposed as a new healthcare governance system. The second part of our review is focused on some of the major challenges the digitalization process has to face, particularly privacy issues, system complexity and opacity, and ethical concerns related to legal aspects and healthcare disparities. Analyzing these open issues, we aim to present some of the future directions that in our opinion should be pursued to implement AI in clinical practice.

Artificial intelligence in critical illness and its impact on patient care: a comprehensive review

Artificial intelligence (AI) has great potential to improve the field of critical care and enhance patient outcomes. This paper provides an overview of current and future applications of AI in critical illness and its impact on patient care, including its use in perceiving disease, predicting changes in pathological processes, and assisting in clinical decision-making. To achieve this, it is important to ensure that the reasoning behind AI-generated recommendations is comprehensible and transparent and that AI systems are designed to be reliable and robust in the care of critically ill patients. These challenges must be addressed through research and the development of quality control measures to ensure that AI is used in a safe and effective manner. In conclusion, this paper highlights the numerous opportunities and potential applications of AI in critical care and provides guidance for future research and development in this field. By enabling the perception of disease, predicting changes in pathological processes, and assisting in the resolution of clinical decisions, AI has the potential to revolutionize patient care for critically ill patients and improve the efficiency of health systems.

Using machine learning for the early prediction of sepsis-associated ARDS in the ICU and identification of clinical phenotypes with differential responses to treatment

Background: An early diagnosis model with clinical phenotype classification is key for the early identification and precise treatment of sepsis-associated acute respiratory distress syndrome (ARDS). This study aimed to: 1) build a machine learning diagnostic model for patients with sepsis-associated ARDS using easily accessible early clinical indicators, 2) conduct rapid classification of clinical phenotypes in this population, and 3) explore the differences in clinical characteristics, outcomes, and treatment responses of different phenotypes. Methods: This study is based on data from the Telehealth Intensive Care Unit (eICU) and Medical Information Mart for Intensive Care IV (MIMIC-IV). We trained and tested the early diagnostic model of sepsis-associated ARDS patients in the eICU. We used key predictive indicators to cluster sepsis-associated ARDS patients and determine the characteristics and clinical outcomes of different phenotypes, as well to explore the differences of in-hospital mortality among different the positive end-expiratory pressure (PEEP) levels in different phenotypes. These results are verified in MIMIC-IV to evaluate whether they are repeatable. Results: Among the diagnostic models constructed in 19,249 sepsis patients and 5,947 sepsis-associated ARDS patients, the AdaBoost (Decision Tree) model achieved the best performance with an area under the receiver operating characteristic curve (AUC) of 0.895, which is higher than that of the traditional Logistic Regression model (Z = -2.40,p = 0.013), and the accuracy of 70.06%, sensitivity of 78.11% and specificity of 78.74%. We simultaneously identified three sepsis-associated ARDS phenotypes. Cluster 0 (n = 3,669) had the lowest in-hospital mortality rate (6.51%) and fewer laboratory abnormalities (lower WBC (median:15.000 K/mcL), lower blood glucose (median:158.000 mg/dl), lower creatinine (median:1.200 mg/dl), lower lactic acid (median:3.000 mmol/L); p < 0.001). Cluster 1 (n = 1,554) had the highest in-hospital mortality rate (75.29%) and the most laboratory abnormalities (higher WBC (median:18.300 K/mcL), higher blood glucose (median:188.000 mg/dl), higher creatinine (median:2.300 mg/dl), higher lactic acid (median:3.900 mmol/L); p < 0.001). Cluster 2 (n = 724) had the most complex condition, with a moderate in-hospital mortality rate (29.7%) and the longest intensive care unit stay. In Clusters 0 and 1, patients with high PEEP had higher in-hospital mortality rate than those with low PEEP, but the opposite trend was seen in Cluster 2. These results were repeatable in 11,935 patients with sepsis and 2,699 patients with sepsis-associated ARDS patients in the MIMIC-IV cohort. Conclusion: A machine learning diagnostic model of sepsis-associated ARDS patients was established. Three phenotypes with different clinical features and outcomes were clustered, and these had different therapeutic responses. These findings are helpful for the early and rapid identification of sepsis-associated ARDS patients and their precise individualized treatment.

Artificial Intelligence in Intensive Care Medicine: Bibliometric Analysis

Background

Interest in critical care–related artificial intelligence (AI) research is growing rapidly. However, the literature is still lacking in comprehensive bibliometric studies that measure and analyze scientific publications globally.

Objective

The objective of this study was to assess the global research trends in AI in intensive care medicine based on publication outputs, citations, coauthorships between nations, and co-occurrences of author keywords.

Methods

A total of 3619 documents published until March 2022 were retrieved from the Scopus database. After selecting the document type as articles, the titles and abstracts were checked for eligibility. In the final bibliometric study using VOSviewer, 1198 papers were included. The growth rate of publications, preferred journals, leading research countries, international collaborations, and top institutions were computed.

Results

The number of publications increased steeply between 2018 and 2022, accounting for 72.53% (869/1198) of all the included papers. The United States and China contributed to approximately 55.17% (661/1198) of the total publications. Of the 15 most productive institutions, 9 were among the top 100 universities worldwide. Detecting clinical deterioration, monitoring, predicting disease progression, mortality, prognosis, and classifying disease phenotypes or subtypes were some of the research hot spots for AI in patients who are critically ill. Neural networks, decision support systems, machine learning, and deep learning were all commonly used AI technologies.

Conclusions

This study highlights popular areas in AI research aimed at improving health care in intensive care units, offers a comprehensive look at the research trend in AI application in the intensive care unit, and provides an insight into potential collaboration and prospects for future research. The 30 articles that received the most citations were listed in detail. For AI-based clinical research to be sufficiently convincing for routine critical care practice, collaborative research efforts are needed to increase the maturity and robustness of AI-driven models.

Systematized and efficient: organization of critical care in the future

Since the advent of critical care in the twentieth century, the core elements that are the foundation for critical care systems, namely to care for critically ill and injured patients and to save lives, have evolved enormously. The past half-century has seen dramatic advancements in diagnostic, organ support, and treatment modalities in critical care, with further improvements now needed to achieve personalized critical care of the highest quality. For critical care to be even higher quality in the future, advancements in the following areas are key: the physical ICU space; the people that care for critically ill patients; the equipment and technologies; the information systems and data; and the research systems that impact critically ill patients and families. With acutely and critically ill patients and their families as the absolute focal point, advancements across these areas will hopefully transform care and outcomes over the coming years.

Machine learning-based suggestion for critical interventions in the management of potentially severe conditioned patients in emergency department triage

Providing timely intervention to critically ill patients is a challenging task in emergency departments (ED). Our study aimed to predict early critical interventions (CrIs), which can be used as clinical recommendations. This retrospective observational study was conducted in the ED of a tertiary hospital located in a Korean metropolitan city. Patient who visited ED from January 1, 2016, to December 31, 2018, were included. Need of six CrIs were selected as prediction outcomes, namely, arterial line (A-line) insertion, oxygen therapy, high-flow nasal cannula (HFNC), intubation, Massive Transfusion Protocol (MTP), and inotropes and vasopressor. Extreme gradient boosting (XGBoost) prediction model was built by using only data available at the initial stage of ED. Overall, 137,883 patients were included in the study. The areas under the receiver operating characteristic curve for the prediction of A-line insertion was 0·913, oxygen therapy was 0.909, HFNC was 0.962, intubation was 0.945, MTP was 0.920, and inotropes or vasopressor administration was 0.899 in the XGBoost method. In addition, an increase in the need for CrIs was associated with worse ED outcomes. The CrIs model was integrated into the study site's electronic medical record and could be used to suggest early interventions for emergency physicians.