Background: Artificial intelligence (AI) has been increasingly employed in healthcare across diverse domains, including medical imaging, personalized diagnostics, therapeutic interventions, and predictive analytics using electronic health records. Its integration is particularly impactful in critical care, where AI has demonstrated the potential to enhance patient outcomes. This systematic review critically evaluates the current applications of AI within the domain of critical care nursing. Methods: This systematic review is registered with PROSPERO (CRD42024545955) and was conducted in accordance with PRISMA guidelines. Comprehensive searches were performed across MEDLINE/PubMed, SCOPUS, CINAHL, and Web of Science. Results: The initial review identified 1364 articles, of which 24 studies met the inclusion criteria. These studies employed diverse AI techniques, including classical models (e.g., logistic regression), machine learning approaches (e.g., support vector machines, random forests), deep learning architectures (e.g., neural networks), and generative AI tools (e.g., ChatGPT). The analyzed health outcomes encompassed postoperative complications, ICU admissions and discharges, triage assessments, pressure injuries, sepsis, delirium, and predictions of adverse events or critical vital signs. Most studies relied on structured data from electronic medical records, such as vital signs and laboratory results, supplemented by unstructured data, including nursing notes and patient histories; two studies also integrated audio data. Conclusion: AI demonstrates significant potential in nursing, facilitating the use of clinical practice data for research and decision-making. The choice of AI techniques varies based on the specific objectives and requirements of the model. However, the heterogeneity of the studies included in this review limits the ability to draw definitive conclusions about the effectiveness of AI applications in critical care nursing. Future research should focus on more robust, interventional studies to assess the impact of AI on nursing-sensitive outcomes. Additionally, exploring a broader range of health outcomes and AI applications in critical care will be crucial for advancing AI integration in nursing practices.

Background: Performing emergency surgery for bowel obstruction continues to place a significant strain on the healthcare system. Conventional assessment methods for outcomes in bowel obstruction cases often concentrate on isolated factors, and the evaluation of results for individuals with bowel obstruction remains poorly studied. This study aimed to examine the risk factors associated with major postoperative complications. Methods: We retrospectively analyzed 99 patients undergoing surgery from 2015 to 2022. We divided the patients into two groups: (1) benign-related obstruction (n = 68) and (2) cancer-related obstruction (n = 31). We used logistic regression, KNN, and XGBOOST. We calculated the receiver operating characteristic curve and accuracy of the model. Results: Colon obstructions were more frequent in the cancer group (p = 0.005). Operative time, intestinal resection, and stoma were significantly more frequent in the cancer group. Major complications were at 41% for the cancer group vs. 20% in the benign group (p = 0.03). Uni- and multivariate analysis showed that the significant risk factors for major complications were cancer-related obstruction and CRP. The best model was KNN, with an accuracy of 0.82. Conclusions: Colonic obstruction is associated with tumor-related blockage. Malignant cancer and an increase in C-reactive protein (CRP) are significant risk factors for patients who have undergone emergency surgery due to major complications. KNN could improve the process of counseling and the perioperative management of patients with intestinal obstruction in emergency settings.

Accurate prediction of postoperative complications can inform shared decisions regarding prognosis, preoperative risk-reduction, and postoperative resource use. We hypothesized that multi-task deep learning models would outperform conventional machine learning models in predicting postoperative complications, and that integrating high-resolution intraoperative physiological time series would result in more granular and personalized health representations that would improve prognostication compared to preoperative predictions. In a longitudinal cohort study of 56,242 patients undergoing 67,481 inpatient surgical procedures at a university medical center, we compared deep learning models with random forests and XGBoost for predicting nine common postoperative complications using preoperative, intraoperative, and perioperative patient data. Our study indicated several significant results across experimental settings that suggest the utility of deep learning for capturing more precise representations of patient health for augmented surgical decision support. Multi-task learning improved efficiency by reducing computational resources without compromising predictive performance. Integrated gradients interpretability mechanisms identified potentially modifiable risk factors for each complication. Monte Carlo dropout methods provided a quantitative measure of prediction uncertainty that has the potential to enhance clinical trust. Multi-task learning, interpretability mechanisms, and uncertainty metrics demonstrated potential to facilitate effective clinical implementation.© 2023. The Author(s).

Sepsis is one of the leading causes of mortality in hospitalized patients. Despite this fact, a reliable means of predicting sepsis onset remains elusive. Early and accurate sepsis onset predictions could allow more aggressive and targeted therapy while maintaining antimicrobial stewardship. Existing detection methods suffer from low performance and often require time-consuming laboratory test results.To study and validate a sepsis prediction method, InSight, for the new Sepsis-3 definitions in retrospective data, make predictions using a minimal set of variables from within the electronic health record data, compare the performance of this approach with existing scoring systems, and investigate the effects of data sparsity on InSight performance.We apply InSight, a machine learning classification system that uses multivariable combinations of easily obtained patient data (vitals, peripheral capillary oxygen saturation, Glasgow Coma Score, and age), to predict sepsis using the retrospective Multiparameter Intelligent Monitoring in Intensive Care (MIMIC)-III dataset, restricted to intensive care unit (ICU) patients aged 15 years or more. Following the Sepsis-3 definitions of the sepsis syndrome, we compare the classification performance of InSight versus quick sequential organ failure assessment (qSOFA), modified early warning score (MEWS), systemic inflammatory response syndrome (SIRS), simplified acute physiology score (SAPS) II, and sequential organ failure assessment (SOFA) to determine whether or not patients will become septic at a fixed period of time before onset. We also test the robustness of the InSight system to random deletion of individual input observations.In a test dataset with 11.3% sepsis prevalence, InSight produced superior classification performance compared with the alternative scores as measured by area under the receiver operating characteristic curves (AUROC) and area under precision-recall curves (APR). In detection of sepsis onset, InSight attains AUROC = 0.880 (SD 0.006) at onset time and APR = 0.595 (SD 0.016), both of which are superior to the performance attained by SIRS (AUROC: 0.609; APR: 0.160), qSOFA (AUROC: 0.772; APR: 0.277), and MEWS (AUROC: 0.803; APR: 0.327) computed concurrently, as well as SAPS II (AUROC: 0.700; APR: 0.225) and SOFA (AUROC: 0.725; APR: 0.284) computed at admission (P<.001 for all comparisons). Similar results are observed for 1-4 hours preceding sepsis onset. In experiments where approximately 60% of input data are deleted at random, InSight attains an AUROC of 0.781 (SD 0.013) and APR of 0.401 (SD 0.015) at sepsis onset time. Even with 60% of data missing, InSight remains superior to the corresponding SIRS scores (AUROC and APR, P<.001), qSOFA scores (P=.0095; P<.001) and superior to SOFA and SAPS II computed at admission (AUROC and APR, P<.001), where all of these comparison scores (except InSight) are computed without data deletion.Despite using little more than vitals, InSight is an effective tool for predicting sepsis onset and performs well even with randomly missing data.

Determine if deep learning detects sepsis earlier and more accurately than other models. To evaluate model performance using implementation-oriented metrics that simulate clinical practice.We trained internally and temporally validated a deep learning model (multi-output Gaussian process and recurrent neural network [MGP-RNN]) to detect sepsis using encounters from adult hospitalized patients at a large tertiary academic center. Sepsis was defined as the presence of 2 or more systemic inflammatory response syndrome (SIRS) criteria, a blood culture order, and at least one element of end-organ failure. The training dataset included demographics, comorbidities, vital signs, medication administrations, and labs from October 1, 2014 to December 1, 2015, while the temporal validation dataset was from March 1, 2018 to August 31, 2018. Comparisons were made to 3 machine learning methods, random forest (RF), Cox regression (CR), and penalized logistic regression (PLR), and 3 clinical scores used to detect sepsis, SIRS, quick Sequential Organ Failure Assessment (qSOFA), and National Early Warning Score (NEWS). Traditional discrimination statistics such as the C-statistic as well as metrics aligned with operational implementation were assessed.The training set and internal validation included 42 979 encounters, while the temporal validation set included 39 786 encounters. The C-statistic for predicting sepsis within 4 h of onset was 0.88 for the MGP-RNN compared to 0.836 for RF, 0.849 for CR, 0.822 for PLR, 0.756 for SIRS, 0.619 for NEWS, and 0.481 for qSOFA. MGP-RNN detected sepsis a median of 5 h in advance. Temporal validation assessment continued to show the MGP-RNN outperform all 7 clinical risk score and machine learning comparisons.We developed and validated a novel deep learning model to detect sepsis. Using our data elements and feature set, our modeling approach outperformed other machine learning methods and clinical scores.© The Author(s) 2020. Published by Oxford University Press on behalf of the American Medical Informatics Association.

The heterogeneous nature of sepsis renders determining its underlying causes difficult, which may delay diagnosis and intervention. VitalCare-SEPsis Score (VC-SEPS) is a deep learning-based algorithm that predicts sepsis and monitors patient conditions based on electronic medical record data. However, few studies have prospectively compared medical artificial intelligence software algorithms and traditional scoring systems to predict sepsis. This prospective observational study attempted to validate the predictive performance and risk stratification of VC-SEPS for early prediction of sepsis.

Fluid management remains a critical challenge in the treatment of septic shock, with individualized approaches lacking. This study aims to develop a statistical model based on transcriptomics to identify subgroups of septic shock patients with varied responses to fluid strategy. The study encompasses 494 septic shock patients. A benefit score is derived from the transcriptome space, with higher values indicating greater benefits from restrictive fluid strategy. Adherence to the recommended strategy is associated with a hazard ratio of 0.82 (95% confidence interval: 0.64-0.92). When applied to the baseline hospital mortality rate of 16%, adherence to the recommended fluid strategy could potentially lower this rate to 13%. A proteomic signature comprising six proteins is developed to predict the benefit score, yielding an area under the curve of 0.802 (95% confidence interval: 0.752-0.846) in classifying patients who may benefit from a restrictive strategy. In this work, we develop a proteomic signature with potential utility in guiding fluid strategy for septic shock patients.© 2024. The Author(s).

Acute kidney injury (AKI) is a common complication in sepsis. However, the trajectories of sepsis-induced AKI and their transcriptional profiles are not well characterized.

The occurrence of acute kidney injury (AKI) was associated with an increased mortality rate among acute pancreatitis (AP) patients, indicating the importance of accurately predicting the mortality rate of critically ill patients with acute pancreatitis–associated acute kidney injury (AP-AKI) at an early stage. This study aimed to develop and validate machine learning–based predictive models for in-hospital mortality rate in critically ill patients with AP-AKI by comparing their performance with the traditional logistic regression (LR) model.

Detecting liver dysfunction/failure in the intensive care unit poses a challenge as individuals afflicted with these conditions often appear symptom-free, thereby complicating early diagnoses and contributing to unfavorable patient outcomes. The objective of this endeavor was to improve the chances of early diagnosis of liver dysfunction/failure by creating a predictive model for the critical care setting. This model has been designed to produce an index that reflects the probability of severe liver dysfunction/failure for patients in intensive care units, utilizing machine learning techniques.This effort used comprehensive open-access patient databases to build and validate machine learning-based models for predicting the likelihood of severe liver dysfunction/failure. Two artificial neural network model architectures that derived a novel 0-100 Liver Failure Risk Index were developed and validated using the comprehensive patient databases. Data used to train and develop the models included clinical (patient vital signs) and laboratory results related to liver function which included liver function test results. The performance of the developed models was compared in terms of sensitivity, specificity, and the mean lead time to diagnosis.The best model performance demonstrated an 83.3 % sensitivity and a specificity of 77.5 % in diagnosing severe liver dysfunction/failure. This model accurately identified these patients a median of 17.5 hours before their clinical diagnosis, as documented in their electronic health records. The predictive diagnostic capability of the developed models is crucial to the intensive care unit setting, where treatment and preventative interventions can be made to avoid severe liver dysfunction/failure.Our machine learning approach facilitates early and timely intervention in the hepatic function of critically ill patients by their healthcare providers to prevent or minimize associated morbidity and mortality. HIPPOKRATIA 2024, 28 (1):1-10.Copyright 2024, Hippokratio General Hospital of Thessaloniki.

Existing predictive models in critical care, specifically for postoperative critically ill patients, often struggle to accurately predict prolonged intensive care unit (ICU) stays, a key aspect of patient care. The integration of artificial intelligence (AI) offers a promising approach for bridging this gap. We aimed to develop an AI-based model to predict mortality and prolonged ICU stay in postoperative critically ill patients, enhance prognostic accuracy, and address the shortcomings of current models.This retrospective study included data from 6,029 postoperative critically ill patients from two medical centers, including a wide range of clinical, surgical, and laboratory variables. Multiple machine-learning models, including extreme gradient boosting, light gradient boosting, category boosting, random forest, and multilayer perceptron, were employed. A soft-voting ensemble model was developed to aggregate the strengths of individual models. The models underwent external validation, and the SHapley Additive exPlanations (SHAP) method was utilized to assess the impact of various features on predictions.In internal validation, the ensemble model demonstrated superior performance with an area under the receiver operating characteristic curve (AUROC) of 0.8812 for mortality and 0.7944 for prolonged ICU stay. It achieved 0.9095 accuracy and an F1 score of 0.7014 for mortality predictions. For prolonged ICU stay, it attained an accuracy of 0.9368 and an F1 score of 0.5762. During external validation, the model maintained high performance, with an AUROC of 0.8330 for mortality and 0.7376 for prolonged ICU stay. It showed 0.9200 accuracy and an F1 score of 0.6768 for mortality and 0.9028 accuracy with an F1 score of 0.5689 for prolonged ICU stay. SHAP analysis confirmed that key predictors, including emergency surgery, serum osmolality, lactate levels, and diastolic blood pressure, remained significant.This study represents a significant advancement in the application of AI in critical care, especially for postoperative critically ill patients. The developed AI model outperformed existing models in predicting mortality and prolonged ICU stay, demonstrating notable accuracy and reliability. Its ability to identify critical, under-emphasized clinical factors could enhance decision-making in critical care settings. Although promising, further validation in diverse clinical settings is essential to confirm the model's efficacy and broader applicability.© 2025. The Author(s).

Timely care in a specialised neuro-intensive therapy unit (ITU) reduces mortality and hospital stays. Planned admissions to ITU following surgery are safer than unplanned ones. However, post-operative care decisions remain subjective. This study used artificial intelligence (AI), specifically natural language processing (NLP) to analyse electronic health records (EHRs) of elective neurosurgery patients from University College London Hospital (UCLH) and predict ITU admissions. Using a refined CogStack-MedCAT NLP model, we extracted clinical concepts from 2268 patient records and trained AI models to classify admissions into ward and ITU. The Random Forest model achieved a recall of 0.87 (CI 0.82-0.91) for ITU admissions, reducing the proportion of unplanned ITU cases missed by human experts from 36% to 4%. Interpretability analysis confirmed the use of clinically relevant concepts. The study highlights the opportunity for AI to aid in allocating resources for neurosurgical patients but requires further research and integration into practice.© 2025. The Author(s).

Sepsis is the third leading cause of death worldwide and the main cause of mortality in hospitals, but the best treatment strategy remains uncertain. In particular, evidence suggests that current practices in the administration of intravenous fluids and vasopressors are suboptimal and likely induce harm in a proportion of patients. To tackle this sequential decision-making problem, we developed a reinforcement learning agent, the Artificial Intelligence (AI) Clinician, which extracted implicit knowledge from an amount of patient data that exceeds by many-fold the life-time experience of human clinicians and learned optimal treatment by analyzing a myriad of (mostly suboptimal) treatment decisions. We demonstrate that the value of the AI Clinician's selected treatment is on average reliably higher than human clinicians. In a large validation cohort independent of the training data, mortality was lowest in patients for whom clinicians' actual doses matched the AI decisions. Our model provides individualized and clinically interpretable treatment decisions for sepsis that could improve patient outcomes.

Remote monitoring is essential for healthcare digital transformation, however, this poses greater burdens on healthcare providers to review and respond as the data collected expands. This study developed a multimodal neural network to automate assessments of patient-generated data from remote postoperative wound monitoring. Two interventional studies including adult gastrointestinal surgery patients collected wound images and patient-reported outcome measures (PROMs) for 30-days postoperatively. Neural networks for PROMs and images were combined to predict surgical site infection (SSI) diagnosis within 48 h. The multimodal neural network model to predict confirmed SSI within 48 h remained comparable to clinician triage (0.762 [0.690-0.835] vs 0.777 [0.721-0.832]), with an excellent performance on external validation. Simulated usage indicated an 80% reduction in staff time (51.5 to 9.1 h) without compromising diagnostic accuracy. This multimodal approach can effectively support remote monitoring, alleviating provider burden while ensuring high-quality postoperative care.© 2025. The Author(s).

Background/Objectives: Colorectal anastomotic leak (CAL) is one of the most severe postoperative complications in colorectal surgery, impacting patient morbidity and mortality. Current risk assessment methods rely on clinical and intraoperative factors, but no real-time predictive tool exists. This study aimed to develop an artificial intelligence model based on intraoperative laparoscopic recording of the anastomosis for CAL prediction. Methods: A convolutional neural network (CNN) was trained with annotated frames from colorectal surgery videos across three international high-volume centers (Instituto Português de Oncologia de Lisboa, Hospital das Clínicas de Ribeirão Preto, and Royal Liverpool University Hospital). The dataset included a total of 5356 frames from 26 patients, 2007 with CAL and 3349 showing normal anastomosis. Four CNN architectures (EfficientNetB0, EfficientNetB7, ResNet50, and MobileNetV2) were tested. The models’ performance was evaluated using their sensitivity, specificity, accuracy, and area under the receiver operating characteristic (AUROC) curve. Heatmaps were generated to identify key image regions influencing predictions. Results: The best-performing model achieved an accuracy of 99.6%, AUROC of 99.6%, sensitivity of 99.2%, specificity of 100.0%, PPV of 100.0%, and NPV of 98.9%. The model reliably identified CAL-positive frames and provided visual explanations through heatmaps. Conclusions: To our knowledge, this is the first AI model developed to predict CAL using intraoperative video analysis. Its accuracy suggests the potential to redefine surgical decision-making by providing real-time risk assessment. Further refinement with a larger dataset and diverse surgical techniques could enable intraoperative interventions to prevent CAL before it occurs, marking a paradigm shift in colorectal surgery.

Clinical notes recorded during a patient's perioperative journey holds immense informational value. Advances in large language models (LLMs) offer opportunities for bridging this gap. Using 84,875 preoperative notes and its associated surgical cases from 2018 to 2021, we examine the performance of LLMs in predicting six postoperative risks using various fine-tuning strategies. Pretrained LLMs outperformed traditional word embeddings by an absolute AUROC of 38.3% and AUPRC of 33.2%. Self-supervised fine-tuning further improved performance by 3.2% and 1.5%. Incorporating labels into training further increased AUROC by 1.8% and AUPRC by 2%. The highest performance was achieved with a unified foundation model, with improvements of 3.6% for AUROC and 2.6% for AUPRC compared to self-supervision, highlighting the foundational capabilities of LLMs in predicting postoperative risks, which could be potentially beneficial when deployed for perioperative care.© 2025. The Author(s).

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.