Real-time risk monitoring is critical but challenging in intensive care units (ICUs) due to the lack of real-time updates for most clinical variables. Although real-time predictions have been integrated into various risk monitoring systems, existing systems do not address uncertainties in risk assessments. We developed a novel framework based on commonly used systems like the Sequential Organ Failure Assessment (SOFA) score by incorporating uncertainties to improve the effectiveness of real-time risk monitoring.

This study included 5351 patients admitted to the Cardiothoracic ICU in the National University Hospital in Singapore. We developed machine learning models to predict long lead-time variables and computed real-time SOFA scores using predictions. We calculated intervals to capture uncertainties in risk assessments and validated the association of the estimated real-time scores and intervals with mortality and readmission.

Our model outperforms SOFA score in predicting 24-h mortality: Nagelkerke's R-squared (0.224 vs. 0.185, p < 0.001) and the area under the receiver operating characteristic curve (AUC) (0.870 vs. 0.843, p < 0.001), and significantly outperforms quick SOFA (Nagelkerke's R-squared = 0.125, AUC = 0.778). Our model also performs better in predicting 30-day readmission. We confirmed a positive net reclassification improvement (NRI) of our model over the SOFA score (0.184, p < 0.001). Similarly, we enhanced two additional scoring systems.

Incorporating uncertainties improved existing scores in real-time monitoring, which could be used to trigger on-demand laboratory tests, potentially improving early detection, reducing unnecessary testing, and thereby lowering healthcare expenditures, mortality, and readmission rates in clinical practice.

The online version contains supplementary material available at 10.1007/s13755-024-00331-5.

Platelet indices at admission offer the most opportune time for clinical decision-making, as they provide earliest insights, unlike later assessments during the intensive care unit (ICU) stay. There is emerging evidence suggesting the utility of platelet indices in predicting mortality. The objective of this study was, for the first time as far as the literature indicates, to elucidate the utility of seven platelet indices at admission in a large ICU cohort using Sysmex XN-series analysers. This cross-sectional study enrolled 592 ICU patients. The association of platelet indices at admission with the in-ICU and 90-day mortality was evaluated using logistic regression and receiver operating characteristic curve analysis. Of the platelet indices studied, absolute-immature platelet fraction (A-IPF), and mean platelet volume (MPV) and percentage-immature platelet fraction (%-IPF) were shown to be independently associated with predicting the in-ICU and 90-day mortality, respectively. The A-IPF cut-off value for predicting the in-ICU mortality was >6.4 × 109/L (adjusted area under the curve (aAUC) 0.736, and adjusted Odds Ratio (aOR) 1.04), and the MPV and %-IPF cut-off values for predicting the 90-day mortality were >9.5 fL (aAUC 0.759, and aOR 1.26) and >6.3% (aAUC 0.762, and aOD 1.06), respectively (all p < 0.05). Admission A-IPF was the best predictor of in-ICU mortality, while admission MPV and %-IPF were the best predictors of 90-day mortality. These indices, all measured at admission, provide the earliest possible data relevant to mortality prediction. These are routinely available indices which deserve to be considered for new future ICU scoring systems.

Numerous grading scales were proposed for subarachnoid hemorrhage (SAH) to assess the likelihood of unfavorable neurological outcomes (UO) and the risk of delayed cerebral ischemia (DCI). We aimed to validate the Hemorrhage, Age, Treatment, Clinical Status, and Hydrocephalus (HATCH) score and the VASOGRADE, a simple grading scale for prediction of DCI after aneurysmal SAH.

This was a retrospective single-center study of patients with nontraumatic SAH (January 2016 to December 2021) admitted to the intensive care unit. We performed a receiver operating characteristic (ROC) curve analysis to assess the discriminative ability of the HATCH and the VASOGRADE to identify patients who had UO at 3 months (defined as Glasgow Outcome Scale score of 1-3), hospital mortality, and DCI and compared their performance with the World Federation of Neurosurgical Surgeons, the modified Fisher, the Sequential Organ Failure Assessment, and the Acute Physiology and Chronic Health Evaluation II scales. We performed a multivariate logistic regression analysis to assess the association between HATCH and UO at 3 months and between VASOGRADE and DCI.

We included 262 consecutive patients with nontraumatic SAH. DCI was observed in 82 patients (31.3%), whereas 78 patients (29.8%) died during hospital stay and 133 patients (51%) had UO at 3 months. HATCH was independently associated with UO (odds ratio 1.61, 95% confidence interval [CI] 1.36-1.90) and had an area under the ROC curve (AUROC) of 0.83 (95% CI 0.77-0.88), comparable to the Acute Physiology and Chronic Health Evaluation II (AUROC 0.84, 95% CI 0.79-0.89) and Sequential Organ Failure Assessment (AUROC 0.83, 95% CI 0.77-0.88).

Hemorrhage, Age, Treatment, Clinical Status, and Hydrocephalus and VASOGARDE scores had a good performance to predict UO or in-hospital mortality and DCI, respectively; however, their performance did not outperform nonspecific routinely used scores.

Background: Current severity scoring systems in intensive care units (ICUs) are complex and time-consuming, limiting their utility for rapid clinical decision-making. This study aimed to develop and validate simplified prediction models using readily available biomarkers for assessing in-hospital mortality risk. Methods: We analyzed 19,720 adult ICU patients in this retrospective study. Three prediction models were developed: a basic model using lactate-to-albumin ratio (LAR) and neutrophil percent-to-albumin ratio (NPAR) and two enhanced models incorporating mechanical ventilation and continuous renal replacement therapy. Model performance was evaluated against Sequential Organ Failure Assessment (SOFA) score and Acute Physiology and Chronic Health Evaluation (APACHE) II score using machine learning approaches and validated through comprehensive subgroup analyses. Results: Among individual biomarkers, SOFA score showed the highest discriminatory power (area under these curves [AUC] 0.931), followed by LAR (AUC 0.830), CAR (AUC 0.749), and NPAR (AUC 0.748). Our enhanced Model 3 demonstrated exceptional predictive performance (AUC 0.929), statistically comparable to SOFA (p = 0.052), and showed a trend toward superiority over APACHE II (AUC 0.900, p = 0.079). Model 2 performed comparably to APACHE II (AUC 0.913, p = 0.430), while Model 1, using only LAR and NPAR, achieved robust performance (AUC 0.898) despite its simplicity. Subgroup analyses across different ICU types demonstrated consistent performance of all three models, supporting their broad clinical applicability. Conclusions: This study introduces novel, simplified prediction models that rival traditional scoring systems in accuracy while offering significantly faster implementation. These findings represent a crucial step toward more efficient and practical risk assessment in critical care, potentially enabling earlier clinical interventions and improved patient outcomes.

Acute lung injury (ALI) or its more severe form, acute respiratory distress syndrome (ARDS), represents a critical condition characterized by extensive inflammation within the airways. Necroptosis, a form of cell death, has been implicated in the pathogenesis of various inflammatory diseases. However, the precise characteristics and mechanisms of necroptosis in ARDS remain unclear. Thus, our study seeks to elucidate the specific alterations and regulatory factors associated with necroptosis in ARDS and to identify potential therapeutic targets for the disease. We discovered that necroptosis mediates the progression of ALI through the activation and formation of the RIPK1/RIPK3/MLKL complex. Moreover, we substantiated the involvement of both MYD88 and TRIF in the activation of the TLR4 signaling pathway in ALI. Furthermore, we have developed a lipid micelle-encapsulated drug targeting MLKL in alveolar type II epithelial cells and successfully applied it to treat ALI in mice. This targeted nanoparticle selectively inhibited necroptosis, thereby mitigating epithelial cell damage and reducing inflammatory injury. Our study delves into the specific mechanisms of necroptosis in ALI and proposes novel targeted therapeutic agents, presenting innovative strategies for the management of ARDS.

This study explored the trajectories of health-related quality of life (HRQOL) and the factors influencing these trajectories.

Prospective observational cohort study.

19 intensive care units (ICUs) in South Korea.

We used the Medical Outcomes Study Short Form version 2 (SF-36v2) to assess HRQOL at 3, 6, 12, and 24 months post-discharge. Additionally, we evaluated intensive care experience, post-intensive care syndrome, and demographic and clinical characteristics to identify factors. HRQOL trajectory groups were identified via latent class growth modeling, with determining factors analyzed using multinomial logistic regression.

The analysis identified three distinct groups for the physical component summary (PCS) and mental component summary (MCS) of the SF-36v2. For the PCS, the groups were labeled "Resilient Stable," "Moderate Recovered," and "Slow Recovering." For the MCS, the classifications were "Resilient Stable," "Low Recovered," and "Persistent Low." The determinants of the PCS Moderate Recovered and Slow Recovering Groups included older age, female gender, less educated, increased comorbidities, discharge to extended care facilities, and post-intensive care syndrome. Conversely, the MCS Low Recovered and Persistent Low Groups were determined by the intensive care experience and post-intensive care syndrome.

Our study identified specific vulnerable groups for PCS and MCS and their determinants in terms of HRQOL recovery among ICU survivors.

There is a need for a preemptive approach for survivors with determinants that place them in vulnerable groups for poorer HRQOL as well as systematic monitoring of post-intensive care syndrome in various healthcare settings.

Blood-related infections are a significant concern in healthcare. They can lead to serious medical complications and even death if not promptly diagnosed and treated. Throughout time, medical research has sought to identify clinical factors and strategies to improve the management of these conditions. The increasing adoption of electronic health records has led to a wealth of electronically available medical information and predictive models have emerged as invaluable tools. This manuscript offers a detailed survey of machine-learning techniques used for the diagnosis and prognosis of bacteraemia, bloodstream infections, and sepsis shedding light on their efficacy, potential limitations, and the intricacies of their integration into clinical practice.

This study presents a comprehensive analysis derived from a thorough search across prominent databases, namely EMBASE, Google Scholar, PubMed, Scopus, and Web of Science, spanning from their inception dates to October 25, 2023. Eligibility assessment was conducted independently by investigators, with inclusion criteria encompassing peer-reviewed articles and pertinent non-peer-reviewed literature. Clinical and technical data were meticulously extracted and integrated into a registry, facilitating a holistic examination of the subject matter. To maintain currency and comprehensiveness, readers are encouraged to contribute manuscript suggestions and/or reports for integration into this living registry.

While machine learning (ML) models exhibit promise in advanced disease stages such as sepsis, early stages remain underexplored due to data limitations. Biochemical markers emerge as pivotal predictors during early stages such as bacteraemia, or bloodstream infections, while vital signs assume significance in sepsis prognosis. Integrating temporal trend information into conventional machine learning models appears to enhance performance. Unfortunately, sequential deep learning models face challenges, showing minimal performance improvements and significant drops in external datasets, potentially due to learning missing patterns within the scarce data available rather than understanding disease dynamics. Real-life implementation receives limited attention, as meeting design requirements proves challenging within existing healthcare infrastructure. The data collected in an event-based fashion during clinical practice is insufficient to fully harness the potential of these data-hungry models. Despite limitations, opportunities abound in leveraging flexible models and exploiting real-time non-invasive data collection technologies such as wearable devices or microneedles. Addressing research gaps in early disease stages, harnessing patient history data often underused, and embracing continual diagnostics beyond treatment initiation are crucial for improving healthcare decision-making support and adoption across the entire management pathway.

This comprehensive survey illuminates the landscape of ML applications in blood-related infection management, offering insights for future research and clinical practice. Implementing clinical ML-based clinical decision support systems requires balancing research with practical considerations. Current methodologies often lead to complex models lacking transparency and practical validation. Integration into healthcare systems faces regulatory, privacy, and trust challenges. Clear presentations and adherence to standards are essential to boost confidence in machine learning models for real-world healthcare applications.

Sepsis remains a leading cause of morbidity and mortality worldwide due to its rapid progression and heterogeneous nature. This review explores the potential of Artificial Intelligence (AI) to transform sepsis management, from early detection to personalized treatment and real-time monitoring. AI, particularly through machine learning (ML) techniques such as random forest models and deep learning algorithms, has shown promise in analyzing electronic health record (EHR) data to identify patterns that enable early sepsis detection. For instance, random forest models have demonstrated high accuracy in predicting sepsis onset in intensive care unit (ICU) patients, while deep learning approaches have been applied to recognize complications such as sepsis-associated acute respiratory distress syndrome (ARDS). Personalized treatment plans developed through AI algorithms predict patient-specific responses to therapies, optimizing therapeutic efficacy and minimizing adverse effects. AI-driven continuous monitoring systems, including wearable devices, provide real-time predictions of sepsis-related complications, enabling timely interventions. Beyond these advancements, AI enhances diagnostic accuracy, predicts long-term outcomes, and supports dynamic risk assessment in clinical settings. However, ethical challenges, including data privacy concerns and algorithmic biases, must be addressed to ensure fair and effective implementation. The significance of this review lies in addressing the current limitations in sepsis management and highlighting how AI can overcome these hurdles. By leveraging AI, healthcare providers can significantly enhance diagnostic accuracy, optimize treatment protocols, and improve overall patient outcomes. Future research should focus on refining AI algorithms with diverse datasets, integrating emerging technologies, and fostering interdisciplinary collaboration to address these challenges and realize AI's transformative potential in sepsis care.

Machine learning (ML) is increasingly used to predict clinical deterioration in intensive care unit (ICU) patients through scoring systems. Although promising, such algorithms often overfit their training cohort and perform worse at new hospitals. Thus, external validation is a critical - but frequently overlooked - step to establish the reliability of predicted risk scores to translate them into clinical practice. We systematically reviewed how regularly external validation of ML-based risk scores is performed and how their performance changed in external data.

We searched MEDLINE, Web of Science, and arXiv for studies using ML to predict deterioration of ICU patients from routine data. We included primary research published in English before December 2023. We summarised how many studies were externally validated, assessing differences over time, by outcome, and by data source. For validated studies, we evaluated the change in area under the receiver operating characteristic (AUROC) attributable to external validation using linear mixed-effects models.

We included 572 studies, of which 84 (14.7%) were externally validated, increasing to 23.9% by 2023. Validated studies made disproportionate use of open-source data, with two well-known US datasets (MIMIC and eICU) accounting for 83.3% of studies. On average, AUROC was reduced by -0.037 (95% CI -0.052 to -0.027) in external data, with more than 0.05 reduction in 49.5% of studies.

External validation, although increasing, remains uncommon. Performance was generally lower in external data, questioning the reliability of some recently proposed ML-based scores. Interpretation of the results was challenged by an overreliance on the same few datasets, implicit differences in case mix, and exclusive use of AUROC.

Heart transplantation is the gold standard treatment for end-stage heart failure patients. However, the shortage of donor hearts limits its applicability. This study aims to evaluate the risk factors associated with survival within 1-year after heart transplantation.

A single-center retrospective cohort study evaluated 299 adult patients who underwent transplantation at the Heart Institute (Incor) between January 2013 and December 2019. Univariate and multivariate Cox regression analyses were conducted to identify independent predictors of 1-year survival among well-established prognostic clinical characteristics described in the literature. Patients were followed until death or the last observation on October 12, 2022. A Simple Risk Index was created based on the hazard ratio of each factor.

Chagas disease was the most common cause of cardiomyopathy (36%). Most patients were male (65%) with a median age of 50 (39-58) years. Four variables observed during the last clinical assessment in the intensive care unit before surgery were found to be statistically significant: maximum Sequential Organ Failure Assessment (SOFA) score, creatinine clearance in 3 quartile categories, C-reactive protein in 3 categories, and white blood cell count in 3 categories. The model demonstrated good discrimination (C-index = 0.74) and calibration. The group at high risk (>20 points) exhibited significantly higher mortality rates at 1 year (p < 0.001).

The study introduces a risk prediction score for 1-year post-transplant mortality in a reference center in Brazil. The score is based on four variables: maximum SOFA score, creatinine clearance, C-reactive protein, and white blood cell count.

To provide a viable tool for the early clinical identification of high-risk populations in patients with sepsis.

Sepsis-associated delirium (SAD) has the potential to significantly impact the short- and long-term prognosis of patients. However, accurately predicting and effectively managing SAD remains a significant challenge.

This study employed a retrospective analysis of adult sepsis patients admitted to the intensive care unit (ICU) for the first time. Patients were divided into two groups based on their initial Braden score upon admission to the ICU: a high-risk group (≤ 15 points) and a low-risk group (> 15 points). The relationship between Braden score and delirium was assessed using logistic regression and restricted cubic splines, while restricted mean survival time was employed to analyse the relationship between Braden scores and patients' 90- and 180-day mortality.

Of the 28,312 patients included in the study, those in the high-risk group exhibited a significantly elevated risk of delirium (44.8% vs. 29.7%) and higher 90-day (28.7% vs. 19.4%) and 180-day (33.2% vs. 24.1%) mortality rates (all p < 0.001). After adjusting for confounding variables, logistic regression demonstrated that the risk of delirium was 1.54 times higher in the high-risk group (95% CI = 1.45-1.64, p < 0.001). Following propensity score matching, the difference in survival was statistically significant at both time points, with the high-risk group having a reduced survival rate of 7.50 days (95% CI = -8.24, -6.75; p < 0.001) and 15.74 days (95% CI = -17.40, -14.08; p < 0.001) at 90 days and 180 days, respectively.

The Braden score is a simple and effective tool for the early identification of patients at increased risk of adverse outcomes in sepsis.

Retrospective study.

The Braden score can be employed by clinical nurses for the purpose of early identification of poor prognostic risk in patients with sepsis.

This study was conducted according to the Strengthening Research in Observational Studies in Epidemiology (STROBE) guidelines.

Patients were involved in the sample of the study.

Patients with traumatic brain injury (TBI) frequently exhibit concomitant immunosuppression. In this study, we evaluated the predictive values of soluble programmed death-1 (sPD-1) and soluble programmed death ligand-1 (sPD-L1) in patients with severe TBI. Peripheral blood sPD-1 and sPD-L1 levels were measured within 48 h of patient admission. A total of 20 healthy volunteers and 82 patients were enrolled in this study. The levels of sPD-1 and sPD-L1 were upregulated in patients with severe TBI (P < 0.001). They were significantly increased in the post-TBI severe pneumonia group and among non-survivors (P < 0.001). The area under the curves (AUCs) for sPD-1 and sPD-L1 levels to predict severe pneumonia were 0.714 and 0.696, respectively, and the AUCs to predict mortality were 0.758 and 0.735. The levels of sPD-1 and sPD-L1 are correlated with the GCS scores at admission, APACHE II scores, length of MV, and time elapsed to mortality. The levels of sPD-1 and sPD-L1 emerged as independent predictive factors for severe pneumonia and mortality. This study demonstrates that upregulation of sPD-1 and sPD-L1 in severe TBI patients is significantly associated with severe pneumonia and mortality, suggesting their potential as predictive biomarkers for these outcomes.

The identification of efficient predictors for short-term mortality among patients with myocardial infarction (MI) in coronary care units (CCU) remains a challenge. This study seeks to investigate the potential of machine learning (ML) to improve risk prediction and develop a predictive model specifically tailored for 30-day mortality in critical MI patients.

This study focused on MI patients extracted from the Medical Information Mart for Intensive Care-IV database. The patient cohort was randomly stratified into derivation (n = 1,389, 70%) and validation (n = 595, 30%) groups. Independent risk factors were identified through eXtreme Gradient Boosting (XGBoost) and random decision forest (RDF) methodologies. Subsequently, multivariate logistic regression analysis was employed to construct predictive models. The discrimination, calibration and clinical utility were assessed utilizing metrics such as receiver operating characteristic (ROC) curve, calibration plot and decision curve analysis (DCA).

A total of 1,984 patients were identified (mean [SD] age, 69.4 [13.0] years; 659 [33.2%] female). The predictive performance of the XGBoost and RDF-based models demonstrated similar efficacy. Subsequently, a 30-day mortality prediction algorithm was developed using the same selected variables, and a regression model was visually represented through a nomogram. In the validation group, the nomogram (Area Under the Curve [AUC]: 0.835, 95% Confidence Interval [CI]: [0.774-0.897]) exhibited superior discriminative capability for 30-day mortality compared to the Sequential Organ Failure Assessment (SOFA) score [AUC: 0.735, 95% CI: (0.662-0.809)]. The nomogram (Accuracy: 0.914) and the SOFA score (Accuracy: 0.913) demonstrated satisfactory calibration. DCA indicated that the nomogram outperformed the SOFA score, providing a net benefit in predicting mortality.

The ML-based predictive model demonstrated significant efficacy in forecasting 30-day mortality among MI patients admitted to the CCU. The prognostic factors identified were age, blood urea nitrogen, heart rate, pulse oximetry-derived oxygen saturation, bicarbonate, and metoprolol use. This model serves as a valuable decision-making tool for clinicians.

Aim The aim of the present study was to assess the disseminated intravascular coagulation (DIC) and its correlation with DIC scores (International Society on Thrombosis and Haemostasis (ISTH), sepsis-induced coagulopathy (SIC)) and Sequential Organ Failure Assessment (SOFA) score in medical intensive care unit (MICU) patients. Methods The study was conducted at the medical intensive care unit at Dr. D.Y. Patil Medical College and Hospital, D.Y. Patil Vidyapeeth, Pimpri, Pune spanning from October 2020 to September 2022. A total of 100 patients admitted to the hospital ICU satisfying qSOFA score were included in the current study. Approval was obtained from the institutional ethics committee before commencing the study. All patients and their family members included in the study were provided with a detailed explanation of the study. Clinical history of illness and physical examination were done in detail. The laboratory values were obtained and were calculated with the International Society on Thrombosis and Haemostasis (ISTH), sepsis-induced coagulopathy (SIC) and Sequential Organ Failure Assessment (SOFA) scores. Results The average age of the study population was 52.08 ± 16.44 years. Within the study population, 65% were male and 35% were female. Within the group being studied, the average pulse rate was 66.64 ± 17.33 beats per minute, the average systolic blood pressure was 83.7 ± 11.38 mm Hg, the average diastolic blood pressure was 59.7 ± 10.49 mm Hg, and the average respiratory rate was 38.4 ± 4.8. The average Glasgow Coma Scale (GCS) among the participants was 9.51 ± 1.74. The average qSOFA score across the study participants was 2.58 ± 0.6. The study population consisted of 60% survivors and 40% non-survivors. Regarding the study population, 57.15% of individuals experienced mortality as a result of DIC. The statistical analysis revealed a significant difference in the mean ISTH score between the result groups at 48 hours. The disparity in the average SOFA score at admission, 24 hours, 48 hours, day 7 and day 14 between the outcomes (survivors and non-survivors) was statistically significant. Conclusion This research suggests that there is a positive link between higher scores on the estimated ISTH, SIC and SOFA scales. The prognosis of critically sick patients is negatively correlated with the progressive increase in DIC scores throughout follow-up, while a stable or declining DIC score is indicative of a more favorable prognosis. There was no significant link seen between non-overt disseminated intravascular coagulation (DIC) mortality and DIC scores.

Identifying risk factors and improving prognostication for mortality among patients with sepsis-associated acute kidney injury (AKI) undergoing continuous kidney replacement therapy (CKRT) is important in improving the adverse prognosis of this patient population. This study aimed to compare the prognostic value of existing systemic inflammation biomarkers and determine the optimal systemic inflammation biomarker in patients with sepsis-associated AKI receiving CKRT.

This multi-center, retrospective, observational cohort study included 1,500 patients with sepsis-associated AKI treated with intensive care and CKRT. The main predictor was a panel of 13 different systemic inflammation biomarkers. The primary outcome was 28-day mortality after CKRT initiation. Secondary outcomes included 90-day mortality after CKRT initiation, CKRT duration, kidney replacement therapy dependence at discharge, and lengths of intensive care unit (ICU) and hospital stays.

When added to the widely accepted Acute Physiology and Chronic Health Evaluation II score, platelet-to-albumin ratio (PAR) and neutrophil-platelet score (NPS) had the highest improvements in prognostication of 28-day mortality, where the corresponding increases in C-statistic were 0.01 (95% confidence interval [CI], 0.00-0.02) and 0.02 (95% CI, 0.01-0.03). Similar findings were observed for 90-day mortality. The 28- and 90-day mortality rates were significantly lower for the higher PAR and NPS quartiles. These associations remained significant even after adjustment for potential confounding variables in multivariable Cox proportional hazards models.

Of the available systemic inflammation biomarkers, the addition of PAR or NPS to conventional ICU prediction models improved the prognostication of patients with sepsis-associated AKI receiving intensive care and CKRT.

The intensive care unit (ICU) is a finite and expensive resource with demand not infrequently exceeding capacity. Understanding ICU capacity strain is essential to gain situational awareness. Increased capacity strain can influence ICU triage decisions, which rely heavily on clinical judgment. Having an admission and triage protocol with which clinicians are very familiar can mitigate difficult, inappropriate admissions. This article reviews these concepts and methods of in-hospital triage.

The identification of patients at greater mortality risk of death at admission into an intensive cardiovascular care unit (ICCU) has relevant consequences for clinical decision-making. We described patient characteristics at admission into an ICCU by predicted mortality risk assessed with noncardiac intensive care unit (ICU) and evaluated their performance in predicting patient outcomes.

A total of 202 consecutive patients (130 men, 75 ± 12 years) were admitted into our tertiary-care ICCU in a 20-week period. We evaluated, on the first 24 h data, in-hospital mortality risk according to Acute Physiology and Chronic Health Evaluation II (APACHE II) and Simplified Acute Physiology Score 3 (SAPS 3); Sepsis related Organ Failure Assessment (SOFA) Score and the Mayo Cardiac intensive care unit Admission Risk Score (M-CARS) were also calculated.

Predicted mortality was significantly lower than observed (5% during ICCU and 7% at discharge) for APACHE II and SAPS 3 (17% for both scores). Mortality risk was associated with older age, more frequent comorbidities, severe clinical presentation and complications. The APACHE II, SAPS 3, SOFA and M-CARS had good discriminative ability in distinguishing deaths and survivors with poor calibration of risk scores predicting mortality.

In a recent contemporary cohort of patients admitted into the ICCU for a variety of acute and critical cardiovascular conditions, scoring systems used in general ICU had good discrimination for patients' clinical severity and mortality. Available scores preserve powerful discrimination but the overestimation of mortality suggests the importance of specific tailored scores to improve risk assessment of patients admitted into ICCUs.

Background/Objectives: Septic shock is a severe condition with high mortality necessitating precise prognostic tools for improved patient outcomes. This study aimed to evaluate the collective predictive value of the Simplified Acute Physiology Score 3 (SAPS-3) and lactate measurements (initial, peak, last, and clearance rates within the first 24 h) in patients with septic shock. Specifically, it sought to determine how these markers enhance predictive accuracy for 28-day mortality beyond SAPS-3 alone. Methods: This retrospective cohort study analyzed data from 66 septic shock patients at two ICUs of Vienna General Hospital (2017-2019). SAPS-3 and lactate levels (initial, peak, last measurement within 24 h, and 24 h clearance) were obtained from electronic health records. Logistic regression models were constructed to identify predictors of 28-day mortality, and receiver operating characteristic (ROC) curves assessed predictive accuracy. Results: Among 66 patients, 36 (55%) died within 28 days. SAPS-3 scores significantly differed between survivors and non-survivors (76 vs. 85 points; p = 0.016). First, last, and peak lactate were significantly higher in non-survivors compared to survivors (all p < 0.001). The combination of SAPS-3 and first lactate produced the highest predictive accuracy (AUC = 80.6%). However, 24 h lactate clearance was not predictive of mortality. Conclusions: Integrating SAPS-3 with lactate measurements, particularly first lactate, improves predictive accuracy for 28-day mortality in septic shock patients. First lactate serves as an early, robust prognostic marker, providing crucial information for clinical decision-making and care prioritization. Further large-scale studies are needed to refine these predictive tools and validate their efficacy in guiding treatment strategies.

Currently, there is a lack of ideal risk prediction tools in the field of emergency general surgery (EGS). The American Association for the Surgery of Trauma recommends developing risk assessment tools specifically for EGS-related diseases. In this study, we sought to utilize machine learning (ML) algorithms to explore and develop a web-based calculator for predicting five perioperative risk events of eight common operations in EGS.

This study focused on patients with EGS and utilized electronic medical record systems to obtain data retrospectively from five centers in China. Five ML algorithms, including Random Forest (RF), Support Vector Machine, Naive Bayes, XGBoost, and Logistic Regression, were employed to construct predictive models for postoperative mortality, pneumonia, surgical site infection, thrombosis, and mechanical ventilation >48 h. The optimal models for each outcome event were determined based on metrics, including the value of the Area Under the Curve, F1 score, and sensitivity. A comparative analysis was conducted between the optimal models and Emergency Surgery Score (ESS), Acute Physiology and Chronic Health Evaluation II (APACHE II) score, and American Society of Anesthesiologists (ASA) classification. A web-based calculator was developed to determine corresponding risk probabilities.

Based on 10 993 patients with EGS, we determined the optimal RF model. The RF model also exhibited strong predictive performance compared with the ESS, APACHE II score, and ASA classification. Using this optimal model, the authors developed an online calculator with a questionnaire-guided interactive interface, catering to both the preoperative and postoperative application scenarios.

The authors successfully developed an ML-based calculator for predicting the risk of postoperative adverse events in patients with EGS. This calculator accurately predicted the occurrence risk of five outcome events, providing quantified risk probabilities for clinical diagnosis and treatment.

Liver cirrhosis patients admitted to intensive care unit (ICU) have a high mortality rate.

To establish and validate a nomogram for predicting in-hospital mortality of ICU patients with liver cirrhosis.

We extracted demographic, etiological, vital sign, laboratory test, comorbidity, complication, treatment, and severity score data of liver cirrhosis patients from the Medical Information Mart for Intensive Care IV (MIMIC-IV) and electronic ICU (eICU) collaborative research database (eICU-CRD). Predictor selection and model building were based on the MIMIC-IV dataset. The variables selected through least absolute shrinkage and selection operator analysis were further screened through multivariate regression analysis to obtain final predictors. The final predictors were included in the multivariate logistic regression model, which was used to construct a nomogram. Finally, we conducted external validation using the eICU-CRD. The area under the receiver operating characteristic curve (AUC), decision curve, and calibration curve were used to assess the efficacy of the models.

Risk factors, including the mean respiratory rate, mean systolic blood pressure, mean heart rate, white blood cells, international normalized ratio, total bilirubin, age, invasive ventilation, vasopressor use, maximum stage of acute kidney injury, and sequential organ failure assessment score, were included in the multivariate logistic regression. The model achieved AUCs of 0.864 and 0.808 in the MIMIC-IV and eICU-CRD databases, respectively. The calibration curve also confirmed the predictive ability of the model, while the decision curve confirmed its clinical value.

The nomogram has high accuracy in predicting in-hospital mortality. Improving the included predictors may help improve the prognosis of patients.

Severity of illness scoring systems are used in intensive care units to enable the calculation of adjusted outcomes for audit and benchmarking purposes. Similar tools are lacking for pre-hospital emergency medicine. Therefore, using a national helicopter emergency medical services database, we developed and internally validated a mortality prediction algorithm.

We conducted a multicentre retrospective observational register-based cohort study based on the patients treated by five physician-staffed Finnish helicopter emergency medical service units between 2012 and 2019. Only patients aged 16 and over treated by physician-staffed units were included. We analysed the relationship between 30-day mortality and physiological, patient-related and circumstantial variables. The data were imputed using multiple imputations employing chained equations. We used multivariate logistic regression to estimate the variable effects and performed derivation of multiple multivariable models with different combinations of variables. The models were combined into an algorithm to allow a risk estimation tool that accounts for missing variables. Internal validation was assessed by calculating the optimism of each performance estimate using the von Hippel method with four imputed sets.

After exclusions, 30 186 patients were included in the analysis. 8611 (29%) patients died within the first 30 days after the incident. Eleven predictor variables (systolic blood pressure, heart rate, oxygen saturation, Glasgow Coma Scale, sex, age, emergency medical services vehicle type [helicopter vs ground unit], whether the mission was located in a medical facility or nursing home, cardiac rhythm [asystole, pulseless electrical activity, ventricular fibrillation, ventricular tachycardia vs others], time from emergency call to physician arrival and patient category) were included. Adjusted for optimism after internal validation, the algorithm had an area under the receiver operating characteristic curve of 0.921 (95% CI 0.918 to 0.924), Brier score of 0.097, calibration intercept of 0.000 (95% CI -0.040 to 0.040) and slope of 1.000 (95% CI 0.977 to 1.023).

Based on 11 demographic, mission-specific, and physiologic variables, we developed and internally validated a novel severity of illness algorithm for use with patients encountered by physician-staffed helicopter emergency medical services, which may help in future quality improvement.

The standard severity scores were used for predicting hospital mortality of intensive care unit (ICU) patients. Recently, the new predictive score, Simplified Mortality Score for the ICU (SMS-ICU), was developed for predicting 90-day mortality.

To validate the ability of the SMS-ICU and compare with sepsis severity score (SSS) and original severity scores for predicting 90-day mortality in sepsis patients.

An analysis of retrospective data was conducted in the ICU of a university teaching hospital. Also, 90-day mortality was used for the primary outcome.

A total of 1,161 patients with sepsis were included. The 90-day mortality was 42.4%. The SMS-ICU presented the area under the receiver operating characteristic curve (AUROC) of 0.71, whereas the SSS had significantly higher AUROC than that of the SMS-ICU (AUROC 0.876, p < 0.001). The acute physiology and chronic health evaluation (APACHE) II and IV, and the simplified acute physiology scores (SAPS) II demonstrated good discrimination, with an AUROC above 0.90. The SMS-ICU provides poor calibration for 90-day mortality prediction, similar to the SSS and other standard severity scores. Furthermore, 90-day mortality was underestimated by the SMS-ICU, which had a standardized mortality ratio (SMR) of 1.36. The overall performance by Brier score demonstrated that the SMS-ICU was inferior to the SSS (0.222 and 0.169, respectively). Also, SAPS II presented the best overall performance with a Brier score of 0.092.

The SMS-ICU indicated lower performance compared to the SSS, standard severity scores. Consequently, modifications are required to enhance the performance of the SMS-ICU.

Sathaporn N, Khwannimit B. Comparative Predictive Accuracies of the Simplified Mortality Score for the Intensive Care Unit, Sepsis Severity Score, and Standard Severity Scores for 90-day Mortality in Sepsis Patients. Indian J Crit Care Med 2024;28(4):343-348.

Acute-on-chronic liver failure (ACLF) implies high short-term mortality rates and usually requires intensive care unit (ICU) admission. Proper prognosis for these patients is crucial for early referral for liver transplantation. The superiority of CLIF-C ACLF score in Asian patients with ACLF admitted to an ICU remains inconclusive when compared to other scoring systems. The purpose of the study is (i) to compare the predictive performance of original MELD, MELD-Lactate, CLIF-C ACLF, CLIF-C ACLF-Lactate, and APACHE-II scores for short-term mortality assessment. (ii) to build and validate a novel scoring system and to compare its predictive performance to that of the original five scores. Two hundred sixty-five consecutive cirrhotic patients with ACLF who were admitted to our ICU were enrolled. The prognostic values for mortality were assessed by ROC analysis. A novel model was developed and internally validated using fivefold cross-validation. Alcohol abuse was identified as the primary etiology of cirrhosis. The AUROC of the five prognostic scores were not significantly superior to each other in predicting 1-month and 3-month mortality. The newly developed prognostic model, incorporating age, alveolar-arterial gradient (A-a gradient), BUN, total bilirubin level, INR, and HE grades, exhibited significantly improved performance in predicting 1-month and 3-month mortality with AUROC of 0.863 and 0.829, respectively, as compared to the original five prognostic scores. The novel ACLF model seems to be superior to the original five scores in predicting short-term mortality in ACLF patients admitted to an ICU. Further rigorous validation is required.

Exertional heatstroke (EHS), a fatal illness, pronounces multiple organ dysfunction syndrome (MODS) and high mortality rate. Currently, no ideal factor prognoses EHS. Decreased monocyte human leukocyte-DR antigen (mHLA-DR) has been observed in critically ill individuals, particularly in those with sepsis. While most research focus on the pro-inflammatory response exploration in EHS, there are few studies related to immunosuppression, and no report targeted on mHLA-DR in EHS. The present study tried to explore the prognostic value of mHLA-DR levels in EHS patients.

This was a single-center retrospective study. Clinical data of EHS patients admitted to the intensive care unit of the General Hospital of Southern Theatre Command between January 1, 2008, and December 31, 2020, were recorded and analyzed.

Seventy patients with 54 survivors and 16 nonsurvivors were ultimately enrolled. Levels of mHLA-DR in the nonsurvivors (41.8% [38.1-68.1]%) were significantly lower than those in the survivors (83.1% [67.6-89.4]%, p < 0.001). Multivariate logistic regression indicated that mHLA-DR (odds ratio [OR] = 0.939; 95% confidence interval [CI]: 0.892-0.988; p = 0.016) and Glasgow coma scale (GCS) scores (OR = 0.726; 95% CI: 0.591-0.892; p = 0.002) were independent risk factors related with in-hospital mortality rate in EHS. A nomogram incorporated mHLA-DR with GCS demonstrated excellent discrimination and calibration abilities. Compared to the traditional scoring systems, the prediction model incorporated mHLA-DR with GCS had the highest area under the curve (0.947, 95% CI: [0.865-0.986]) and Youden index (0.8333), with sensitivity of 100% and specificity of 83.33%, and a greater clinical net benefit.

Patients with EHS were at a risk of early experiencing decreased mHLA-DR early. A nomogram based on mHLA-DR with GCS was developed to facilitate early identification and timely treatment of individuals with potentially poor prognosis.

Risk stratification has potential to guide triage and decision-making in cardiogenic shock (CS). We assessed the prognostic performance of the IABP-SHOCK II score, derived in Europe for acute myocardial infarct-related CS (AMI-CS), in a contemporary North American cohort, including different CS phenotypes.

The critical care cardiology trials network (CCCTN) coordinated by the TIMI study group is a multicenter network of cardiac intensive care units (CICU). Participating centers annually contribute ≥2 months of consecutive medical CICU admissions. The IABP-SHOCK II risk score includes age > 73 years, prior stroke, admission glucose > 191 mg/dl, creatinine > 1.5 mg/dl, lactate > 5 mmol/l, and post-PCI TIMI flow grade < 3. We assessed the risk score across various CS etiologies.

Of 17,852 medical CICU admissions 5,340 patients across 35 sites were admitted with CS. In patients with AMI-CS (n = 912), the IABP-SHOCK II score predicted a >3-fold gradient in in-hospital mortality (low risk = 26.5%, intermediate risk = 52.2%, high risk = 77.5%, P < .0001; c-statistic = 0.67; Hosmer-Lemeshow P = .79). The score showed a similar gradient of in-hospital mortality in patients with non-AMI-related CS (n = 2,517, P < .0001) and mixed shock (n = 923, P < .001), as well as in left ventricular (<0.0001), right ventricular (P = .0163) or biventricular (<0.0001) CS. The correlation between the IABP-SHOCK II score and SOFA was moderate (r2 = 0.17) and the IABP-SHOCK II score revealed a significant risk gradient within each SCAI stage.

In an unselected international multicenter registry of patients admitted with CS, the IABP- SHOCK II score only moderately predicted in-hospital mortality in a broad population of CS regardless of etiology or irrespective of right, left, or bi-ventricular involvement.

Driving pressure (∆P) is a core therapeutic component of mechanical ventilation (MV). Varying levels of ∆P have been employed during MV depending on the type of underlying pathology and severity of injury. However, ∆P levels have also been shown to closely impact hard endpoints such as mortality. Considering this, conducting an in-depth review of ∆P as a unique, outcome-impacting therapeutic modality is extremely important. There is a need to understand the subtleties involved in making sure ∆P levels are optimized to enhance outcomes and minimize harm. We performed this narrative review to further explore the various uses of ∆P, the different parameters that can affect its use, and how outcomes vary in different patient populations at different pressure levels. To better utilize ∆P in MV-requiring patients, additional large-scale clinical studies are needed.

Community-acquired pneumonia (CAP) is a common reason for intensive care unit (ICU) admission and sepsis. Acute kidney injury (AKI) is a frequent complication of community-acquired pneumonia and is associated with increased short- and long-term morbidity and mortality and healthcare costs.

Describe the prevalence of AKI in patients with CAP requiring mechanical ventilation and evaluate its association with inhospital mortality.

Retrospective cohort.

Intensive care unit.

We included patients with CAP on mechanical ventilation. Patients were categorized according to the development of AKI in the first 24 hours of ICU admission using the Kidney Disease Improving Global Outcomes (KDIGO) classification from no AKI, stage 1 AKI, stage 2 AKI, and stage 3 AKI.

The primary outcome was hospital mortality. Secondary outcomes were ICU mortality, hospital and ICU length of stay, ventilation duration, tracheostomy, and renal replacement therapy requirement.

Of 1536 patients included in the study, 829 patients (54%) had no AKI while 707 (46%) developed AKI. In-hospital mortality was 288/829 (34.8%) for patients with no AKI, 43/111 (38.7%) for stage 1 AKI, 86/216 (40%) for stage 2 AKI, and 196/380 (51.7%) for stage 3 AKI (P<.0001). Multivariate analysis revealed that stages 1, 2, or 3 AKI compared to no AKI were not independently associated with in-hospital mortality. Older age, vasopressor use; decreased Glasgow coma scale, PaO2/Fio2 ratio and platelet count, increased bilirubin, lactic acid and INR were associated with increased mortality while female sex was associated with reduced mortality.

Among mechanically ventilated patients with CAP, AKI was common and was associated with higher crude mortality. The higher mortality could not be attributed alone to AKI, but rather appeared to be related to multi-organ dysfunction.

Single-center retrospective study with no data on baseline serum creatinine and the use of estimated baseline creatinine distributions based on the MDRD (Modification of Diet in Renal Disease)equation which may lead to an overestimation of AKI. Second, we did not have data on the microbiology of pneumonia, appropriateness of antibiotic therapy or the administration of other medications that have been demonstrated to be associated with AKI.

Vaccination helped in reducing mortality and disease severity due to COVID-19. Some patients can develop breakthrough infections. The effect of vaccination in critically ill patients admitted with breakthrough infections is not well studied. We designed a study to estimate the effect of vaccination on ICU mortality in critically ill COVID-19 patients by using propensity score matching.

We included patients from 15th June 2020 to 31st December 2021. Inclusion criteria were unvaccinated and vaccinated COVID-19 patients requiring intensive care unit (ICU) admission. The institutional ethics committee approval was obtained (institutional ethics committee, IEC 08/2023, Clinical trial registry, India CTRI/2023/01/049142). The primary outcome was ICU mortality. The secondary outcomes were the length of ICU stay and duration of mechanical ventilation. We used multivariable logistic regression (MLR) and propensity score matching (PSM) for the statistical analysis.

Total of 667 patients (79.31%) were unvaccinated and 174 (20.68%) vaccinated. The mean age was 57.11 [standard deviation (SD) 15.13], and 70.27% were males. The ICU mortality was 56.60% [95% confidence interval (CI) 53.24-60%]. The results of MLR and PSM method showed that vaccinated patients were less likely to be associated with mortality [adjusted odds ratio (AOR), 95% CI using logistic regression: 0.52 (0.29, 0.94), and by propensity score matching: 0.83 (0.77, 0.91)].

The findings of this study support COVID-19 vaccination as an effective method for reducing case fatality not only in the general population but also in critically ill patients, and it has important public health implications.

This study assessed model performance of the Acute Physiology and Chronic Health Evaluation (APACHE) III and Japan Risk of Death (JROD) when degraded by the number and category of missing variables. We also examined the impact of missing data on predicted mortality for facilities with missing physiological variables.

We obtained data from the Japanese Intensive care PAtient Database (JIPAD). We calculated observed and predicted mortality rates using the APACHE III and JROD and the standardized mortality ratio (SMR) by the number and category of missing variables. Smoothed spline curves were calculated for the SMR to the missing proportion of the facility.

A total of 61,357 patients from 57 ICUs were included between April 2015 and March 2019. The APACHE III and JROD SMRs increased as the number of missing values increased. The SMR in the APACHE III model was elevated in facilities with a larger proportion of missing in each of the APS categories, arterial blood gas, albumin, glucose, and bilirubin. Facilities with a high proportion of missing albumin data preserved their SMRs in only the JROD model.

An increased number of missing physiological variables resulted in falsely low predicted mortality rates and high SMRs.

The evaluation of acute poisoning is challenging due to varied toxic substances and clinical presentations. The new-Poisoning Mortality Score was recently developed to assess patients with acute poisoning and showed good performance in predicting in-hospital mortality. The objective of this study is to externally validate the performance of the new-Poisoning Mortality Score and to compare it with the Modified Early Warning Score.

This retrospective analysis used data from the 2019-2020 Injury Surveillance Cohort, established by the Korea Center for Disease Control and Prevention, to perform external validation of the new-Poisoning Mortality Score. The statistical performances of the new-Poisoning Mortality and Modified Early Warning Scores were assessed and compared in terms of discrimination and calibration. Discrimination analysis involved metrics such as sensitivity, specificity, accuracy, and the area under the receiver operating characteristic curve. For calibration analysis, the Hosmer-Lemeshow goodness-of-fit test was utilized and calibration curves for each score were generated to elucidate the relationship between observed and predicted mortalities.

This study analysed 16,570 patients with acute poisoning. Significant differences were observed between survivors and those who died in-hospital, including age, sex, and vital signs. The new-Poisoning Mortality Score showed better performance over the Modified Early Warning Score in predicting in-hospital mortality, in terms of the area under the receiver operating characteristic curve (0.947 versus 0.800), sensitivity (0.863 versus 0.667), specificity (0.912 versus 0.817), and accuracy (0.911 versus 0.814). When evaluated through calibration curves, the new-Poisoning Mortality Score showed better concordance between predicted and observed mortalities. In subgroup analyses, the score system consistently showed strong performance, excelling particularly in substances with high mortality indices and remaining superior in all substances as a group.

Our study has helped to validate the new-Poisoning Mortality Score as an effective tool for predicting in-hospital mortality in patients with acute poisoning in the emergency department. The score system demonstrated superior performance over the Modified Early Warning Score in various metrics. Our findings suggest that the new-Poisoning Mortality Score can contribute to the enhancement of clinical decision-making and patient management.

Sepsis is common in the intensive care unit (ICU). Two of the ICU's most widely used mortality prediction models are the Simplified Acute Physiology Score 3 (SAPS-3) and the Sequential Organ Failure Assessment (SOFA) score. We aimed to assess the mortality prediction performance of SAPS-3 and SOFA upon ICU admission for sepsis and find a simpler mortality prediction model for these patients to be used in clinical practice and when conducting studies.

A retrospective study of adult patients fulfilling the Sepsis-3 criteria admitted to four general ICUs was performed. A simple prognostic model was created using backward stepwise multivariate logistic regression. The area under the curve (AUC) of SAPS-3, SOFA and the simple model was assessed.

One thousand nine hundred eighty four admissions were included. A simple six-parameter model consisting of age, immunosuppression, Glasgow Coma Scale, body temperature, C-reactive protein and bilirubin had an AUC of 0.72 (95% confidence interval (CI) 0.69-0.75) for 30-day mortality, which was non-inferior to SAPS-3 (AUC 0.75, 95% CI 0.72-0.77) (p = 0.071). SOFA had an AUC of 0.67 (95% CI 0.64-0.70) and was inferior to SAPS-3 (p < 0.001) and our simple model (p = 0.0019).

SAPS-3 has a lower prognostic value in sepsis than in the general ICU population. SOFA performs less well than SAPS-3. Our simple six-parameter model predicts mortality just as well as SAPS-3 upon ICU admission for sepsis, allowing the design of simple studies and performance monitoring.

Acute neurological emergencies are highly prevalent in intensive care units (ICUs) and impose a substantial burden on patients. This study aims to describe the epidemiology of patients requiring neurocritical care in Brazil, and their differences based on primary acute neurological diagnoses and to identify predictors of mortality and unfavourable outcomes, along with the disease burden of each condition at intensive care unit admission. This prospective cohort study included patients requiring neurocritical care admitted to 36 ICUs in four Brazilian regions who were followed for 30 days or until ICU discharge (Aug-Sep in 2018, 1 month). Of 4245 patients admitted to the participating ICUs, 1194 (28.1%) were patients with acute neurological disorders requiring neurocritical care and were included. Patients requiring neurocritical care had a mean mortality rate 1.7 times higher than ICU patients not requiring neurocritical care (17.21% versus 10.1%, respectively). Older age, emergency admission, higher number of potential secondary injuries, and worse APACHE II, SAPS III, SOFA, and Glasgow coma scale scores on ICU admission are independent predictors of mortality and poor outcome among patients with acute neurological diagnoses. The estimated total DALYs were 4482.94 in the overall cohort, and the diagnosis with the highest DALYs was traumatic brain injury (1634.42). Clinical, epidemiological, treatment, and ICU outcome characteristics vary according to the primary neurologic diagnosis. Advanced age, a lower GCS score and a higher number of potential secondary injuries are independent predictors of mortality and unfavourable outcomes in patients requiring neurocritical care. The findings of this study are essential to guide education policies, prevention, and treatment of severe acute neurocritical diseases.

We investigated the prognostic performance of scoring systems by the intensive care unit (ICU) type. This was a retrospective observational study using data from the Marketplace for Medical Information in the Intensive Care IV database. The primary outcome was in-hospital mortality. We obtained Sequential Organ Failure Assessment (SOFA), Acute Physiology and Chronic Health Evaluation (APACHE) III, and Simplified Acute Physiology Score (SAPS) II scores in each ICU type. Prognostic performance was evaluated with the area under the receiver operating characteristic curve (AUROC) and was compared among ICU types. A total of 29,618 patients were analyzed, and the in-hospital mortality was 12.4%. The overall prognostic performance of APACHE III was significantly higher than those of SOFA and SAPS II (0.807, [95% confidence interval, 0.799-0.814], 0.785 [0.773-0.797], and 0.795 [0.787-0.811], respectively). The prognostic performance of SOFA, APACHE III, and SAPS II scores was significantly different between ICU types. The AUROC ranges of SOFA, APACHE III, and SAPS II were 0.723-0.826, 0.728-0.860, and 0.759-0.819, respectively. The neurosurgical and surgical ICUs had lower prognostic performance than other ICU types. The prognostic performance of scoring systems in patients with suspected infection is significantly different according to ICU type. APACHE III systems have the highest prediction performance. ICU type may be a significant factor in the prognostication.

Comorbidity, frailty, and decreased cognitive function lead to a higher risk of death in elderly patients (more than 65 years of age) during acute medical events. Early and accurate illness severity assessment can support appropriate decision making for clinicians caring for these patients. We aimed to develop ELDER-ICU, a machine learning model to assess the illness severity of older adults admitted to the intensive care unit (ICU) with cohort-specific calibration and evaluation for potential model bias.

In this retrospective, international multicentre study, the ELDER-ICU model was developed using data from 14 US hospitals, and validated in 171 hospitals from the USA and Netherlands. Data were extracted from the Medical Information Mart for Intensive Care database, electronic ICU Collaborative Research Database, and Amsterdam University Medical Centers Database. We used six categories of data as predictors, including demographics and comorbidities, physical frailty, laboratory tests, vital signs, treatments, and urine output. Patient data from the first day of ICU stay were used to predict in-hospital mortality. We used the eXtreme Gradient Boosting algorithm (XGBoost) to develop models and the SHapley Additive exPlanations method to explain model prediction. The trained model was calibrated before internal, external, and temporal validation. The final XGBoost model was compared against three other machine learning algorithms and five clinical scores. We performed subgroup analysis based on age, sex, and race. We assessed the discrimination and calibration of models using the area under receiver operating characteristic (AUROC) and standardised mortality ratio (SMR) with 95% CIs.

Using the development dataset (n=50 366) and predictive model building process, the XGBoost algorithm performed the best in all types of validations compared with other machine learning algorithms and clinical scores (internal validation with 5037 patients from 14 US hospitals, AUROC=0·866 [95% CI 0·851-0·880]; external validation in the US population with 20 541 patients from 169 hospitals, AUROC=0·838 [0·829-0·847]; external validation in European population with 2411 patients from one hospital, AUROC=0·833 [0·812-0·853]; temporal validation with 4311 patients from one hospital, AUROC=0·884 [0·869-0·897]). In the external validation set (US population), the median AUROCs of bias evaluations covering eight subgroups were above 0·81, and the overall SMR was 0·99 (0·96-1·03). The top ten risk predictors were the minimum Glasgow Coma Scale score, total urine output, average respiratory rate, mechanical ventilation use, best state of activity, Charlson Comorbidity Index score, geriatric nutritional risk index, code status, age, and maximum blood urea nitrogen. A simplified model containing only the top 20 features (ELDER-ICU-20) had similar predictive performance to the full model.

The ELDER-ICU model reliably predicts the risk of in-hospital mortality using routinely collected clinical features. The predictions could inform clinicians about patients who are at elevated risk of deterioration. Prospective validation of this model in clinical practice and a process for continuous performance monitoring and model recalibration are needed.

National Institutes of Health, National Natural Science Foundation of China, National Special Health Science Program, Health Science and Technology Plan of Zhejiang Province, Fundamental Research Funds for the Central Universities, Drug Clinical Evaluate Research of Chinese Pharmaceutical Association, and National Key R&D Program of China.

Characterizing medical interventions delivered to ICU patients over time and their relationship to outcomes can help set expectations and inform decisions made by patients, clinicians, and health systems.

To determine whether distinct and clinically relevant pathways of medical intervention can be identified among adult ICU patients with acute respiratory failure.

Retrospective observational study using all-payer administrative claims data from 2012 to 2014. Patients were identified from the Healthcare Cost and Utilization Project State Inpatient Databases from Maryland, Massachusetts, Nevada, and Washington.

Patterns of cumulative medical intervention delivery, over time, using temporal k-means clustering of interventions delivered up to hospital days 0, 5, 10, 20, and up to discharge.

A total of 12,175 admissions were identified and divided into training (75%; n = 9,130) and validation sets (25%; n = 3,045). Without applying a priori classification and using only medical interventions to cluster, we identified three distinct pathways of intervention accounting for 93.5% of training set admissions. We found 45.9% of admissions followed a "cardiac" intervention pathway (e.g., cardiac catheterization, cardioversion); 36.7% followed a "general" pathway (e.g., diagnostic interventions); and 17.4% followed a "prolonged" pathway (e.g., tracheostomy, gastrostomy). Prolonged pathway admissions had longer median hospital length of stay (13 d; interquartile range [IQR], 7.5-18.5 d) compared with cardiac (5; IQR, 2.5-7.5) and general (5; IQR, 3-7). In-hospital death occurred in 24.6% of prolonged pathway admissions compared with 17.9% of cardiac and 6.9% of general. Findings were confirmed in the validation set.

Most ICU admissions for acute respiratory failure follow one of three clinically relevant pathways of medical intervention which are associated with hospitalization outcomes. This study helps define the longitudinal nature of critical care delivery, which can inform efforts to predict patient outcomes, communicate with patients and their families, and organize critical care resources.

Lung ultrasound (LUS) is a known imaging modality employed for monitoring patients in an intensive care unit. This study evaluates, LUS in assessing disease severity and prognosis, by correlating its score with the three commonly used clinical severity scoring systems (CSSS), namely, sequential organ failure assessment (SOFA) score, acute physiology and chronic health evaluation (APACHE) II score, and simplified acute physiology score (SAPS) II.

This single-center prospective observational study included 54 adult patients of primary lung disease-induced acute respiratory distress syndrome (ARDS), on invasive ventilation. The primary objective was to correlate LUS score with SOFA score. Secondary objectives were to correlate LUS score with APACHE II and SAPS II scores. LUS score was also correlated with the estimated mortality derived from the above-mentioned scores. A subgroup analysis on COVID-19-positive cases was also carried out. All scores were calculated on the initiation of mechanical ventilation, daily for 7 days or mortality, whichever was earlier.

A significant positive correlation (P < 0.001) was found between LUS and all three severity scores, as well as their corresponding estimated mortality percentages, for all days of the study period, in both non-COVID-19 ARDS patients and in COVID-19 patients. The merit of all four scores in differentiating between the survivor and mortality group for the duration of study also showed significant (P < 0.05) to very significant (P < 0.001) results.

Point-of-care LUS in conjunction with CSSS is a reliable tool for assessing the severity and progression of primary lung disease.

The rapid adoption of electronic health record (EHR) systems in US hospitals from 2008 to 2014 produced novel data elements for analysis. Concurrent innovations in computing architecture and machine learning (ML) algorithms have made rapid consumption of health data feasible and a powerful engine for clinical innovation. In critical care research, the net convergence of these trends has resulted in an exponential increase in outcome prediction research. In the following article, we explore the history of outcome prediction in the intensive care unit (ICU), the growing use of EHR data, and the rise of artificial intelligence and ML (AI) in critical care.

To investigate the prevalence of euthyroid sick syndrome (ESS) and to evaluate the outcomes and risk factors associated with ESS among hospitalized patients with diabetic ketosis (DK) or diabetic ketoacidosis (DKA).

Laboratory and clinical data of 396 adult hospitalized DK/DKA patients with or without ESS were collected and analyzed. Spearman linear analysis and multivariable logistic regression analyses were used to evaluate correlated factors of thyroid hormones and risk factors of ESS.

Most of the individuals were diagnosed with type 2 diabetes (359/396, 90.7%). The prevalence of ESS was 57.8% (229/396). Patients in ESS group were older and had a longer course of diabetes. Levels of thyroid hormones, serum lipids, and parameters reflecting acidosis were significantly decreased in ESS group. The proportion of patients with infection, acute renal injury and DKA was significantly higher in ESS group than in control group, accompanied by longer hospitalization stay and higher hospitalization costs. Free triiodothyronine positively correlates with albumin, eGFR, parameters reflecting acidosis and lipid profiles (All P < 0.001), and negatively correlates with age, onset age, 24-h urine albumin, hsCRP and WBC count (All P < 0.001). Hypoalbuminemia, low level of carbon dioxide combining power, high level of HbA1c and WBC, and co-infection are shown to be risk factors for ESS (OR = 0.866, 0.933, 1.112, 1.146, 1.929, respectively; All P < 0.05).

The prevalence of ESS was high in adult DK/DKA patients. Patients with ESS had inferior clinical and socioeconomic outcomes. Early recognition and management of patients with ESS may be necessary to improve outcome.

With uncertain prognostic utility of existing predictive scoring systems for COVID-19-related illness, the International Severe Acute Respiratory and Emerging Infection Consortium (ISARIC) 4C Mortality Score was developed by the International Severe Acute Respiratory and Emerging Infection Consortium as a COVID-19 mortality prediction tool. We sought to externally validate this score among critically ill patients admitted to an intensive care unit (ICU) with COVID-19 and compare its discrimination characteristics to that of the Acute Physiology and Chronic Health Evaluation (APACHE) II and Sequential Organ Failure Assessment (SOFA) scores.

We enrolled all consecutive patients admitted with COVID-19-associated respiratory failure between 5 March 2020 and 5 March 2022 to our university-affiliated and intensivist-staffed ICU (Jewish General Hospital, Montreal, QC, Canada). After data abstraction, our primary outcome of in-hospital mortality was evaluated with an objective of determining the discriminative properties of the ISARIC 4C Mortality Score, using the area under the curve of a logistic regression model.

A total of 429 patients were included, 102 (23.8%) of whom died in hospital. The receiver operator curve of the ISARIC 4C Mortality Score had an area under the curve of 0.762 (95% confidence interval [CI], 0.717 to 0.811), whereas those of the SOFA and APACHE II scores were 0.705 (95% CI, 0.648 to 0.761) and 0.722 (95% CI, 0.667 to 0.777), respectively.

The ISARIC 4C Mortality Score is a tool that had a good predictive performance for in-hospital mortality in a cohort of patients with COVID-19 admitted to an ICU for respiratory failure. Our results suggest a good external validity of the 4C score when applied to a more severely ill population.