Scoring systems in the intensive care unit: A compendium

Development and validation of novel interpretable survival prediction models based on drug exposures for severe heart failure during vulnerable period

BACKGROUND

Severe heart failure (HF) has a higher mortality during vulnerable period while targeted predictive tools, especially based on drug exposures, to accurately assess its prognoses remain largely unexplored. Therefore, this study aimed to utilize drug information as the main predictor to develop and validate survival models for severe HF patients during this period.

METHODS

We extracted severe HF patients from the MIMIC-IV database (as training and internal validation cohorts) as well as from the MIMIC-III database and local hospital (as external validation cohorts). Three algorithms, including Cox proportional hazards model (CoxPH), random survival forest (RSF), and deep learning survival prediction (DeepSurv), were applied to incorporate the parameters (partial hospitalization information and exposure durations of drugs) for constructing survival prediction models. The model performance was assessed mainly using area under the receiver operator characteristic curve (AUC), brier score (BS), and decision curve analysis (DCA). The model interpretability was determined by the permutation importance and Shapley additive explanations values.

RESULTS

A total of 11,590 patients were included in this study. Among the 3 models, the CoxPH model ultimately included 10 variables, while RSF and DeepSurv models incorporated 24 variables, respectively. All of the 3 models achieved respectable performance metrics while the DeepSurv model exhibited the highest AUC values and relatively lower BS among these models. The DCA also verified that the DeepSurv model had the best clinical practicality.

CONCLUSIONS

The survival prediction tools established in this study can be applied to severe HF patients during vulnerable period by mainly inputting drug treatment duration, thus contributing to optimal clinical decisions prospectively.

Comparison of Four Severity Assessment Scoring Systems in Critically Ill Patients for Predicting Patient Outcomes: A Prospective Observational Study From a Single Tertiary Center in Central India

Background and aim A variety of scoring systems are employed in intensive care units (ICUs) with the objective of predicting patient morbidity and mortality. The present study aimed to compare four different severity assessment scoring systems, namely, Acute Physiology and Chronic Health Evaluation II (APACHE II), Rapid Emergency Medicine Score (REMS), Sequential Organ Failure Assessment (SOFA), and Simplified Acute Physiologic Score II (SAPS II) to predict prognosis of all patients admitted to a mixed medical ICU of a tertiary care teaching hospital in central India. Methods The prospective observational study included 1136 patients aged 18 years or more, admitted to the mixed medical ICU. All patients underwent severity assessment using the four scoring systems, namely APACHE II, SOFA, REMS, and SAPS II, after admission. Predicted mortality was calculated from each of the scores and actual patient outcomes were noted. Receiver operating curve analysis was undertaken to identify the cut-off value of individual scoring systems for predicting mortality with optimum sensitivity and specificity. Calibration and discrimination were employed to ascertain the validity of each scoring model. Bivariate and multivariable logistic regression analyses among the study participants were conducted to identify the best scoring system, after adjusting for potential confounders. Results Final analysis was done on 957 study participants (mean (±SD) age-58.4 (±12.9) years; males-62.2%). The mortality rate was 14.7%. APACHE II, SOFA, SAPS II, and REMS scores were significantly higher among the non-survivors as compared to the survivors (p<0.05). SAPS II was found to have the highest AUC of 0.981 (p<0.001). SAPS II score >58 had 93.6% sensitivity, 94.1% specificity, 73.3% PPV, 98.8% NPV, and 94.0% diagnostic accuracy in predicting mortality. This scoring system also had the best calibration. Binary logistic regression showed that all four scoring systems were significantly associated with ICU mortality. After adjusting for each other, only SAPS II remained significantly associated with ICU mortality. Conclusion Both SAPS II and APACHE II were observed to have good calibration and discriminatory power; however, SAPS II had the best prediction power suggesting that it may be a useful tool for clinicians and researchers in assessing the severity of illness and mortality risk in critically ill patients.

The effect of abdominal massage and in-bed ROM exercise on gastrointestinal complications and comfort in intensive care unit patients receiving enteral nutrition: A randomized controlled trial

AIM

Abdominal massage facilitates gastric and colonic motility, reduces intra-abdominal distension and increases circulation. In-bed range of motion (ROM) exercise has effects on muscle strength, cardiac parameters and excretion. The aim of this study was to assess the effects of abdominal massage and in-bed ROM exercise on gastrointestinal complications and patient comfort in intensive care patients receiving enteral nutrition.

METHODS

This randomized controlled trial was conducted in the internal intensive care units of two tertiary public hospitals. The sample consisted of 130 patients randomly assigned to three groups (abdominal massage = 44, in-bed ROM exercise = 43, control = 43). The individuals received abdominal massage and in-bed ROM exercises every morning before enteral feeding for 3 days. We assessed gastrointestinal complications and comfort levels of the patients 24 h after each intervention.

RESULTS

While the differences in abdominal distention, defecation status, constipation, and gastric residual volume complications were significant (p < .05), there was no significant difference in diarrhea and vomiting (p > .05). Comfort level showed a statistically significant change in the experimental groups in the in-group comparison (p < .05).

CONCLUSION

Abdominal massage and in-bed ROM exercise reduce abdominal distention, constipation and gastric residual volume. Abdominal massage affects the frequency of defecation; and, both interventions increase the comfort while reducing the pain level over time.

Mortality and its associated factors among mechanically ventilated adult patients in the intensive care units of referral hospitals in Northwest Amhara, Ethiopia, 2023

Background

Worldwide, nearly half of the patients admitted to intensive care units require ventilatory support. Despite advances in intensive care unit patient management and mechanical ventilator utilization, the odds of mortality among mechanically ventilated patients are higher in resource-limited settings. Little is known about the mortality of patients on mechanical ventilation outside the capital of Ethiopia. This study aimed to assess mortality and its associated factors among mechanically ventilated adult patients in intensive care units.

Method

An institutional-based cross-sectional study was conducted on mechanically ventilated patients in intensive care units from 1 February 2020 to 1 March 2023. A simple random sampling technique was used to select 434 patients' charts. A data extraction tool designed on the Kobo toolbox, a smartphone data collection platform, was used to collect the data. The data were exported into Microsoft Excel 2019 and then into Stata 17 for data management and analysis. Descriptive statistics were used to summarize the characteristics of the study participants. A bivariable logistic regression was conducted, and variables with p ≤ 0.20 were recruited for multivariable analysis. Statistical significance was declared at p < 0.05, and the strength of associations was summarized using an adjusted odds ratio with 95% confidence intervals.

Result

A total of 404 charts of mechanically ventilated patients were included, with a completeness rate of 93.1%. The overall proportion of mortality was 62.87%, with a 95% CI of (58.16-67.58). In the multivariable logistic regression, age 41-70 years (AOR: 4.28, 95% CI: 1.89-9.62), sepsis (AOR: 2.43, 95% CI: 1.08-5.46), reintubation (AOR: 2.76, 95% CI: 1.06-7.21), and sedation use (AOR: 0.41, 95% CI: 0.18-0.98) were found to be significant factors associated with the mortality of mechanically ventilated patients in the intensive care unit.

Conclusion

The magnitude of mortality among mechanically ventilated patients was high. Factors associated with increased odds of death were advanced age, sepsis, and reintubation. However, sedation use was a factor associated with decreased mortality. Healthcare professionals in intensive care units should pay special attention to patients with sepsis, those requiring reintubation, those undergoing sedation, and those who are of advanced age.

Analysis of risk factors for weaning failure from mechanical ventilation in critically ill older patients with coronavirus disease 2019

Objective

This study aimed to investigate the factors influencing weaning failure from invasive mechanical ventilation (IMV) in critically ill older patients with coronavirus disease 2019 (COVID-19).

Methods

We enrolled critically ill older patients with COVID-19 who were admitted to the medical intensive care unit (ICU) and received IMV between December 2022 and June 2023.

Results

We included 68 critically ill older patients with COVID-19 (52 male [76.5 %] and 16 female individuals [23.5 %]). The patients' median age (interquartile range) was 75.5 (70.3-82.8) years. The median length of ICU stay was 11.5 (7.0-17.8) days; 34 cases (50.0 %) were successfully weaned from IMV. The successfully weaned group had a higher proportion of underlying chronic obstructive pulmonary disease [6 (17.6 %) vs. 0, P = 0.033] and fewer cases of diabetes [7 (20.6 %) vs. 16 (47.1 %), P = 0.021] compared with the weaning failure group. Serum lactate levels [1.5 (1.2-2.3) vs. 2.6 (1.9-3.1) mmol/L, P < 0.001], blood urea nitrogen [8.2 (6.3-14.4) vs. 11.4 (8.0-21.3) mmol/L, P = 0.033], Acute Physiology and Chronic Health Evaluation (APACHE) II score [19.0 (12.0-23.3) vs. 22.5 (16.0-29.3), P = 0.014], and hospitalization days before endotracheal intubation [1.0 (0.0-5.0) vs. 3.0 (0.0-11.0), P = 0.023] were significantly decreased in the successfully weaned group, whereas PaO2/FiO2 [148.3 (94.6-200.3) vs. 101.1 (67.0-165.1), P = 0.038] and blood lymphocyte levels [0.6 (0.4-1.0) vs. 0.5 (0.2-0.6) 109/L, P = 0.048] were significantly increased, compared with the weaning failure group. Multivariate logistic regression analysis showed that diabetes (OR= 3.413, 95 %CI 1.029-11.326), P = 0.045), APACHE II Score (OR = 1.089, 95 % CI 1.008-1.175), P = 0.030), and hospitalization days before endotracheal intubation (OR = 1.137, 95 % CI 1.023-1.264), P = 0.017) were independent risk factors for weaning failure.

Conclusion

In critically ill older patients with COVID-19 with diabetes, higher APACHE II Score, and longer hospitalization days before endotracheal intubation, weaning from IMV was more challenging. The study could help develop strategies for improving COVID-19 treatment.

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

Background

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.

Objective

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.

Method

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.

Results

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.

Conclusion

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.

How to cite this article

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.

A hybrid modeling framework for generalizable and interpretable predictions of ICU mortality across multiple hospitals

The development of reliable mortality risk stratification models is an active research area in computational healthcare. Mortality risk stratification provides a standard to assist physicians in evaluating a patient's condition or prognosis objectively. Particular interest lies in methods that are transparent to clinical interpretation and that retain predictive power once validated across diverse datasets they were not trained on. This study addresses the challenge of consolidating numerous ICD codes for predictive modeling of ICU mortality, employing a hybrid modeling approach that integrates mechanistic, clinical knowledge with mathematical and machine learning models . A tree-structured network connecting independent modules that carry clinical meaning is implemented for interpretability. Our training strategy utilizes graph-theoretic methods for data analysis, aiming to identify the functions of individual black-box modules within the tree-structured network by harnessing solutions from specific max-cut problems. The trained model is then validated on external datasets from different hospitals, demonstrating successful generalization capabilities, particularly in binary-feature datasets where label assessment involves extrapolation.

Comparison of the Recent ExPreS Score, WEANSNOW Score, and the Parsimonious HACOR Score as the Best Predictor of Weaning: An Externally Validated Prospective Observational Study

Background

Since weaning failure is multifactorial, comprehensive weaning scores encompassing not only the respiratory component but also nonrespiratory aspects are quintessential for successful weaning prediction.

Materials and methods

This was a single-center prospective observational study on 128 intensive care unit (ICU) patients undergoing spontaneous breathing trials (SBT). The extubation prediction score (ExPreS), heart rate, acidosis, consciousness, oxygenation, respiratory rate (HACOR), and weaning parameters, endotracheal tube size, arterial blood gas analysis, nutrition, secretions, neuromuscular affecting agents, obstructive airway problems and wakefulness (WEANSNOW) scores were compared for their diagnostic accuracy for successful weaning prediction.

Results

Out of 128 patients, 49 (38.3%) patients had weaning failure, and 79 (61.7%) had weaning success. The patients in the weaning failure group had significantly higher APACHE II scores, WEANSNOW scores, HACOR scores, MV days, and significantly lower ExPreS scores as compared to the successful weaning group. Multivariable regression analysis showed that ExPreS score p = 0.015, adjusted OR 0.960, 95% CI (0.929-0.992) and HACOR score p < 0.001, adjusted OR 1.357, 95% CI (1.176-1.567) were independent predictors of weaning failure. The HACOR score had an AUC of 0.830, cut-off ≥5, p < 0.001, sensitivity 76%, specificity 68%, diagnostic accuracy 70% to predict weaning failure. The ExPreS score had an AUC of 0.735, cut-off ≥69, p < 0.001, sensitivity of 70.9%, specificity of 69.4%, and diagnostic accuracy of 70.3% to predict weaning success. Both the HACOR and ExPreS scores were good models for predicting weaning outcomes (model quality 0.76 and 0.64 respectively).

Conclusion

The parsimonious HACOR score is comparable to the ExPreS score for the prediction of weaning outcomes in critically ill patients.

How to cite this article

Nayak G, Chaudhuri S, Ravindranath S, Todur P. Comparison of the Recent ExPreS Score, WEANSNOW Score, and the Parsimonious HACOR Score as the Best Predictor of Weaning: An Externally Validated Prospective Observational Study. Indian J Crit Care Med 2024;28(3):273-279.

RAPID-ED: A predictive model for risk assessment of patient's early in-hospital deterioration from emergency department

Introduction

The objective of this multi-center retrospective cohort study was to devise a predictive tool known as RAPID-ED. This model identifies non-traumatic adult patients at significant risk for cardiac arrest within 48 hours post-admission from the emergency department.

Methods

Data from 224,413 patients admitted through the emergency department (2016-2020) was analyzed, incorporating vital signs, lab tests, and administered therapies. A multivariable regression model was devised to anticipate early cardiac arrest. The efficacy of the RAPID-ED model was evaluated against traditional scoring systems like National Early Warning Score (NEWS) and Modified Early Warning Score (MEWS) and its predictive ability was gauged via the area under the receiver operating characteristic curve (AUC) in both hold-out validation set and external validation set.

Results

RAPID-ED outperformed traditional models in predicting cardiac arrest with an AUC of 0.819 in the hold-out validation set and 0.807 in the external validation set. In this critical care update, RAPID-ED offers an innovative approach to assessing patient risk, aiding emergency physicians in post-discharge care decisions from the emergency department. High-risk score patients (≥13) may benefit from early ICU admission for intensive monitoring.

Conclusion

As we progress with advancements in critical care, tools like RAPID-ED will prove instrumental in refining care strategies for critically ill patients, fostering an improved prognosis and potentially mitigating mortality rates.

A study on the risk stratification for patients within 24 hours of admission for risk of hospital-acquired urinary tract infection using Bayesian network models

Early identification of patients at risk of hospital-acquired urinary tract infections (HA-UTI) enables the initiation of timely targeted preventive and therapeutic strategies. Machine learning (ML) models have shown great potential for this purpose. However, existing ML models in infection control have demonstrated poor ability to support explainability, which challenges the interpretation of the result in clinical practice, limiting the adaption of the ML models into a daily clinical routine. In this study, we developed Bayesian Network (BN) models to enable explainable assessment within 24 h of admission for risk of HA-UTI. Our dataset contained 138,250 unique hospital admissions. We included data on admission details, demographics, lifestyle factors, comorbidities, vital parameters, laboratory results, and urinary catheter. Models developed from a reduced set of five features were characterized by transparency compared to models developed from a full set of 50 features. The expert-based clinical BN model over the reduced feature space showed the highest performance (area under the curve = 0.746) compared to the naïve- and tree-augmented-naïve BN models. Moreover, models developed from expert-based knowledge were characterized by enhanced explainability.

Utilizing predictive machine-learning modelling unveils feature-based risk assessment system for hyperinflammatory patterns and infectious outcomes in polytrauma

Purpose

Earlier research has identified several potentially predictive features including biomarkers associated with trauma, which can be used to assess the risk for harmful outcomes of polytraumatized patients. These features encompass various aspects such as the nature and severity of the injury, accompanying health conditions, immune and inflammatory markers, and blood parameters linked to organ functioning, however their applicability is limited. Numerous indicators relevant to the patients` outcome are routinely gathered in the intensive care unit (ICU) and recorded in electronic medical records, rendering them suitable predictors for risk assessment of polytraumatized patients.

Methods

317 polytraumatized patients were included, and the influence of 29 clinical and biological features on the complication patterns for systemic inflammatory response syndrome (SIRS), pneumonia and sepsis were analyzed with a machine learning workflow including clustering, classification and explainability using SHapley Additive exPlanations (SHAP) values. The predictive ability of the analyzed features within three days after admission to the hospital were compared based on patient-specific outcomes using receiver-operating characteristics.

Results

A correlation and clustering analysis revealed that distinct patterns of injury and biomarker patterns were observed for the major complication classes. A k-means clustering suggested four different clusters based on the major complications SIRS, pneumonia and sepsis as well as a patient subgroup that developed no complications. For classification of the outcome groups with no complications, pneumonia and sepsis based on boosting ensemble classification, 90% were correctly classified as low-risk group (no complications). For the high-risk groups associated with development of pneumonia and sepsis, 80% of the patients were correctly identified. The explainability analysis with SHAP values identified the top-ranking features that had the largest impact on the development of adverse outcome patterns. For both investigated risk scenarios (infectious complications and long ICU stay) the most important features are SOFA score, Glasgow Coma Scale, lactate, GGT and hemoglobin blood concentration.

Conclusion

The machine learning-based identification of prognostic feature patterns in patients with traumatic injuries may improve tailoring personalized treatment modalities to mitigate the adverse outcomes in high-risk patient clusters.

Temperature-Neutrophils-Multiple Organ Failure Grading as a Prognostic Indicator in Fournier Gangrene

Background: Severity scoring systems are used widely to predict prognosis in managing various diseases and to tailor the treatment of patients in a personalized way, not in a general concept, by making a risk assessment. This study examines the importance of the Temperature-Neutrophils-Multiple Organ Failure (TNM) scoring system, a new scoring system, in evaluating the prognosis in patients with Fournier gangrene (FG). Patients and Methods: Patients who were operated on with the diagnosis of FG in our clinic between 2012 and 2022 were analyzed with a single-center cross-sectional retrospective study design. Demographic data (age, gender), pre-operative evaluation, body temperature, neutrophil ratio, presence of multiple organ failure, TNM score, and post-operative survival data were recorded. The patients were grouped as those with post-operative hospital mortality (group 1) and without (group 2). Results: The study included 167 patients. Twenty-two (13.2%) of the patients were in group 1 and 145 (86.8%) were in group 2. According to the TNM score, the frequency of stage 3-4 was higher in group 1 than in group 2 (p < 0.001). Patients ≥65 years of age had a 4.80 (95% confidence interval [CI], 1.87-12.29) times greater mortality risk than patients <65. Patients with comorbid disease had a 4.56 (95% CI, 1.47-14.14) times greater risk of mortality than patients without. Patients with TNM scores 3-4 had a 9.38 (95% CI, 3.01-29.28) times greater risk of exit than patients with scores 1-2. Conclusions: The TNM system is a new scoring system that is created quickly using simple laboratory and clinical data in patients with FG and is useful in predicting mortality. Therefore, its clinical use will benefit FG and other deep soft tissue infections.

A prospective observational study to correlate lung ultrasound with clinical severity and prognosis score in patients with primary pulmonary pathology on invasive ventilatory support

Background

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.

Methods

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.

Results

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.

Conclusion

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

Severity-of-Illness Scores and Discharge Disposition in Patients Admitted to Long-Term Acute Care Hospitals

BACKGROUND

After an intensive care unit (ICU) admission, nearly 20% of survivors of chronic critical illness require admission to a long-term acute care hospital (LTACH) for continued subspecialty care. The effect of the burden of medical comorbidities on discharge disposition after LTACH admission remains unclear.

METHODS

A retrospective cohort study was performed involving patients with chronic critical illness who were discharged from the medical ICU and admitted to an LTACH between 2016 and 2018. The patients' Acute Physiology and Chronic Health Evaluation II (APACHE II), Sequential Organ Failure Assessment (SOFA), Nutrition Risk in the Critically Ill (NUTRIC), and Charlson Comorbidity Index (CCI) scores at the time of LTACH admission were calculated from electronic medical records. The mean scores on each instrument were compared by discharge disposition.

RESULTS

A total of 156 patients were admitted to the LTACH from the medical ICU between 2016 and 2018. They had a mean (SD) age of 61.5 (13.3) years, a mean (SD) body mass index of 28.1 (8.3), a median (IQR) ICU stay of 16.3 (1-108) days, and a median (IQR) LTACH stay of 38.2 (1-227) days. Patients who were discharged home had lower mean (SD) APACHE II (14.6 [5.0] vs 18.2 [5.4], P = .01), SOFA (3.3 [2.1] vs 4.6 [2.1], P = .03), NUTRIC (3.3 [1.4] vs 4.6 [1.4], P = .001), and CCI (4.3 [2.5] vs 6.1 [2.8], P = .02) scores on admission to the LTACH than those who were not discharged home.

CONCLUSION

Severity-of-illness scores on admission to an LTACH can be used to predict patients' likelihood of being discharged home.

Unraveling the Predictive Potential of Rapid Scoring in Pleural Infection: A Critical Review

Pleural infection, or pleural empyema, is a severe medical condition associated with high morbidity and mortality rates. Timely and accurate prognostication is crucial for optimizing patient outcomes and resource allocation. Rapid scoring systems have emerged as promising tools in pleural infection prognostication, integrating various clinical and laboratory parameters to assess disease severity and quantitatively predict short-term and long-term outcomes. This review article critically evaluates existing rapid scoring systems, including CURB-65 (confusion, uremia, respiratory rate, blood pressure, age ≥ 65 years), A-DROP (age (male >70 years, female >75 years), dehydration, respiratory failure, orientation disturbance, and low blood pressure), and APACHE II (acute physiology and chronic health evaluation II), assessing their predictive accuracy and limitations. Our analysis highlights the potential clinical implications of rapid scoring, including risk stratification, treatment tailoring, and follow-up planning. We discuss practical considerations and challenges in implementing rapid scoring such as data accessibility and potential sources of bias. Furthermore, we emphasize the importance of validation, transparency, and multidisciplinary collaboration to refine and enhance the clinical applicability of these scoring systems. The prospects for rapid scoring in pleural infection management are promising, with ongoing research and data science advances offering improvement opportunities. Ultimately, the successful integration of rapid scoring into clinical practice can potentially improve patient care and outcomes in pleural infection management.

Investigating the Utility of the SOFA Score and Creating a Modified SOFA Score for Predicting Mortality in the Intensive Care Units in a Tertiary Hospital in Jordan

Background

The utility of the Sequential Organ Failure Assessment (SOFA) score in predicting mortality in the intensive care unit (ICU) has been demonstrated before, but serial testing in various settings is required to validate and improve the score. This study examined the utility of the SOFA score in predicting mortality in Jordanian ICU patients and aimed to find a modified score that required fewer laboratory tests.

Methods

A prospective observational study was conducted at Jordan University Hospital (JUH). All adult patients admitted to JUH ICUs between June and December 2020 were included in the study. SOFA scores were measured daily during the whole ICU stay. A modified SOFA score (mSOFA) was constructed from the available laboratory, clinical, and demographic data. The performance of the SOFA, mSOFA, qSOFA, and SIRS in predicting ICU mortality was assessed using the area under the receiver operating characteristic curve (AUROC).

Results

194 patients were followed up. SOFA score (mean ± SD) at admission was significantly higher in non-survivors (7.5 ± 3.9) compared to survivors (2.4 ± 2.2) and performed the best in predicting ICU mortality (AUROC = 0.8756, 95% CI: 0.8117-0.9395) compared to qSOFA (AUROC = 0.746, 95% CI: 0.655-0.836) and SIRS (AUROC = 0.533, 95% CI: 0.425-0.641). The constructed mSOFA included points for the hepatic and CNS SOFA scores, in addition to one point each for the presence of chronic kidney disease or the use of breathing support; it performed as well as the SOFA score in this cohort or better than the SOFA score in a subgroup of patients with heart disease.

Conclusion

SOFA score was a good predictor of mortality in a Jordanian ICU population and better than qSOFA, while SIRS could not predict mortality. Furthermore, the proposed mSOFA score which employed fewer laboratory tests could be used after validation from larger studies.

A data-driven model for early prediction of need for invasive mechanical ventilation in pediatric intensive care unit patients

RATIONALE

Acute respiratory failure is a life-threatening clinical outcome in critically ill pediatric patients. In severe cases, patients can require mechanical ventilation (MV) for survival. Early recognition of these patients can potentially help clinicians alter the clinical course and lead to improved outcomes.

OBJECTIVES

To build a data-driven model for early prediction of the need for mechanical ventilation in pediatric intensive care unit (PICU) patients.

METHODS

The study consists of a single-center retrospective observational study on a cohort of 13,651 PICU patients admitted between 1/01/2010 and 5/15/2018 with a prevalence of 8.06% for MV due to respiratory failure. XGBoost (extreme gradient boosting) and a convolutional neural network (CNN) using medication history were used to develop a prediction model that could yield a time-varying "risk-score"-a continuous probability of whether a patient will receive MV-and an ideal global threshold was calculated from the receiver operating characteristics (ROC) curve. The early prediction point (EPP) was the first time the risk-score surpassed the optimal threshold, and the interval between the EPP and the start of the MV was the early warning period (EWT). Spectral clustering identified patient groups based on risk-score trajectories after EPP.

RESULTS

A clinical and medication history-based model achieved a 0.89 area under the ROC curve (AUROC), 0.6 sensitivity, 0.95 specificity, 0.55 positive predictive value (PPV), and 0.95 negative predictive value (NPV). Early warning time (EWT) median [inter-quartile range] of this model was 9.9[4.2-69.2] hours. Clustering risk-score trajectories within a six-hour window after the early prediction point (EPP) established three patient groups, with the highest risk group's PPV being 0.92.

CONCLUSIONS

This study uses a unique method to extract and apply medication history information, such as time-varying variables, to identify patients who may need mechanical ventilation for respiratory failure and provide an early warning period to avert it.

Acute physiology and chronic health evaluation score and mortality of patients admitted to intermediate care units of a hospital in a low- and middle-income country: A cross-sectional study from Pakistan

Background

Intermediate care units (IMCUs) serve as a bridge between general wards and intensive care units by providing close monitoring and rapid response to medical emergencies. We aim to identify the common acute medical conditions in patients admitted to IMCU and compare the predicted mortality of these conditions by acute physiology and chronic health evaluation-II (APACHE-II) score with actual mortality.

Methods

A cross-sectional study was conducted at a tertiary care hospital from 2017 to 2019. All adult internal medicine patients admitted to IMCUs were included. Acute conditions were defined as those of short duration (<3 weeks) that require hospitalization. The APACHE-II score was used to determine the severity of these patients' illnesses.

Results

Mean (standard deviation [SD]) age was 62 (16.5) years, and 493 (49.2%) patients were male. The top three acute medical conditions were acute and chronic kidney disease in 399 (39.8%), pneumonia in 303 (30.2%), and urinary tract infections (UTIs) in 211 (21.1%). The mean (SD) APACHE-II score of these patients was 12.5 (5.4). The highest mean APACHE-II (SD) score was for acute kidney injury (14.7 ± 4.8), followed by sepsis/septic shock (13.6 ± 5.1) and UTI (13.4 ± 5.1). Sepsis/septic shock was associated with the greatest mortality (odds ratio [OR]: 6.9 [95% CI (confidence interval): 4.5-10.6]), followed by stroke (OR: 3.9 [95% CI: 1.9-8.3]) and pneumonia (OR: 3.0 [95% CI: 2.0-4.5]).

Conclusions

Sepsis/septic shock, stroke, and pneumonia are the leading causes of death in our IMCUs. The APACHE-II score predicted mortality for most acute medical conditions but underestimated the risk for sepsis and stroke.

The Addition of the Geriatric Nutritional Risk Index to the Prognostic Scoring Systems Did Not Improve Mortality Prediction in Trauma Patients in the Intensive Care Unit

Background

Malnutrition is prevalent among critically ill patients and has been associated with a poor prognosis. This study sought to determine whether the addition of a nutritional indicator to the various variables of prognostic scoring models can improve the prediction of mortality among trauma patients in the intensive care unit (ICU).

Methods

This study's cohort included 1,126 trauma patients hospitalized in the ICU between January 1, 2018, and December 31, 2021. Two nutritional indicators, the prognostic nutrition index (PNI), a calculation based on the serum albumin concentration and peripheral blood lymphocyte count, and the geriatric nutritional risk index (GNRI), a calculation based on the serum albumin concentration and the ratio of current body weight to ideal body weight, were examined for their association with the mortality outcome. The significant nutritional indicator was served as an additional variable in prognostic scoring models of the Trauma and Injury Severity Score (TRISS), the Acute Physiology and Chronic Health Evaluation (APACHE II), and the mortality prediction models (MPM II) at admission, 24, 48, and 72 h in the mortality outcome prediction. The predictive performance was determined by the area under the receiver operating characteristic curve.

Results

Multivariate logistic regression revealed that GNRI (OR, 0.97; 95% CI, 0.96-0.99; p=0.007), but not PNI (OR, 0.99; 95% CI, 0.97-1.02; p=0.518), was independent risk factor for mortality. However, none of these predictive scoring models showed a significant improvement in prediction when the GNRI variable is incorporated.

Conclusions

The addition of GNRI as a variable to the prognostic scoring models did not significantly enhance the performance of the predictors.

Quantitative Electroencephalography Analysis for Improved Assessment of Consciousness Levels in Deep Coma Patients Using a Proposed Stimulus Stage

"Coma" is defined as an inability to obey commands, to speak, or to open the eyes. So, a coma is a state of unarousable unconsciousness. In a clinical setting, the ability to respond to a command is often used to infer consciousness. Evaluation of the patient's level of consciousness (LeOC) is important for neurological evaluation. The Glasgow Coma Scale (GCS) is the most widely used and popular scoring system for neurological evaluation and is used to assess a patient's level of consciousness. The aim of this study is the evaluation of GCSs with an objective approach based on numerical results. So, EEG signals were recorded from 39 patients in a coma state with a new procedure proposed by us in a deep coma state (GCS: between 3 and 8). The EEG signals were divided into four sub-bands as alpha, beta, delta, and theta, and their power spectral density was calculated. As a result of power spectral analysis, 10 different features were extracted from EEG signals in the time and frequency domains. The features were statistically analyzed to differentiate the different LeOC and to relate with the GCS. Additionally, some machine learning algorithms have been used to measure the performance of the features for distinguishing patients with different GCSs in a deep coma. This study demonstrated that GCS 3 and GCS 8 patients were classified from other levels of consciousness in terms of decreased theta activity. To the best of our knowledge, this is the first study to classify patients in a deep coma (GCS between 3 and 8) with 96.44% classification performance.

Predisposition, Insult, Response, and Organ Dysfunction: A Well-constructed Score!

How to cite this article: Kannan A, Jindal A. Predisposition, Insult, Response, and Organ Dysfunction: A Well-constructed Score! Indian J Crit Care Med 2023;27(2):150.

Factors Affecting the Relationship Between Stress and Anxiety in Critically Ill Patients: A Partial Least Squares Structural Equation Modeling Approach

This study aimed to examine the factors affecting the relationship between stress and anxiety in critically ill patients. A cross-sectional research paradigm was employed to enroll patients admitted to the medical intensive care unit (ICU) of a medical university hospital. Partial least squares structural equation modeling (PLS-SEM) was used to examine the data. A total of 90 ICU patients were included in this study; 56 were men and 34 were women. The patients' mean age was 65.3 years. Only the emotional responses dimension of illness was significantly positively correlated with stress. However, the emotional responses dimension of illness representation, acute physiology and chronic health evaluation system (APACHE) score, age, and education level were significantly positively correlated with anxiety. Nevertheless, treatment control was significantly negatively correlated with anxiety. Overall, illness representations (emotional responses and treatment control), APACHE score, age, and education were important predictors of anxiety, with an explanatory power of 37.9%. We recommend that for clinically relevant practice, besides focusing on ICU patients' illness representation, attention should also be paid to their individual characteristics, such as differences in age and education levels.

An overview and policy implications of national nurse identifier systems: A call for unity and integration

There is a clear and growing need to be able record and track the contributions of individual registered nurses (RNs) to patient care and patient care outcomes in the US and also understand the state of the nursing workforce. The National Academies of Sciences, Engineering, and Medicine report, The Future of Nursing 2020-2030: Charting a Path to Achieve Health Equity (2021), identified the need to track nurses' collective and individual contributions to patient care outcomes. This capability depends upon the adoption of a unique nurse identifier and its implementation within electronic health records. Additionally, there is a need to understand the nature and characteristics of the overall nursing workforce including supply and demand, turnover, attrition, credentialing, and geographic areas of practice. This need for data to support workforce studies and planning is dependent upon comprehensive databases describing the nursing workforce, with unique nurse identification to support linkage across data sources. There are two existing national nurse identifiers- the National Provider Identifier and the National Council of State Boards of Nursing Identifier. This article provides an overview of these two national nurse identifiers; reviews three databases that are not nurse specific to understand lessons learned in the development of those databases; and discusses the ethical, legal, social, diversity, equity, and inclusion implications of a unique nurse identifier.

Nomogram Prediction Model of Hypernatremia on Mortality in Critically Ill Patients

Objective

To investigate the value of hypernatremia in the intensive care unit (ICU) for the risk prediction of mortality in severe patients.

Methods

Clinical data of critically ill patients admitted to the ICU of Beijing Friendship Hospital, were collected for retrospective analysis. Univariate and multivariate logistic regression analyses were employed to analyze the influencing factors. Nomograms predicting the mortality were constructed with R software and validated with repeated sampling.

Results

A total of 442 cases were eligible for this study. Hypernatremia within 48 hours of ICU admission, change in sodium concentration (CNa+) within 48 hours, septic shock, APACHE II score, hyperlactatemia within 48 hours, use of continuous renal replacement therapy (CRRT) within 48 hours, and the use of mechanical ventilation (MV) within 48 hours of ICU admission were all identified as independent risk factors for death within 28 days of ICU admission. These predictors were included in a nomogram of 28-day mortality in severe patients, which was constructed using R software.

Conclusion

The nomogram could predict the individualized risk of 28-day mortality based on the above factors. The model has better discrimination and accuracy and has high clinical application value.

The relationship between acute physiology and chronic health evaluation-II, sequential organ failure assessment, Charlson comorbidity index and nutritional scores and length of intensive care unit stay of patients hospitalized in the intensive care unit due to chronic obstructive pulmonary disease

Aim: It is known that disease severity and nutritional status are determinants of prognosis in patients hospitalized in the intensive care unit (ICU). Different scoring systems are used to evaluate the nutritional status and disease severity of intensive care patients. It will be very useful in clinical practice to determine the intensive care scores that are in harmony with the nutritional parameters and affect the length of stay in the ICU in patients hospitalized with the diagnosis of chronic obstructive pulmonary disease (COPD). It was aimed to determine the relationship between acute physiology and chronic health evaluation-II (Apache-II), sequential organ failure assessment (SOFA), and Charlson comorbidity index (CCI) with nutritional scores in intensive care patients with a diagnosis of COPD. Also, it was aimed to determine the scoring systems that affect the length of stay in the ICU. Material and Method: Nutritional risk score-2002 (NRS-2002), prognostic nutritional index (PNI), modified nutritional risk in critically ill (mNutric) score, albumin, Apache-II, SOFA and CCI values and intensive care unit length of stay of the patients hospitalized in the intensive care unit due to COPD were recorded. The scoring systems that affect the length of stay in the ICU and the relationship between nutritional scores and Apache-II, SOFA and CCI was analyzed using statistical methods. Results: A significant correlation was found between only CCI and all nutritional scores. Only the CCI value was found to be significantly higher in those found to be at high risk compared to all nutritional scoring systems. CCI cut-off value determined according to nutritional scoring was determined as 4.5 according to PNI and albumin, and 5.5 according to mNutric score and NRS-2002. It was determined that CCI affects the length of stay in the intensive care unit. Conclusion: CCI is a scoring system that is compatible with nutritional parameters and affects the length of stay in the intensive care unit. Therefore, we think that CCI can be used to predict prognosis and nutritional risk in patients with COPD in the intensive care unit and to predict the length of stay in the intensive care unit. In terms of malnutrition risk, a cut-off value of ≥6 can be used for CCI.

Discrete-time survival analysis in the critically ill: a deep learning approach using heterogeneous data

Prediction of survival for patients in intensive care units (ICUs) has been subject to intense research. However, no models exist that embrace the multiverse of data in ICUs. It is an open question whether deep learning methods using automated data integration with minimal pre-processing of mixed data domains such as free text, medical history and high-frequency data can provide discrete-time survival estimates for individual ICU patients. We trained a deep learning model on data from patients admitted to ten ICUs in the Capital Region of Denmark and the Region of Southern Denmark between 2011 and 2018. Inspired by natural language processing we mapped the electronic patient record data to an embedded representation and fed the data to a recurrent neural network with a multi-label output layer representing the chance of survival at different follow-up times. We evaluated the performance using the time-dependent concordance index. In addition, we quantified and visualized the drivers of survival predictions using the SHAP methodology. We included 37,355 admissions of 29,417 patients in our study. Our deep learning models outperformed traditional Cox proportional-hazard models with concordance index in the ranges 0.72–0.73, 0.71–0.72, 0.71, and 0.69–0.70, for models applied at baseline 0, 24, 48, and 72 h, respectively. Deep learning models based on a combination of entity embeddings and survival modelling is a feasible approach to obtain individualized survival estimates in data-rich settings such as the ICU. The interpretable nature of the models enables us to understand the impact of the different data domains.

Enabling Timely Medical Intervention by Exploring Health-Related Multivariate Time Series with a Hybrid Attentive Model

Modern healthcare practice, especially in intensive care units, produces a vast amount of multivariate time series of health-related data, e.g., multi-lead electrocardiogram (ECG), pulse waveform, blood pressure waveform and so on. As a result, timely and accurate prediction of medical intervention (e.g., intravenous injection) becomes possible, by exploring such semantic-rich time series. Existing works mainly focused on onset prediction at the granularity of hours that was not suitable for medication intervention in emergency medicine. This research proposes a Multi-Variable Hybrid Attentive Model (MVHA) to predict the impending need of medical intervention, by jointly mining multiple time series. Specifically, a two-level attention mechanism is designed to capture the pattern of fluctuations and trends of different time series. This work applied MVHA to the prediction of the impending intravenous injection need of critical patients at the intensive care units. Experiments on the MIMIC Waveform Database demonstrated that the proposed model achieves a prediction accuracy of 0.8475 and an ROC-AUC of 0.8318, which significantly outperforms baseline models.

Severity of Illness Scoring for Pediatric Interfacility Transport: A North American Survey

OBJECTIVE

Severity of illness scoring during pediatric critical care transport may provide objective data to determine illness trajectory and disposition and contribute to quality assurance data for pediatric transport programs. The objective of this study was to ascertain the breadth of severity of illness scoring tool application among North American pediatric critical care transport teams.

METHODS

A cross-sectional quantitative survey using REDCap was distributed to 137 North American pediatric transport programs. Baseline team characteristics were established along with questions related to severity of illness tool application.Descriptive statistics were used for analysis.

RESULTS

There were 55 responses (40%), and of those, 13 (24%) use a severity of illness scoring tool within their practice. A variety of tools were used including: Transport Risk Index of Physiologic Stability, Children's Hospital Medical Center Cincinnati, Canadian Triage and Acuity Score, Transport Risk Assessment in Pediatrics, Pediatric Early Warning Scores, Levels of Acuity, Transport Pediatric Early Warning Scores, and an unspecified tool. The timing of scoring, team personnel who applied the score, and the frequency of analysis varied between transport programs.

CONCLUSIONS

Severity of illness scoring is not consistently performed by pediatric interfacility transport programs in North America. Among the programs that use a scoring tool, there is variability in its application. There is no universally accepted or performed severity of illness scoring tool for pediatric interfacility transport.Future research to validate and standardize a pediatric transport severity of illness scoring tool for North America is necessary.

Early detection and treatment of acute illness in medical patients with novel software: a prospective quality improvement initiative

OBJECTIVE

An ageing population and rising healthcare costs place healthcare systems at risk of failure. Our goal was to develop a technology that would identify illness early, initiate action and therein improve patient care, outcomes and save healthcare resources.

DESIGN

This was a prospective interventional quality improvement study.

SETTING

A 40 bed medical floor in a 300 bed Canadian tertiary care regional referral hospital.

PARTICIPANTS

General ward patients randomly assigned to control or treatment groups. There was no cross-over or loss to follow-up.

INTERVENTION

We designed an algorithm and software programme capable of detecting the sentinel change in a deteriorating patient's clinical condition and once detected direct early investigation and care. Study duration was 1 year.

MAIN OUTCOME MEASURES

Primary outcome was patient transfer from the general medical ward to the intensive care unit (ICU). The secondary outcome was the time needed to (1) order investigations (2) contact senior medical staff and (3) senior medical staff intervention.

RESULTS

We identified a decrease in the transfer of patients from the medical ward to the ICU. Over the course of the study including 273 patients (110 in the control group and 163 in the treatment group), transfers dropped from 14 to 3 with a relative risk reduction of 85.54% (95% CI 84.96 to 86.1), a number needed to treat of 9.19 (95% CI 9.01 to 9.36) and a absolute risk reduction of 10.89% (95% CI 10.7 to 11.1). We also found a statistically significant reduction in the time required to order investigations (p=0.049), contact senior medical staff (p=0.040) and senior medical staff intervention (p=0.045).

CONCLUSION

A novel algorithm and software in the hands of nursing staff identified acute illness with adequate sensitivity and specificity to dramatically reduce ICU transfers and time to clinical intervention on a medical ward.

Outcome Prediction in Critically-Ill Patients with Venous Thromboembolism and/or Cancer Using Machine Learning Algorithms: External Validation and Comparison with Scoring Systems

Intensive care unit (ICU) patients with venous thromboembolism (VTE) and/or cancer suffer from high mortality rates. Mortality prediction in the ICU has been a major medical challenge for which several scoring systems exist but lack in specificity. This study focuses on two target groups, namely patients with thrombosis or cancer. The main goal is to develop and validate interpretable machine learning (ML) models to predict early and late mortality, while exploiting all available data stored in the medical record. To this end, retrospective data from two freely accessible databases, MIMIC-III and eICU, were used. Well-established ML algorithms were implemented utilizing automated and purposely built ML frameworks for addressing class imbalance. Prediction of early mortality showed excellent performance in both disease categories, in terms of the area under the receiver operating characteristic curve (AUC–ROC): VTE-MIMIC-III 0.93, eICU 0.87, cancer-MIMIC-III 0.94. On the other hand, late mortality prediction showed lower performance, i.e., AUC–ROC: VTE 0.82, cancer 0.74–0.88. The predictive model of early mortality developed from 1651 VTE patients (MIMIC-III) ended up with a signature of 35 features and was externally validated in 2659 patients from the eICU dataset. Our model outperformed traditional scoring systems in predicting early as well as late mortality. Novel biomarkers, such as red cell distribution width, were identified.

Medication regimen complexity vs patient acuity for predicting critical care pharmacist interventions

PURPOSE

Quantifying and predicting critical care pharmacist (CCP) workload has significant ramifications for expanding CCP services that improve patient outcomes. Medication regimen complexity has been proposed as an objective, pharmacist-oriented metric that demonstrates relationships to patient outcomes and pharmacist interventions. The purpose of this evaluation was to compare the relationship of medication regimen complexity versus a traditional patient acuity metric for evaluating pharmacist interventions.

SUMMARY

This was a post hoc analysis of a previously completed prospective, observational study. Pharmacist interventions were prospectively collected and tabulated at 24 hours, 48 hours, and intensive care unit (ICU) discharge, and the electronic medical record was reviewed to collect patient demographics, medication data, and outcomes. The primary outcome was the relationship between medication regimen complexity-intensive care unit (MRC-ICU) score, Acute Physiology and Chronic Health Evaluation (APACHE) II score, and pharmacist interventions at 24 hours, 48 hours, and ICU discharge. These relationships were determined by Spearman rank-order correlation (rS) and confirmed by calculating the beta coefficient (β) via multiple linear regression adjusting for patient age, gender, and admission type. Data on 100 patients admitted to a mixed medical/surgical ICU were retrospectively evaluated. Both MRC-ICU and APACHE II scores were correlated with ICU interventions at all 3 time points (at 24 hours, rS = 0.370 [P < 0.001] for MRC-ICU score and rS = 0.283 [P = 0.004] for APACHE II score); however, this relationship was not sustained for APACHE II in the adjusted analysis (at 24 hours, β = 0.099 [P = 0.001] for MRC-ICU and β = 0.031 [P = 0.085] for APACHE II score).

CONCLUSION

A pharmacist-oriented score had a stronger relationship with pharmacist interventions as compared to patient acuity. As pharmacists have demonstrated value across the continuum of patient care, these findings support that pharmacist-oriented workload predictions require tailored metrics, beyond that of patient acuity.

Serum osmolarity does not predict mortality in patients with respiratory failure

We aimed to determine the parameters that affect mortality in pulmonary intensive care units that are faster and inexpensive to determine than existing scoring systems. The relationship between serum osmolarity and prognosis was demonstrated for predialysis patients, in acute pulmonary embolism, heart failure, acute coronary syndrome, myocardial infarction, and acute spontaneous intracerebral hemorrhage in the literature. We hypothesized that serum osmolarity, which is routinely evaluated, may have prognostic significance in patients with respiratory failure.This study comprised 449 patients treated in the Pulmonary Intensive Care Clinic (PICU) of our hospital between January 1, 2020, and December 31, 2020. The modified Charlson Comorbidity Index (mCCI), Acute Physiology and Chronic Health Assessment (APACHE II), Sequential Organ Failure Evaluation Score (SOFA), Nutrition Risk Screening 2002 (NRS-2002), and hospitalization serum osmolarity levels were measured.Of the 449 patients included in the study, 65% (n = 292) were female and the mean age of all patients was 69.86 ± 1.72 years. About 83.1% (n = 373) of the patients included in the study were discharged with good recovery. About 4.9% (n = 22) were transferred to the ward because their intensive care needs were over. About 6.9% (n = 31) were transferred to the tertiary intensive care unit after their status deteriorated. About 5.1% (n = 23) died in the PICU. In the mortality group, APACHE II (P = .005), mCCI (P < .001), NRS-2002 total score (P < .001), and SOFA score (P < .001) were significantly higher. There was no statistically significant difference between the groups in terms of serum osmolarity levels.Although we could not determine serum osmolarity as a practical method to predict patient prognosis in this study, we assume that our results will guide future studies on this subject.

Using Machine Learning to Predict Mortality for COVID-19 Patients on Day 0 in the ICU

Rationale: Given the expanding number of COVID-19 cases and the potential for new waves of infection, there is an urgent need for early prediction of the severity of the disease in intensive care unit (ICU) patients to optimize treatment strategies. Objectives: Early prediction of mortality using machine learning based on typical laboratory results and clinical data registered on the day of ICU admission. Methods: We retrospectively studied 797 patients diagnosed with COVID-19 in Iran and the United Kingdom (U.K.). To find parameters with the highest predictive values, Kolmogorov-Smirnov and Pearson chi-squared tests were used. Several machine learning algorithms, including Random Forest (RF), logistic regression, gradient boosting classifier, support vector machine classifier, and artificial neural network algorithms were utilized to build classification models. The impact of each marker on the RF model predictions was studied by implementing the local interpretable model-agnostic explanation technique (LIME-SP). Results: Among 66 documented parameters, 15 factors with the highest predictive values were identified as follows: gender, age, blood urea nitrogen (BUN), creatinine, international normalized ratio (INR), albumin, mean corpuscular volume (MCV), white blood cell count, segmented neutrophil count, lymphocyte count, red cell distribution width (RDW), and mean cell hemoglobin (MCH) along with a history of neurological, cardiovascular, and respiratory disorders. Our RF model can predict patient outcomes with a sensitivity of 70% and a specificity of 75%. The performance of the models was confirmed by blindly testing the models in an external dataset. Conclusions: Using two independent patient datasets, we designed a machine-learning-based model that could predict the risk of mortality from severe COVID-19 with high accuracy. The most decisive variables in our model were increased levels of BUN, lowered albumin levels, increased creatinine, INR, and RDW, along with gender and age. Considering the importance of early triage decisions, this model can be a useful tool in COVID-19 ICU decision-making.

Comparison of Pediatric Sequential Organ Failure Assessment and Pediatric Risk of Mortality III Score as Mortality Prediction in Pediatric Intensive Care Unit

Objective: To assess and compare the diagnostic accuracy of the Pediatric Risk of Mortality (PRISM) III score and Pediatric Sequential Organ Failure Assessment (p-SOFA) for the prediction of mortality in critically ill children.

Methodology: This was a cross-validation study conducted at the Pediatric Intensive Care Unit (PICU) of the National Institute of Child Health Karachi from February 2021 to July 2021. Two hundred eighty-six critically ill children of age one month to 15 years of either gender staying in PICU for more than 24 hours were included. Within 24 hours of admission, the p-SOFA and PRISM III 24 scores were calculated for all eligible children. The outcome of the study was mortality within 30 days of PICU admitted children. Data were analyzed using Statistical Package for the Social Sciences (SPSS) version 23.

Results: The median age was 24 months (range: 1-144 months). The 30-day mortality was estimated as 57%. The p-SOFA and PRISM scores were significantly greater in children who did not survive than survivors. The maximum p-SOFA score (area under the curve (AUC)=0.81, 95% CI=0.76-0.86, p=0.001) and PRISM III 24 score (AUC=0.75, 95% CI=0.69-0.81, p=0.001) had good discrimination for 30-day mortality. For the prediction of 30-day mortality at the cut-off value of p-SOFA>2, the sensitivity was 93.87%, specificity was 38.21%, and accuracy was 69.93%. Whereas at the cut-off value of PRISM III 24 score>8, the sensitivity was 55.83%, specificity was 77.24%, and accuracy was 65.03%.

Conclusion: The p-SOFA score is a good predictor for 30-day mortality in critically ill children and had better accuracy than the PRISM III 24 score.

Pragmatic study of a thromboprophylaxis algorithm in critically ill patients with SARS-COV-2 infection

The optimal thromboprophylactic strategy for patients affected by Coronavirus disease 2019 (COVID-19) has been debated among experts. This study evaluated the safety and efficacy of a thromboprophylaxis algorithm. This was a retrospective, single-center study in critically ill patients admitted to the intensive care unit (University affiliated Hospital) for acute respiratory failure due to Severe Acute Respiratory Syndrome-Coronavirus 2 (SARS-CoV-2). From March 16 to April 9, 2020, thromboprophylaxis was adjusted according to weight (control group, n = 19) and after this date, thromboprophylaxis depended on an algorithm based on thrombotic and hemorrhagic risk factors (protocol group, n = 13). With regard to safety (number of major bleeding events and blood transfusions), the groups were not significantly different. With regard to efficacy, the number of thrombotic events decreased from 37 to 0%, p = 0.025 after implementation of the algorithm. Also, peak fibrinogen dropped from 8.6 (7.2-9.3) to 6.5 (4.6-8.4) g/L, p = 0.041 and D-dimers from 2194 (1464-3763) to 1486 (900-2582) ng/mL, p = 0.0001. In addition, length of stay declined from 19 (10-31) to 5 (3-19) days, p = 0.009. In conclusion, a tailored thromboprophylaxis algorithm (risk stratification based on clinical parameters and biological markers) reduce thrombotic phenomena in critically ill COVID-19 patients without increasing major bleeding.

Profile of referrals to an intensive care unit from a regional hospital emergency centre in KwaZulu-Natal

Introduction

The objective was to describe the clinical characteristics, disease profile and outcome of patients referred from a regional hospital Emergency Centre (EC) to the Intensive Care Unit (ICU).

Methods

A retrospective review was performed using data extracted from the Integrated Critical Care Electronic Database (iCED). Data were extracted from the database with respect to patient characteristics, Society of Critical Care Medicine (SCCM) grading, and outcome of the ICU referral. Modified early warning scores (MEWS) were calculated from EC referral data.

Results

There were a total of 2187 referrals. Of these, 56.3% (1231/2187) were male. The mean age of referrals was 36 years. Of the referred patients, 41.5% (907/2187) were initially accepted for admission. A further 378 patients were accepted for admission after a follow up ICU review. Medical conditions accounted for the majority of patient referrals, followed by general surgery and trauma. Most patients initially accepted to ICU were classified as SCCM I and II and had a mean MEWS of 4. Almost half of the patients experienced a delay in admission, most commonly due to a lack of ICU bed availability. ICU mortality was 13.6% for patients admitted from the EC.

Discussion

The EC population referred to the ICU was young with a high burden of medical and trauma conditions. Decisions to accept patients to ICU are limited by available resources, and there was a need to apply ICU triage criteria. Delays in the transfer of ICU patients from the EC increase the workload and contribute to EC crowding.

A Review of Mortality Risk Prediction Models in Smartphone Applications

Healthcare professionals in healthcare systems need access to freely available, real-time, evidence-based mortality risk prediction smartphone applications to facilitate resource allocation. The objective of this study is to evaluate the quality of smartphone mobile health applications that include mortality prediction models, and corresponding information quality. We conducted a systematic review of commercially available smartphone applications in Google Play for Android, and iTunes for iOS smartphone applications. We performed initial screening, data extraction, and rated smartphone application quality using the Mobile Application Rating Scale: user version (uMARS). The information quality of smartphone applications was evaluated using two patient vignettes, representing low and high risk of mortality, based on critical care data from the Medical Information Mart for Intensive Care (MIMIC) III database. Out of 3051 evaluated smartphone applications, 33 met our final inclusion criteria. We identified 21 discrete mortality risk prediction models in smartphone applications. The most common mortality predicting models were Sequential Organ Failure Assessment (SOFA) (n = 15) and Acute Physiology and Clinical Health Assessment II (n = 13). The smartphone applications with the highest quality uMARS scores were Observation-NEWS 2 (4.64) for iOS smartphones, and MDCalc Medical Calculator (4.75) for Android smartphones. All SOFA-based smartphone applications provided consistent information quality with the original SOFA model for both the low and high-risk patient vignettes. We identified freely available, high-quality mortality risk prediction smartphone applications that can be used by healthcare professionals to make evidence-based decisions in critical care environments.

Perioperative Risk Stratification: A Need for an Improved Assessment in Surgery and Anesthesia-A Pilot Study

Background and Objectives: Numerous scoring systems have been introduced into modern medicine. None of the scoring systems assessed both anesthetic and surgical risk of the patient, predict the morbidity, mortality, or the need for postoperative intensive care unit admission. The aim of this study was to compare the anesthetic and surgical scores currently used, for a better evaluation of perioperative risks, morbidity, and mortality. Material and Methods: This is a pilot, prospective, observational study. We enrolled 50 patients scheduled for elective surgery. Anesthetic and surgery risk was assessed using American Society of Anesthesiologists (ASA) scale, Physiological and Operative Severity Score for the enumeration of Mortality and morbidity (P-POSSUM), Acute Physiology and Chronic Health Evaluation (APACHE II), and Surgical APGAR Score (SAS) scores. The real and the estimated length of stay (LOS) were registered. Results: We obtained several statistically significant positive correlations: ASA score–P-POSSUM (p < 0.01, r = 0.465); ASA score–SAS, (p < 0.01, r = −0.446); ASA score–APACHE II, (p < 0.01 r = 0.519); predicted LOS and ASA score (p < 0.01, r = 0.676); predicted LOS and p-POSSUM (p < 0.01, r = 0.433); and predicted LOS and APACHE II (p < 0.01, r = 0.454). A significant negative correlation between predicted LOS, real LOS, ASA class, and SAS (p < 0.05) was observed. We found a statistically significant difference between the predicted and actual LOS (p < 001). Conclusions: Anesthetic, surgical, and severity scores, used together, provide clearer information about mortality, morbidity, and LOS. ASA scale, associated with surgical scores and severity scores, presents a better image of the patient’s progress in the perioperative period. In our study, APACHE II is the best predictor of mortality, followed by P-POSSUM and SAS. P-POSSUM score and ASA scale may be complementary in terms of preoperative physiological factors, providing valuable information for postoperative outcomes.

Association of the All-Patient Refined Diagnosis-Related Groups Severity of Illness and Risk of Mortality Classification with Outcomes

OBJECTIVES

Diagnosis-related groups (DRGs) is a patient classification system used to characterize the types of patients that the hospital manages and to compare the resources needed during hospitalization. The DRG classification is based on International Classification of Diseases diagnoses, procedures, demographics, discharge status, and complications or comorbidities and compares hospital resources and outcomes used to determine how much Medicare pays the hospital for each "product/medical condition." The All-Patient Refined DRG (APR-DRG) incorporated severity of illness (SOI) and risk of mortality (ROM) into the DRG system to adjust for patient complexity to compare resource utilization, complication rates, and lengths of stay.

METHODS

This study included 18,478 adult patients admitted to a tertiary care center in Lubbock, Texas during a 1-year period. We recorded the APR-DRG SOI and ROM and some clinical information on these patients, including age, sex, admission shock index, admission glucose and lactate levels, diagnoses based on International Classification of Diseases, Tenth Revision discharge coding, length of stay, and mortality. We compared the levels of SOI and ROM across this clinical information.

RESULTS

As the levels of SOI and ROM increase (which indicates increased disease severity and risk of mortality), age, glucose levels, lactate levels, shock index, length of stay, and mortality increased significantly (P < 0.001). Multiple logistic regression analysis demonstrated that each unit increase in ROM and SOI level was significantly associated with an 11.45 and a 10.37 times increase in the odds of in-hospital mortality, respectively. The C-statistics for the corresponding models are 0.947 and 0.929, respectively. When both ROM and SOI were included in the model, the magnitudes of increase in odds of in-hospital mortality were 5.61 and 1.17 times for ROM and SOI, respectively. The C-statistic is 0.949.

CONCLUSIONS

This study indicates that the APR-DRG SOI and ROM scores provide a classification system that is associated with mortality and correlates with other clinical variables, such as the shock index and lactate levels, which are available on admission.

Improvement of APACHE II score system for disease severity based on XGBoost algorithm

BACKGROUND

Prognostication is an essential tool for risk adjustment and decision making in the intensive care units (ICUs). In order to improve patient outcomes, we have been trying to develop a more effective model than Acute Physiology and Chronic Health Evaluation (APACHE) II to measure the severity of the patients in ICUs. The aim of the present study was to provide a mortality prediction model for ICUs patients, and to assess its performance relative to prediction based on the APACHE II scoring system.

METHODS

We used the Medical Information Mart for Intensive Care version III (MIMIC-III) database to build our model. After comparing the APACHE II with 6 typical machine learning (ML) methods, the best performing model was screened for external validation on anther independent dataset. Performance measures were calculated using cross-validation to avoid making biased assessments. The primary outcome was hospital mortality. Finally, we used TreeSHAP algorithm to explain the variable relationships in the extreme gradient boosting algorithm (XGBoost) model.

RESULTS

We picked out 14 variables with 24,777 cases to form our basic data set. When the variables were the same as those contained in the APACHE II, the accuracy of XGBoost (accuracy: 0.858) was higher than that of APACHE II (accuracy: 0.742) and other algorithms. In addition, it exhibited better calibration properties than other methods, the result in the area under the ROC curve (AUC: 0.76). we then expand the variable set by adding five new variables to improve the performance of our model. The accuracy, precision, recall, F1, and AUC of the XGBoost model increased, and were still higher than other models (0.866, 0.853, 0.870, 0.845, and 0.81, respectively). On the external validation dataset, the AUC was 0.79 and calibration properties were good.

CONCLUSIONS

As compared to conventional severity scores APACHE II, our XGBoost proposal offers improved performance for predicting hospital mortality in ICUs patients. Furthermore, the TreeSHAP can help to enhance the understanding of our model by providing detailed insights into the impact of different features on the disease risk. In sum, our model could help clinicians determine prognosis and improve patient outcomes.

Intensive Care Unit Scoring Systems

BACKGROUND

Illness severity scoring systems are commonly used in critical care. When applied to the populations for whom they were developed and validated, these tools can facilitate mortality prediction and risk stratification, optimize resource use, and improve patient outcomes.

OBJECTIVE

To describe the characteristics and applications of the scoring systems most frequently applied to critically ill patients.

METHODS

A literature search was performed using MEDLINE to identify original articles on intensive care unit scoring systems published in the English language from 1980 to 2020. Search terms associated with critical care scoring systems were used alone or in combination to find relevant publications.

RESULTS

Two types of scoring systems are most frequently applied to critically ill patients: those that predict risk of in-hospital mortality at the time of intensive care unit admission (Acute Physiology and Chronic Health Evaluation, Simplified Acute Physiology Score, and Mortality Probability Models) and those that assess and characterize current degree of organ dysfunction (Multiple Organ Dysfunction Score, Sequential Organ Failure Assessment, and Logistic Organ Dysfunction System). This article details these systems' differing features and timing of use, score calculation, patient populations, and comparative performance data.

CONCLUSION

Critical care nurses must be aware of the strengths, limitations, and specific characteristics of severity scoring systems commonly used in intensive care unit patients to effectively employ these tools in clinical practice and critically appraise research findings based on their use.

Risk Factors for 28-Day Mortality in a Surgical ICU: A Retrospective Analysis of 347 Cases

Purpose

Advances in surgical techniques and intensive care over the past decades have significantly reduced the mortality rates of critically ill surgical patients. However, evaluations of risk factors associated with mortality in surgical intensive care units (ICUs) are limited. The aim of this study was to analyze the independent risk factors for 28-day mortality of surgical ICU patients.

Patients and Methods

The clinical data of adult patients who were admitted to the surgical ICU in the First Affiliated Hospital of Xi’an Jiaotong University from June 2013 to June 2017 were collected. Univariate and multivariable logistic regression analyses were performed to examine risk factors associated with 28-day mortality.

Results

A total of 347 patients were included in this analysis. The overall 28-day mortality rate was 32.6%. The major causes of surgical ICU admission were gastrointestinal diseases (46.7%), infection (20.5%), trauma (8.9%), respiratory diseases (8.9%) and cardiovascular diseases (6.6%). The univariate analysis showed age, total bilirubin, prothrombin time, international normalized ratio, arterial lactate level, APACHE II and SOFA score at ICU admission were significantly associated with 28-day mortality. In the multivariate analysis, however, age [Odds Ratio (OR): 2.899, 95% CI: 1.427–5.890, P=0.003], hypertension [OR: 3.630, 95% CI: 1.545–8.531, P=0.003], platelet count [OR: 1.004, 95% CI: 1.001–1.007, P=0.015], arterial lactate level [OR: 1.186, 95% CI: 1.088–1.293, P<0.001] and SOFA score [OR: 1.289, 95% CI: 1.131–1.469, P<0.001] were identified as the independent risk factors for 28-day mortality of patients in the surgical ICU.

Conclusion

In patients admitted to the surgical ICU, age 65 and older, a high arterial lactate level and SOFA score at ICU admission were associated with increased 28-day mortality.

COVID-19 free oncologic surgical hub: The experience of reallocation of a gynecologic oncology unit during pandemic outbreak

INTRODUCTION

During the SARS-CoV-2 pandemic, the majority of healthcare resources of the affected Italian regions were allocated to COVID-19 patients. Due to lack of resources and high risk of death, most cancer patients have been shifted to non-surgical treatments. The following reports our experience of a Gynaecologic Oncology Unit's reallocation of resources in a COVID-19 free surgical oncologic hub in order to guarantee standard quality of surgical activities.

MATERIALS AND METHODS

This is a prospective observational study performed in the Gynaecologic Oncology Unit, on the outcomes of the reallocation of surgical activities outside the University Hospital of Bologna, Italy, during the Italian lockdown period. Here, we described our COVID-19 free surgical oncologic pathway, in terms of lifestyle restrictions, COVID-19 screening measures, and patient clinical, surgical and follow up outcomes.

RESULTS

During the lockdown period (March 9th - May 4th, 2020), 83 patients were scheduled for oncological surgery, 51 patients underwent surgery. Compared to pre-COVID period, we performed the same activities: number of cases scheduled for surgery, type of surgery and surgical and oncological results. No cases of COVID-19 infection were recorded in operated patients and in medical staff. Patients were compliant and well accepted the lifestyle restrictions and reorganization of the care.

CONCLUSIONSONCLUSIONS

Our experience showed that the prioritization of oncological surgical care and the allocation of resources during a pandemic in COVID-19 free surgical hubs is an appropriate choice to guarantee oncological protocols.

Age, Frailty, Resuscitation and Intensive Care: With Reference to COVID-19

Discussion regarding cardiopulmonary resuscitation and admission to an intensive care unit is frequently fraught in the context of older age. It is complicated by the fact that the presence of multiple comorbidities and frailty adversely impact on prognosis. Cardiopulmonary resuscitation and mechanical ventilation are not appropriate for all. Who decides and how? This paper discusses the issues, biases, and potential harms involved in decision-making. The basis of decision making requires fairness in the distribution of resources/healthcare (distributive justice), yet much of the printed guidance has taken a utilitarian approach (getting the most from the resource provided). The challenge is to provide a balance between justice for the individual and population justice.

Assessment of the Clinical Interpreter of Death in Life-Threatening Infective Cases Admitted in the Intensive Care Unit of a North-Eastern State of India

Objectives

The clinical factors affecting a patient's condition monitored over time could be useful not only to decide on an intervention that may increase the patients' possibilities of survival but also to predict the treatment outcome. Therefore, this study evaluates the clinical factors as predictors of mortality among severe sepsis patients admitted in the intensive care unit (ICU) of a tertiary care center.

Method

We did a prospective study on over 50 life-threatening infective cases with different causes admitted in the ICU. Clinical and biochemical parameters like temperature, heart rate, blood pressure, bicarbonate levels, blood lactate levels, and pH were monitored at admission, after 24 hours, and after 72 hours. The statistical analysis was done using Microsoft Excel (Microsoft Corporation, Redmond, WA) and the Statistical Package for the Social Studies (SPSS) version 22 (IBM Corp., Armonk, NY). We have obtained ethical clearance from the ethics committee (human) of Assam Medical College and Hospital, Dibrugarh. Before the collection of the data, we also took informed consent from the participants.

Results

The mean age of non-survivors was 44.35±11.64 years and that of survivors was 36.60±9.28 years, and the difference was statistically significant (p-value <0.003). An analysis of values of the various vital signs indicated substantial differences in the mean at different time intervals among survivors and non-survivors (p-value <0.05). Among non-survivors, mean temperature, pulse, and rate of respiration were observed to increase over time while blood pressure and oxygen saturation levels were significantly decreasing. Compared to survivors, the mean lactate levels of non-survivors at different time intervals were statistically significant (p-value <0.05). It is also observed that the pH of non-survivors was lower than survivors, and the mean pH value significantly different at different time intervals among the two groups (p-value <0.05).

Conclusion

The temperature, pulse, rate of respiration, blood pressure, and oxygen saturation levels are essential determinants of patient mortality in those suffering from a severe infection, besides serial lactate levels, bi-carbonate levels, and pH levels.

A randomized trial to compare procalcitonin and C-reactive protein in assessing severity of sepsis and in guiding antibacterial therapy in Egyptian critically ill patients

BACKGROUND

Procalcitonin (PCT) and C-reactive protein (CRP) are the main used biomarkers for sepsis and in guiding antibiotic therapy, although PCT high cost limits its use in developing countries.

OBJECTIVE

Comparing between PCT and CRP in assessing severity of sepsis and in guiding antibacterial therapy in critically ill patients.

METHODS

In a prospective randomized study, 60 patients were included from an Egyptian Intensive Care Unit. Patients were divided into CRP and PCT groups. CRP and PCT were measured at baseline and on days 4 and 7. Validity, sensitivity, and specificity of both biomarkers and their correlation with sepsis scores (Acute Physiology and Chronic Health Evaluation II (APACHE II) and Sepsis-related Organ Failure Assessment (SOFA)) were evaluated. Antibacterial continuation at days 4 and 7 was assessed.

RESULTS

The diagnostic accuracy, specificity, and sensitivity of PCT were higher than CRP (80.79% vs 69.45%, 36% vs 28.7%, 87.6% vs 72.4%, respectively). PCT levels were significantly correlated with APACHE II score (P ≤ 0.0001) and SOFA score (P = 0.005), while CRP levels were not correlated with APACHEII and SOFA scores,(P > 0.05). PCT was associated with less antibacterial exposure (33% stopped their antibiotics on day 4 versus 6% in CRP, P = 0.009). Only 33% continued their antibacterial regimen in PCT group after 7 days versus 83% in CRP group (*P ≤ 0.0001).

CONCLUSION

PCT is a more accurate diagnostic and prognostic biomarker than CRP in patients with sepsis. PCT significantly shortened patients' exposure to antibacterial therapy and hospital length of stay.

External validation of INCREMENT-CPE score in a retrospective cohort of carbapenemase-producing Klebsiella pneumoniae bloodstream infections in critically ill patients

OBJECTIVES

Our aim was to validate the INCREMENT-CPE score (ICS) in patients hospitalized in the intensive care unit (ICU) with bacteraemia due to carbapenemase-producing Klebsiella pneumoniae (CP-Kp).

METHODS

The study was conducted in the ICU of the University General Hospital of Patras, Greece, during a 10-year period (2010-2019). Patients with monomicrobial bacteraemia due to CP-Kp were included. Primary outcome was 14-day mortality. MICs of meropenem, tigecycline, fosfomycin and ceftazidime/avibactam were determined by Etest, whereas for colistin the broth microdilution method was applied. PCR for bla_KPC, bla_VIM, bla_NDM and bla_OXA genes was used.

RESULTS

Among 384 CP-Kp bacteraemias, most were primary (166, 43.2%) followed by catheter-related (143, 37.2%). Most isolates carried bla_KPC (318, 82.8%). Fourteen-day mortality was 26.3% (101 patients). ICS score was 11.1 ± 4.2. An ICS ≥10 showed a sensitivity of 98.0% and a negative predictive value of 98.7%. The area under the curve of ICS (0.800) was comparable to those of the Pitt bacteraemia score (0.799), the Simplified Acute Physiology Score II (SAPS II) (0.797) and the Sequential Organ Failure Assessment score (SOFA) (0.815).

CONCLUSIONS

ICS showed predictive efficacy similar to that of the SAPS II, SOFA and Pitt bacteraemia scores.

Incidence and Risk Factors of Delirium in the Intensive Care Unit: A Prospective Cohort

Purpose

The purpose of this study was to determine the incidence, risk factors, and impact of delirium on outcomes in ICU patients. In addition, the scoring systems were measured consecutively to characterize how these scores changed with time in patients with and without delirium. Material and Methods. A prospective cohort study enrolling 400 consecutive patients admitted to the ICU between 2018 and 2019 due to trauma or surgery. Patients were followed up for the development of delirium over ICU days using the Confusion Assessment Method (CAM) for the ICU and Intensive Care Delirium Screening Checklist (ICDSC). Cox model logistic regression analysis was used to explore delirium risk factors.

Results

Delirium occurred in 108 (27%) patients during their ICU stay, and the median onset of delirium was 4 (IQR 3–4) days after admission. According to multivariate cox regression, the expected hazard for delirium was 1.523 times higher in patients who used mechanical ventilator as compared to those who did not (HR: 1.523, 95% CI: 1.197-2.388, P < 0.001).

Conclusion

Our findings suggest that an important opportunity for improving the care of critically ill patients may be the determination of modifiable risk factors for delirium in the ICU. In addition, the scoring systems (APACHE IV, SOFA, and RASS) are useful for the prediction of delirium in critically ill patients.