Simplified Acute Physiology Score Research Articles

Stratifying Mortality Risk in Intensive Care: A Comprehensive Analysis Using Cluster Analysis and Classification and Regression Tree Algorithms

Abstract Background Machine learning (ML) can be promising for stratifying patients into homogeneous groups and assessing mortality based on score combination. Using ML, we compared mortality prediction performance for clustered and non-clustered models and tried to develop a simple decision algorithm to predict the patient’s cluster membership with classification and regression trees (CART). Methods Retrospective study involving patients requiring ICU admission (1st January 2011–16th September 2022). Clusters were identified by combining Charlson Comorbidity Index (CCI) plus Simplified Acute Physiology Score II (SAPS II) or Sequential Organ Failure Assessment (SOFA). Intercluster and survival analyses were performed. We analyzed the relationship with mortality with multivariate logistic regressions and receiver operating characteristic curves (ROC) for models with and without clusters. Nested models were compared with Likelihood Ratio Tests (LRT). Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) were compared for non-nested models. With the best model, we used CART to build a decision tree for patient’s membership. Results Our sample consisted of 2605 patients (mortality 59.7%). For both score combinations, we identified two clusters (A and B for CCI + SAPS II, α and β for CCI + SOFA). Belonging to cluster B/β was associated with shorter survival times (Peto-Peto p-values < 0.0001) and increased mortality (Odds-ratio 4.65 and 5.44, respectively). According to LRT and ROC analysis, clustered models performed better, and CCI + SOFA showed the lowest AIC and BIC values (AIC = 3021.21, BIC = 3132.65). Using CART (β cluster positive case) the accuracy of the decision tree was 94.8%. Conclusion Clustered models significantly improved mortality prediction. The CCI + SOFA clustered model showed the best balance between complexity and data fit and should be preferred. Developing a user-friendly decision-making algorithm for cluster membership with CART showed high accuracy. Further validation studies are needed to confirm these findings.

Population Pharmacokinetic Modeling of Unbound Meropenem in Patients Undergoing Continuous Renal Replacement Therapy: An Observational Cohort Study.

The most effective dosing strategy of meropenem for patients undergoing continuous renal replacement therapy (CRRT) remains uncertain. This study aimed to analyze the population pharmacokinetics (popPKs) of unbound meropenem and establish an appropriate dosing approach. This prospective study involved 19 patients for the development of a popPK model and an additional 10 for its validation. Ethical approval was obtained. The clearance of unbound meropenem was influenced by the sequential organ failure assessment (SOFA) score [=2.22 × (SOFA score/12)^1.88] and the effluent flow rate from the CRRT device, with an interindividual variability of 44.5%. The volume of distribution was affected by the simplified acute physiology score II [=23.1 × (simplified acute physiology score II/52)^1.54]. Monte Carlo simulations suggested meropenem doses ranging from 1.0 to 3.0 g/d using continuous infusion to achieve a target time above the 4 times of minimum inhibitory concentration of the unbound form (%fT>4×MIC) of 100% for definitive therapy. For empirical therapy, a dose of 1.0 g/d using continuous infusion was recommended to target %fT>MIC of 100%. This study developed a popPK model for unbound meropenem in patients undergoing CRRT and formulated dosing guidelines. UMIN000024321.

External Validation of the PREdiction of Survival on Extracorporeal Membrane Oxygenation Therapy (PRESET) Score: A Single Center Cohort Experience.

Acute respiratory distress syndrome (ARDS) is a life-threatening condition affecting >10% of intensive care unit (ICU) patients worldwide with a mortality of up to 59% depending on severity. Extracorporeal membrane oxygenation (ECMO) is a potentially life-saving procedure in severe ARDS but is technically and financially challenging. In recent years, various scoring systems have been proposed to select patients most likely to benefit from ECMO, with the PREdiction of Survival on ECMO Therapy (PRESET) score being one of the most used. We collected data from 283 patients with ARDS of various etiology who underwent veno-venous (V-V) ECMO therapy at a German tertiary care ICU from January 2012 to December 2022. Median age in the cohort was 56 years, and 64.31% were males. The in-hospital mortality rate was 50.88% (n = 144). The median (25%; 75% quartile) severity scores were 38 (31; 49) for Simplified Acute Physiology Score (SAPS) II, 12 (10; 13) for Sequential Organ Failure Assessment (SOFA) and 7 (5; 8) for PRESET. Simplified Acute Physiology Score-II displayed the best prognostic value (area under the receiver operating characteristic [AUROC]: 0.665 [confidence interval (CI): 0.574-0.756; p = 0.046]). Prediction performance was weak in all analyzed scores despite good calibration. Simplified Acute Physiology Score-II had the best discrimination after adjustment of our original cohort. The use of scores explored in this study for patient selection for eligibility for V-V ECMO is not recommendable.

A comparison of Simplified Acute Physiology Score II and Sepsis-related Organ Failure Assessment Score for prediction of mortality after Intensive Care Unit cardiac arrest.

This study investigates the predictive value and suitable cutoff values of the Sepsis-related Organ Failure Assessment Score (SOFA) and Simplified Acute Physiology Score II (SAPS-II) to predict mortality during or after Intensive Care Unit Cardiac Arrest (ICU-CA). In this secondary analysis the ICU database of a German university hospital with five ICU was screened for all ICU-CA between 2016-2019. SOFA and SAPS-II were used for prediction of mortality during ICU-CA, hospital-stay and one-year-mortality. Receiver operating characteristic curves (ROC), area under the ROC (AUROC) and its confidence intervals were calculated. If the AUROC was significant and considered "acceptable," cutoff values were determined for SOFA and SAPS-II by Youden Index. Odds ratios and sensitivity, specificity, positive and negative predictive values were calculated for the cutoff values. A total of 114 (78 male; mean age: 72.8±12.5 years) ICU-CA were observed out of 14,264 ICU-admissions (incidence: 0.8%; 95% CI: 0.7-1.0%). 29.8% (N.=34; 95% CI: 21.6-39.1%) died during ICU-CA. SOFA and SAPS-II were not predictive for mortality during ICU-CA (P>0.05). Hospital-mortality was 78.1% (N.=89; 95% CI: 69.3-85.3%). SAPS-II (recorded within 24 hours before and after ICU-CA) indicated a better discrimination between survival and death during hospital stay than SOFA (AUROC: 0.81 [95% CI: 0.70-0.92] vs. 0.70 [95% CI: 0.58-0.83]). A SAPS-II-cutoff-value of 43.5 seems to be suitable for prognosis of hospital mortality after ICU-CA (specificity: 87.5%, sensitivity: 65.6%; SAPS-II>43.5: 87.5% died in hospital; SAPS-II<43.5: 65.6% survived; odds ratio:13.4 [95% CI: 3.25-54.9]). Also for 1-year-mortality (89.5%; 95% CI: 82.3-94.4) SAPS-II showed a better discrimination between survival and death than SOFA: AUROC: 0.78 (95% CI: 0.65-0.91) vs. 0.69 (95% CI: 0.52-0.87) with a cutoff value of the SAPS-II of 40.5 (specificity: 91.7%, sensitivity: 64.3%; SAPS-II>40.5: 96.4% died; SAPS-II<40.5: 42.3% survived; odd ratio: 19.8 [95% CI: 2.3-168.7]). Compared to SOFA, SAPS-II seems to be more suitable for prediction of hospital and 1-year-mortality after ICU-CA.

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.

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.

Lactate as a Predictor of 30-Day Mortality in Cardiogenic Shock.

Background/Objectives: This study sought to evaluate the efficacy of various lactate measurements within the first 24 h post-intensive care unit (ICU) admission for predicting 30-day mortality in cardiogenic shock patients. It compared initial lactate levels, 24 h levels, peak levels, and 24 h clearance, alongside the Simplified Acute Physiology Score 3 (SAPS3) score, to enhance early treatment decision-making. Methods: A retrospective analysis of 64 patients assessed the prognostic performance of lactate levels and SAPS3 scores using logistic regression and AUROC calculations. Results: Of the baseline parameters, only the SAPS3 score predicted survival independently. The lactate level after 24 h (LL) was the most accurate predictor of mortality, outperforming initial levels, peak levels, and 24 h-clearance, and showing a significant AUROC. LL greater than 3.1 mmol/L accurately predicted mortality with high specificity and moderate sensitivity. Conclusions: Among lactate measurements for predicting 30-day mortality in cardiogenic shock, the 24 h lactate level was the most effective one, suggesting its superiority for early prognostication over initial or peak levels and lactate clearance.

Patient characteristics associated with posttraumatic stress symptoms in intensive care unit survivors during a one-year follow-up: A multicenter study

BackgroundIntensive care unit (ICU) patients are at risk of suffering from posttraumatic stress symptoms (PTSS) after ICU survival. ObjectivesTo describe the prevalence of high levels of PTSS the first year after ICU admission. Further, to identify specific combinations of patient characteristics (latent classes based on pre-ICU data, demographics, and clinical characteristics), and to investigate possible associations among these classes and PTSS at 3, 6, and 12 months after ICU admission. MethodsSelf-reported PTSS were measured with Impact of Event Scale-Revised (IES-R). PTSS and possible predictive factors (pre-ICU data, demographics, and clinical characteristics) were analyzed using descriptive statistics, latent class analysis, and linear mixed model for repeated measures. ResultsHigh PTSS levels (IES-R ≥ 33) were reported by 14.9 % (95 % confidence interval [CI] [10.0; 21.1]), 16.7 % (95 % CI [11.5; 23.1]), and 18.4 % (95 % CI [12.9; 25.0]) of patients (sample 1, n = 174) at 3, 6, and 12 months, respectively. Three latent classes were identified (sample 2, n = 417). PTSS were significantly associated with class 2 (male with longer hospital stay) at 6 months and class 3 (age≥70, lower level of education, higher Simplified Acute Physiology Score, being mechanically ventilated) at all three measurement times. ConclusionsThe prevalence of high levels of PTSS is the greatest 12 months after ICU admission. Health professionals can use this information to be aware of specific groups of ICU patients reporting PTSS during the first year and follow up on these.

Construction and evaluation of short-term and long-term mortality risk prediction model for patients with sepsis based on MIMIC-IV database.

Given the high incidence and mortality rate of sepsis, early identification of high-risk patients and timely intervention are crucial. However, existing mortality risk prediction models still have shortcomings in terms of operation, applicability, and evaluation on long-term prognosis. This study aims to investigate the risk factors for death in patients with sepsis, and to construct the prediction model of short-term and long-term mortality risk. Patients meeting sepsis 3.0 diagnostic criteria were selected from the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database and randomly divided into a modeling group and a validation group at a ratio of 7꞉3. Baseline data of patients were analyzed. Univariate Cox regression analysis and full subset regression were used to determine the risk factors of death in patients with sepsis and to screen out the variables to construct the prediction model. The time-dependent area under the curve (AUC), calibration curve, and decision curve were used to evaluate the differentiation, calibration, and clinical practicability of the model. A total of 14 240 patients with sepsis were included in our study. The 28-day and 1-year mortality were 21.45% (3 054 cases) and 36.50% (5 198 cases), respectively. Advanced age, female, high sepsis-related organ failure assessment (SOFA) score, high simplified acute physiology score II (SAPS II), rapid heart rate, rapid respiratory rate, septic shock, congestive heart failure, chronic obstructive pulmonary disease, liver disease, kidney disease, diabetes, malignant tumor, high white blood cell count (WBC), long prothrombin time (PT), and high serum creatinine (SCr) levels were all risk factors for sepsis death (all P<0.05). Eight variables, including PT, respiratory rate, body temperature, malignant tumor, liver disease, septic shock, SAPS II, and age were used to construct the model. The AUCs for 28-day and 1-year survival were 0.717 (95% CI 0.710 to 0.724) and 0.716 (95% CI 0.707 to 0.725), respectively. The calibration curve and decision curve showed that the model had good calibration degree and clinical application value. The short-term and long-term mortality risk prediction models of patients with sepsis based on the MIMIC-IV database have good recognition ability and certain clinical reference significance for prognostic risk assessment and intervention treatment of patients.

The value of five scoring systems in predicting the prognosis of patients with sepsis-associated acute respiratory failure.

Our study aimed to identify the optimal scoring system for predicting the prognosis of patients with sepsis-associated acute respiratory failure (SA-ARF). All data were taken from the fourth version of the Markets in Intensive Care Medicine (MIMIC-IV) database. Independent risk factors for death in hospitals were confirmed by regression analysis. The predictive value of the five scoring systems was evaluated by receiving operating characteristic (ROC) curves. Kaplan‒Meier curves showed the impact of acute physiology score III (APSIII) on survival and prognosis in patients with SA-ARF. Decision curve analysis (DCA) identified a scoring system with the highest net clinical benefit. ROC curve analysis showed that APS III (AUC: 0.755, 95% Cl 0.714-0.768) and Logical Organ Dysfunction System (LODS) (AUC: 0.731, 95% Cl 0.717-0.7745) were better than Simplified Acute Physiology Score II (SAPS II) (AUC: 0.727, 95% CI 0.713-0.741), Oxford Acute Severity of Illness Score (OASIS) (AUC: 0.706, 95% CI 0.691-0.720) and Sequential Organ Failure Assessment (SOFA) (AUC: 0.606, 95% CI 0.590-0.621) in assessing in-hospital mortality. Kaplan‒Meier survival analysis patients in the high-APS III score group had a considerably poorer median survival time. The DCA curve showed that APS III may provide better clinical benefits for patients. We demonstrated that the APS III score is an excellent predictor of in-hospital mortality.

Machine learning-based prediction of in-hospital mortality for critically ill patients with sepsis-associated acute kidney injury

Objectives This study aims to develop and validate a prediction model in-hospital mortality in critically ill patients with sepsis-associated acute kidney injury (SA-AKI) based on machine learning algorithms. Methods Patients who met the criteria for inclusion were identified in the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database and divided according to the validation (n = 2440) and development (n = 9756, 80%) queues. Ensemble stepwise feature selection method was used to screen for effective features. The prediction models of short-term mortality were developed by seven machine learning algorithms. Ten-fold cross-validation was used to verify the performance of the algorithm in the development queue. The area under the receiver operating characteristic curve (ROC-AUC) was used to evaluate the differentiation accuracy and performance of the prediction model in the validation queue. The best-performing model was interpreted by Shapley additive explanations (SHAP). Results A total of 12,196 patients were enrolled in this study. Eleven variables were finally chosen to develop the prediction model. The AUC of the random forest (RF) model was the highest value both in the Ten-fold cross-validation and evaluation (AUC: 0.798, 95% CI: 0.774–0.821). According to the SHAP plots, old age, low Glasgow Coma Scale (GCS) score, high AKI stage, reduced urine output, high Simplified Acute Physiology Score (SAPS II), high respiratory rate, low temperature, low absolute lymphocyte count, high creatinine level, dysnatremia, and low body mass index (BMI) increased the risk of poor prognosis. Conclusions The RF model developed in this study is a good predictor of in-hospital mortality for patients with SA-AKI in the intensive care unit (ICU), which may have potential applications in mortality prediction.

Evolution of Clinical Characteristics and Outcomes of Critically Ill Patients 90 Years Old or Older Over a 12-Year Period: A Retrospective Cohort Study.

The global population is aging, and the proportion of very elderly patients 90 years old or older in the ICU is expected to increase. The changes in the comorbidities and outcomes of very elderly patients hospitalized in the ICU that have occurred over time are unknown. Retrospective observational cohort study. ICUs at a single academic hospital in Germany. Ninety years old or older and admitted to the ICU between January 1, 2008, and April 30, 2019. None. Of the 92,958 critically ill patients, 1,108 were 90 years old or older. The study period was divided into two halves: January 1, 2008-August 30, 2013, and September 1, 2013-April 30, 2019. The number of patients 90 years old or older increased from the first period (n = 391; 0.90% of total admissions) to the second period (n = 717; 1.44%). The patients' demographic characteristics were similar between the both time periods. The median Charlson Comorbidity Index was higher during the first period (1 [interquartile range, 1-3]) than compared with the second time period (1 [0-2]; p = 0.052). The Simplified Acute Physiology Score (SAPS) II was higher during the first time period (38 [29-49]) than during the second period (35 [27-45]; p = 0.005). Vasopressor therapy was necessary in 40% (n = 158) and 43% (n = 310) of patients in each time period, respectively (p = 0.363). Invasive mechanical ventilation was administered in 37% (n = 146) and 34% (n = 243) of patients in each time period, respectively (p = 0.250). The median length of the ICU stay was significantly lower in the first time period than in the second time period (1.4 vs. 1.7 d; p = 0.002). The ICU (18% vs. 18%; p = 0.861) and hospital (31% vs. 29%; p = 0.395) mortality rates were comparable between the two groups. The 1-year mortality was significantly lower during the second time period than during the first time period (61% vs. 56%; p = 0.029). Cox regression analysis revealed that the SAPS II, medical cause of admission, mechanical ventilation requirement, and vasopressor use were associated with 1-year mortality. The number of patients 90 years old or older who were treated in the ICU has increased in recent years. While the patients' clinical characteristics and short-term outcomes have not changed significantly, the long-term mortality of these patients has improved in recent years.

Development and validation of a nomogram for predicting in-hospital mortality of patients with cervical spine fractures without spinal cord injury

BackgroundThe incidence of cervical spine fractures is increasing every day, causing a huge burden on society. This study aimed to develop and verify a nomogram to predict the in-hospital mortality of patients with cervical spine fractures without spinal cord injury. This could help clinicians understand the clinical outcome of such patients at an early stage and make appropriate decisions to improve their prognosis.MethodsThis study included 394 patients with cervical spine fractures from the Medical Information Mart for Intensive Care III database, and 40 clinical indicators of each patient on the first day of admission to the intensive care unit were collected. The independent risk factors were screened using the Least Absolute Shrinkage and Selection Operator regression analysis method, a multi-factor logistic regression model was established, nomograms were developed, and internal validation was performed. A receiver operating characteristic (ROC) curve was drawn, and the area under the ROC curve (AUC), net reclassification improvement (NRI), and integrated discrimination improvement (IDI) were calculated to evaluate the discrimination of the model. Moreover, the consistency between the actual probability and predicted probability was reflected using the calibration curve and Hosmer–Lemeshow (HL) test. A decision curve analysis (DCA) was performed, and the nomogram was compared with the scoring system commonly used in clinical practice to evaluate the clinical net benefit.ResultsThe nomogram indicators included the systolic blood pressure, oxygen saturation, respiratory rate, bicarbonate, and simplified acute physiology score (SAPS) II. The results showed that our model had satisfactory predictive ability, with an AUC of 0.907 (95% confidence interval [CI] = 0.853–0.961) and 0.856 (95% CI = 0.746–0.967) in the training set and validation set, respectively. Compared with the SAPS-II system, the NRI values of the training and validation sets of our model were 0.543 (95% CI = 0.147–0.940) and 0.784 (95% CI = 0.282–1.286), respectively. The IDI values of the training and validation sets were 0.064 (95% CI = 0.004–0.123; P = 0.037) and 0.103 (95% CI = 0.002–0.203; P = 0.046), respectively. The calibration plot and HL test results confirmed that our model prediction results showed good agreement with the actual results, where the HL test values of the training and validation sets were P = 0.8 and P = 0.95, respectively. The DCA curve revealed that our model had better clinical net benefit than the SAPS-II system.ConclusionWe explored the in-hospital mortality of patients with cervical spine fractures without spinal cord injury and constructed a nomogram to predict their prognosis. This could help doctors assess the patient’s status and implement interventions to improve prognosis accordingly.

Critically ill patients with high predicted mortality: Incidence and outcome

ObjectiveAs calculated by the severity scores, an unknown number of patients are admitted to the Intensive Care Unit (ICU) with a very high risk of death. Clinical studies have poorly addressed this population, and their prognosis is largely unknown. DesignPost hoc analysis of a multicenter, cohort, longitudinal, observational, retrospective study (CIMbA). SettingSixteen Portuguese multipurpose ICUs. PatientsPatients with a Simplified Acute Physiology Score II (SAPS II) predicted hospital mortality above 80% on admission to the ICU (high-risk group); A comparison with the remaining patients was obtained. InterventionsNone. Main Variables of InterestHospital, 30 days, 1 year mortality. ResultsWe identified 4546 patients (59.9% male), 12.2% of the whole population. Their SAPS II predicted hospital mortality was 89.0±5.8%, whilst the observed mortality was lower, 61.0%. This group had higher mortality, both during the first 30 days (aHR 3.52 [95% CI 3.34–3.71]) and from day 31 to day 365 after ICU admission (aHR 1.14 [95%CI 1.04–1.26]), respectively. However, their hospital standardized mortality ratio was similar to the other patients (0.69 vs. 0.69, P=.92). At one year of follow-up, 30% of patients in the high-risk group were alive. ConclusionsRoughly 12% of patients admitted to the ICU for more than 24h had a SAPS II score predicted mortality above 80%. Their hospital standardized mortality was similar to the less severe population and 30% were alive after one year of follow-up.

Heart rate complexity helps mortality prediction in the intensive care unit: A pilot study using artificial intelligence

BackgroundIn intensive care units (ICUs), accurate mortality prediction is crucial for effective patient management and resource allocation. The Simplified Acute Physiology Score II (SAPS-2), though commonly used, relies heavily on comprehensive clinical data and blood samples. This study sought to develop an artificial intelligence (AI) model utilizing key hemodynamic parameters to predict ICU mortality within the first 24 h and assess its performance relative to SAPS-2. MethodsWe conducted an analysis of select hemodynamic parameters and the structure of heart rate curves to identify potential predictors of ICU mortality. A machine-learning model was subsequently trained and validated on distinct patient cohorts. The AI algorithm’s performance was then compared to the SAPS-2, focusing on classification accuracy, calibration, and generalizability. Measurements and main resultsThe study included 1298 ICU admissions from March 27th, 2015, to March 27th, 2017. An additional cohort from 2022 to 2023 comprised 590 patients, resulting in a total dataset of 1888 patients. The observed mortality rate stood at 24.0%. Key determinants of mortality were the Glasgow Coma Scale score, heart rate complexity, patient age, duration of diastolic blood pressure below 50 mmHg, heart rate variability, and specific mean and systolic blood pressure thresholds. The AI model, informed by these determinants, exhibited a performance profile in predicting mortality that was comparable, if not superior, to the SAPS-2. ConclusionsThe AI model, which integrates heart rate and blood pressure curve analyses with basic clinical parameters, provides a methodological approach to predict in-hospital mortality in ICU patients. This model offers an alternative to existing tools that depend on extensive clinical data and laboratory inputs. Its potential integration into ICU monitoring systems may facilitate more streamlined mortality prediction processes.

The use of continuous renal replacement therapy in critically ill patients with COVID-19-related acute kidney injury

Background/Aim. Patients with severe clinical COVID-19 are at higher risk of developing acute kidney injury (AKI). The aim of the study was to analyze the risk factors for AKI/AKI on chronic kidney disease (CKD) and the results of treatment using continuous renal replacement therapy (CRRT) in critically ill COVID-19 patients. Methods. The study included 101 COVID-19 patients with AKI treated with CRRT out of a total of 293 patients with AKI. The study was conducted from March 2020 to July 2021 at the University Clinical Center of Vojvodina, Serbia. Results. The average age of patients was 64.69 ? 9.71 years. Out of the total number of patients, 82.2% were male, of whom 75.2% suffered from hypertension. On invasive mechanical ventilation (IMV) were 93.7% of patients, and 92.1% were on vasopressor therapy. The average length of IMV until the beginning of CRRT was 4.65 ? 4 .57 days. In the first 24 hrs after starting IMV, 60% of patients had to undergo CRRT. Before administering CRRT, the average Simplified Acute Physiology Score II was 39.13 ? 14.45, creatinine 312 ?mol/L [Interquartile Range (IQR) 208.0?437.5], procalcitonin 2.70 ng/L (IQR 0.62?7.20), while 10.9% of patients had SpO2/FiO2 index &gt; 200 and 41.6% had anuria. The mean number of procedures was 2.01 ? 1.36. The most frequent modality was hemodiafiltration in 67.3% of patients, and 46% used the oXiris? membrane. Using binary logistic regression, including demographic parameters, comorbidities, as well as clinical parameters before CRRT, it was found that patients with previous kidney disease were 3.43 times more susceptible to developing AKI, and patients with SpO2/FiO2 index ? 200 were 69% less susceptible to developing AKI/AKI on CKD requiring CRRT in the first 24 hrs from the start of IMV. Conclusion. Determining the risk factors for AKI/AKI on CKD is important for planning the prevention of these conditions that require the application of CRRT with the correct choice of dialysis modality and dose, membrane/filter type, and anticoagulant dose.

Epidemiologic features and outcomes associated with caustic ingestion among adults admitted in intensive care unit from 2013 to 2019: a French national observational study.

Caustic ingestion is a potential life-threatening condition associated with high morbidity and mortality. Data on patients admitted to Intensive Care Unit (ICU) for severe caustic ingestion are lacking. We aimed to describing epidemiological features and outcomes of patients admitted to ICU for caustic ingestion in France. In a retrospective, observational, and multicenter study, data from the national French Programme de Médicalisation des Systèmes d'Informations (PMSI) database were analysed from 2013 to 2019. In-hospital mortality rate (primary outcome) and in-ICU complications (secondary outcomes) were reported and analysed. 569 patients (289 males (50.8%), with median age of 49years [interquartile (26-62)] were admitted in 65 French ICU for severe caustic ingestion. Five hundred and thirteen patients (90%) were admitted for intentional caustic ingestion. The median length of stay in ICU was 14.0 [4.0-31.0] days. In-hospital mortality occurred in 56 patients (9.8%). In multivariate analysis, age and simplified acute physiology score II were associated with in-hospital mortality age of 40-59years [OR = 15.3 (2.0-115.3)], age of 60-79years [OR = 23.6 (3.1-182.5)], and age > 80years [OR = 37.0 (4.2-328.6)] and SAPS 2 score [OR = 1.0018 (1.003-1.033), p < 0.001]. During ICU stay, 423 complications (74%) were reported in 505 patients (89%). Infectious (244 (42.9%)), respiratory (207 (36.4%)), surgical 62 (10.9%), haemorrhagic (64 (11.2%)) and thrombo-embolic and (35 (6.2%)) complications were the most frequently reported during ICU stay. ICU admission for severe caustic ingestion is associated with 9.8% mortality and 74% complications. Age > 40years and SAPS 2 score were independently associated with mortality.

Acute kidney injury in critical COVID-19 patients: usefulness of urinary biomarkers and kidney proximal tubulopathy

Tubular injury is the main cause of acute kidney injury (AKI) in critically ill COVID-19 patients. Proximal tubular dysfunction (PTD) and changes in urinary biomarkers, such as NGAL, TIMP-2, and IGFBP7 product ([TIMP-2]•[IGFBP7]), could precede AKI. We conducted a prospective cohort study from 2020/03/09 to 2020/05/03, which consecutively included all COVID-19 patients who had at least one urinalysis, to assess the incidence of PTD and AKI, and the effectiveness of PTD, NGAL, and [TIMP-2]•[IGFBP7] in AKI and persistent AKI prediction using the area under the receiver operating characteristic curves (AUCs), Kaplan–Meier methodology (log-rank tests), and Cox models. Among the 60 patients admitted to the ICU with proven COVID-19 (median age: 63-year-old (interquartile range: IQR, 55–74), 45 males (75%), median simplified acute physiology score (SAPS) II: 34 (IQR, 22–47) and median BMI: 25.7 kg/m2 (IQR, 23.3–30.8)) analyzed, PTD was diagnosed in 29 patients (48%), AKI in 33 (55%) and persistent AKI in 20 (33%). Urinary NGAL had the highest AUC for AKI prediction: 0.635 (95%CI: 0.491–0.779) and persistent AKI prediction: 0.681 (95%CI: 0.535–0.826), as compared to PTD and [TIMP-2]•[IGFBP7] (AUCs <0.6). AKI was independently associated with higher SAPSII (HR = 1.04, 95%CI: 1.01–1.06, p = 0.005) and BMI (HR = 1.07, 95%CI: 1.00–1.14, p = 0.04) and persistent AKI with higher SAPSII (HR = 1.03, 95%CI: 1.00–1.06, p = 0.048) and nephrotoxic drug use (HR = 3.88, 95%CI: 1.20–12.5, p = 0.02). In conclusion, in critically ill COVID-19 patients, the incidence of PTD and AKI was relatively high. NGAL was the best urinary biomarker for predicting AKI, but only clinical severity was independently associated with its occurrence.

Critically ill patients with high predicted mortality: Incidence and outcome

ObjectiveAs calculated by the severity scores, an unknown number of patients are admitted to the Intensive Care Unit (ICU) with a very high risk of death. Clinical studies have poorly addressed this population, and their prognosis is largely unknown. DesignPost hoc analysis of a multicenter, cohort, longitudinal, observational, retrospective study (CIMbA). SettingSixteen Portuguese multipurpose ICUs. PatientsPatients with a Simplified Acute Physiology Score II (SAPS II) predicted hospital mortality above 80% on admission to the ICU (high-risk group); A comparison with the remaining patients was obtained. InterventionsNone. Main Variables of InterestHospital, 30 days, 1 year mortality. ResultsWe identified 4546 patients (59.9% male), 12.2% of the whole population. Their SAPS II predicted hospital mortality was 89.0±5.8%, whilst the observed mortality was lower, 61.0%. This group had higher mortality, both during the first 30 days (aHR 3.52 [95% CI 3.34–3.71]) and from day 31 to day 365 after ICU admission (aHR 1.14 [95%CI 1.04–1.26]), respectively. However, their hospital standardized mortality ratio was similar to the other patients (0.69 vs. 0.69, P=.92). At one year of follow-up, 30% of patients in the high-risk group were alive. ConclusionsRoughly 12% of patients admitted to the ICU for more than 24h had a SAPS II score predicted mortality above 80%. Their hospital standardized mortality was similar to the less severe population and 30% were alive after one year of follow-up.

Machine Learning Algorithms Predict Successful Weaning From Mechanical Ventilation Before Intubation: Retrospective Analysis From the Medical Information Mart for Intensive Care IV Database.

The prediction of successful weaning from mechanical ventilation (MV) in advance of intubation can facilitate discussions regarding end-of-life care before unnecessary intubation. We aimed to develop a machine learning-based model that predicts successful weaning from ventilator support based on routine clinical and laboratory data taken before or immediately after intubation. We used the Medical Information Mart for Intensive Care IV database, which is an open-access database covering 524,740 admissions of 382,278 patients in Beth Israel Deaconess Medical Center, United States, from 2008 to 2019. We selected adult patients who underwent MV in the intensive care unit (ICU). Clinical and laboratory variables that are considered relevant to the prognosis of the patient in the ICU were selected. Data collected before or within 24 hours of intubation were used to develop machine learning models that predict the probability of successful weaning within 14 days of ventilator support. Developed models were integrated into an ensemble model. Performance metrics were calculated by 5-fold cross-validation for each model, and a permutation feature importance and Shapley additive explanations analysis was conducted to better understand the impacts of individual variables on outcome prediction. Of the 23,242 patients, 19,025 (81.9%) patients were successfully weaned from MV within 14 days. Using the preselected 46 clinical and laboratory variables, the area under the receiver operating characteristic curve of CatBoost classifier, random forest classifier, and regularized logistic regression classifier models were 0.860 (95% CI 0.852-0.868), 0.855 (95% CI 0.848-0.863), and 0.823 (95% CI 0.813-0.832), respectively. Using the ensemble voting classifier using the 3 models above, the final model revealed the area under the receiver operating characteristic curve of 0.861 (95% CI 0.853-0.869), which was significantly better than that of Simplified Acute Physiology Score II (0.749, 95% CI 0.742-0.756) and Sequential Organ Failure Assessment (0.588, 95% CI 0.566-0.609). The top features included lactate and anion gap. The model's performance achieved a plateau with approximately the top 21 variables. We developed machine learning algorithms that can predict successful weaning from MV in advance to intubation in the ICU. Our models can aid the appropriate management for patients who hesitate to decide on ventilator support or meaningless end-of-life care.

Association between chronic obstructive pulmonary disease and 28-day mortality in patients with sepsis: a retrospective study based on the MIMIC-III database

BackgroundSepsis is a common cause of mortality in critically ill patients, and chronic obstructive pulmonary disease (COPD) is one of the most common comorbidities in septic patients. However, the impact of COPD on patients with sepsis remained unclear. Therefore, the purpose of this study aimed to assess the effect of COPD on the prognosis of septic patients based on Medical Information Mart for Intensive Care (MIMIC-III) database.MethodsIn this retrospective study based on the (MIMIC)-III database version 1.4 (v1.4), we collected clinical data and 28-day all-cause mortality from patients with sepsis in intensive care unit (ICU) and these patients met the diagnostic criteria of Sepsis 3 on ICU admission between 2008 and 2012. International Classification of Diseases (ICD-9) (4660, 490, 4910, 4911, 49120, 49121, 4918, 4919, 4920, 4928, 494, 4940, 4941, 496) was used to identified COPD. We applied Kaplan–Meier analysis to compare difference of 28-day all-cause mortality between septic patients with and without COPD. Cox proportional-hazards model was applied to explore the risk factor associated with 28-day all-cause mortality in patients with sepsis.ResultsSix thousand two hundred fifty seven patients with sepsis were included in this study, including 955 (15.3%) patients with COPD and 5302 patients without COPD (84.7%). Compared with patients without COPD, patients with COPD were older (median: 73.5 [64.4, 82.0] vs 65.8 [52.9, 79.1], P < 0.001), had higher simplified acute physiology score II (SAPSII) (median: 40.0 [33.0, 49.0] vs 38.0 [29.0,47.0], P < 0.001) and greater proportion of mechanical ventilatory support (MV) (55.0% vs 48.9%, P = 0.001). In our study, septic patients with COPD had higher 28-day all-cause mortality (23.6% vs 16.4%, P < 0.001) than patients without COPD. After adjusting for covariates, the results showed that COPD was an independent risk factor for the 28-day all-cause mortality of patients with sepsis (HR 1.30, 95%CI: 1.12–1.50, P = 0.001).ConclusionsCOPD was an independent risk factor of 28-day all-cause mortality in septic patients. Clinically, septic patients with COPD should be given additional care.