Comparison of APACHE II and three abbreviated APACHE II scores for predicting outcome among emergency trauma patients

Objective: to compare the ability of the APACHE II score and three different abbreviated APACHE II scores: simplified APACHE II (s-APACHE II), Rapid Acute Physiology score (RAPS) and Rapid Emergency Medicine score to evaluate in-hospital mortality of trauma patients at the emergency department (ED). Methods: retrospective analysis of a prospective cohort study. All patients' victims of trauma admitted to the ED, during a 5 months period. For all entries to the ED, APACHE II score was calculated. APACHE II system was abbreviated by excluding the laboratory data to calculate s-APACHE II score for each patient. Individual data were reanalyzed to calculate RAPS and REMS. APACHE II score and its subcomponents were collected, and in-hospital mortality was assessed. The area under the receiver operating characteristic (AUROC) curve was used to determine the predictive value of each score. Results: 163 patients were analyzed. In-hospital mortality rate was 10.4%. s-APACHE II, RAPS and REMS scores were correlated with APACHE II score (r2= 0.96, r2= 0.82, r2= 0.92; p < 0.0001). Scores had similar accuracy in predicting mortality ([AUROC 0.777 [95% CI 0.705 to 0.838] for APACHE II, AUROC 0.788 [95% CI 0.717 to 0.848] for s-APACHE II, AUROC 0.806 [95% CI 0.737 to 0.864] for RAPS, AUROC 0.761 [95% CI 0.688 to 0.824] for REMS. Conclusion: abbreviated APACHE II scores have similar ability to evaluate in-hospital mortality of emergency trauma patients in comparison to APACHE II score.

Download Full-text

Predictive accuracy of APACHE II score in predicting mortality in poly Trauma patients.

The Professional Medical Journal ◽

10.29309/tpmj/2021.28.12.6852 ◽

2021 ◽

Vol 28 (12) ◽

pp. 1752-1757

Author(s):

Ibtisam Ahmed Khan ◽

Muhammad Kareem Ullah ◽

Saeed Mahmood ◽

Adnan Sadiq Butt ◽

Naeem Sarwar ◽

...

Keyword(s):

Hospital Mortality ◽

Diagnostic Accuracy ◽

Predictive Accuracy ◽

Treatment Plan ◽

Apache Ii ◽

Apache Ii Score ◽

Mortality Data ◽

Trauma Patients ◽

Efficient Treatment ◽

Sensitivity Specificity

Objective: To find diagnostic precision of APACHE II score in predicting mortality in poly Trauma patients within first 24 hours of hospitalization. Study Design: Cross Sectional study. Setting: Emergency Department of Lahore General Hospital. Period: 2018-2019. Materials & Methods: A total of 270 patients who fulfilled selection criteria were enrolled in the study. To calculate APACHE II score, age, vitals, CBC level, Glasgow coma scale score and chronic health points were measured. Patients were classified as per their APACHE II score. After calculating APACHE II score patients were managed according to trauma severity and followed up till 24 hours to note the mortality. Data was analyzed in SPSS v. 20. Results: The mean age of patients was 38.53 ± 11.67 years with 173(63.91%) male and 97(36.09%) were female patients. Out of 270 cases, in hospital mortality occurred in 99(36.5%) while other 171(63.5%) were alive within 24 hours of admission. According to APACHE II score, 99(36.5%) cases had > 11.5 score and rests of 171(63.5%) had APACHE II ≤ 11.5. The sensitivity, specificity, PPV, NPV and diagnostic accuracy of APACHE II was 89.16%, 93.2%, 88.1%, 93.84% and 91.74%. Conclusion: According to this study, high accuracy of APACHE II for prediction of in-hospital mortality with high sensitivity, specificity, PPV, NPV and diagnostic accuracy as 89.16%, 93.2%, 88.1%, 93.84% and 91.74%. Using APACHE II in future we can devise an efficient treatment plan for poly trauma patients to reduce the probability of hospital mortality.

Download Full-text

Predictive accuracy of Apache-II for mortality in Poly Trauma patients.

The Professional Medical Journal ◽

10.29309/tpmj/2020.27.11.4460 ◽

2020 ◽

Vol 27 (11) ◽

pp. 2314-2319

Author(s):

Manzoor Qadir Joyia ◽

Mudassar Murtaza ◽

Mohammad Ansar Aslam ◽

Fakhar Irfan ◽

Hira Liaqat ◽

...

Keyword(s):

Hospital Mortality ◽

Diagnostic Accuracy ◽

General Hospital ◽

Predictive Accuracy ◽

Treatment Plan ◽

Apache Ii ◽

Apache Ii Score ◽

Trauma Patients ◽

Cross Sectional ◽

Efficient Treatment

Objectives: The objective of our study was to find diagnostic accuracy of APACHE-II score to predict mortality in poly trauma patients within first 24 hours of hospitalization. Study Design: Cross Sectional study. Setting: Department of Emergency Lahore General Hospital. Period: 25 March, 2016 to 25 September, 2016. Material & Methods: A total of 230 patients who fulfilled inclusion criteria were enrolled in the study from emergency department of Lahore General Hospital, informed consent was taken from all patients or their attendants to take their demographic profile (name, age, gender and contact no) and other necessary clinical data. To calculate APACHE-II score, vital signs, blood / serum profile, GCS, age and prolong health problems were measured on patients’ arrival. Patients were classified as per their APACHE-II score. After calculating APACHE-II score patients were managed according to trauma severity and followed up till 24 hours to note the in- hospital mortality. All the data was recorded on a Performa. Statistical analysis was carried out using SPSS 20. Results: Out of 230 patients, 147 (63.91%) were male and 83(36.09%) were female; mean age was 38.53 ± 11.67 years. Out of 230 cases, in hospital mortality occurred in 84(36.5%) while other 146(63.5%) were alive within 24 hours of admission. According to APACHE-II score, 84(36.5%) cases had > 11.5 score and rests of 146(63.5%) had APACHE-II ≤ 11.5. The sensitivity, specificity, PPV, NPV and diagnostic accuracy of APACHE-II was 89.16%, 93.2%, 88.1%, 93.84% and 91.74% respectively. Conclusion: According to the findings of this study, we found APACHE-II highly accurate for indicating in-hospital mortality. Using APACHE-II in future we can devise an efficient treatment plan for poly trauma patients to reduce the probability of hospital mortality.

Download Full-text

Predicting Burn Mortality Using a Simple Novel Prediction Model

Indian Journal of Plastic Surgery ◽

10.1055/s-0040-1721867 ◽

2021 ◽

Author(s):

Sneha Sharma ◽

Raman Tandon

Keyword(s):

Logistic Regression ◽

Regression Analysis ◽

Prediction Model ◽

Receiver Operating Characteristic ◽

Logistic Regression Analysis ◽

Operating Characteristic ◽

Binary Logistic Regression ◽

Apache Ii ◽

Apache Ii Score ◽

Binary Logistic Regression Analysis

Abstract Background Prediction of outcome for burn patients allows appropriate allocation of resources and prognostication. There is a paucity of simple to use burn-specific mortality prediction models which consider both endogenous and exogenous factors. Our objective was to create such a model. Methods A prospective observational study was performed on consecutive eligible consenting burns patients. Demographic data, total burn surface area (TBSA), results of complete blood count, kidney function test, and arterial blood gas analysis were collected. The quantitative variables were compared using the unpaired student t-test/nonparametric Mann Whitney U-test. Qualitative variables were compared using the ⊠2-test/Fischer exact test. Binary logistic regression analysis was done and a logit score was derived and simplified. The discrimination of these models was tested using the receiver operating characteristic curve; calibration was checked using the Hosmer—Lemeshow goodness of fit statistic, and the probability of death calculated. Validation was done using the bootstrapping technique in 5,000 samples. A p-value of <0.05 was considered significant. Results On univariate analysis TBSA (p <0.001) and Acute Physiology and Chronic Health Evaluation II (APACHE II) score (p = 0.004) were found to be independent predictors of mortality. TBSA (odds ratio [OR] 1.094, 95% confidence interval [CI] 1.037–1.155, p = 0.001) and APACHE II (OR 1.166, 95% CI 1.034–1.313, p = 0.012) retained significance on binary logistic regression analysis. The prediction model devised performed well (area under the receiver operating characteristic 0.778, 95% CI 0.681–0.875). Conclusion The prediction of mortality can be done accurately at the bedside using TBSA and APACHE II score.

Download Full-text

The Relationship of the ACCP/SCCM Consensus Conference Classification of Sepsis to Mortality and Multiorgan Dysfunction among Medical ICU Patients

Journal of Intensive Care Medicine ◽

10.1177/088506669601100604 ◽

1996 ◽

Vol 11 (6) ◽

pp. 326-334 ◽

Cited By ~ 4

Author(s):

Marin H. Kollef ◽

Paul R. Eisenberg

Keyword(s):

Septic Shock ◽

Severe Sepsis ◽

Hospital Mortality ◽

Consensus Conference ◽

Organ System ◽

Apache Ii ◽

Apache Ii Score ◽

Icu Patients ◽

Multiorgan Dysfunction

To determine the relation between the proposed ACCP/SCCM Consensus Conference classification of sepsis and hospital outcomes, we conducted a single-center, prospective observational study at Barnes Hospital, St. Louis, MO, an academic tertiary care hospital. A total of 324 consecutive patients admitted to the medical intensive care unit (ICU) were studied for prospective patient surveillance and data collection. The main outcome measures were the number of acquired organ system derangements and hospital mortality. Fifty-seven (17.6%) patients died during the study period. The proposed classifications of sepsis (e.g., systemic inflammatory response syndrome [SIRS], sepsis, severe sepsis, septic shock) correlated with hospital mortality ( r = 0.330; p < 0.001) and development of an Organ System Failure Index (OSFI) of 3 or greater ( r = 0.426; p < 0.001). Independent determinants of hospital mortality for this patient cohort ( p < 0.05) were development of an OSFI of 3 or greater (adjusted odds ratio [AOR], 13.9; 95% confidence interval [CI], 6.4–30.2; p < 0.001); presence of severe sepsis or septic shock (AOR, 2.6; 95% CI, 1.2–5.6; p = 0.002), and an APACHE II score ≥ of 18 or greater (AOR, 2.4; 95% CI, 1.0–5.8; p = 0.045). Intra-abdominal infection (AOR, 19.1; 95% CI, 1.6–230.1; p = 0.011), an APACHE II score ≥ of 18 or greater (AOR, 8.9; 95% CI, 4.2–18.6; p < 0.001), and presence of severe sepsis or septic shock (AOR, 2.9; 95% CI, 1.5–5.4; p = 0.001) were independently associated with development of an OSFI of 3 or greater. These data confirm that acquired multiorgan dysfunction is the most important predictor of mortality among medical ICU patients. In addition, they identify the proposed ACCP/SCCM Consensus Conference classification of sepsis as an additional independent determinant of both hospital mortality and multiorgan dysfunction.

Download Full-text

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

BMC Medical Informatics and Decision Making ◽

10.1186/s12911-021-01591-x ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Yan Luo ◽

Zhiyu Wang ◽

Cong Wang

Keyword(s):

Intensive Care ◽

Hospital Mortality ◽

Patient Outcomes ◽

External Validation ◽

Apache Ii ◽

Validation Dataset ◽

Apache Ii Score ◽

Severity Scores ◽

The Impact ◽

Improve Patient

Abstract 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.

Download Full-text

Influencing Factors and Prevention of Sepsis or Acute Kidney Injury in 85 Patients with Severe Trauma

Evidence-based Complementary and Alternative Medicine ◽

10.1155/2021/5754114 ◽

2021 ◽

Vol 2021 ◽

pp. 1-7

Author(s):

Hong Zhang ◽

Dan Chen ◽

Lihua Wang ◽

Bing Li

Keyword(s):

Risk Factors ◽

High Risk ◽

Influencing Factors ◽

Severe Trauma ◽

Apache Ii ◽

Apache Ii Score ◽

Trauma Patients ◽

Risk Of Death ◽

Disturbance Of Consciousness ◽

Prevention And Treatment

Severe trauma can cause systemic reactions, leading to massive bleeding, shock, asphyxia, and disturbance of consciousness. At the same time, patients with severe trauma are at high risk of sepsis and acute renal injury. The occurrence of complications will increase the difficulty of clinical treatment, improve the mortality rate, and bring heavy physical and mental burdens and economic pressure to patients and their families. It is of great clinical significance to understand the high risk factors of sepsis and AKI and actively formulate prevention and treatment measures. In this study, the clinical data of 85 patients with severe trauma were analyzed by univariate and multivariate logistic regression to identify the risk factors leading to sepsis or AKI and analyze the prevention and treatment strategies. The results showed that multiple injuries, APACHE II score on admission, SOFA score on admission, and mechanical ventilation were independent influencing factors of sepsis in patients with severe trauma, while hemorrhagic shock, APACHE II score on admission, CRRT, and sepsis were independent influencing factors of AKI in patients with severe trauma. Severe trauma patients complicated with sepsis or AKI will increase the risk of death. In the course of treatment, prevention and intervention should be given as far as possible to reduce the incidence of complications.

Download Full-text

Prognosis of Patients with Rheumatic Diseases Admitted to Intensive Care

Anaesthesia and Intensive Care ◽

10.1177/0310057x1704500110 ◽

2017 ◽

Vol 45 (1) ◽

pp. 67-72 ◽

Cited By ~ 6

Author(s):

M. Beil ◽

S. Sviri ◽

V. de la Guardia ◽

I. Stav ◽

E. Ben-Chetrit ◽

...

Keyword(s):

Intensive Care ◽

Rheumatic Disease ◽

Rheumatic Diseases ◽

Matched Control ◽

Apache Ii ◽

Apache Ii Score ◽

Control Group ◽

Control Groups ◽

Predicting Outcome ◽

And Gender

Variable mortality rates have been reported for patients with rheumatic diseases admitted to an intensive care unit (ICU). Due to the absence of appropriate control groups in previous studies, it is not known whether the presence of a rheumatic disease constitutes a risk factor. Moreover, the accuracy of the Acute Physiology and Chronic Health Evaluation II (APACHE II) score for predicting outcome in this group of patients has been questioned. The primary goal of this study was to compare outcome of patients with rheumatic diseases admitted to a medical ICU to those of controls. The records of all patients admitted between 1 April 2003 and 30 June 2014 (n=4020) were screened for the presence of a rheumatic disease during admission (n=138). The diagnosis of a rheumatic disease was by standard criteria for these conditions. An age- and gender-matched control group of patients without a rheumatic disease was extracted from the patient population in the database during the same period (n=831). Mortality in ICU, in hospital and after 180 days did not differ significantly between patients with and without rheumatic diseases. There was no difference in the performance of the APACHE II score for predicting outcome in patients with rheumatic diseases and controls. This score, as well as a requirement for the use of inotropes or vasopressors, accurately predicted hospital mortality in the group of patients with rheumatic diseases. In conclusion, patients with a rheumatic condition admitted to intensive care do not do significantly worse than patients without such a disease.

Download Full-text

Outcomes of Critically Ill Gynecological Cancer Patients Admitted to Intensive Care Unit

American Journal of Hospice and Palliative Medicine® ◽

10.1177/1049909112437028 ◽

2012 ◽

Vol 30 (1) ◽

pp. 7-11 ◽

Cited By ~ 4

Author(s):

Silvio A. Ñamendys-Silva ◽

María O. González-Herrera ◽

Julia Texcocano-Becerra ◽

Angel Herrera-Gómez

Keyword(s):

Intensive Care Unit ◽

Intensive Care ◽

Prognostic Factors ◽

Mortality Rate ◽

Hospital Mortality ◽

Critically Ill ◽

Critically Ill Patients ◽

Gynecological Cancer ◽

Apache Ii ◽

Apache Ii Score

Purpose: To assess the characteristics of critically ill patients with gynecological cancer, and to evaluate their prognosis. Methods: Fifty-two critically ill patients with gynecological cancer admitted to intensive care unit (ICU) were included. Univariate and multivariate logistic regressions were used to identify factors associated with hospital mortality. Results: Thirty-five patients (67.3%) had carcinoma of the cervix uteri and 11 (21.2%) had ovarian cancer. The mortality rate in the ICU was 17.3% (9 of 52) and hospital mortality rate were 23%(12 of 52). In the multivariate analysis, independent prognostic factors for hospital mortality were vasopressor use (odds ratio [OR] = 8.60, 95% confidence interval [CI] 2.05-36; P = .03) and the Acute Physiology and Chronic Health Evaluation (APACHE) II score (OR = 1.43, 95% CI 1.01-2.09; P = .048). Conclusions: The independent prognostic factors for hospital mortality were the need for vasopressors and the APACHE II score.

Download Full-text

The Utility of Acute Physiology and Chronic Health Evaluation II Scores for Prediction of Mortality among Intensive Care Unit (ICU) and Non-ICU Patients with Methicillin-Resistant Staphylococcus aureus Bacteremia

Infection Control and Hospital Epidemiology ◽

10.1086/665731 ◽

2012 ◽

Vol 33 (6) ◽

pp. 558-564 ◽

Cited By ~ 15

Author(s):

Vanessa Stevens ◽

Thomas P. Lodise ◽

Brian Tsuji ◽

Meagan Stringham ◽

Jill Butterfield ◽

...

Keyword(s):

Intensive Care Unit ◽

Staphylococcus Aureus ◽

Intensive Care ◽

Hospital Mortality ◽

Chronic Health Evaluation ◽

Apache Ii ◽

Apache Ii Score ◽

Health Evaluation ◽

Icu Patients ◽

Time Points

Objective.Bloodstream infections due to methicillin-resistant Staphylococcus aureus (MRSA) have been associated with significant risk of in-hospital mortality. The acute physiology and chronic health evaluation (APACHE) II score was developed and validated for use among intensive care unit (ICU) patients, but its utility among non-ICU patients is unknown. The aim of this study was to determine the ability of APACHE II to predict death at multiple time points among ICU and non-ICU patients with MRSA bacteremia.Design.Retrospective cohort study.Participants.Secondary analysis of data from 200 patients with MRSA bacteremia at 2 hospitals.Methods.Logistic regression models were constructed to predict overall in-hospital mortality and mortality at 48 hours, 7 days, 14 days, and 30 days using APACHE II scores separately in ICU and non-ICU patients. The performance of APACHE II scores was compared with age adjustment alone among all patients. Discriminatory ability was assessed using the c-statistic and was compared at each time point using X2 tests. Model calibration was assessed using the Hosmer-Lemeshow goodness-of-fit test.Results.APACHE II was a significant predictor of death at all time points in both ICU and non-ICU patients. Discrimination was high in all models, with c-statistics ranging from 0.72 to 0.84, and was similar between ICU and non-ICU patients at all time points. APACHE II scores significantly improved the prediction of overall and 48-hour mortality compared with age adjustment alone.Conclusions.The APACHE II score may be a valid tool to control for confounding or for the prediction of death among ICU and non-ICU patients with MRSA bacteremia.

Download Full-text