Predictive Performance of two Measures of Prognostic Mortality of Cancer Patients in Intensive Care Unit in Jordan: A Comparative Single-Centre Study

Abstract

Background: Information is presently insufficient about using Acute Physiology and Chronic Health Evaluation (APACHE) mortality predicting models for cancer patients in intensive care unit (ICU). Objective: To evaluates the performance of APACHE II and IV in predicting mortality for cancer patients in ICU. Interventions/Methods: This was a retrospective study including adult patients admitted to an ICU in a medical center in Jordan. Actual mortality rate was determined and compared with mortality rates predicted by APACHE II and IV models. Receiver operating characteristic (ROC) analysis was used to assess the sensitivity, specificity and predictive performance of both scores. Binary logistic regression analysis was used to determine the effect that APACHE II, APACHE IV and other sample characteristics have on predicting mortality. Results: 251 patients (survived=80; none-survived=171) were included in the study with an actual mortality rate of 68.1%. APACHE II and APACHE IV scores demonstrated similar predicted mortality rates (43.3% vs. 43.0%), sensitivity (52.6% vs. 52.0%), and specificity (76.3%, 76.2%), respectively. The area under (AUC), the ROC curve for APACHE II score was 0.714 (95% confidence interval [CI] 0.645–0.783), and AUC for APACHE IV score was 0.665 (95% CI 0.595–0.734). Conclusions: As APACHE ӀӀ and ӀV mortality models demonstrate insufficient predicting performance, there is no need to consider APACHE IV in our ICU instead of using APACHE ӀӀ as it has more variables and need longer data extraction time. Implications for Practice: We suggest that other approaches in addition to the available models should be attempted to improve the accuracy of cancer prognosis in ICU. Further, it is also required to adjust the available models.

Prognostic Value of Procalcitonin, C-Reactive Protein, and Lactate Levels in Emergency Evaluation of Cancer Patients with Suspected Infection

“…Using this rationale, we were able to formulate a prediction score that can accurately guide patient treatment based on mortality risk. With an AUROC of 0.88, the prediction score appears to have excellent discrimination compared with other scoring systems, such as the Acute Physiology and Chronic Health Evaluation II score (0.714-0.828), Acute Physiology and Chronic Health Evaluation IV score (0.665-0.82), and Simplified Acute Physiology Score II (0.71-0.778) [46][47][48][49]. In addition, the absence of a poor fit in the Hosmer-Lemeshow statistic (0.837) indicates that the final prediction model was wellcalibrated; no major discrepancy was noted between the observed and expected mortality rate predicted by the final model.…”

Outcome prediction for critical care patients with respiratory neoplasms using a multilayer perceptron neural network

“…( 1 , 14 , 28 ) The variable sepsis was included as it has been demonstrated to negatively affect cancer mortality in ICU. ( 1 - 3 , 29 )…”

“…( 1 ) An increasing number of patients with lung cancer are at risk of admission to an intensive care unit (ICU) due to cancer-related complications or treatment complications. ( 2 , 3 ) Considering the high incidence of respiratory neoplasms and their negative prognosis, it would be highly beneficial to develop effective clinical predictors of short-term mortality for ICU patients with lung cancer ( 4 ) in order to help clinicians to identify lung cancer patients at high risk of mortality influencing clinical decisions to improve outcomes.…”

“…Studies validating the predictive capabilities of traditional ICU scoring systems among ICU patients with cancer suggest that their ability to predict mortality remains suboptimal. ( 3 )…”

“…These scores are broadly utilized in general ICU patients, but may be less accurate in the case of ICU patients with cancer. ( 3 ) Therefore, the developed model intends to provide better predictive performance than the general ICU scoring systems. Additional features that have been demonstrated to have an important prognostic value for mortality in ICU patients with cancer were included in the developed model.…”