APACHE II score for critically ill patients with a solid tumor: A reclassification study

SOFA score is superior to APACHE-II score in predicting the prognosis of critically ill patients with acute kidney injury undergoing continuous renal replacement therapy

Background

Acute kidney injury (AKI) is the most common cause of organ failure in multiple organ dysfunction syndrome (MODS) and is associated with increased mortality. This study aimed at determining the efficacy of sequential organ failure assessment (SOFA), and acute physiology and chronic health evaluation II (APACHE-II) scoring systems in assessing the prognosis of critically ill patients with AKI undergoing continuous renal replacement therapy (CRRT). At present, APACHE-II score and SOFA score were also used to evaluate and predict the prognosis of critically ill patients with AKI.

Methods

The predictive value of SOFA and APACHE-II scores for 28- and 90-d mortality in patients with AKI undergoing CRRT were determined by multivariate analysis, sensitivity analysis, and curve-fitting analysis.

Results

A total of 836 cases were included in this study. Multivariate Cox logistic regression analysis showed that SOFA scores were associated with 28- and 90-d mortality in patients with AKI undergoing CRRT. The adjusted HR of SOFA for 28-d mortality were 1.18 (1.14, 1.21), 1.24 (1.18, 1.31), and 1.19 (1.13, 1.24) in the three models, respectively, and the adjusted HR of SOFA for 90-d mortality was 1.12 (1.09, 1.16), 1.15 (1.10, 1.19), and 1.15 (1.10, 1.19), respectively. The subgroup analysis showed that the SOFA score was associated with 28-d and 90-d mortality in patients with AKI undergoing CRRT. APACHE-II score was not associated with 28- and 90-d mortality patients with AKI undergoing CRRT. Curve fitting analysis showed that SOFA scores increased had a higher prediction accuracy for 28- and 90-d than APACHE-II.

Conclusions

The SOFA score showed a higher accuracy of mortality prediction in critically ill patients with AKI undergoing CRRT than the APACHE-II score.

Machine learning-based patient classification system for adult patients in intensive care units: A cross-sectional study

AIM

This study aimed to develop a patient classification system that stratifies patients admitted to the intensive care unit based on their disease severity and care needs.

BACKGROUND

Classifying patients into homogenous groups based on clinical characteristics can optimize nursing care. However, an objective method for determining such groups remains unclear.

METHODS

Predictors representing disease severity and nursing workload were considered. Patients were clustered into subgroups with different characteristics based on the results of a clustering algorithm. A patient classification system was developed using a partial least squares regression model.

RESULTS

Data of 300 patients were analysed. Cluster analysis identified three subgroups of critically patients with different levels of clinical trajectories. Except for blood potassium levels (p = .29), the subgroups were significantly different according to disease severity and nursing workload. The predicted value ranges of the regression model for Classes A, B and C were <1.44, 1.44-2.03 and >2.03. The model was shown to have good fit and satisfactory prediction efficiency using 200 permutation tests.

CONCLUSIONS

Classifying patients based on disease severity and care needs enables the development of tailored nursing management for each subgroup.

IMPLICATIONS FOR NURSING MANAGEMENT

The patient classification system can help nurse managers identify homogeneous patient groups and further improve the management of critically ill patients.

The mNCP-SPI Score Predicting Risk of Severe COVID-19 among Mild-Pneumonia Patients on Admission

Purpose

To predict the risk of developing severe pneumonia among mild novel coronavirus pneumonia (mNCP) patients on admission.

Methods

A retrospective cohort study was conducted at three hospitals in Shanghai and Wuhan from January 2020 to February 2020. Real-time polymerasechain–reaction assays were used to detect COVID-19. A total of 529 patients diagnosed with NCP were recruited from three hospitals and classified by four severity types during hospitalization following the standards of the Chinese Diagnosis and Treatment of Pneumonia Caused by New Coronavirus Infection (eighth version). Patients were excluded if admitted by ICU on admission (n=92, on a general ward while meeting the condition of severe or critical type on admission (n=25), or there was insufficient clinical information (n=64). In sum, 348 patients with mNCP were finally included, and 68 developed severe pneumonia.

Results

mNCP severity prognostic index values were calculated based on multivariate logistic regression: history of diabetes (OR 2.064, 95% CI 1.010–4.683; p=0.043), time from symptom onset to admission ≥7 days (OR 1.945, 95% CI 1.054–3.587; p=0.033), lymphocyte count ≤0.8 (OR 1.816, 95% CI 1.008–3.274; p=0.047), myoglobin ≥90 mg/L (OR 2.496, 95% CI 1.235–5.047; p=0.011), and D-dimer ≥0.5 mg/L (OR 2.740, 95% CI 1.395–5.380; p=0.003). This model showed a c-statistics of 0.747, with sensitivity and specificity 0.764 and 0.644, respectively, under cutoff of 165.

Conclusion

We designed a clinical predictive tool for risk of severe pneumonia among mNCP patients to provided guidance for medicines. Further studies are required for external validation.

Performance of three prognostic models in critically ill patients with cancer: a prospective study

BACKGROUND

The aim of the study was to evaluate the performance of "Acute Physiology and Chronic Health Evaluation II" (APACHE-II), "Simplified Acute Physiology Score 3" (SAPS-3), and "APACHE-II Score for Critically Ill Patients with a Solid Tumor" (APACHE-II_CCP) models in cancer patients admitted to ICU.

METHODS

Prospective cohort study of 414 patients with an active solid tumor. Discrimination was assessed by area under receiver operating characteristic (AROC) curves and calibration by Hosmer-Lemeshow goodness-of-fit C test (H-L).

RESULTS

The hospital mortality rate was 32.6%. In the total cohort, discrimination for prognostic models were: APACHE-II_CCP (AROC 0.98), APACHE-II (AROC 0.96), SAPS-3 for Central and South American countries (SAPS-3_CSA) (AROC 0.95), and SAPS-3 (AROC 0.91). Calibration was good (p value of H-L test > 0.05) using APACHE-II_CCP, APACHE-II and SAPS-3_CSA models. Estimation of the probability of death was more precise with APACHE-II_CCP (standardized mortality ratio, SMR = 1.03) and SAPS-3 (SMR = 1.08) models. Further analysis showed that discrimination was high with all prognostic model whether for patients with planned ICU admission (AROC APACHE-II_CCP 0.97, APACHE-II 0.96, SAPS-3 0.95, SAPS-3_CSA 0.95) or for patients with unplanned ICU admission (AROC APACHE-II_CCP 0.97, APACHE-II 0.94, SAPS-3 0.86, SAPS-3_CSA 0.95). Calibration was good for all predictive models in both subgroups (p value of H-L test > 0.05, except for APACHE-II model inpatients with planned ICU admission).

CONCLUSIONS

In this prospective study, general predictive models (e.g., APACHE-II, SAPS-3) and cancer-specific models (e.g., APACHE-II_CCP) are accurate in predicting hospital mortality. Other studies confirming these results are required.