A new method to predict hospital mortality in severe community acquired pneumonia

Machine learning-based model for predicting all-cause mortality in severe pneumonia

BACKGROUND

Severe pneumonia has a poor prognosis and high mortality. Current severity scores such as Acute Physiology and Chronic Health Evaluation (APACHE-II) and Sequential Organ Failure Assessment (SOFA), have limited ability to help clinicians in classification and management decisions. The goal of this study was to analyse the clinical characteristics of severe pneumonia and develop a machine learning-based mortality-prediction model for patients with severe pneumonia.

METHODS

Consecutive patients with severe pneumonia between 2013 and 2022 admitted to Beijing Chaoyang Hospital affiliated with Capital Medical University were included. In-hospital all-cause mortality was the outcome of this study. We performed a retrospective analysis of the cohort, stratifying patients into survival and non-survival groups, using mainstream machine learning algorithms (light gradient boosting machine, support vector classifier and random forest). We aimed to construct a mortality-prediction model for patients with severe pneumonia based on their accessible clinical and laboratory data. The discriminative ability was evaluated using the area under the receiver operating characteristic curve (AUC). The calibration curve was used to assess the fit goodness of the model, and decision curve analysis was performed to quantify clinical utility. By means of logistic regression, independent risk factors for death in severe pneumonia were figured out to provide an important basis for clinical decision-making.

RESULTS

A total of 875 patients were included in the development and validation cohorts, with the in-hospital mortality rate of 14.6%. The AUC of the model in the internal validation set was 0.8779 (95% CI, 0.738 to 0.974), showing a competitive discrimination ability that outperformed those of traditional clinical scoring systems, that is, APACHE-II, SOFA, CURB-65 (confusion, urea, respiratory rate, blood pressure, age ≥65 years), Pneumonia Severity Index. The calibration curve showed that the in-hospital mortality in severe pneumonia predicted by the model fit reasonably with the actual hospital mortality. In addition, the decision curve showed that the net clinical benefit was positive in both training and validation sets of hospitalised patients with severe pneumonia. Based on ensemble machine learning algorithms and logistic regression technique, the level of ferritin, lactic acid, blood urea nitrogen, creatine kinase, eosinophil and the requirement of vasopressors were identified as top independent predictors of in-hospital mortality with severe pneumonia.

CONCLUSION

A robust clinical model for predicting the risk of in-hospital mortality after severe pneumonia was successfully developed using machine learning techniques. The performance of this model demonstrates the effectiveness of these techniques in creating accurate predictive models, and the use of this model has the potential to greatly assist patients and clinical doctors in making well-informed decisions regarding patient care.

Prediction of mortality risk in patients with severe community-acquired pneumonia in the intensive care unit using machine learning

The aim of this study was to develop and validate a machine learning-based mortality risk prediction model for patients with severe community-acquired pneumonia (SCAP) in the intensive care unit (ICU). We collected data from two centers as the development and external validation cohorts. Variables were screened using the Recursive Feature Elimination method. Five machine learning algorithms were used to build predictive models. Models were evaluated through nested cross-validation to select the best one. The model was interpreted using Shapley Additive Explanations. We selected the optimal model to generate the web calculator. A total of 23 predictive features were selected. The Light Gradient Boosting Machine (LightGBM) model had an area under the receiver operating characteristic curve (AUC) of 0.842 (95% CI: 0.757-0.927), with an external 5-fold cross-validation average AUC of 0.842 ± 0.038, which was superior to the other models. External validation results also demonstrated good performance by the LightGBM model with an AUC of 0.856 (95% CI: 0.792-0.921). Based on this, we generated a web calculator by combining five high importance predictive factors. The LightGBM model was confirmed to be efficient and stable in predicting the mortality risk of patients with SCAP admitted to the ICU. The web calculator based on the LightGBM model can provide clinicians with a prognostic evaluation tool.

Clinical profile analysis and nomogram for predicting in-hospital mortality among elderly severe community-acquired pneumonia patients: a retrospective cohort study

BACKGROUND

Severe community-acquired pneumonia is one of the most lethal forms of CAP with high mortality. For rapid and accurate decisions, we developed a mortality prediction model specifically tailored for elderly SCAP patients.

METHODS

The retrospective study included 2365 elderly patients. To construct and validate the nomogram, we randomly divided the patients into training and testing cohorts in a 70% versus 30% ratio. The primary outcome was in-hospital mortality. Univariate and multivariate logistic regression analyses were used in the training cohort to identify independent risk factors. The robustness of this model was assessed using the C index, ROC and AUC. DCA was employed to evaluate the predictive accuracy of the model.

RESULTS

Six factors were used as independent risk factors for in-hospital mortality to construct the prediction model, including age, the use of vasopressor, chronic renal disease, neutrophil, platelet, and BUN. The C index was 0.743 (95% CI 0.719-0.768) in the training cohort and 0.731 (95% CI 0.694-0.768) in the testing cohort. The ROC curves and AUC for the training cohort and testing cohort (AUC = 0.742 vs. 0.728) indicated a robust discrimination. And the calibration plots showed a consistency between the prediction model probabilities and observed probabilities. Then, the DCA demonstrated great clinical practicality.

CONCLUSIONS

The nomogram incorporated six risk factors, including age, the use of vasopressor, chronic renal disease, neutrophil, platelet and BUN, which had great predictive accuracy and robustness, while also demonstrating clinical practicality at ICU admission.

Erector spinae muscle-based nomogram for predicting in-hospital mortality among older patients with severe community-acquired pneumonia

BACKGROUND

No multivariable model incorporating erector spinae muscle (ESM) has been developed to predict clinical outcomes in older patients with severe community-acquired pneumonia (SCAP). This study aimed to construct a nomogram based on ESM to predict in-hospital mortality in patients with SCAP.

METHODS

Patients aged ≥ 65 years with SCAP were enrolled in this prospective observational study. Least absolute selection and shrinkage operator and multivariable logistic regression analyses were used to identify risk factors for in-hospital mortality. A nomogram prediction model was constructed. The predictive performance was evaluated using the concordance index (C-index), calibration curve, net reclassification improvement (NRI), integrated discrimination improvement (IDI), and decision curve analysis.

RESULTS

A total of 490 patients were included, and the in-hospital mortality rate was 36.1%. The nomogram included the following independent risk factors: mean arterial pressure, peripheral capillary oxygen saturation, Glasgow Coma Scale score (GCS), lactate, lactate dehydrogenase, blood urea nitrogen levels, and ESM cross-sectional area. Incorporating ESM into the base model with other risk factors significantly improved the C-index from 0.803 (95% confidence interval [CI], 0.761-0.845) to 0.836 (95% CI, 0.798-0.873), and these improvements were confirmed by category-free NRI and IDI. The ESM-based nomogram demonstrated a high level of discrimination, good calibration, and overall net benefits for predicting in-hospital mortality compared with the combination of confusion, urea, respiratory rate, blood pressure, and age ≥ 65 years (CURB-65), Pneumonia Severity Index (PSI), Acute Physiology and Chronic Health Evaluation II (APACHEII), and Sequential Organ Failure Assessment (SOFA).

CONCLUSIONS

The proposed ESM-based nomogram for predicting in-hospital mortality among older patients with SCAP may help physicians to promptly identify patients prone to adverse outcomes.

TRIAL REGISTRATION

This study was registered at www.chictr.org.cn (registration number Chi CTR-2300070377).

Neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), and systemic immune inflammation index (SII) to predict postoperative pneumonia in elderly hip fracture patients

PURPOSE

Investigate the association between the neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), and systemic immune-inflammation index (SII) about the presence of postoperative pneumonia (POP) in geriatric patients with hip fractures. Compare the predictive value of these biomarkers for POP and assess their potential for early detection of POP.

METHODS

We retrospectively included elderly patients with hip fractures who underwent surgical treatment at our institution. POP was diagnosed according to the guidelines provided by the American Thoracic Society. We collected neutrophil, lymphocyte, and platelet counts upon admission to calculate the NLR, PLR, and SII. Receiver operating characteristic curves were utilized to establish the optimal cutoff values for each index. Multivariate logistic regression analysis and propensity score matching analysis were utilized to assess the independent association between each index and POP after adjusting for demographic, comorbidity, and surgery-related variables.

RESULTS

The study included a total of 1199 patients, among whom 111 cases (9.26%) developed POP. NLR exhibited the highest predictive value for POP in elderly patients with hip fractures compared to PLR and SII (AUC = 0.648, 95% CI 0.594-0.701). A high NLR, using the optimal cutoff value of 5.84, was significantly associated with an increased incidence of POP (OR = 2.24, 95% CI 1.43-3.51). This finding remained statistically significant even after propensity score matching (OR = 2.04, 95% CI 1.31-3.20).

CONCLUSIONS

Among the three inflammatory/immune markers considered, the NLR demonstrates the highest reliability as a predictor for POP in elderly patients with hip fractures. Therefore, it serves as a valuable tool for early identification.

Association between white blood cell count to hemoglobin ratio and risk of in-hospital mortality in patients with lung cancer

BACKGROUND

The objective of this study was to investigate the association between white blood cell count to hemoglobin ratio (WHR) and risk of in-hospital mortality in patients with lung cancer.

METHODS

In this retrospective cohort study, the medical records of patients with lung cancer were retrieved from the electronic ICU (eICU) Collaborative Research Database between 2014 and 2015. The primary outcome was in-hospital mortality. The secondary outcome was the length of stay in intensive care unit (ICU). The cut-off value for the WHR was calculated by the X-tile software. The Cox model was applied to assess the association between WHR and in-hospital mortality among patients with lung cancer and the linear regression model was used to investigate the association between WHR and length of ICU stay. Subgroup analyses of age (< 65 years or >  = 65 years), Acute Physiology and Chronic Health Evaluation (APACHE) score (< 59 or >  = 59), gender, ventilation (yes or no), and vasopressor (yes or no) in patients with lung cancer were conducted.

RESULTS

Of the 768 included patients with lung cancer, 153 patients (19.92%) died in the hospital. The median total follow-up time was 6.88 (4.17, 11.23) days. The optimal cut-off value for WHR was 1.4. ICU lung cancer patients with WHR >  = 1.4 had a significantly higher risk of in-hospital mortality [Hazard ratio: (HR): 1.65, 95% confidence interval (CI): 1.15 to 2.38, P = 0.007) and length of stay in ICU (HR: 0.63, 0.01, 95% CI: 1.24 to 0.045, P = 0.045). According to the subgroup analysis, WHR was found to be associated with in-hospital mortality in patients with higher APACHE score (HR: 1.60, 95% CI: 1.06 to 2.41, P = 0.024), in male patients (HR: 1.87, 95% CI: 1.15 to 3.04, P = 0.012), and in patients with the treatment of ventilation (HR: 2.33, 95% CI: 1.49 to 3.64, P < 0.001).

CONCLUSION

This study suggests the association between WHR and risk of in-hospital mortality in patients with lung cancer and length of stay, which indicates the importance of attention to WHR for patients with lung cancer.

Development and validation of an in-hospital mortality risk prediction model for patients with severe community-acquired pneumonia in the intensive care unit

BACKGROUND

A high mortality rate has always been observed in patients with severe community-acquired pneumonia (SCAP) admitted to the intensive care unit (ICU); however, there are few reported predictive models regarding the prognosis of this group of patients. This study aimed to screen for risk factors and assign a useful nomogram to predict mortality in these patients.

METHODS

As a developmental cohort, we used 455 patients with SCAP admitted to ICU. Logistic regression analyses were used to identify independent risk factors for death. A mortality prediction model was built based on statistically significant risk factors. Furthermore, the model was visualized using a nomogram. As a validation cohort, we used 88 patients with SCAP admitted to ICU of another hospital. The performance of the nomogram was evaluated by analysis of the area under the receiver operating characteristic (ROC) curve (AUC), calibration curve analysis, and decision curve analysis (DCA).

RESULTS

Lymphocytes, PaO2/FiO2, shock, and APACHE II score were independent risk factors for in-hospital mortality in the development cohort. External validation results showed a C-index of 0.903 (95% CI 0.838-0.968). The AUC of model for the development cohort was 0.85, which was better than APACHE II score 0.795 and SOFA score 0.69. The AUC for the validation cohort was 0.893, which was better than APACHE II score 0.746 and SOFA score 0.742. Calibration curves for both cohorts showed agreement between predicted and actual probabilities. The results of the DCA curves for both cohorts indicated that the model had a high clinical application in comparison to APACHE II and SOFA scoring systems.

CONCLUSIONS

We developed a predictive model based on lymphocytes, PaO2/FiO2, shock, and APACHE II scores to predict in-hospital mortality in patients with SCAP admitted to the ICU. The model has the potential to help physicians assess the prognosis of this group of patients.

Machine learning-based prediction of in-ICU mortality in pneumonia patients

Conventional severity-of-illness scoring systems have shown suboptimal performance for predicting in-intensive care unit (ICU) mortality in patients with severe pneumonia. This study aimed to develop and validate machine learning (ML) models for mortality prediction in patients with severe pneumonia. This retrospective study evaluated patients admitted to the ICU for severe pneumonia between January 2016 and December 2021. The predictive performance was analyzed by comparing the area under the receiver operating characteristic curve (AU-ROC) of ML models to that of conventional severity-of-illness scoring systems. Three ML models were evaluated: (1) logistic regression with L2 regularization, (2) gradient-boosted decision tree (LightGBM), and (3) multilayer perceptron (MLP). Among the 816 pneumonia patients included, 223 (27.3%) patients died. All ML models significantly outperformed the Simplified Acute Physiology Score II (AU-ROC: 0.650 [0.584-0.716] vs 0.820 [0.771-0.869] for logistic regression vs 0.827 [0.777-0.876] for LightGBM 0.838 [0.791-0.884] for MLP; P < 0.001). In the analysis for NRI, the LightGBM and MLP models showed superior reclassification compared with the logistic regression model in predicting in-ICU mortality in all length of stay in the ICU subgroups; all age subgroups; all subgroups with any APACHE II score, PaO₂/FiO₂ ratio < 200; all subgroups with or without history of respiratory disease; with or without history of CVA or dementia; treatment with mechanical ventilation, and use of inotropic agents. In conclusion, the ML models have excellent performance in predicting in-ICU mortality in patients with severe pneumonia. Moreover, this study highlights the potential advantages of selecting individual ML models for predicting in-ICU mortality in different subgroups.

Development and validation of a survival prediction model in elder patients with community-acquired pneumonia: a MIMIC-population-based study

BACKGROUND

To develop a prediction model predicting in-hospital mortality of elder patients with community-acquired pneumonia (CAP) admitted to the intensive care unit (ICU).

METHODS

In this cohort study, data of 619 patients with CAP aged ≥ 65 years were obtained from the Medical Information Mart for Intensive Care III (MIMIC III) 2001-2012 database. To establish the robustness of predictor variables, the sample dataset was randomly partitioned into a training set group and a testing set group (ratio: 6.5:3.5). The predictive factors were evaluated using multivariable logistic regression, and then a prediction model was constructed. The prediction model was compared with the widely used assessments: Sequential Organ Failure Assessment (SOFA), Pneumonia Severity Index (PSI), systolic blood pressure, oxygenation, age and respiratory rate (SOAR), CURB-65 scores using positive predictive value (PPV), negative predictive value (NPV), accuracy (ACC), area under the curve (AUC) and 95% confidence interval (CI). The decision curve analysis (DCA) was used to assess the net benefit of the prediction model. Subgroup analysis based on the pathogen was developed.

RESULTS

Among 402 patients in the training set, 90 (24.63%) elderly CAP patients suffered from 30-day in-hospital mortality, with the median follow-up being 8 days. Hemoglobin/platelets ratio, age, respiratory rate, international normalized ratio, ventilation use, vasopressor use, red cell distribution width/blood urea nitrogen ratio, and Glasgow coma scales were identified as the predictive factors that affect the 30-day in-hospital mortality. The AUC values of the prediction model, the SOFA, SOAR, PSI and CURB-65 scores, were 0.751 (95% CI 0.749-0.752), 0.672 (95% CI 0.670-0.674), 0.607 (95% CI 0.605-0.609), 0.538 (95% CI 0.536-0.540), and 0.645 (95% CI 0.643-0.646), respectively. DCA result demonstrated that the prediction model could provide greater clinical net benefits to CAP patients admitted to the ICU. Concerning the pathogen, the prediction model also reported better predictive performance.

CONCLUSION

Our prediction model could predict the 30-day hospital mortality in elder patients with CAP and guide clinicians to identify the high-risk population.

A prediction model for hospital mortality in patients with severe community-acquired pneumonia and chronic obstructive pulmonary disease

BACKGROUND

No personalized prediction model or standardized algorithm exists to identify those at high risk of death among severe community-acquired pneumonia (SCAP) patients with chronic obstructive pulmonary disease (COPD). The aim of this study was to investigate the risk factors and to develop a useful nomogram for prediction of mortality in those patients.

METHODS

We performed a retrospective, observational, cohort study in the intensive care unit (ICU) of West China Hospital, Sichuan University with all consecutive SCAP patients with COPD between December 2011 and December 2018. The clinical data within 24 h of admission to ICU were collected. The primary outcome was hospital mortality. We divided the patients into training and testing cohorts (70% versus 30%) randomly. In the training cohort, univariate and multivariate logistic regression analysis were used to identify independent risk factors applied to develop a nomogram. The prediction model was assessed in both training and testing cohorts.

RESULTS

Finally, 873 SCAP patients with COPD were included, among which the hospital mortality was 41.4%. In training cohort, the independent risk factors for hospital mortality were increased age, diabetes, chronic renal diseases, decreased systolic blood pressure (SBP), and elevated fibrinogen, interleukin 6 (IL-6) and blood urea nitrogen (BUN). The C index was 0.840 (95% CI 0.809-0.872) in training cohort and 0.830 (95% CI 0.781-0.878) in testing cohort. Furthermore, the time-dependent AUC, calibration plots, DCA and clinical impact curves indicated the model had good predictive performance. Significant association of risk stratification based on nomogram with mortality was also found (P for trend < 0.001). The restricted cubic splines suggested that estimated associations between these predictors and hospital mortality were all linear relationships.

CONCLUSION

We developed a prediction model including seven risk factors for hospital mortality in patients with SCAP and COPD. It can be used for early risk stratification in clinical practice after more external validation.

SOFA Score Plus Impedance Ratio Predicts Mortality in Critically Ill Patients Admitted to the Emergency Department: Retrospective Observational Study

Background: The Sequential Organ Failure Assessment (SOFA) is a scoring system used for the evaluation of disease severity and prognosis of critically ill patients. The impedance ratio (Imp-R) is a novel mortality predictor. Aims: This study aimed to evaluate the combination of the SOFA + Imp-R in the prediction of mortality in critically ill patients admitted to the Emergency Department (ED). Methods: A retrospective cohort study was performed in adult patients with acute illness admitted to the ED of a tertiary-care referral center. Baseline SOFA score and bioelectrical impedance analysis to obtain the Imp-R were performed within the first 24 h after admission to the ED. A Cox regression analysis was performed to evaluate the mortality risk of the initial SOFA score plus the Imp-R. Harrell’s C-statistic and decision curve analyses (DCA) were performed. Results: Out of 325 patients, 240 were included for analysis. Overall mortality was 31.3%. Only 21.3% of non-surviving patients died after hospital discharge, and 78.4% died during their hospital stay. Of the latter, 40.6% died in the ED. The SOFA and Imp-R values were higher in non-survivors and were significantly associated with mortality in all models. The combination of the SOFA + Imp-R significantly predicted 30-day mortality, in-hospital mortality, and ED mortality with an area under the curve (AUC) of 0.80 (95% CI: 74–0.86), 0.79 (95% CI: 0.74–0.86) and 0.75 (95% CI: 0.66–0.84), respectively. The DCA showed that combining the SOFA + Imp-R improved the prediction of mortality through the lower risk thresholds. Conclusions: The addition of the Imp-R to the baseline SOFA score on admission to the ED improves mortality prediction in severely acutely ill patients admitted to the ED.

A literature review of severity scores for adults with influenza or community-acquired pneumonia - implications for influenza vaccines and therapeutics

Influenza vaccination and antiviral therapeutics may attenuate disease, decreasing severity of illness in vaccinated and treated persons. Standardized assessment tools, definitions of disease severity, and clinical endpoints would support characterizing the attenuating effects of influenza vaccines and antivirals. We review potential clinical parameters and endpoints that may be useful for ordinal scales evaluating attenuating effects of influenza vaccines and antivirals in hospital-based studies. In studies of influenza and community-acquired pneumonia, common physiologic parameters that predicted outcomes such as mortality, ICU admission, complications, and duration of stay included vital signs (hypotension, tachypnea, fever, hypoxia), laboratory results (blood urea nitrogen, platelets, serum sodium), and radiographic findings of infiltrates or effusions. Ordinal scales based on these parameters may be useful endpoints for evaluating attenuating effects of influenza vaccines and therapeutics. Factors such as clinical and policy relevance, reproducibility, and specificity of measurements should be considered when creating a standardized ordinal scale for assessment.

Derivation and Validation of a Novel Severity Scoring System for Pneumonia at Intensive Care Unit Admission

BACKGROUND

Severity stratification scores developed in intensive care units (ICUs) are used in interventional studies to identify the most critically ill. Studies that evaluate accuracy of these scores in ICU patients admitted with pneumonia are lacking. This study aims to determine performance of severity scores as predictors of mortality in critically ill patients admitted with pneumonia.

METHODS

Prospective cohort study in a general ICU in Brazil. ICU severity scores (Simplified Acute Physiology Score 3 [SAPS 3] and Sepsis-Related Organ Failure Assessment [qSOFA]), prognostic scores of pneumonia (CURB-65 [confusion, urea, respiratory rate, blood pressure, age] and CRB-65 [confusion, respiratory rate, blood pressure, age]), and clinical and epidemiological variables in the first 6 hours of hospitalization were analyzed.

RESULTS

Two hundred patients were included between 2015 and 2018, with a median age of 81 years (interquartile range, 67-90 years) and female predominance (52%), primarily admitted from the emergency department (65%) with community-acquired pneumonia (CAP, 80.5%). SAPS 3, CURB-65, CRB-65,and qSOFA all exhibited poor performance in predicting mortality. Multivariate regression identified variables independently associated with mortality that were used to develop a novel pneumonia-specific ICU severity score (Pneumonia Shock score) that outperformed SAPS 3, CURB-65, and CRB-65. The Shock score was validated in an external multicenter cohort of critically ill patients admitted with CAP.

CONCLUSIONS

We created a parsimonious score that accurately identifies patients with pneumonia at highest risk of ICU death. These findings are critical to accurately stratify patients with severe pneumonia in therapeutic trials that aim to reduce mortality.

Risk factors for death in tuberculosis patients requiring ICU care

The prognostic factor for in-hospital mortality in tuberculosis (TB) patients requiring intensive care unit (ICU) care remains unclear. Therefore, a retrospective study was conducted aiming to estimate the in-hospital mortality rate and the risk factors for mortality in a high-burden setting. All patients with culture-confirmed TB that were admitted to the ICU of the hospital between March 2012 and April 2019 were identified retrospectively. Data, such as demographic characteristics, comorbidities, laboratory measures and mortality, were obtained from medical records. The Cox proportional hazards regression model was used to identify prognostic factors that influence in-hospital mortality. A total of 82 ICU patients with confirmed TB were included in the analysis, and 22 deaths were observed during the hospital stay, 21 patients died in the ICU. In the multivariable model adjusted for sex and age, the levels of serum albumin and white blood cell (WBC) count were significantly associated with mortality in TB patients requiring ICU care (all P < 0.01), the hazard ratios were 0.8 (95% confidence interval (CI): 0.7–0.9) per 1 g/l and 1.1 (95% CI: 1.0–1.2) per 1 × 10⁹/l, respectively. In conclusion, in-hospital mortality remains high in TB patients requiring ICU care. Low serum albumin level and high WBC count significantly impact the risk of mortality in these TB patients in China.

Prognostic factors in elderly patients admitted to the intensive care unit with community-acquired pneumonia

OBJECTIVE

We aimed to determine the clinical, radiological and laboratory findings that may indicate poor prognosis in severe community acquired pneumonia (CAP) requiring intensified care to reduce the risk of death.

METHODS

The medical histories, demographic characteristics and laboratory values of over 65 years old patients admitted to the intensive care unit (ICU) and diagnosed with CAP were recorded.

RESULTS

Total of 86 patients were included in the study. Among those patients 39 were discharged from the ICU with health but 47 were expired. Diastolic blood pressure was significantly lower in expired patients (p = 0.044). In multivariate analysis, older age (>78 years) (p = 0.004), at admission elevated blood glucose (>108 mg/dL) levels (p = 0.048), decreased serum albumin (<3.5 g/dL) levels (p = 0.043), elevated serum procalcitonin levels (>0.63 μg/L) (p = 0.034) and in blood gas analysis decreased pH (<7.35) (p = 0.042)and increased lactate (>2mmol/L) (p = 0.001) were the significant risk factors for in-ICU mortality.

CONCLUSIONS

At old age, blood glucose and procalcitonin levels increased at the time of admission, serum albumin levels decreased, pH decreased in blood gas analysis and lactate levels increased, and significant mortality determinants in CAP patients over 65 years of age who applied to the intensive care unit.

E-selectin as a prognostic factor of patients hospitalized due to acute inflammatory respiratory diseases: a single institutional study

When examining patients with acute inflammatory respiratory diseases, it is difficult to distinguish between infectious pneumonia and interstitial pneumonia and predict patient prognosis at the beginning of treatment. In this study, we assessed whether endothelial selectin (E-selectin) predicts the outcome of patients with acute inflammatory respiratory diseases. We measured E-selectin serum levels in 101 patients who were admitted to our respiratory care unit between January 2013 and December 2013 because of acute inflammatory respiratory diseases that were eventually diagnosed as interstitial pneumonia (n = 38) and lower respiratory tract infection (n = 63). Seven of these patients (n = 101) died. The pneumonia severity score was significantly higher and the oxygen saturation of arterial blood measured by pulse oximeter (SpO₂)/fraction of inspiratory oxygen (FiO₂) was significantly lower in the deceased patients than in the surviving patients. There were significantly fewer peripheral lymphocytes and significantly higher E-selectin serum levels in the deceased patients than in the surviving patients. In the multiple logistic regression analysis, the E-selectin serum levels and SpO₂/FiO₂ ratio were independent predictive factors of prognosis. The risk of death during acute respiratory disease was determined using a receiver operating characteristic (ROC) curve analysis. The area under the curve (AUC) was 0.871 as calculated from the ES, and the cutoff value was 6453.04 pg/ml, with a sensitivity of 1.00 and a specificity of 0.72 (p = 0.0027). E-selectin may be a useful biomarker for predicting the prognosis of patients with acute inflammatory respiratory diseases.

Diagnosis and treatment of acute pulmonary inflammation in critically ill patients: The role of inflammatory biomarkers

Pneumonia and acute respiratory distress syndrome are common and important causes of respiratory failure in the intensive care unit with a significant impact on morbidity, mortality and health care utilization despite early antimicrobial therapy and lung protective mechanical ventilation. Both clinical entities are characterized by acute pulmonary inflammation in response to direct or indirect lung injury. Adjunct anti-inflammatory treatment with corticosteroids is increasingly used, although the evidence for benefit is limited. The treatment decisions are based on radiographic, clinical and physiological variables without regards to inflammatory state. Current evidence suggests a role of biomarkers for the assessment of severity, and distinguishing sub-phenotypes (hyper-inflammatory versus hypo-inflammatory) with important prognostic and therapeutic implications. Although many inflammatory biomarkers have been studied the most common and of interest are C-reactive protein, procalcitonin, and pro-inflammatory cytokines including interleukin 6. While extensively studied as prognostic tools (prognostic enrichment), limited data are available for the role of biomarkers in determining appropriate initiation, timing and dosing of adjunct anti-inflammatory treatment (predictive enrichment).

Predictive role of monocyte-to-lymphocyte ratio in patients with Klebsiella pneumonia infection: A single-center experience

The aim of the study is to explore whether monocyte-to-lymphocyte ratio (MLR) provides predictive value of the severity in patients with Klebsiella pneumonia infection (KPI).Patients in a tertiary medical center with Klebsiella pneumonia infection from 2014 to 2017 were recruited in this study. Patients with Klebsiella pneumonia infection were stratified into two groups based on the National Early Warning Score (NEWS). MLR was calculated by dividing monocytes count by lymphocytes count obtained from routine blood examination. The area under the curve (AUC) values was determined using the receiver-operating characteristic (ROC) curve. The correlation between the variables was tested with Pearson or Spearman correlation analysis. Ordinal logistic regression analysis was used to assess the relationship between MLR and the severity of Klebsiella pneumonia infection.One hundred fifty-two patients were finally enrolled for analysis. Among those, 43 (28.29%) cases had severe KPI. MLR was found to be an independent risk factor of the serious Klebsiella pneumonia infection (OR: 23.74, 95% CI: 5.41-104.11, P < .001). Besides, MLR was positively correlated with NEWS score (r = 0.57, P < .001). In the receiver-operating characteristic (ROC) curve analysis, MLR, with an optimal cut-off value of 0.665, predicted the severe coronary lesion with a sensitivity of 79.4% and specificity of 84.4%.MLR was an independent predictor of the severe Klebsiella pneumonia infection. Compared with neutrophil-to-lymphocyte ratio (NLR), MLR has a better performance to evaluate the severity of Klebsiella pneumonia infection.

Early prediction of treatment failure in severe community-acquired pneumonia: The PRoFeSs score

PURPOSE

To identify a single/panel of biomarkers and to provide a point score that, after 48 h of treatment, could early predict treatment failure at fifth day of Intensive Care Unit (ICU) stay in severe community-acquired pneumonia (SCAP) patients.

MATERIALS AND METHODS

Single-center, prospective cohort study of 107 ICU patients with SCAP. Primary outcome included death or absence of improvement in Sequential Organ Failure Assessment score by ≥2 points within 5 days of treatment. Biomarkers were evaluated within 12 h of first antibiotic dose (D1) and 48 h after the first assessment (D3).

RESULTS

A model based on Charlson's score and a panel of biomarkers (procalcitonin on D1 and D3, B-natriuretic peptide on D1, D-dimer and lactate on D3) had good discrimination for primary outcome in both derivation (AUC 0.82) and validation (AUC 0.76) samples and was well calibrated (X² = 0.98; df = 1; p = .32). A point score system (PRoFeSs score) built on the estimates of regression coefficients presented good discrimination (AUC 0.81; 95% Confidence Interval 0.72-0.89) for primary outcome.

CONCLUSIONS

In SCAP, a combination of biomarkers measured at admission and 48 h later may early predict treatment failure. PRoFeSs score may recognize patients with poor short-term prognosis.

Severity scoring systems for pneumonia: current understanding and next steps

PURPOSE OF REVIEW

To describe the current understanding and clinical applicability of severity scoring systems in pneumonia management.

RECENT FINDINGS

Severity scores in community-acquired pneumonia are strong markers of mortality, but are not necessarily clinical decision-aid tools. The use of severity scores to support outpatient care in low-risk patients has moderate-to-strong evidence available in the literature, mainly for the pneumonia severity index, and must be applied together with clinical judgment. It is not clear that severity scores are helpful to guide empiric antibiotic treatment. The inclusion of biomarkers and performance status might improve the predictive performance of the well known severity scores in community-acquired pneumonia. We should improve our methods for score evaluation and move toward the development of decision-aid tools.

SUMMARY

The application of the available evidence favors the use of severity scoring systems to improve the delivery of care for pneumonia patients. The incorporation of new methodologies and the formulation of different questions other than mortality prediction might help the further development of severity scoring systems, and enhance their support to the clinical decision-making process for the pneumonia-management cascade.

Diagnostic value of blood parameters for community-acquired pneumonia

BACKGROUND

Community-acquired pneumonia (CAP) has a high rate of morbidity and mortality. Blood parameters, including neutrophil, platelet, lymphocyte, monocyte, neutrophil to lymphocyte ratio (NLR), platelet to lymphocyte ratio (PLR), and monocyte to lymphocyte ratio (MLR), have been proposed as indicators of systemic inflammation and infection. However, few studies have focused on the diagnostic value of blood parameters for CAP.

OBJECTIVE

The study aims to determine the diagnostic value of blood parameters for CAP and to investigate their relationship with disease severity.

METHODS

CAP patients who fulfilled the inclusion criteria were enrolled in this study. Healthy age- and gender-matched subjects were also enrolled as a control group. Blood parameters, blood biochemistry, C-reactive protein (CRP), erythrocyte sedimentation rate (ESR), procalcitonin (PCT), days in hospital, body temperature, pneumonia severity index (PSI), and CURB-65 were recorded. The area under the curve (AUC) values was determined using the receiver-operating characteristic (ROC) curve. The correlation between the variables was tested with Pearson correlation analysis.

RESULTS

The study included 80 CAP patients and 49 healthy subjects. White blood cell (WBC), neutrophil, monocyte, MLR, PLR, and NLR levels in the CAP group were higher than that of control group, while lymphocyte and hemoglobin (HGB) levels were lower (P < 0.05). The ROC curve result showed that NLR and MLR yielded higher AUC values than other variables. Monocyte was positively correlated with ESR and negatively with body temperature, aspartate aminotransferase (AST), and creatinine (CREA). NLR was positively correlated with CRP, PCT, days in hospital, alanine aminotransferase (ALT), AST, and PSI. MLR was positively correlated with CRP, PCT, and body temperature. An increase in ALT or AST of >2 times of normal was defined as liver injury, and CAP patients were divided into the liver normal group and liver injury group. Sixty-nine patients belonged to the liver normal group, and 11 patients belonged to the liver injury group. Blood parameters, ESR, CRP, PCT, PSI, and CURB-65 were compared between the two groups. The results demonstrated that the monocyte level in the liver injury group was lower than that of the liver normal group (P < 0.05). The ROC curve result showed that the AUC value of monocyte for liver injury was 0.838 (95% confidence interval: 0.733-0.943), which was higher than other variables.

CONCLUSIONS

NLR and MLR were elevated in CAP patients, resulting in a higher diagnostic value for CAP. NLR showed a significant correlation to PSI, indicating the disease severity of CAP. Monocyte had a higher diagnostic value for liver injury in CAP patients.

Risk stratification and prediction value of procalcitonin and clinical severity scores for community-acquired pneumonia in ED

OBJECTIVE

Community-acquired pneumonia (CAP) is a common presentation to the emergency department (ED) and has high mortality rates. The aim of our study is to investigate the risk stratification and prognostic prediction value of precalcitonin (PCT) and clinical severity scores on patients with CAP in ED.

METHODS

226 consecutive adult patients with CAP admitted in ED of a tertiary teaching hospital were enrolled. Demographic information and clinical parameters including PCT levels were analyzed. CURB65, PSI, SOFA and qSOFA scores were calculated and compared between the severe CAP (SCAP) and non-severe CAP (NSCAP) group or the death and survival group. Receiver-operating characteristic (ROC) curves for 28-day mortality were calculated for each predictor using cut-off values. Logistic regression models and area under the curve (AUC) analysis were performed to compare the performance of predictors.

RESULTS

Fifty-one patients were classified as SCAP and forty-nine patients died within 28days. There was significant difference between either SCAP and NSCAP group or death and survival group in PCT level and CURB65, PSI, SOFA, qSOFA scores (p < 0.001). The AUCs of the PCT and CURB65, PSI, SOFA and qSOFA in predicting SCAP were 0.875, 0.805, 0.810, 0.852 and 0.724, respectively. PCT is superior in predicting SCAP and the models combining PCT and SOFA demonstrated superior performance to those of PCT or the CAP severity score alone. The AUCs of the PCT and CURB65, PSI, SOFA and qSOFA in predicting 28-day mortality were 0.822, 0.829, 0.813, 0.913 and 0.717, respectively. SOFA achieved the highest AUC and the combination of PCT and SOFA had the highest superiority over other combinations in predicting 28-day mortality.

CONCLUSION

Serum PCT is a valuable single predictor for SCAP. SOFA is superior in prediction of 28-day mortality. Combination of PCT and SOFA could improve the performance of single predictors. More further studies with larger sample size are warranted to validate our results.