Materiały źródłowe

• #1 The National Early Warning Score (NEWS) for outcome prediction in emergency department patients with community-acquired pneumonia: results from a 6-year prospective cohort study | BMJ Open

  https://bmjopen.bmj.com/content/6/9/e011021

  Objective To investigate the accuracy of the National Early Warning Score (NEWS) to predict mortality and adverse clinical outcomes for patients with community-acquired pneumonia (CAP) compared to standard risk scores such as the pneumonia severity index (PSI) and CURB-65. […] Our primary outcome was all-cause mortality within 6years of follow-up. Secondary outcomes were adverse clinical outcome defined as intensive care unit (ICU) admission, empyema and unplanned hospital readmission all occurring within 30days after admission. […] 6-year overall mortality was 45.1% (n=417) with a stepwise increase with higher NEWS categories. […] For prediction of ICU admission, NEWS showed moderate discrimination (AUC 0.73) and improved the prognostic accuracy of a regression model, including PSI (AUC from 0.66 to 0.74, p=0.001) and CURB-65 (AUC from 0.64 to 0.73, p=0.015).

• #1 FluA-p score: a novel prediction rule for mortality in influenza A-related pneumonia patients

  https://pmc.ncbi.nlm.nih.gov/articles/PMC7206684/

  The pneumonia severity index (PSI) and the CURB-65 (confusion, urea, respiratory rate, blood pressure, age65years) score have been shown to predict mortality in community-acquired pneumonia. Their ability to predict influenza-related pneumonia, however, is less well-established. […] The 30-day mortality of FluA-p patients was 19.6% (136/693). […] Our results showed that a FluA-p score was easy to derive and that it served as a reliable prediction rule for 30-day mortality in FluA-p patients. The score could also effectively stratify FluA-p patients into relevant risk categories and thereby help treatment providers to make more rational clinical decisions. […] Our study not only assessed several risk factors, but also developed a simple and reliable prediction tool for predicting mortality in patients with FluA-p. Our method showed greater predictive validity than did the common pneumonia severity scores of PSI and CURB-65. […] We developed a simple and reliable prediction rule for 30-day mortality in patients hospitalised with FluA-p. The prediction rule could help clinicians to more accurately assess influenza disease severity.

• #1 Development of a new prognostic model to predict pneumonia outcome using artificial intelligence-based chest radiograph results | Scientific Reports

  https://www.nature.com/articles/s41598-024-65488-1

  This study aimed to develop a new simple and effective prognostic model using artificial intelligence (AI)-based chest radiograph (CXR) results to predict the outcomes of pneumonia. […] Therefore, a new prognostic model incorporating AI-based CXR results along with traditional pneumonia severity score could be a simple and useful tool for predicting pneumonia outcomes in clinical practice. […] In the present study, we showed that a new prognostic score composed of AI-based CXR results improved the prediction of pneumonia prognosis when combined with the previously known pneumonia severity score. […] Our findings showed that the power of predicting the patients prognosis and mortality increased when the consolidation score on CXRs presented by AI was combined with the patients clinical characteristics. […] This study demonstrates that a new prognostic model incorporating AI-based CXR result, along with traditional pneumonia severity scores, could provide a simple and effective method for predicting pneumonia outcomes.

• #1 Open resource of clinical data from patients with pneumonia for the prediction of COVID-19 outcomes via deep learning | Nature Biomedical Engineering

  https://www.nature.com/articles/s41551-020-00633-5

  Data from patients with coronavirus disease 2019 (COVID-19) are essential for guiding clinical decision making, for furthering the understanding of this viral disease, and for diagnostic modelling. […] We show the utility of the database for prediction of COVID-19 morbidity and mortality outcomes using a deep learning algorithm trained with data from 1,170 patients and 19,685 manually labelled CT slices. […] In an independent validation cohort of 351 patients, the algorithm discriminated between negative, mild and severe cases with areas under the receiver operating characteristic curve of 0.944, 0.860 and 0.884, respectively. […] For morbidity outcomes, the area under the curve (AUC) values of HUST-19 are 0.978, 0.921 and 0.931 for predicting negative cases (control), mild or regular (type I) and severe or critically ill (type II) patients, respectively.

• #1 Pneumonia in patients with cirrhosis: risk factors associated with mortality and predictive value of prognostic models | Respiratory Research | Full Text

  https://respiratory-research.biomedcentral.com/articles/10.1186/s12931-018-0934-5

  Cirrhotic patients with pneumonia have a dramatically increased mortality. […] To recognize the risk factors of mortality and to optimize stratification are critical for improving survival rate. […] Patients triggered acute-on-chronic liver failure (ACLF) highly increased mortality (46.4% vs 4.5% for 30-day, 69.6% vs 11.2% for 90-day). […] Age, inappropriate empirical antibiotic therapy, bacteremia, white blood cell count (WBC) and total bilirubin were independent factors for mortality in current study. […] This study found age, bacteremia, WBC, total bilirubin and inappropriate empirical antibiotic therapy were independently associated with increased mortality. […] Pneumonia triggered ACLF remarkably increased mortality. […] CLIF-SOFA was more accurate in predicting mortality than other five prognostic models.

• #1 Predict community-acquired pneumonia outcome using time series data and machine learning | medRxiv

  https://www.medrxiv.org/content/10.1101/2025.03.11.25323764v1.full-text

  Community-acquired pneumonia (CAP) is an acute respiratory condition associated with high mortality in adult populations and is potentially more serious in older patients. Accurate and consistently applied prediction of outcome may contribute to reduce in-hospital mortality. […] Recent literature has shown that machine learning (ML) has the potential to improve outcome prediction, but the sparse and incomplete nature of the data present a challenge for the development of models that can be implemented clinically. […] This approach might represent an opportunity to anticipate adverse outcomes. These results suggest that ML models utilising time series can have sizable impact in the prediction of CAP outcome, from many perspectives: Complementing currently applied scoring systems approaches like CURB65 in hospital settings, prediction of mortality or forecasting the severity of patients from vital signs that have shown correlation with CAP mortality. […] The models presented require further validation and development, although they present important indication for CAP mortality prediction.

• #1 Predicting in-hospital mortality in pneumonia-associated septic shock patients using a classification and regression tree: a nested cohort study | Journal of Intensive Care | Full Text

  https://jintensivecare.biomedcentral.com/articles/10.1186/s40560-018-0335-3

  Pneumonia complicated by septic shock is associated with significant morbidity and mortality. Classification and regression tree methodology is an intuitive method for predicting clinical outcomes using binary splits. We aimed to improve the prediction of in-hospital mortality in patients with pneumonia and septic shock using decision tree analysis. […] Overall mortality (51%) in patients with pneumonia complicated by septic shock is high. Increased time to administration of antimicrobial therapy, Acute Physiology and Chronic Health Evaluation II Score, serum lactate, and age were associated with increased in-hospital mortality. Classification and regression tree methodology offers a simple prognostic model with good performance in predicting in-hospital mortality. […] Time to administration of appropriate antimicrobial therapy remained the most important predictor of in-hospital mortality in this population.

• #1 Predictive Value of IL-6 and PDGF-AA for Short-term Mortality Risk in | IJGM

  https://www.dovepress.com/predictive-value-of-il-6-and-pdgf-aa-for-28-day-mortality-risk-in-crit-peer-reviewed-fulltext-article-IJGM

  Identification of prognostic biomarkers for critical illness are essential to improving mortality in the context of precision medicine. The purpose of this study was to evaluate the prognostic value of interleukin-6 (IL-6) and platelet-derived growth factor AA(PDGF-AA) in predicting 28-day mortality in critically ill patients. […] Among 199 patients, 139 died and 60 survived within 28 days, IL-6 and PDGF-AA levels were higher in the non-survival group. […] This study highlights the importance of monitoring serum levels of IL-6 and PDGF-AA in critically ill patients. Compared with the marker alone, combinations with other conventional risk factors have better predictive values. […] The logistic regression analysis revealed that IL-6 and PDGF-AA were both independent risk factors associated with 28-day mortality. […] We also found that the PDGF-AA level was an independent risk factor for 28-day mortality in critically ill patients. […] Overall, our data showed that serum IL-6 and PDGF-AA levels are significant for the diagnosis and prognosis assessment of critically ill patients.

• #1 Prognostic biomarkers in predicting mortality in respiratory patients with ventilator-associated pneumonia | The Egyptian Journal of Bronchology | Full Text

  https://ejb.springeropen.com/articles/10.1186/s43168-021-00062-1

  Ventilator-associated pneumonia (VAP) is the most common nosocomial infection. The aim of this study is to evaluate prognostic efficiency RDW, NLR, and the Sequential Organ Failure Assessment (SOFA) score for mortality prediction in respiratory patients with VAP. These variables had a good diagnostic performance for mortality prediction AUC 0.811 for SOFA at diagnosis of VAP, 0.777 for RDW, 0.728 for NLR, and 0.840 for combined of NLR and RDW. The combination of the three parameters demonstrated excellent diagnostic performance (AUC 0.889). Consequently, RDW and NLR are simple, yet promising markers for ICU physicians in monitoring the clinical course, assessment of organ dysfunction, and predicting mortality in mechanically ventilated patients. The Sequential Organ Failure Assessment (SOFA) score is a simple and prognostic score that can calculate both the number and the severity of organ dysfunction in six organ systems. Patients with a higher SOFA score mostly have a higher mortality rate. The current study demonstrated that, non-survivors were more likely to be elderly with higher WBC and creatinine and lower albumin without statistical significance. Moreover, non-survivors group had significantly higher RDW and NLR than survivors at the time of VAP diagnosis. The ROC curve analysis to predict in-hospital mortality showed AUC 0.728 for NLR and 0.777 for RDW, 0.764 for SOFA at admission, 0.811 for SOFA at diagnosis of VAP. A positive correlation was found between SOFA score at diagnosis of VAP and NLR, and between SOFA score and RDW. This study assessed 136 patients diagnosed as VAP; the mortality rate was 39.7%. SOFA score helped to predict the severity status and impact of organ failure on the mortality outcome. The highest score can diagnose of highest point of multiorgan dysfunction. The present study showed good predictive discrimination for mortality (AUC, 0.729). The present study has several strengths. To our knowledge, this was the first study that predicts mortality for respiratory patients with VAP by using blood biomarkers either RDW, NLR, or both with good performance. Therefore, this study recommends the use of blood biomarkers with the one of the simplest ICU score (SOFA score) in the rapid diagnosis of critical patients as a daily works in ICU.

• #1 Sepsis Burden in a Major Romanian Emergency Center—An 18-Year Retrospective Analysis of Mortality and Risk Factors

  https://www.mdpi.com/1648-9144/61/5/864

  Pneumonia (OR = 2.08, 95% CI: 1.89–2.28) […] Pneumonia and cirrhosis were the strongest predictors, indicating a more than twofold increased mortality risk (adjusted OR = 2.43, 95% CI: 2.19–2.69 and adjusted OR = 2.32, 95% CI: 1.90–2.85, respectively) […] The in-hospital mortality was significantly associated with the presence of comorbidities. The in-hospital mortality rate was significantly higher among those with cancer (60.7%), cirrhosis (65.95%), chronic kidney disease (62.1%), chronic obstructive pulmonary disease (63.2%), and pneumonia (67.8%) compared to those without these comorbidities.

• #1 Cryptococcosis in Non-HIV Immunocompromised Hosts: Epidemiology, Pathogenesis, and Management | IntechOpen

  https://www.intechopen.com/online-first/1213803

  In cryptococcosis, serum CrAg is now a well-accepted diagnostic biomarker for detecting or confirming cryptococcal infection; like in HIV patients with cryptococcus infection, high titers herald a poor prognosis. […] Regarding cryptococcus meningitis in non-HIV patients, over the years there have been described significant prognostic factors, including low CSF glucose, high CSF lactate, high CSF cryptococcal antigen titer ( or = 1:1024), initial level of consciousness, the presence of seizure, hydrocephalus, and central nervous system vasculitis. […] Non-HIV immunosuppressed hosts have been noted to have a poorer prognosis. […] In a retrospective study that included 302 patients diagnosed with cryptococcosis between 1996 and 2010, mortality was highest in the NHNT group (27%) vs. SOT (14%) and HIV (20%).

• #1

  https://journals.lww.com/annals-of-medicine-and-surgery/fulltext/2025/05000/effectiveness_of_bronchoscopy_assisted.10.aspx

  Patients with lung cancer and impaired cough strength have an increased risk of postoperative respiratory complications. This study aimed to investigate the effectiveness of bronchoscopy-assisted postoperative respiratory management in reducing these complications. Bronchoscopy-assisted postoperative respiratory management was a promising strategy to prevent respiratory complications in patients with lung cancer and impaired cough strength. Our findings challenge the notion that weak airway competence is a contraindication for lung surgery. Early bronchoscopic intervention and diligent evaluation of airway secretions and cough strength offer substantial potential to improve patient outcomes. Weak cough strength and moderate-to-abundant secretions are strong predictors of unsuccessful extubation in critically ill patients following a spontaneous breathing trial. Our study successfully applied the airway competence assessment model to guide respiratory management in the immediate postoperative phase in patients with lung cancer. Our study highlighted the efficacy of bronchoscopy-assisted postoperative respiratory management as a successful strategy to mitigate postoperative respiratory complications in patients with lung cancer and impaired cough strength.

• #2 Predict community-acquired pneumonia outcome using time series data and machine learning | medRxiv

  https://www.medrxiv.org/content/10.1101/2025.03.11.25323764v1

  Community-acquired pneumonia (CAP) is an acute respiratory condition associated with high mortality in adult populations and is potentially more serious in older patients. Accurate and consistently applied prediction of outcome may contribute to reduce in-hospital mortality. […] Recent literature has shown that machine learning (ML) has the potential to improve outcome prediction, but the sparse and incomplete nature of the data present a challenge for the development of models that can be implemented clinically. […] This approach might represent an opportunity to anticipate adverse outcomes. These results suggest that ML models utilising time series can have sizable impact in the prediction of CAP outcome, from many perspectives: Complementing currently applied scoring systems approaches like CURB65 in hospital settings, prediction of mortality or forecasting the severity of patients from vital signs that have shown correlation with CAP mortality. The models presented require further validation and development, although they present important indication for CAP mortality prediction.

• #2 The National Early Warning Score (NEWS) for outcome prediction in emergency department patients with community-acquired pneumonia: results from a 6-year prospective cohort study | BMJ Open

  https://bmjopen.bmj.com/content/6/9/e011021

  NEWS provides additional prognostic information with regard to risk of ICU admission and complications and thereby improves traditional clinical-risk scores in the management of patients with CAP in the ED setting. […] This first study evaluating NEWS in a large population with CAP from a multicentre study with a 6-year follow-up has three key findings. First, NEWS is a moderate predictor for adverse clinical outcomes, particularly ICU admission, and to a lesser degree for empyema in patients presenting with CAP to the ED. […] Second, NEWS improves the PSI and CURB-65 for prediction of ICU admission. […] Third, although NEWS is associated with mortality, this score has a lower prognostic performance compared to standard CAP scores and did not improve their performance. […] We found NEWS to provide additional prognostic information with regard to risk of ICU admission and empyema, thereby improving traditional clinical CAP risk scores in the management of patients in the ED setting.

• #2 Development of a new prognostic model to predict pneumonia outcome using artificial intelligence-based chest radiograph results

  https://pmc.ncbi.nlm.nih.gov/articles/PMC11193777/

  This study aimed to develop a new simple and effective prognostic model using artificial intelligence (AI)-based chest radiograph (CXR) results to predict the outcomes of pneumonia. […] Therefore, a new prognostic model incorporating AI-based CXR results along with traditional pneumonia severity score could be a simple and useful tool for predicting pneumonia outcomes in clinical practice. […] In the present study, we showed that a new prognostic score composed of AI-based CXR results improved the prediction of pneumonia prognosis when combined with the previously known pneumonia severity score. […] Our findings showed that the power of predicting the patients prognosis and mortality increased when the consolidation score on CXRs presented by AI was combined with the patients clinical characteristics. […] In conclusion, our study demonstrates that a new prognostic model incorporating AI-based CXR result, along with traditional pneumonia severity scores, could provide a simple and effective method for predicting pneumonia outcomes.

• #2 Pneumonia in patients with cirrhosis: risk factors associated with mortality and predictive value of prognostic models | Respiratory Research | Full Text

  https://respiratory-research.biomedcentral.com/articles/10.1186/s12931-018-0934-5

  The factors that associated with 30- and 90-day mortality were listed in Additional file 2: Table S2. […] Inappropriate empirical antibiotic therapy was critical for predicting 30-days and 90-days mortality. […] Bacteremia was also related to higher mortality. […] CLIF-SOFA in predicting 30-day and 90-day mortality at onset of pneumonia were higher than those of five other predicting models. […] Cirrhosis patients who complicated with pneumonia were at high risks of undesirable prognosis. […] Age, WBC, bacteremia and total bilirubin were significant in affecting outcomes, while appropriate empirical antibiotic therapy was important in improving survival. […] CLIF-SOFA model was superior to other scoring system in predicting 30-day and 90-day mortality.

• #2 Predicting in-hospital mortality in pneumonia-associated septic shock patients using a classification and regression tree: a nested cohort study | Journal of Intensive Care | Full Text

  https://jintensivecare.biomedcentral.com/articles/10.1186/s40560-018-0335-3

  The CART model for predicting mortality in patients with pneumonia and septic shock is depicted in Fig. 1. Variables included within the model were the time to administration of appropriate antimicrobial therapy, APACHE II score, serum lactate, and age. The most important predictor of in-hospital mortality was the time to appropriate antimicrobial therapy. […] In this study, a mechanism for predicting the probability of in-hospital mortality was developed using CART methodology. […] Our study complements previous research by highlighting the importance of early intervention and administration of appropriate antimicrobial therapy to optimize outcomes in patients with septic shock. […] Overall mortality in patients with pneumonia and septic shock is high (51% in the CATSS dataset). Increasing time to appropriate antimicrobial therapy, APACHE II score, serum lactate, and age were significantly associated with in-hospital mortality. CART models offer simple prognostic models with good performance.

• #2 Cryptococcosis in Non-HIV Immunocompromised Hosts: Epidemiology, Pathogenesis, and Management | IntechOpen

  https://www.intechopen.com/online-first/1213803

  On univariate analyses, prognostic factors positively associated with 90-day mortality included cancer (P = 0.018), fever (P = 0.031), altered mental status (P = 0.001), positive blood cultures (P 0.001), and high (1:512) serum CrAg (P = 0.021). […] In multivariable logistic regression analyses, cryptococcemia [odds ratio (OR) 5.09, 95% confidence interval (CI) 2.5410.22; P 0.001], baseline opening pressure of 25 cm H2O (OR 2.93, 95% CI 1.256.88; P = 0.013), and altered mental status (OR 1.96, 95% CI 0.983.91; P = 0.057) were associated with increased odds of mortality. […] Another retrospective study included 28 confirmed cryptococcal infections between 2005 and 2017. […] The case fatality rate was highest among patients with underlying hematologic malignancies (63%), followed by SOT (50%) and HIV patients (20%).

• #3 Pneumonia in patients with cirrhosis: risk factors associated with mortality and predictive value of prognostic models | Respiratory Research | Full Text

  https://respiratory-research.biomedcentral.com/articles/10.1186/s12931-018-0934-5

  Cirrhotic patients with pneumonia have a dramatically increased mortality. […] To recognize the risk factors of mortality and to optimize stratification are critical for improving survival rate. […] Patients triggered acute-on-chronic liver failure (ACLF) highly increased mortality (46.4% vs 4.5% for 30-day, 69.6% vs 11.2% for 90-day). […] Age, inappropriate empirical antibiotic therapy, bacteremia, white blood cell count (WBC) and total bilirubin were independent factors for mortality in current study. […] This study found age, bacteremia, WBC, total bilirubin and inappropriate empirical antibiotic therapy were independently associated with increased mortality. […] Pneumonia triggered ACLF remarkably increased mortality. […] CLIF-SOFA was more accurate in predicting mortality than other five prognostic models.

• #3 Cryptococcosis in Non-HIV Immunocompromised Hosts: Epidemiology, Pathogenesis, and Management | IntechOpen

  https://www.intechopen.com/online-first/1213803

  A 12-year review at a tertiary care center (University of Kentucky HealthCare system) included 114 patients with cryptococcosis; 23 (20.2%) had HIV infection, 11 (9.6%) had transplants (nine patients had SOT and two had stem cell transplants), and 80 (70.2%) were NHNT patients. […] Overall, mortality was 28.1% (32/114), and relapse occurred in 10.5% (12/114) of patients. […] The mortality trend was higher (OR = 2.346, p = 0.287) in the transplant group (45.5%, 5/11) than in the HIV (26.1%, 6/23) and NHNT groups (26.3%, 21/80). […] Chronic liver disease had a large and statistically significant association with mortality on multivariate analysis (OR = 3.583, p = 0.013), which was more pronounced than the HIV or transplant groups.

• #3 Pneumonia in patients with cirrhosis: risk factors associated with mortality and predictive value of prognostic models | Respiratory Research | Full Text

  https://respiratory-research.biomedcentral.com/articles/10.1186/s12931-018-0934-5

  The factors that associated with 30- and 90-day mortality were listed in Additional file 2: Table S2. […] Inappropriate empirical antibiotic therapy was critical for predicting 30-days and 90-days mortality. […] Bacteremia was also related to higher mortality. […] CLIF-SOFA in predicting 30-day and 90-day mortality at onset of pneumonia were higher than those of five other predicting models. […] Cirrhosis patients who complicated with pneumonia were at high risks of undesirable prognosis. […] Age, WBC, bacteremia and total bilirubin were significant in affecting outcomes, while appropriate empirical antibiotic therapy was important in improving survival. […] CLIF-SOFA model was superior to other scoring system in predicting 30-day and 90-day mortality.

• #3 Open resource of clinical data from patients with pneumonia for the prediction of COVID-19 outcomes via deep learning | Nature Biomedical Engineering

  https://www.nature.com/articles/s41551-020-00633-5

  Data from patients with coronavirus disease 2019 (COVID-19) are essential for guiding clinical decision making, for furthering the understanding of this viral disease, and for diagnostic modelling. […] We show the utility of the database for prediction of COVID-19 morbidity and mortality outcomes using a deep learning algorithm trained with data from 1,170 patients and 19,685 manually labelled CT slices. […] In an independent validation cohort of 351 patients, the algorithm discriminated between negative, mild and severe cases with areas under the receiver operating characteristic curve of 0.944, 0.860 and 0.884, respectively. […] For morbidity outcomes, the area under the curve (AUC) values of HUST-19 are 0.978, 0.921 and 0.931 for predicting negative cases (control), mild or regular (type I) and severe or critically ill (type II) patients, respectively.

• #3 Sepsis Burden in a Major Romanian Emergency Center—An 18-Year Retrospective Analysis of Mortality and Risk Factors

  https://www.mdpi.com/1648-9144/61/5/864

  Pneumonia (OR = 2.08, 95% CI: 1.89–2.28) […] Pneumonia and cirrhosis were the strongest predictors, indicating a more than twofold increased mortality risk (adjusted OR = 2.43, 95% CI: 2.19–2.69 and adjusted OR = 2.32, 95% CI: 1.90–2.85, respectively) […] The in-hospital mortality was significantly associated with the presence of comorbidities. The in-hospital mortality rate was significantly higher among those with cancer (60.7%), cirrhosis (65.95%), chronic kidney disease (62.1%), chronic obstructive pulmonary disease (63.2%), and pneumonia (67.8%) compared to those without these comorbidities.

Zobacz więcej