High Mean Platelet Volume Associates with In-Hospital Mortality in Severe Pneumonia Patients

Novel pneumonia score based on a machine learning model for predicting mortality in pneumonia patients on admission to the intensive care unit

BACKGROUND

Scores for predicting the long-term mortality of severe pneumonia are lacking. The purpose of this study is to use machine learning methods to develop new pneumonia scores to predict the 1-year mortality and hospital mortality of pneumonia patients on admission to the intensive care unit (ICU).

METHODS

The study population was screened from the MIMIC-IV and eICU databases. The main outcomes evaluated were 1-year mortality and hospital mortality in the MIMIC-IV database and hospital mortality in the eICU database. From the full data set, we separated patients diagnosed with community-acquired pneumonia (CAP) and ventilator-associated pneumonia (VAP) for subgroup analysis. We used common shallow machine learning algorithms, including logistic regression, decision tree, random forest, multilayer perceptron and XGBoost.

RESULTS

The full data set of the MIMIC-IV database contained 4697 patients, while that of the eICU database contained 13760 patients. We defined a new pneumonia score, the "Integrated CCI-APS", using a multivariate logistic regression model including six variables: metastatic solid tumor, Charlson Comorbidity Index, readmission, congestive heart failure, age, and Acute Physiology Score III. The area under the curve (AUC) and accuracy of the integrated CCI-APS were assessed in three data sets (full, CAP, and VAP) using both the test set derived from the MIMIC-IV database and the external validation set derived from the eICU database. The AUC value ranges in predicting 1-year and hospital mortality were 0.784-0.797 and 0.691-0.780, respectively, and the corresponding accuracy ranges were 0.723-0.725 and 0.641-0.718, respectively.

CONCLUSIONS

The main contribution of this study was a benchmark for using machine learning models to build pneumonia scores. Based on the idea of integrated learning, we propose a new integrated CCI-APS score for severe pneumonia. In the prediction of 1-year mortality and hospital mortality, our new pneumonia score outperformed the existing score.

Establishment and Validation of the Risk Nomogram of Poor Prognosis in Patients with Severe Pulmonary Infection Complicated with Respiratory Failure

Objective

To investigate the prognosis of patients with severe pulmonary infection combined with respiratory failure and analyze the influencing factors of prognosis.

Methods

The clinical data of 218 patients with severe pneumonia complicated with respiratory failure were retrospectively analyzed. The risk factors were analyzed by univariate and multivariate logistic regression analyses. The risk nomogram and Bootstrap self-sampling method were used for internal inspection. Calibration curves and receiver operating characteristic (ROC) curve were drawn to assess the predictive ability of the model.

Results

Among 218 patients, 118 (54.13%) cases had a good prognosis and 100 (45.87%) cases had a poor prognosis. Multivariate logistic regression analysis showed that the number of complicated basic diseases ≥5, APACHE II score >20, MODS score >10, PSI score >90, and multi-drug resistant bacterial infection were independent risk factors affecting the prognosis (P<0.05), and the level of Alb was an independent protective factor (P<0.05). The consistency index (C-index) was 0.775, and the Hosmer Lemeshow goodness-of-fit test showed that the model was not significant (P>0.05). The area under the curve (AUC) was 0.813 (95% CI: 0.778~0.895), with the sensitivity of 83.20%, and the specificity of 77.00%.

Conclusion

The risk nomograph model had good discrimination and accuracy in predicting the prognosis of patients with severe pulmonary infection combined with respiratory failure, which may provide a basis for early identification and intervention of patients at clinical risk and improve the prognosis.

Platelet Abnormalities in Children with Laboratory-Confirmed Influenza

BACKGROUND

The role of platelets in the immune response against influenza has been raised, and a diagnostic or prognostic value of platelet parameter abnormalities, including platelet count (PLT), or mean platelet volume (MPV), has been suggested. The study aimed to analyze the prognostic value of platelet parameters in children hospitalized due to laboratory-confirmed influenza.

METHODS

We retrospectively verified the platelet parameters (PLT, MPV, MPV/PLT, and PLT/lymphocyte ratio regarding the influenza complications (acute otitis media, pneumonia, and lower respiratory tract infection-LRTI), and the clinical course (antibiotic treatment, tertiary care transfer, and death).

RESULTS

An abnormal PLT was observed in 84 out of 489 laboratory-confirmed cases (17.2%, 44 thrombocytopaenia cases, and 40 thrombocytoses). Patients' age correlated negatively with PLT (rho = -0.46) and positively with MPV/PLT (rho = 0.44), while MPV was not age-dependent. The abnormal PLT correlated with increased odds of complications (OR = 1.67), including LRTI (OR = 1.89). Thrombocytosis was related to increased odds of LRTI (OR = 3.64), and radiologically/ultrasound-confirmed pneumonia (OR = 2.15), mostly in children aged under 1 year (OR = 4.22 and OR = 3.79, respectively). Thrombocytopaenia was related to antibiotic use (OR = 2.41) and longer hospital stays (OR = 3.03). A lowered MPV predicted a tertiary care transfer (AUC = 0.77), while MPV/PLT was the most versatile parameter in predicting LRTI (AUC = 0.7 in <1 yo), pneumonia (AUC = 0.68 in <1 yo), and antibiotic treatment (AUC = 0.66 in 1-2 yo and AUC = 0.6 in 2-5 yo).

CONCLUSIONS

Platelet parameters, including PLT count abnormalities and MPV/PLT ratio, are related to the increased odds of complications and a more severe disease course, and may add important data in assessing pediatric influenza patients, but should be interpreted cautiously due to age-related specificities.

Relationship of platelet counts, platelet volumes, and Curb-65 scores in the prognosis of COVID-19 patients

OBJECTIVES

This study investigated the relationship between 28-day mortality in patients with COVID-19 pneumonia and the CURB-65 score, platelet count (PLT), mean platelet volume (MPV), and MPV/PLT ratio (MPR).

METHODS

A total of 247 patients with COVID-19 pneumonia who presented to the emergency department between March 15, 2020 and May 15, 2020 were retrospectively analyzed. The age, gender, clinical presentation, history of chronic disease, thoracic computed tomography findings, MPV, PLT, MPR, CURB-65 scores, and 28-day mortality of patients were recorded.

RESULTS

The patients had a mean age of 51 years (IQR: 39-63 years) and 55.5% were females. The most common symptom was cough (30.4% of patients). The most common comorbidity was hypertension (13.4%), 49.8% of the cases showed intermediate involvement, and 7.7% of patients died within the first 28 days. The mean MPV was 9.71 ± 1.15, the mean PLT was 226.68 ± 83.82, and the mean MPR was 0.056 ± 0.12. There were significant correlations of 28-day mortality with the CURB-65 score, MPV, and MPR levels (p = 0.000, p = 0.034, and p = 0.034, respectively). No significant correlation was found between the PLT count and 28-day mortality (p = 0.105).

CONCLUSIONS

In addition to the CURB-65 score, MPV and MPR values can be used to predict 28-day mortality in patients with COVID-19 pneumonia.

Mean platelet volume/platelet count ratio predicts severe pneumonia of COVID-19

Background

Although platelet mean volume/platelet count ratio (MPR) is considered to be a crucial marker of inflammatory and infectious diseases, the relationship between MPR and novel coronavirus infectious disease 2019 (COVID‐19) remains unclear.

Methods

In this retrospective study, 85 patients with confirmed COVID‐19 were enrolled and divided into low and high MPR group. Data from repeated measures were compared by the generalized estimating equations. Cox regression analyses were performed to assess the impact of MPR on the incidence of severe pneumonia (SP), with inverse probability of treatment weighting (IPTW) used to reduce confounding bias. The primary outcome is the incidence of SP of COVID‐19.

Results

During follow‐up, 17 (20.0%) patients were developed to SP. Compared with mild patients, patients with SP developed showed a higher MPR level at baseline, day 1, day 2, and day 3 after admission (P = .005, P = .015, P = .009, and P = .032, respectively). Kaplan‐Meier method showed a higher incidence of SP in the high MPR group than the low MPR group (log‐rank test = 10.66, P = .001). After adjustment, high MPR was associated with an elevated incidence of SP (HR, 5.841, 95% CI, 1.566‐21.791, P = .009). The IPTW method also suggested that MPR was a significant factor related to the incidence of SP (HR, 8.337, 95% CI, 4.045‐17.182, P < .001).

Conclusion

High MPR level is an independent risk factor for severe pneumonia in patients with COVID‐19.