Next Steps in Pneumonia Severity Scores

How to assess survival prognosis in patients hospitalized for community-acquired pneumonia in 2024?

PURPOSE OF REVIEW

Community-acquired pneumonia (CAP) is increasingly recognized as a complex, multisystemic disease with the potential to cause both acute and long-term sequelae, significantly impacting patient mortality rates. In this manuscript, the authors review the current methodologies for assessing mortality risk among CAP patients.

RECENT FINDINGS

The most common prediction scores for ICU care and short-term mortality include Pneumonia Severity Index (PSI), CURB-65, SMART COP, SCAP, and ATS/IDSA criteria. These models have clinical utility in the prediction of short-term mortality, but they have significant limitations in addressing long-term mortality. For patients who are discharged alive from the hospital, we do not have scores to predict long term mortality.

SUMMARY

The development of an optimal prognostic tool for postacute sequelae of CAP is imperative. Such a tool should identify specific populations at increased risk. Moreover, accurately identifying at-risk populations is essential for their inclusion in clinical trials that evaluate potential therapies designed to improve short and long-term clinical outcomes in patients with CAP.

Artificial intelligence for the optimal management of community-acquired pneumonia

PURPOSE OF REVIEW

This timely review explores the integration of artificial intelligence (AI) into community-acquired pneumonia (CAP) management, emphasizing its relevance in predicting the risk of hospitalization. With CAP remaining a global public health concern, the review highlights the need for efficient and reliable AI tools to optimize resource allocation and improve patient outcomes.

RECENT FINDINGS

Challenges in CAP management delve into the application of AI in predicting CAP-related hospitalization risks, and complications, and mortality. The integration of AI-based risk scores in managing CAP has the potential to enhance the accuracy of predicting patients at higher risk, facilitating timely intervention and resource allocation. Moreover, AI algorithms reduce variability associated with subjective clinical judgment, promoting consistency in decision-making, and provide real-time risk assessments, aiding in the dynamic management of patients with CAP.

SUMMARY

The development and implementation of AI-tools for hospitalization in CAP represent a transformative approach to improving patient outcomes. The integration of AI into healthcare has the potential to revolutionize the way we identify and manage individuals at risk of severe outcomes, ultimately leading to more efficient resource utilization and better overall patient care.

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.