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.

Worldwide Trends in Registering Real-World Studies at ClinicalTrials.gov: A Cross-Sectional Analysis.

Objective: The purpose of this study was to characterize real-world studies (RWSs) registered at ClinicalTrials.gov to help investigators better conduct relevant research in clinical practice. Methods: A retrospective analysis of 944 studies was performed on February 28, 2023. Results: A total of 944 studies were included. The included studies involved a total of 48 countries. China was the leading country in terms of the total number of registered studies (37.9%, 358), followed by the United States (19.7%, 186). Regarding intervention type, 42.4% (400) of the studies involved drugs, and only 9.1% (86) of the studies involved devices. Only 8.5% (80) of the studies mentioned both the detailed study design type and data source in the "Brief Summary". A total of 49.4% (466) of studies had a sample size of 500 participants and above. Overall, 63% (595) of the studies were single-center studies. A total of 213 conditions were covered in the included studies. One-third of the studies (32.7%, 309) involved neoplasms (or tumors). China and the United States were very different regarding the study of different conditions. Conclusion: Although the pandemic has provided new opportunities for RWSs, the rigor of scientific research still needs to be emphasized. Special attention needs to be given to the correct and comprehensive description of the study design in the Brief Summary of registered studies, thereby promoting communication and understanding. In addition, deficiencies in ClinicalTrials.gov registration data remain prominent.