Below is a summary of “Clinical features and risk factors for adverse clinical outcomes in central pulmonary embolism using machine learning analysis” by Martinez et al., published in the May 2023 issue of Pulmonology.
Central pulmonary embolism (PE), an independent predictor of thrombolysis in earlier studies, was associated with high thrombotic burden. Further knowledge of the indicators of unfavorable outcome in these patients was required for better risk classification. The investigators sought to identify independent predictors of adverse clinical outcomes in patients with central PE in order to improve risk stratification and management for their study.
This was a large, retrospective, observational, single-center study of hospitalized patients with central PE. Data were collected on patient demographics, comorbidities, clinical features on admission, imaging results, treatment, and outcomes. Utilizing multivariate standard logistic regression and least absolute shrinkage selection operator (LASSO) machine learning logistic regression to identify factors associated with a complex of adverse clinical outcomes such as vasopressor use, ventilator use, and inpatient mortality was analyzed. A sensitivity analysis was also performed.
A total of 654 patients diagnosed with central PE participated in the study. The mean age of patients was 63.1 years, 59% were female and 82% were African American. Composite adverse outcomes occurred in her 18% of patients (n = 115). Several independent predictors of adverse clinical outcome were identified, including elevated serum creatinine (odds ratio). [OR] = 1.37, 95% CI = 1.20–1.57; P. = 0.0001), increased white blood cell (WBC) count (OR = 1.10, 95% CI = 1.05 to 1.15; P. < 0.001), higher simplified pulmonary embolism severity index (sPESI) score (OR = 1.47, 95% CI = 1.18 to 1.84; P. = 0.001), increased serum troponin (OR = 1.26, 95% CI = 1.02–1.56; P. = 0.03), increased respiratory rate (OR = 1.03, 95% CI = 1.0–1.05; P. = 0.02). However, right ventricular dysfunction on imaging and saddle PE location did not predict adverse outcomes.
Several independent predictors of adverse clinical outcome were identified in patients with central PE, including elevated serum creatinine, elevated white blood cell count, elevated sPESI score, elevated serum troponin, and increased respiratory rate. The results of this study provide valuable insights into risk stratification and clinical management of patients with central PE, highlighting the importance of early recognition and appropriate intervention..
sauce: resmedjournal.com/article/S0954-6111(23)00183-X/fulltext
