Machine learning-extended sPESI for 1-year mortality prediction in pulmonary embolism

Key Points

• This research aims to improve 1-year mortality predictions in pulmonary embolism using a machine learning-extended sPESI framework.
• Utilized machine learning algorithms to analyze data from pulmonary embolism cases.
• Focused on physiological indicators from the patient's initial presentation.
• Developed a risk stratification model to assess long-term mortality risk.
• The machine learning model provided enhanced accuracy in predicting 1-year mortality.
• Demonstrated the ability to capture both acute and long-term health vulnerabilities.
• Indicated that individualized patient management could improve outcomes.