Machine Learning-Based Early Warning System for Predicting Venous Thromboembolism in Lymphoma Patients Undergoing Chemotherapy

Strategic Insights -

Researchers at Chongqing University Cancer Hospital have developed a machine learning-based early warning system to predict venous thromboembolism (VTE) in lymphoma patients undergoing chemotherapy. The system, known as VTE-EWS, uses 12 clinical variables and six machine learning algorithms to identify patients at high risk of VTE. According to a new report, the VTE-EWS demonstrated strong predictive performance, with accuracies ranging from 0.71 to 0.87 and area under the curve (AUC) values from 0.78 to 0.84.

Key Takeaways:

  • The VTE-EWS was developed and validated using data from 1,141 lymphoma patients hospitalized for chemotherapy across four academic medical centers between February 2020 and February 2024.
  • The system selected six key variables, including white blood cell count, D-dimer levels, central venous catheter use, age, chemotherapy cycles, and ECOG performance status, to predict VTE risk visually.
  • Patients with a predicted probability of 0.7 or higher were classified as high-risk.
  • The VTE-EWS identified more high-risk patients and provided greater clinical benefit than the Khorana Score (KS).
  • The system's performance was compared to the KS, and the VTE-EWS showed improved predictive power.

Statistics:

  • 1,141 lymphoma patients were included in the study, with 799 patients from Chongqing University Cancer Hospital and 342 patients from three other centers.
  • The external validation set included 342 patients from three other centers.
  • The VTE-EWS demonstrated strong predictive performance, with accuracies ranging from 0.71 to 0.87 and AUC values from 0.78 to 0.84.
  • 12 clinical variables were used to build the machine learning models.
  • 6 machine learning algorithms were applied to build the VTE-EWS.
  • 6 key variables were selected for the nomogram to predict VTE risk visually.
  • The study found that the VTE-EWS identified more high-risk patients and provided greater clinical benefit than the KS.

Sources:

  • Frontiers in Oncology, 2025;15:1566905
  • Zailin Yang, Tingting Jiang, Xinyi Tang, et al. Development and validation of a machine learning-based early warning system for predicting venous thromboembolism risk in hospitalized lymphoma patients undergoing chemotherapy: a multicenter and retrospective cohort study. Frontiers in Oncology, 2025;15:1566905.
  • Frontiers Media Sa, Avenue Du Tribunal Federal 34, Lausanne, Ch-1015, Switzerland.
  • NewsRx. Reports Summarize Venous Thromboembolism Findings from Chongqing University Cancer Hospital (Development and validation of a machine learning-based early warning system for predicting venous thromboembolism risk in hospitalized lymphoma patients undergoing chemotherapy: a multicenter and retrospective cohort study). Cardiovascular Week, September 15, 2025; p 2936.