Development, validation, and clinical utility of risk prediction models for cancer-associated venous thromboembolism: A retrospective and prospective cohort study
In this study, the CA-VTE risk prediction models developed in seven survival ML algorithms outperformed Khorana Score. Combining with D-dimer can improve model performance. Applying the nomogram based on the optimal COX_DD model allows oncology nurse to reassess CA-VTE risk once a week. The prediction models developed using survival ML algorithms in this study may contribute to the dynamic and accurate risk assessment of CA-VTE for cancer survivors.
Authors
- Qian Lü (ORCID: https://orcid.org/0000-0003-2611-3284)
- Weiyin Gao (ORCID: https://orcid.org/0000-0002-9847-7004)
- Bo Jiang (ORCID: https://orcid.org/0000-0001-9446-8875)
- B. Kameswara Rao (ORCID: https://orcid.org/0000-0002-2792-2385)
- Chong Wang (ORCID: https://orcid.org/0000-0002-1515-9669)
- Lihui Liu (ORCID: https://orcid.org/0000-0002-7861-6812)
- Xiao Wang (ORCID: https://orcid.org/0000-0002-4056-0155)
- Shuai Jin (ORCID: https://orcid.org/0000-0003-2469-0563)
- Lichuan Zhang (ORCID: https://orcid.org/0000-0002-2565-5199)
- Baosheng Liang
- Hanping Shi
- Dan Qin
Institutions
- Shanxi Medical University (CN)
- Capital Medical University (CN)
- Peking University (CN)
- Second Hospital of Shanxi Medical University (CN)
- Beijing Shijitan Hospital (CN)
Publication Details
- Journal
- Asia-Pacific Journal of Oncology Nursing
- Published
- 2025-03-23
- DOI
- https://doi.org/10.1016/j.apjon.2025.100691
- Citations
- 4
- Primary Topic
- Venous Thromboembolism Diagnosis and Management
- Type
- article
- Field-Weighted Citation Impact
- 7.48
Funders
- Capital Medical University
- Peking University