Semi-Supervised Learning to Improve Generalizability of Cancer Associated-Venous Thromboembolism Risk Prediction Models

View Full Paper

Ask AI

Bookmark

Authors

Discussion

Retrospective and prospective cohort study improves risk prediction in cancer patients, suggesting enhanced accuracy.

Models developed using a semi-supervised learning algorithm achieved better predictive performance than traditional methods.
The overall performance of the machine learning models showed AUC values ranging from 0.816 to 0.868, indicating effective prediction capabilities.
Data was gathered from 2100 cancer patients across both retrospective and prospective cohorts for validation purposes.
Findings support the use of advanced techniques for cancer-associated venous thromboembolism risk assessment, allowing for improved patient care.

Jin et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

View Full Paper

Ask AI

Bookmark

Authors

Retrospective and prospective cohort study improves risk prediction in cancer patients, suggesting enhanced accuracy.

Models developed using a semi-supervised learning algorithm achieved better predictive performance than traditional methods.
The overall performance of the machine learning models showed AUC values ranging from 0.816 to 0.868, indicating effective prediction capabilities.
Data was gathered from 2100 cancer patients across both retrospective and prospective cohorts for validation purposes.
Findings support the use of advanced techniques for cancer-associated venous thromboembolism risk assessment, allowing for improved patient care.

Jin et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark