University of Twente Student Theses
As of Friday, 8 August 2025, the current Student Theses repository is no longer available for thesis uploads. A new Student Theses repository will be available starting Friday, 15 August 2025.
External validation of the INFLUENCE 3.0 model on data from UZ Leuven for 5-year risk estimation of breast cancer recurrence
Grimberg, C.L. (2025) External validation of the INFLUENCE 3.0 model on data from UZ Leuven for 5-year risk estimation of breast cancer recurrence.
Full text not available from this repository.
| Full Text Status: | Access to this publication is restricted |
| Embargo date: | 1 July 2027 |
| Abstract: | Background: Breast cancer surveillance aims to detect locoregional recurrences (LRR) and contralateral breast cancer (CBC), but current strategies are not tailored to individual risk. The INFLUENCE 3.0 model provides personalised risk estimates to support shared decision-making on surveillance. University Hospital UZ Leuven aims to implement this model, but external validation is needed. Methods: Data were used from female breast cancer patients treated curatively at UZ Leuven (2000–2018). After applying exclusion criteria and multiple imputation, the dataset was prepared for compatibility with the INFLUENCE 3.0 model. Calibration was assessed using the Integrated Calibration Index (ICI), E50, E90, and calibration plots. Discrimination was evaluated using the Area Under the Curve (AUC) for cumulative yearly events. Results: The final cohort included 8,548 patients (7,549 non-neoadjuvantly treated; 999 neoadjuvantly treated). Calibration was generally acceptable (ICI and E50 < 0.01), though risks were often overestimated at lower predicted values. Discrimination for LRR was moderate to good (AUC 0.72–0.86 non-NST; >0.82 NST). CBC risk discrimination was poor (AUC ≈ 0.5) in non-NST, but better in NST patients (AUC 0.68–0.88). Conclusion: INFLUENCE 3.0 performed acceptably for LRR risk prediction and may support personalised surveillance. Further model updates are needed to improve CBC risk prediction. |
| Item Type: | Essay (Master) |
| Faculty: | TNW: Science and Technology |
| Subject: | 30 exact sciences in general, 44 medicine, 54 computer science |
| Programme: | Health Sciences MSc (66851) |
| Link to this item: | https://purl.utwente.nl/essays/107252 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page