Prediction models may help to improve patient care and have successfully been developed and deployed in clinical practice. Developing a good prognostic model requires data from many patients. Therefore, data from international cancer registries need to be combined.
This second joint project between the Taiwan Cancer Registry (TCR) and IKNL focusses on developing a prediction model for prostate cancer. Developing a good prognostic model requires data from many patients. Unlike in the Netherlands, prostate cancer in Taiwan is rare (<5500 cases/year). To serve the Taiwanese patient with a well performing prediction model, it may help to combine data from the cancer registries in Taiwan and the Netherlands. Regulations prevent sharing of patient-record data between Taiwan and the Netherlands. The PHT allows for development of prediction models on data distributed in a privacy preserving way.The existing open source PHT (vantage6.ai) implementation between IKNL and the Taiwan Cancer Registry will be used to develop the prediction model.
Expected mid 2020.
Wen-Chung Lee MD PhD
IKNL and TCR
IKNL and TCR
- Lu CL, Wang S, Ji Z, Wu Y, Xiong L, Jiang X, Ohno-Machado L. WebDISCO: a web service for distributed cox model learning without patient-level data sharing. J Am Med Inform. Assoc. 2015;22:1212–1219. doi:10.1093/jamia/ocv083
- Lowrance WT, Scardino PT. Predictive models for newly diagnosed prostate cancer patients. Rev Urol. 2009;11(3):117–126.
- Kerkmeijer LG, Monninkhof EM, van Oort IM, van der Poel HG, de Meerleer G, van Vulpen M. PREDICT: model for prediction of survival in localized prostate cancer. World J Urol. 2016;34(6):789–795. doi:10.1007/s00345-015-1691-4
- Huang CC, Chan SY, Lee WC, Chiang CJ, Lu TP, Cheng HC. Development of a prediction model for breast cancer based on the national cancer registry in Taiwan. Breast Cancer Res. 2019;21:92. doi:10.1186/s13058-019-1172-6
- Keogh RH, Seaman SR, Barrett JK, Taylor-Robinson D, Szczesniak R. Dynamic Prediction of Survival in Cystic Fibrosis: A Landmarking Analysis Using UK Patient Registry Data. Epidemiology. 2019;30:29–37. doi:10.1097/EDE.0000000000000920