student profile: Mr Chongrui Xu


Map

Thesis work

Thesis title: Optimal Feature Selection for the performance of NSCLC survirval analysis Prediction Models

Supervisors: Xiu WANG

Thesis abstract:

�p�Analyze the data after treatment of advanced NSCLC patients to find the optimal feature name and quantity.In this process, the feature selection method has the most critical impact Accuracy. Using Pearson correlation, consensus cluster, cox regression model, compare with Random survirval forest model results for Radiomics data were Concordance index (CI )= 0.71 and 0.69 respectively. The results obtained by adding Immuno and Clinical filtered data are Cox (CI=0.79, Cross validation =0.77) and RSF=(CI=0.71, Cross validation=0.72).However, the cross-validation result for RSF may suffer from highly overfitting in the training sets so there is an unexpected increase after the cross validation. However, the cross-validation result for RSF may suffer from highly overfitting in the training sets so there is an unexpected increase after the cross validation.�/p�

Selected publications

Download citations: PDF RTF Endnote

Conferences

  • Xin, B., Xu, C., Wang, L., Dong, T., Zheng, C., Wang, X. (2018). Integrative Clustering and Supervised Feature Selection for Clinical Applications. 15th International Conference on Control, Automation, Robotics and Vision (ICARCV 2018), Piscataway: Institute of Electrical and Electronics Engineers (IEEE). [More Information]

2018

  • Xin, B., Xu, C., Wang, L., Dong, T., Zheng, C., Wang, X. (2018). Integrative Clustering and Supervised Feature Selection for Clinical Applications. 15th International Conference on Control, Automation, Robotics and Vision (ICARCV 2018), Piscataway: Institute of Electrical and Electronics Engineers (IEEE). [More Information]

Note: This profile is for a student at the University of Sydney. Views presented here are not necessarily those of the University.