Review Articles

Personalised medicine with multiple treatments: a PhD thesis abstract

Zhilan Lou

School of Statistics, East China Normal University, Shanghai, China

Pages 182-184 | Received 07 Oct. 2017, Accepted 21 Oct. 2017, Published online: 08 Nov. 2017,
  • Abstract
  • Full Article
  • References
  • Citations


When there is substantial heterogeneity of treatment effectiveness for comparative treatment selection, it is crucial to identify individualised treatment rules for patients who have heterogeneous responses to treatment. Existing approaches include directly modelling clinical outcome by defining the optimal treatment rule according to the interactions between treatment and covariates and outcome weighted approach that uses clinical outcome as weights to maximise a target function whose value directly reflects correct treatment assignment. All existing articles of estimating individualised treatment rules are all assuming just two treatment assignments. Here we propose an outcome weighted learning approach that uses a vector hinge loss to extend estimating individualised treatment rules in multi-category treatments case. The consistency of the resulting estimator is shown. We also demonstrate the performance of our approach in simulation studies and a real data analysis.


  1. Foster, J. C., Taylor, J. M., & Ruberg, S. J. (2011). Subgroup identification from randomized clinical trial data. Statistics in Medicine, 30(24), 28672880[Google Scholar]
  2. Lee, Y., Lin, Y., & Wahba, G. (2004). Multicategory support vector machines: Theory and application to the classification of microarray data and satellite radiance data. Journal of the American Statistical Association, 99, 6781[Taylor & Francis Online], [Google Scholar]
  3. Su, X., Tsai, C.-L., Wang, H., Nickerson, D. M., & Li, B. (2009). Subgroup analysis via recursive partitioning. The Journal of Machine Learning Research, 10, 141158[Google Scholar]
  4. Zhao, Y., Zeng, D., Rush, A. J., & Kosorok, M. R. (2012). Estimating individualized treatment rules using outcome weighted learning. Stat, 107(499), 11061118[Taylor & Francis Online], [Google Scholar]
  5. Zhang, B, Tsiatis, A., Davidian, M., Zhang, M., & Laber, E. (2012). Estimating optimal treatment regimes from a classification perspective. Stat, 1, 103114[Google Scholar]