code for NSQIP project, Prescriptive Cluster-Dependent Support Vector Machines with an Application to Reducing Hospital Readmissions.
Discover the American College of Surgeons National Surgical Quality Improvement Program® (ACS NSQIP®). ACS NSQIP is the leading nationally validated, risk-adjusted, outcomes-based program to measure and improve the quality of surgical care in the private sector. ACS NSQIP has the tools, training, customization options and, most importantly, data, to keep your hospital ahead of the curve.
If you find it useful, please cite our paper as follows:
@inproceedings{wang2019prescriptive,
title={Prescriptive Cluster-Dependent Support Vector Machines with an Application to Reducing Hospital Readmissions},
author={Wang, Taiyao and Paschalidis, Ioannis Ch},
booktitle={2019 18th European Control Conference (ECC)},
pages={1182--1187},
year={2019},
organization={IEEE}
}
@article{bertsimas2020prescriptive,
title={Prescriptive analytics for reducing 30-day hospital readmissions after general surgery},
author={Bertsimas, Dimitris and Li, Michael Lingzhi and Paschalidis, Ioannis Ch and Wang, Taiyao},
journal={PloS one},
volume={15},
number={9},
pages={e0238118},
year={2020},
publisher={Public Library of Science San Francisco, CA USA}
}
@phdthesis{wang2020data,
title={Data analytics and optimization methods in biomedical systems: from microbes to humans},
author={Wang, Taiyao},
year={2020}
}
RF+XGBOOST
GIT_LIBLINEAR4surgery.m based on plotroc_liblinear.m + liblinear
[L2LR, L1LR, L2L1 SVM, L1L2 SVM]