Peng Xuefeng, Ding Yi, Wihl David, Gottesman Omer, Komorowski Matthieu, Lehman Li-Wei H, Ross Andrew, Faisal Aldo, Doshi-Velez Finale
Harvard University, Paulson School of Engineering and Applied Sciences, Cambridge, MA.
Harvard University, T.H. Chan School of Public Health, Cambridge, MA.
AMIA Annu Symp Proc. 2018 Dec 5;2018:887-896. eCollection 2018.
Sepsis is the leading cause of mortality in the ICU. It is challenging to manage because individual patients respond differently to treatment. Thus, tailoring treatment to the individual patient is essential for the best outcomes. In this paper, we take steps toward this goal by applying a mixture-of-experts framework to personalize sepsis treatment. The mixture model selectively alternates between neighbor-based (kernel) and deep reinforcement learning (DRL) experts depending on patient's current history. On a large retrospective cohort, this mixture-based approach outperforms physician, kernel only, and DRL-only experts.
脓毒症是重症监护病房（ICU）死亡的主要原因。由于个体患者对治疗的反应不同，因此管理起来具有挑战性。因此，根据个体患者的情况量身定制治疗方案对于实现最佳治疗效果至关重要。在本文中，我们通过应用专家混合框架来个性化脓毒症治疗，朝着这一目标迈出了步伐。混合模型根据患者当前的病史在基于邻居（内核）的专家和深度强化学习（DRL）专家之间进行选择性切换。在一个大型回顾性队列中，这种基于混合的方法优于医生、仅使用内核的专家和仅使用DRL的专家。
