Timezone: »

 
Poster
OrganITE: Optimal transplant donor organ offering using an individual treatment effect
Jeroen Berrevoets · James Jordon · Ioana Bica · alexander gimson · Mihaela van der Schaar

Wed Dec 09 09:00 AM -- 11:00 AM (PST) @ Poster Session 3 #979
in Poster Session 4 »

Transplant-organs are a scarce medical resource. The uniqueness of each organ and the patients' heterogeneous responses to the organs present a unique and challenging machine learning problem. In this problem there are two key challenges: (i) assigning each organ "optimally" to a patient in the queue; (ii) accurately estimating the potential outcomes associated with each patient and each possible organ. In this paper, we introduce OrganITE, an organ-to-patient assignment methodology that assigns organs based not only on its own estimates of the potential outcomes but also on organ scarcity. By modelling and accounting for organ scarcity we significantly increase total life years across the population, compared to the existing greedy approaches that simply optimise life years for the current organ available. Moreover, we propose an individualised treatment effect model capable of addressing the high dimensionality of the organ space. We test our method on real and simulated data, resulting in as much as an additional year of life expectancy as compared to existing organ-to-patient policies.

Keywords: Markov Decision Processes · Optimization · Reinforcement Learning and Planning · Stochastic Optimization

Author Information

Jeroen Berrevoets (University of Cambridge)
James Jordon (University of Oxford)
Ioana Bica (University of Oxford)
alexander gimson (Cambridge University Hospitals)
Mihaela van der Schaar (University of Cambridge)

More from the Same Authors