This work considers estimating individual treatment effect (ITE) of organ donations --- with respect to scarcity and quality of match for an organ --- in order to maximize mean life expectancy of a population. Common approaches typically include first-come first-serve, local best patient matching, or most acute. Reviewers were uniformly interested in this application area, and the relative potential of machine learning to improve our collective ability to facilitate organ donations. Additionally, the paper overall is well written and reasoned. I would greatly encourage the authors to take into account feedback from the reviewers. In particular, given grounding in this particular application it is important to elaborate on the potential problems of this approach as well as the likelihood that this will be able to impact existing approaches to assignment. For the latter question, it's likely that in many geographies even an oracle would be dismissed for the perceived equity of existing strategies. This is not a fault of the method, but provides context to readers about the potential impact. Further, toward the point about deferring scope of morality: it is indeed better to acknowledge the complicated nature of this topic, and state assumptions objectively so that the reader can form the appropriate opinion. This is explicitly mentioned in the author response, but it is worth highlighting given the attention given to moral and ethical implications of submissions. NOTE FROM PROGRAM CHAIRS: This paper is given a CONDITIONAL ACCEPT. Using a purely ML-based method to allocate organs raises some clear and substantial ethical concerns. For the camera-ready version, please expand your broader impact statement to include a more thorough discussion of the potential risk of harm, including risk of failure of the method, limitations of learning from outdated historical data, etc. This is a complex question, but it must be addressed for the paper to be suitable for publication. ******************************* Note from Program Chairs: The camera-ready version of this paper has been reviewed with regard to the conditions listed above, and this paper is now fully accepted for publication.