Women are significantly less likely to meet device IFU criterion for EVAR. Aortic neck criteria and iliac access are important for men and women, but more women than men fail to meet IFU criterion. Devices that accommodate shorter infrarenal AAA neck length will have the greatest impact on expanding on-label EVAR regardless of gender. Lower profile devices and those that accommodate higher neck angulation are expected to expand EVAR eligibility further for women. EVAR eligibility is unlikely to be lost as AAAs enlarge to 5.5 cm in women and 6.5 cm in men. Observation of small AAAs until they reach the standard threshold size for repair should not compromise EVAR eligibility.

State abstraction can give rise to models of environments that are both compressed and useful, thereby enabling efficient sequential decision making. In this work, we offer the first formalism and analysis of the trade-off between compression and performance made in the context of state abstraction for Apprenticeship Learning. We build on Rate-Distortion theory, the classic Blahut-Arimoto algorithm, and the Information Bottleneck method to develop an algorithm for computing state abstractions that approximate the optimal tradeoff between compression and performance. We illustrate the power of this algorithmic structure to offer insights into effective abstraction, compression, and reinforcement learning through a mixture of analysis, visuals, and experimentation.

No abstract

No abstract