Abstract

While developments in machine learning led to impressive performance gains on big data, many human subjects data are, in actuality, small and sparsely labeled. Existing methods applied to such data often do not easily generalize to out-of-sample subjects. Instead, models must make predictions on test data that may be drawn from a different distribution, a problem known as zero-shot learning. To address this challenge, we develop an end-to-end framework using a meta-learning approach, which enables the model to rapidly adapt to a new prediction task with limited training data for out-of-sample test data. We use three real-world small-scale human subjects datasets (two randomized control studies and one observational study), for which we predict treatment outcomes for held-out treatment groups. Our model learns the latent treatment effects of each intervention and, by design, can naturally handle multitask …

Metadata

publication

ICHI 2023 - 11th IEEE International Conference on Healthcare Informatics, 2023

year

2023

publication date

2023

authors

Julie Jiang, Kristina Lerman, Emilio Ferrara

link

https://ieeexplore.ieee.org/abstract/document/10337328/

resource_link

https://arxiv.org/pdf/2203.16309

conference

ICHI 2023 - 11th IEEE International Conference on Healthcare Informatics