3 papers
cs.LG2023
Counterfactual Explanations via Locally-guided Sequential Algorithmic Recourse
Edward A. Small, Jeffrey N. Clark, Christopher J. McWilliams +4
Counterfactuals operationalised through algorithmic recourse have become a powerful tool to make artificial intelligence systems explainable. Conceptually, given an individual clas…
cs.HC2023
Strategies for engaging clinical participants in the co-design of software for healthcare domains
Marceli Wac, Raul Santos-Rodriguez, Chris McWilliams +1
Co-design is an effective method for designing software, but implementing it within the clinical setting comes with a set of unique challenges. This makes recruitment and engagemen…
cs.LG2023
Identification, explanation and clinical evaluation of hospital patient subtypes
Enrico Werner, Jeffrey N. Clark, Ranjeet S. Bhamber +5
We present a pipeline in which unsupervised machine learning techniques are used to automatically identify subtypes of hospital patients admitted between 2017 and 2021 in a large U…