Acceptance of Rules Generated by Machine Learning among Medical Experts

92 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

A Survey of Methods for Explaining Black Box Models (2018, background): “The degree of trust on a model increases if the model is built by respecting constraints of monotonicity given by the users [77, 87, 123].”
Learning Credible Models (2017, background): “This restriction could be probabilistic [16] or monotone in certain arguments identified by experts [2, 23, 33].”
Falling Rule Lists (2014, background): “Even with (what seem like) rather severe constraints on the hypothesis space such as monotonicity or sparsity in the number of leaves and nodes, it still seems that the set of accurate classiﬁers is often large enough so that it contains interpretable classiﬁers (see Holte, 1993).”
Methods and Models for Interpretable Linear Classification (2014, background): “In turn, recent approaches to interpretable predictive modeling have sought to produce models with monotonicity constraints so that the relationship between input variables and the predicted response value matches the views of domain experts [10, 87, 114, 77].”
Comprehensible classification models: a position paper (2014, background): “To avoid the discovery of such rules, in [55], if a nominal attribute takes a value that is indicative of membership in a given”
Nearest Neighbour Classification with Monotonicity Constraints (2008, background): “Pazzani et al.[21], report on an application of rule induction algorithms to early detection of dementia, and prediction of mild mental retardation.”