most citedPredictive and Causal Implications of using Shapley Value for Model Interpretation

11 citations · 11 across the 3 of their papers we have counts for

collaborators
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2020

A novel method for Causal Structure Discovery from EHR data, a demonstration on type-2 diabetes mellitus

Xinpeng Shen, Sisi Ma, Prashanthi Vemuri +3

Introduction: The discovery of causal mechanisms underlying diseases enables better diagnosis, prognosis and treatment selection. Clinical trials have been the gold standard for de…

cs.LG2020★ 11 cited

Predictive and Causal Implications of using Shapley Value for Model Interpretation

Sisi Ma, Roshan Tourani

Shapley value is a concept from game theory. Recently, it has been used for explaining complex models produced by machine learning techniques. Although the mathematical definition…