Fig. 1: The transparency and interpretability for understandable models (TIFU). | npj Digital Medicine

Fig. 1: The transparency and interpretability for understandable models (TIFU).

From: Explainable artificial intelligence for mental health through transparency and interpretability for understandability

Fig. 1

The TIFU framework operationalises “explainability” by focusing on how a model can be made understandable (to a user) as a function of transparency and interpretability (both definitions are elaborated in the main text). Algorithms and models will differentially satisfy these requirements and we show the example of logistic regression (in green, at the top of the diagram) as exemplifying a transparent and interpretable model.

Back to article page