Local explanations for classification of ventilation data by neural networks

Neural networks (NNs) have great potential to improve individualization of medicine, e.g., through analysis of signals. However, they are generally not interpretable. Understanding NN decisions is crucial, especially in safety-critical domains such as medicine. This work presents a new method to provide local explanations for classifications of signals made by NNs. Our method extends the Sig-LIME explanation method from one-dimensional signals to multidimensional signals by introducing new perturbation techniques. We evaluate the proposed method on an NN that classifies the positive end-expiratory pressure (PEEP) applied by a ventilator. The evaluation shows that the generated explanations are plausible, stable and concise.

DDC Class

620: Engineering

Lizenz

https://creativecommons.org/licenses/by/4.0/

Publication version

publishedVersion

Name

2511_Bogumil_DOI.pdf

Type

Main Article

Size

284.99 KB

Format

Adobe PDF

Options

Local explanations for classification of ventilation data by neural networks