Investigating Poor Performance Regions of Black Boxes: LIME-based Exploration in Sepsis Detection

TL;DR

This paper uses LIME to analyze and visualize regions where machine learning models underperform in sepsis detection, aiding clinical decision-making by improving interpretability of black box models.

Contribution

It introduces a LIME-based method to identify and analyze poor performance regions in black box classifiers for sepsis detection, enhancing interpretability in clinical settings.

Findings

Identified regions with high error rates in sepsis classification.

Demonstrated effectiveness on the eICU dataset.

Enhanced interpretability aids clinical decision-making.

Abstract

Interpreting machine learning models remains a challenge, hindering their adoption in clinical settings. This paper proposes leveraging Local Interpretable Model-Agnostic Explanations (LIME) to provide interpretable descriptions of black box classification models in high-stakes sepsis detection. By analyzing misclassified instances, significant features contributing to suboptimal performance are identified. The analysis reveals regions where the classifier performs poorly, allowing the calculation of error rates within these regions. This knowledge is crucial for cautious decision-making in sepsis detection and other critical applications. The proposed approach is demonstrated using the eICU dataset, effectively identifying and visualizing regions where the classifier underperforms. By enhancing interpretability, our method promotes the adoption of machine learning models in clinical practice, empowering informed decision-making and mitigating risks in critical scenarios.