Uncertainty-aware INVASE: Enhanced Breast Cancer Diagnosis Feature Selection

TL;DR

This paper introduces an uncertainty-aware version of INVASE that uses Gaussian distributions to quantify confidence, significantly reducing the number of queries needed for accurate breast cancer diagnosis.

Contribution

The paper proposes an enhanced INVASE model with uncertainty quantification modules, improving feature selection efficiency in healthcare diagnostics.

Findings

Reduces queries from nearly 100% to 20% for accurate predictions.

Effectively eliminates predictive bias in breast cancer diagnosis.

Provides open-source implementation and tutorial.

Abstract

In this paper, we present an uncertainty-aware INVASE to quantify predictive confidence of healthcare problem. By introducing learnable Gaussian distributions, we lever-age their variances to measure the degree of uncertainty. Based on the vanilla INVASE, two additional modules are proposed, i.e., an uncertainty quantification module in the predictor, and a reward shaping module in the selector. We conduct extensive experiments on UCI-WDBC dataset. Notably, our method eliminates almost all predictive bias with only about 20% queries, while the uncertainty-agnostic counterpart requires nearly 100% queries. The open-source implementation with a detailed tutorial is available at https://github.com/jx-zhong-for-academic-purpose/Uncertainty-aware-INVASE/blob/main/tutorialinvase%2B.ipynb.