Interpreting Inflammation Prediction Model via Tag-based Cohort Explanation

TL;DR

This paper introduces a novel cohort explanation framework for machine learning models in nutrition science, using tag-based clusters to improve interpretability and trust in inflammation prediction models.

Contribution

The paper presents a new method for cohort explanation based on local feature importance, providing intermediate-level insights that align with domain knowledge.

Findings

Framework generates reliable, interpretable cohort explanations.

Cohort explanations match domain knowledge in inflammation prediction.

Method enhances understanding of complex models in nutrition science.

Abstract

Machine learning is revolutionizing nutrition science by enabling systems to learn from data and make intelligent decisions. However, the complexity of these models often leads to challenges in understanding their decision-making processes, necessitating the development of explainability techniques to foster trust and increase model transparency. An under-explored type of explanation is cohort explanation, which provides explanations to groups of instances with similar characteristics. Unlike traditional methods that focus on individual explanations or global model behavior, cohort explainability bridges the gap by providing unique insights at an intermediate granularity. We propose a novel framework for identifying cohorts within a dataset based on local feature importance scores, aiming to generate concise descriptions of the clusters via tags. We evaluate our framework on a food-based inflammation prediction model and demonstrated that the framework can generate reliable explanations that match domain knowledge.