Skip to main navigation Skip to search Skip to main content

Evaluating LIME and SHAP Under Class Imbalance: A Lung Cancer Prediction Case Study Using CPRD Data

  • Teena Rai*
  • , Jun He
  • , Jaspreet Kaur
  • , Yuan Shen
  • , Mufti Mahmud
  • , David J. Brown
  • , Emma O’Dowd
  • , David R. Baldwin
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

The importance of Explainable Artificial Intelligence (XAI) in medical research has become increasingly evident, especially with regulations such as the EU AI Act mandating its use. XAI techniques such as LIME and SHAP have been primarily used as tools for interpreting machine learning (ML) models used in disease risk prediction, particularly when analysing tabular Electronic Health Record (EHR) data to identify the top k important features. Although these techniques are widely adopted, their evaluation remains limited. This study uses Clinical Practice Research Datalink (CPRD) data to predict lung cancer risk, highlighting the obstacles posed by highly imbalanced datasets when applying these XAI techniques. By analysing training datasets with varying percentage of lung cancer cases, we assess the consistency of explanations generated by LIME and SHAP across different ML models relative to those trained on a balanced dataset. Our findings reveal that as class imbalance increases, the consistency of feature rankings produced by the same model across different training sets decreases. This finding highlights the practical challenges of implementing XAI techniques in healthcare, particularly in handling data imbalance and the careful application of balancing strategies in risk prediction contexts.

Original languageEnglish
Title of host publicationExplainable Artificial Intelligence and Process Mining Applications for Healthcare - 4th International Workshop, XAI-Healthcare 2025, and 2nd International Workshop, PM4H 2025, Proceedings
EditorsJose M. Juarez, Denisse Kim, Carlos Fernandez-Llatas, Owen Johnson, Primoz Kocbek, Gregor Štiglic, Niels Martin, Jorge Munoz-Gama
PublisherSpringer Science and Business Media Deutschland GmbH
Pages35-39
Number of pages5
ISBN (Print)9783032215130
DOIs
StatePublished - 2026
Event4th International Workshop on eXplainable Artificial Intelligence in Healthcare, XAI-Healthcare 2025, and 2nd International Workshop on Process Mining Applications for Healthcare, PM4H 2025 - Pavia, Italy
Duration: 26 Jun 2025 → 26 Jun 2025

Publication series

NameCommunications in Computer and Information Science
Volume2749 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference4th International Workshop on eXplainable Artificial Intelligence in Healthcare, XAI-Healthcare 2025, and 2nd International Workshop on Process Mining Applications for Healthcare, PM4H 2025
Country/TerritoryItaly
CityPavia
Period26/06/25 → 26/06/25

Bibliographical note

Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

  1. SDG 3 - Good Health and Well-being
    SDG 3 Good Health and Well-being

Keywords

  • CPRD
  • LIME
  • SHAP
  • class imbalance
  • consistency
  • evaluation
  • imbalanced data
  • stability

ASJC Scopus subject areas

  • General Computer Science
  • General Mathematics

Fingerprint

Dive into the research topics of 'Evaluating LIME and SHAP Under Class Imbalance: A Lung Cancer Prediction Case Study Using CPRD Data'. Together they form a unique fingerprint.

Cite this