Teena Rai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Teena Rai has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Mufti Mahmud
King Fahd University of Petroleum and Minerals
5 shared publications - David Joseph Brown
Nottingham Trent University
4 shared publications - David R. Baldwin
Department of Respiratory Medicine, Nottingham University Hospitals, Nottingham, UK
4 shared publications - Jaspreet Kaur
University of Nottingham
4 shared publications - Jun He
Renmin University of China, Beijing, China
4 shared publications - Yuan Shen
Nottingham Trent University
4 shared publications
Latest Publications
- 2 June 2026
- Published by Springer Nature
- p. 35-39
Evaluating LIME and SHAP Under Class Imbalance: A Lung Cancer Prediction Case Study Using CPRD Data
- 2 June 2026
- Published by Springer Nature
- p. 35-39
Evaluating LIME and SHAP Under Class Imbalance: A Lung Cancer Prediction Case Study Using CPRD Data
- Open Access
- 13 November 2025
- Published by Frontiers Media SA in Frontiers in Artificial Intelligence
- Vol. 8, 1682919
Evaluating XAI techniques under class imbalance using CPRD data
Introduction: The need for eXplainable Artificial Intelligence (XAI) in healthcare is more critical than ever, especially as regulatory frameworks such as the European Union Artificial Intelligence (EU AI) Act mandate transparency in clinical decision support systems. Post hoc XAI techniques such as Local Interpretable Model-Agnostic Explanations (LIME), SHapley Additive exPlanations (SHAP) and Partial Dependence Plots (PDPs) are widely used to interpret Machine Learning (ML) models for disease risk prediction, particularly in tabular Electronic Health Record (EHR) data. However, their reliability under real-world scenarios is not fully understood. Class imbalance is a common challenge in many real-world datasets, but it is rarely accounted for when evaluating the reliability and consistency of XAI techniques. Methods: In this study, we design a comparative evaluation framework to assess the impact of class imbalance on the consistency of model explanations generated by LIME, SHAP, and PDPs. Using UK primary care data from the Clinical Practice Research Datalink (CPRD), we train three ML models: XGBoost (XGB), Random Forest (RF), and Multi-layer Perceptron (MLP), to predict lung cancer risk and evaluate how interpretability is affected under class imbalance when compared against a balanced dataset. To our knowledge, this is the first study to evaluate explanation consistency under class imbalance across multiple models and interpretation methods using real-world clinical data. Results: Our main finding is that class imbalance in the training data can significantly affect the reliability and consistency of LIME and SHAP explanations when evaluated against models trained on balanced data. To explain these empirical findings, we also present a theoretical analysis of LIME and SHAP to understand why explanations change under different class distributions. It is also found that PDPs exhibit noticeable variation between models trained on imbalanced and balanced datasets with respect to clinically relevant features for predicting lung cancer risk. Discussion: These findings highlight a critical vulnerability in current XAI techniques, i.e., their interpretability are significantly affected under skewed class distributions, which is common in medical data and emphasises the importance of consistent model explanations for trustworthy ML deployment in healthcare.
- 13 November 2025
- Published by Frontiers Media SA in Frontiers in Artificial Intelligence
- Vol. 8, 1682919
Open AccessEvaluating XAI techniques under class imbalance using CPRD data
Introduction: The need for eXplainable Artificial Intelligence (XAI) in healthcare is more critical than ever, especially as regulatory frameworks such as the European Union Artificial Intelligence (EU AI) Act mandate transparency in clinical decision support systems. Post hoc XAI techniques such as Local Interpretable Model-Agnostic Explanations (LIME), SHapley Additive exPlanations (SHAP) and Partial Dependence Plots (PDPs) are widely used to interpret Machine Learning (ML) models for disease risk prediction, particularly in tabular Electronic Health Record (EHR) data. However, their reliability under real-world scenarios is not fully understood. Class imbalance is a common challenge in many real-world datasets, but it is rarely accounted for when evaluating the reliability and consistency of XAI techniques. Methods: In this study, we design a comparative evaluation framework to assess the impact of class imbalance on the consistency of model explanations generated by LIME, SHAP, and PDPs. Using UK primary care data from the Clinical Practice Research Datalink (CPRD), we train three ML models: XGBoost (XGB), Random Forest (RF), and Multi-layer Perceptron (MLP), to predict lung cancer risk and evaluate how interpretability is affected under class imbalance when compared against a balanced dataset. To our knowledge, this is the first study to evaluate explanation consistency under class imbalance across multiple models and interpretation methods using real-world clinical data. Results: Our main finding is that class imbalance in the training data can significantly affect the reliability and consistency of LIME and SHAP explanations when evaluated against models trained on balanced data. To explain these empirical findings, we also present a theoretical analysis of LIME and SHAP to understand why explanations change under different class distributions. It is also found that PDPs exhibit noticeable variation between models trained on imbalanced and balanced datasets with respect to clinically relevant features for predicting lung cancer risk. Discussion: These findings highlight a critical vulnerability in current XAI techniques, i.e., their interpretability are significantly affected under skewed class distributions, which is common in medical data and emphasises the importance of consistent model explanations for trustworthy ML deployment in healthcare.
- 1 October 2025
- Published by Springer Nature
- p. 184-199
Explainable Boosting Machines for Lung Cancer Prediction and Explanation
- 1 October 2025
- Published by Springer Nature
- p. 184-199
Explainable Boosting Machines for Lung Cancer Prediction and Explanation
- 21 July 2025
- Published by Springer Nature
- p. 87-108
Decision Tree Models to Select High-Risk Patients for Lung Cancer Screening and Model Interpretability
- 21 July 2025
- Published by Springer Nature
- p. 87-108
Decision Tree Models to Select High-Risk Patients for Lung Cancer Screening and Model Interpretability
- 5 June 2023
- Published by Springer Nature
- p. 35-39
Decision Tree Approaches to Select High Risk Patients for Lung Cancer Screening Based on the UK Primary Care Data
- 5 June 2023
- Published by Springer Nature
- p. 35-39
Decision Tree Approaches to Select High Risk Patients for Lung Cancer Screening Based on the UK Primary Care Data