Prediction of Metastasis in Paragangliomas and Pheochromocytomas Using Machine Learning Models: Explainability Challenges
Open Access
Abstract
One of the main issues with paragangliomas and pheochromocytomas is that these tumors have up to a 20% rate of metastatic disease, which cannot be reliably predicted. While machine learning models hold great promise for enhancing predictive accuracy, their often opaque nature limits trust and adoption in critical fields such as healthcare. Understanding the factors driving predictions is essential not only for validating their reliability but also for enabling their integration into clinical decision-making. In this paper, we propose an architecture that combines data mining, machine learning, and explainability techniques to improve predictions of metastatic disease in these types of cancer and enhance trust in the models. A wide variety of algorithms have been applied for the development of predictive models, with a focus on interpreting their outputs to support clinical insights. Our methodology involves a comprehensive preprocessing phase to prepare the data, followed by the application of classification algorithms. Explainability techniques were integrated to provide insights into the key factors driving predictions. Additionally, a feature selection process was performed to identify the most influential variables and explore how their inclusion affects model performance. The best-performing algorithm, Random Forest, achieved an accuracy of 96.3%, precision of 96.5%, and AUC of 0.963, among other metrics, combining strong predictive capability with explainability that fosters trust in clinical applications.Keywords
This publication has 38 references indexed in Scilit:
- Machine learning approaches for advanced detection of rare genetic disorders in whole-genome sequencingAlexandria Engineering Journal, 2024
- Research progress on the pathogenesis of the SDHB mutation and related diseasesBiomedicine & Pharmacotherapy, 2023
- Prediction of metastatic pheochromocytoma and paraganglioma: a machine learning modelling study using data from a cross-sectional cohortThe Lancet Digital Health, 2023
- How does the model make predictions? A systematic literature review on the explainability power of machine learning in healthcareArtificial Intelligence in Medicine, 2023
- Transparency and the Black Box Problem: Why We Do Not Trust AIPhilosophy & Technology, 2021
- A Systematic Review of Applications of Machine Learning in Cancer Prediction and DiagnosisArchives of Computational Methods in Engineering, 2021
- A clinical prediction model to estimate the metastatic potential of pheochromocytoma/paraganglioma: ASES scoreSurgery, 2018
- Plasma methoxytyramine: A novel biomarker of metastatic pheochromocytoma and paraganglioma in relation to established risk factors of tumour size, location and SDHB mutation statusEuropean Journal of Cancer, 2012
- RNA-Seq: a revolutionary tool for transcriptomicsNature Reviews Genetics, 2009
- The Hallmarks of CancerCell, 2000