Insights from explainable AI in oesophageal cancer team decisions

Thavanesan, Navamayooran; Farahi, Arya; Parfitt, Charlotte; Belkhatir, Zehor; Azim, Tayyaba; Vallejos, Elvira Perez; Walters, Zoë; Ramchurn, Sarvapali; Underwood, Timothy J.; Vigneswaran, Ganesh

Abstract

Background: Clinician-led quality control into oncological decision-making is crucial for optimising patient care. Explainable artificial intelligence (XAI) techniques provide data-driven approaches to unravel how clinical variables influence this decision-making. We applied global XAI techniques to examine the impact of key clinical decision-drivers when mapped by a machine learning (ML) model, on the likelihood of receiving different oesophageal cancer (OC) treatment modalities by the multidisciplinary team (MDT). Methods: Retrospective analysis of 893 OC patients managed between 2010 and 2022 at our tertiary unit, used a random forests (RF) classifier to predict four possible treatment pathways as determined by the MDT: neoadjuvant chemotherapy followed by surgery (NACT + S), neoadjuvant chemoradiotherapy followed by surgery (NACRT + S), surgery-alone, and palliative management. Variable importance and partial dependence (PD) analyses then examined the influence of targeted high-ranking clinical variables within the ML model on treatment decisions as a surrogate model of the MDT decision-making dynamic. Results: Amongst guideline-variables known to determine treatments, such as Tumour-Node-Metastasis (TNM) staging, age also proved highly important to the RF model (16.1 % of total importance) on variable importance analysis. PD subsequently revealed that predicted probabilities for all treatment modalities change significantly after 75 years (p < 0.001). Likelihood of surgery-alone and palliative therapies increased for patients aged 75–85yrs but lowered for NACT/NACRT. Performance status divided patients into two clusters which influenced all predicted outcomes in conjunction with age. Conclusion: XAI techniques delineate the relationship between clinical factors and OC treatment decisions. These techniques identify advanced age as heavily influencing decisions based on our model with a greater role in patients with specific tumour characteristics. This study methodology provides the means for exploring conscious/subconscious bias and interrogating inconsistencies in team-based decision-making within the era of AI-driven decision support.

Citation

Thavanesan, N., Farahi, A., Parfitt, C., Belkhatir, Z., Azim, T., Vallejos, E. P., Walters, Z., Ramchurn, S., Underwood, T. J., & Vigneswaran, G. (2024). Insights from explainable AI in oesophageal cancer team decisions. Computers in Biology and Medicine, 180, Article 108978. https://doi.org/10.1016/j.compbiomed.2024.108978

• Journal Article Type: Article
• Acceptance Date: Jul 31, 2024
• Online Publication Date: Aug 5, 2024
• Publication Date: 2024-09
• Deposit Date: Oct 9, 2024
• Publicly Available Date: Oct 9, 2024
• Journal: Computers in Biology and Medicine
• Print ISSN: 0010-4825
• Electronic ISSN: 1879-0534
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 180
• Article Number: 108978
• DOI: https://doi.org/10.1016/j.compbiomed.2024.108978
• Keywords: Machine learning, Oesophageal cancer, Multidisciplinary teams, Decision-making
• Public URL: https://nottingham-repository.worktribe.com/output/38118229
• Publisher URL: https://www.sciencedirect.com/science/article/pii/S0010482524010631?via%3Dihub