Bayesian network structure for predicting local tumor recurrence in rectal cancer patients treated with neoadjuvant chemoradiation followed by surgery

• Published in: Physics and imaging in radiation oncology Vol. 22; pp. 1 - 7
• Main Authors: Osong, Biche, Masciocchi, Carlotta, Damiani, Andrea, Bermejo, Inigo, Meldolesi, Elisa, Chiloiro, Giuditta, Berbee, Maaike, Lee, Seok Ho, Dekker, Andre, Valentini, Vincenzo, Gerard, Jean-Pierre, Rödel, Claus, Bujko, Krzysztof, van de Velde, Cornelis, Folkesson, Joakim, Sainato, Aldo, Glynne-Jones, Robert, Ngan, Samuel, Brændengen, Morten, Sebag-Montefiore, David, van Soest, Johan
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.04.2022; Elsevier
• Subjects: Original
• ISSN: 2405-6316; 2405-6316
• DOI: 10.1016/j.phro.2022.03.002

•Algorithmic-based BN structures are more performant than expert structure.•Algorithmically derived BN structures are comparable to a black-box model.•The alignment of BN structures with clinical processes increases interpretability. Tumor recurrence, a characteristic of malignant tumors, is the biggest concern for rectal cancer survivors. The epidemiology of the disease calls for a pressing need to improve healthcare quality and patient outcomes. Prediction models such as Bayesian networks, which can probabilistically reason under uncertainty, could assist caregivers with patient management. However, some concerns are associated with the standard approaches to developing these structures in medicine. Therefore, this study aims to compare Bayesian network structures that stem from these two techniques. A retrospective analysis was performed on 6754 locally advanced rectal cancer (LARC) patients enrolled in 14 international clinical trials. Local tumor recurrence at 2, 3, and 5-years was defined as the endpoints of interest. Five rectal cancer treating physicians from three countries elicited the expert structure. The algorithmic structure was inferred from the data with the hill-climbing algorithm. Structural performance was assessed with calibration plots and area under the curve values. The area under the curve for the expert structure on the training and validation data was above 0.9 and 0.8, respectively, for all the time points. However, the algorithmic structure had superior predictive performance over the expert structure for all time points of interest. We have developed and internally validated a Bayesian networks structure from experts’ opinions, which can predict the risk of a LARC patient developing a tumor recurrence at 2, 3, and 5 years. Our result shows that the algorithmic-based structures are more performant and less interpretable than expert-based structures.