Predicting Lung Cancer Survival Using Probabilistic Reclassification of TNM Editions With a Bayesian Network
Autor: | Dirk De Ruysscher, Melle Sieswerda, Andre Dekker, Gijs Geleijnse, Mieke J. Aarts, Xander Verbeek, Valery E.P.P. Lemmens, Inigo Bermejo |
---|---|
Přispěvatelé: | Radiotherapie, RS: GROW - R3 - Innovative Cancer Diagnostics & Therapy, MUMC+: BST Staf Overig (9) |
Rok vydání: | 2020 |
Předmět: |
0301 basic medicine
Lung Neoplasms Computer science Machine learning computer.software_genre Backward compatibility 03 medical and health sciences 0302 clinical medicine Carcinoma Non-Small-Cell Lung Original Reports medicine Humans Lung cancer Neoplasm Staging business.industry Probabilistic logic Bayesian network Bayes Theorem General Medicine medicine.disease Prognosis 030104 developmental biology 030220 oncology & carcinogenesis Artificial intelligence business computer SYSTEM |
Zdroj: | JCO Clinical Cancer Informatics JCO Clinical Cancer Informatics, 4, 436-443. American Society of Clinical Oncology |
ISSN: | 2473-4276 |
Popis: | PURPOSE The TNM classification system is used for prognosis, treatment, and research. Regular updates potentially break backward compatibility. Reclassification is not always possible, is labor intensive, or requires additional data. We developed a Bayesian network (BN) for reclassifying the 5th, 6th, and 7th editions of the TNM and predicting survival for non–small-cell lung cancer (NSCLC) without training data with known classifications in multiple editions. METHODS Data were obtained from the Netherlands Cancer Registry (n = 146,084). A BN was designed with nodes for TNM edition and survival, and a group of nodes was designed for all TNM editions, with a group for edition 7 only. Before learning conditional probabilities, priors for relations between the groups were manually specified after analysis of changes between editions. For performance evaluation only, part of the 7th edition test data were manually reclassified. Performance was evaluated using sensitivity, specificity, and accuracy. Two-year survival was evaluated with the receiver operating characteristic area under the curve (AUC), and model calibration was visualized. RESULTS Manual reclassification of 7th to 6th edition stage group as ground truth for testing was impossible in 5.6% of the patients. Predicting 6th edition stage grouping using 7th edition data and vice versa resulted in average accuracies, sensitivities, and specificities between 0.85 and 0.99. The AUC for 2-year survival was 0.81. CONCLUSION We have successfully created a BN for reclassifying TNM stage grouping across TNM editions and predicting survival in NSCLC without knowing the true TNM classification in various editions in the training set. We suggest binary prediction of survival is less relevant than predicted probability and model calibration. For research, probabilities can be used for weighted reclassification. |
Databáze: | OpenAIRE |
Externí odkaz: |