Artificial intelligence in predicting bladder cancer outcome: a comparison of neuro-fuzzy modeling and artificial neural networks.
PURPOSE: New techniques for the prediction of tumor behavior are needed, because statistical analysis has a poor accuracy and is not applicable to the individual. Artificial intelligence (AI) may provide these suitable methods. Whereas artificial neural networks (ANN), the best-studied form of AI,...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
2003
|
| _version_ | 1797069926998999040 |
|---|---|
| author | Catto, J Linkens, D Abbod, M Chen, M Burton, J Feeley, K Hamdy, F |
| author_facet | Catto, J Linkens, D Abbod, M Chen, M Burton, J Feeley, K Hamdy, F |
| author_sort | Catto, J |
| collection | OXFORD |
| description | PURPOSE: New techniques for the prediction of tumor behavior are needed, because statistical analysis has a poor accuracy and is not applicable to the individual. Artificial intelligence (AI) may provide these suitable methods. Whereas artificial neural networks (ANN), the best-studied form of AI, have been used successfully, its hidden networks remain an obstacle to its acceptance. Neuro-fuzzy modeling (NFM), another AI method, has a transparent functional layer and is without many of the drawbacks of ANN. We have compared the predictive accuracies of NFM, ANN, and traditional statistical methods, for the behavior of bladder cancer. EXPERIMENTAL DESIGN: Experimental molecular biomarkers, including p53 and the mismatch repair proteins, and conventional clinicopathological data were studied in a cohort of 109 patients with bladder cancer. For all three of the methods, models were produced to predict the presence and timing of a tumor relapse. RESULTS: Both methods of AI predicted relapse with an accuracy ranging from 88% to 95%. This was superior to statistical methods (71-77%; P < 0.0006). NFM appeared better than ANN at predicting the timing of relapse (P = 0.073). CONCLUSIONS: The use of AI can accurately predict cancer behavior. NFM has a similar or superior predictive accuracy to ANN. However, unlike the impenetrable "black-box" of a neural network, the rules of NFM are transparent, enabling validation from clinical knowledge and the manipulation of input variables to allow exploratory predictions. This technique could be used widely in a variety of areas of medicine. |
| first_indexed | 2024-03-06T22:31:37Z |
| format | Journal article |
| id | oxford-uuid:58792656-1899-47d8-a207-dbc85f509627 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-06T22:31:37Z |
| publishDate | 2003 |
| record_format | dspace |
| spelling | oxford-uuid:58792656-1899-47d8-a207-dbc85f5096272022-03-26T17:03:34ZArtificial intelligence in predicting bladder cancer outcome: a comparison of neuro-fuzzy modeling and artificial neural networks.Journal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:58792656-1899-47d8-a207-dbc85f509627EnglishSymplectic Elements at Oxford2003Catto, JLinkens, DAbbod, MChen, MBurton, JFeeley, KHamdy, F PURPOSE: New techniques for the prediction of tumor behavior are needed, because statistical analysis has a poor accuracy and is not applicable to the individual. Artificial intelligence (AI) may provide these suitable methods. Whereas artificial neural networks (ANN), the best-studied form of AI, have been used successfully, its hidden networks remain an obstacle to its acceptance. Neuro-fuzzy modeling (NFM), another AI method, has a transparent functional layer and is without many of the drawbacks of ANN. We have compared the predictive accuracies of NFM, ANN, and traditional statistical methods, for the behavior of bladder cancer. EXPERIMENTAL DESIGN: Experimental molecular biomarkers, including p53 and the mismatch repair proteins, and conventional clinicopathological data were studied in a cohort of 109 patients with bladder cancer. For all three of the methods, models were produced to predict the presence and timing of a tumor relapse. RESULTS: Both methods of AI predicted relapse with an accuracy ranging from 88% to 95%. This was superior to statistical methods (71-77%; P < 0.0006). NFM appeared better than ANN at predicting the timing of relapse (P = 0.073). CONCLUSIONS: The use of AI can accurately predict cancer behavior. NFM has a similar or superior predictive accuracy to ANN. However, unlike the impenetrable "black-box" of a neural network, the rules of NFM are transparent, enabling validation from clinical knowledge and the manipulation of input variables to allow exploratory predictions. This technique could be used widely in a variety of areas of medicine. |
| spellingShingle | Catto, J Linkens, D Abbod, M Chen, M Burton, J Feeley, K Hamdy, F Artificial intelligence in predicting bladder cancer outcome: a comparison of neuro-fuzzy modeling and artificial neural networks. |
| title | Artificial intelligence in predicting bladder cancer outcome: a comparison of neuro-fuzzy modeling and artificial neural networks. |
| title_full | Artificial intelligence in predicting bladder cancer outcome: a comparison of neuro-fuzzy modeling and artificial neural networks. |
| title_fullStr | Artificial intelligence in predicting bladder cancer outcome: a comparison of neuro-fuzzy modeling and artificial neural networks. |
| title_full_unstemmed | Artificial intelligence in predicting bladder cancer outcome: a comparison of neuro-fuzzy modeling and artificial neural networks. |
| title_short | Artificial intelligence in predicting bladder cancer outcome: a comparison of neuro-fuzzy modeling and artificial neural networks. |
| title_sort | artificial intelligence in predicting bladder cancer outcome a comparison of neuro fuzzy modeling and artificial neural networks |
| work_keys_str_mv | AT cattoj artificialintelligenceinpredictingbladdercanceroutcomeacomparisonofneurofuzzymodelingandartificialneuralnetworks AT linkensd artificialintelligenceinpredictingbladdercanceroutcomeacomparisonofneurofuzzymodelingandartificialneuralnetworks AT abbodm artificialintelligenceinpredictingbladdercanceroutcomeacomparisonofneurofuzzymodelingandartificialneuralnetworks AT chenm artificialintelligenceinpredictingbladdercanceroutcomeacomparisonofneurofuzzymodelingandartificialneuralnetworks AT burtonj artificialintelligenceinpredictingbladdercanceroutcomeacomparisonofneurofuzzymodelingandartificialneuralnetworks AT feeleyk artificialintelligenceinpredictingbladdercanceroutcomeacomparisonofneurofuzzymodelingandartificialneuralnetworks AT hamdyf artificialintelligenceinpredictingbladdercanceroutcomeacomparisonofneurofuzzymodelingandartificialneuralnetworks |