Artificial intelligence and bladder cancer arrays.
Non-muscle invasive bladder cancer is a heterogenous disease whose management is dependent upon the risk of progression to muscle invasion. Although the recurrence rate is high, the majority of tumors are indolent and can be managed by endoscopic means alone. The prognosis of muscle invasion is poor...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
2007
|
| _version_ | 1826273586860523520 |
|---|---|
| author | Wild, P Catto, J Abbod, M Linkens, D Herr, A Pilarsky, C Wissmann, C Stoehr, R Denzinger, S Knuechel, R Hamdy, F Hartmann, A |
| author_facet | Wild, P Catto, J Abbod, M Linkens, D Herr, A Pilarsky, C Wissmann, C Stoehr, R Denzinger, S Knuechel, R Hamdy, F Hartmann, A |
| author_sort | Wild, P |
| collection | OXFORD |
| description | Non-muscle invasive bladder cancer is a heterogenous disease whose management is dependent upon the risk of progression to muscle invasion. Although the recurrence rate is high, the majority of tumors are indolent and can be managed by endoscopic means alone. The prognosis of muscle invasion is poor and radical treatment is required if cure is to be obtained. Progression risk in non-invasive tumors is hard to determine at tumor diagnosis using current clinicopathological means. To improve the accuracy of progression prediction various biomarkers have been evaluated. To discover novel biomarkers several authors have used gene expression microarrays. Various statistical methods have been described to interpret array data, but to date no biomarkers have entered clinical practice. Here, we describe a new method of microarray analysis using neurofuzzy modeling (NFM), a form of artificial intelligence, and integrate it with artificial neural networks (ANN) to investigate non-muscle invasive bladder cancer array data (n=66 tumors). We develop a predictive panel of 11 genes, from 2800 expressed genes, that can significantly identify tumor progression (average Logrank p = 0.0288) in the analyzed cancers. In comparison, this panel appears superior to those genes chosen using traditional analyses (average Logrank p = 0.3455) and tumor grade (Logrank, p = 0.2475) in this non-muscle invasive cohort. We then analyze panel members in a new non-muscle invasive bladder cancer cohort (n=199) using immunohistochemistry with six commercially available antibodies. The combination of 6 genes (LIG3, TNFRSF6, KRT18, ICAM1, DSG2 and BRCA2) significantly stratifies tumor progression (Logrank p = 0.0096) in the new cohort. We discuss the benefits of the transparent NFM approach with respect to other reported methods. |
| first_indexed | 2024-03-06T22:30:28Z |
| format | Journal article |
| id | oxford-uuid:581ac3ed-0c8e-4521-98e4-b9990ea6a0d1 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-06T22:30:28Z |
| publishDate | 2007 |
| record_format | dspace |
| spelling | oxford-uuid:581ac3ed-0c8e-4521-98e4-b9990ea6a0d12022-03-26T17:01:09ZArtificial intelligence and bladder cancer arrays.Journal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:581ac3ed-0c8e-4521-98e4-b9990ea6a0d1EnglishSymplectic Elements at Oxford2007Wild, PCatto, JAbbod, MLinkens, DHerr, APilarsky, CWissmann, CStoehr, RDenzinger, SKnuechel, RHamdy, FHartmann, ANon-muscle invasive bladder cancer is a heterogenous disease whose management is dependent upon the risk of progression to muscle invasion. Although the recurrence rate is high, the majority of tumors are indolent and can be managed by endoscopic means alone. The prognosis of muscle invasion is poor and radical treatment is required if cure is to be obtained. Progression risk in non-invasive tumors is hard to determine at tumor diagnosis using current clinicopathological means. To improve the accuracy of progression prediction various biomarkers have been evaluated. To discover novel biomarkers several authors have used gene expression microarrays. Various statistical methods have been described to interpret array data, but to date no biomarkers have entered clinical practice. Here, we describe a new method of microarray analysis using neurofuzzy modeling (NFM), a form of artificial intelligence, and integrate it with artificial neural networks (ANN) to investigate non-muscle invasive bladder cancer array data (n=66 tumors). We develop a predictive panel of 11 genes, from 2800 expressed genes, that can significantly identify tumor progression (average Logrank p = 0.0288) in the analyzed cancers. In comparison, this panel appears superior to those genes chosen using traditional analyses (average Logrank p = 0.3455) and tumor grade (Logrank, p = 0.2475) in this non-muscle invasive cohort. We then analyze panel members in a new non-muscle invasive bladder cancer cohort (n=199) using immunohistochemistry with six commercially available antibodies. The combination of 6 genes (LIG3, TNFRSF6, KRT18, ICAM1, DSG2 and BRCA2) significantly stratifies tumor progression (Logrank p = 0.0096) in the new cohort. We discuss the benefits of the transparent NFM approach with respect to other reported methods. |
| spellingShingle | Wild, P Catto, J Abbod, M Linkens, D Herr, A Pilarsky, C Wissmann, C Stoehr, R Denzinger, S Knuechel, R Hamdy, F Hartmann, A Artificial intelligence and bladder cancer arrays. |
| title | Artificial intelligence and bladder cancer arrays. |
| title_full | Artificial intelligence and bladder cancer arrays. |
| title_fullStr | Artificial intelligence and bladder cancer arrays. |
| title_full_unstemmed | Artificial intelligence and bladder cancer arrays. |
| title_short | Artificial intelligence and bladder cancer arrays. |
| title_sort | artificial intelligence and bladder cancer arrays |
| work_keys_str_mv | AT wildp artificialintelligenceandbladdercancerarrays AT cattoj artificialintelligenceandbladdercancerarrays AT abbodm artificialintelligenceandbladdercancerarrays AT linkensd artificialintelligenceandbladdercancerarrays AT herra artificialintelligenceandbladdercancerarrays AT pilarskyc artificialintelligenceandbladdercancerarrays AT wissmannc artificialintelligenceandbladdercancerarrays AT stoehrr artificialintelligenceandbladdercancerarrays AT denzingers artificialintelligenceandbladdercancerarrays AT knuechelr artificialintelligenceandbladdercancerarrays AT hamdyf artificialintelligenceandbladdercancerarrays AT hartmanna artificialintelligenceandbladdercancerarrays |