Quick Search:

uzh logo
Browse by:

Zurich Open Repository and Archive

Maintenance: Tuesday, July the 26th 2016, 07:00-10:00

ZORA's new graphical user interface will be relaunched (For further infos watch out slideshow ZORA: Neues Look & Feel). There will be short interrupts on ZORA Service between 07:00am and 10:00 am. Please be patient.

Permanent URL to this publication: http://dx.doi.org/10.5167/uzh-28865

Catto, J W F; Abbod, M F; Wild, P J; Linkens, D A; Pilarsky, C; Rehman, I; Rosario, D J; Denzinger, S; Burger, M; Stoehr, R; Knuechel, R; Hartmann, A; Hamdy, F C (2009). The application of artificial intelligence to microarray data: identification of a novel gene signature to identify bladder cancer progression. European Urology, 57(3):398-406.

[img] PDF - Registered users only
View at publisher


BACKGROUND: New methods for identifying bladder cancer (BCa) progression are required. Gene expression microarrays can reveal insights into disease biology and identify novel biomarkers. However, these experiments produce large datasets that are difficult to interpret. OBJECTIVE: To develop a novel method of microarray analysis combining two forms of artificial intelligence (AI): neurofuzzy modelling (NFM) and artificial neural networks (ANN) and validate it in a BCa cohort. DESIGN, SETTING, AND PARTICIPANTS: We used AI and statistical analyses to identify progression-related genes in a microarray dataset (n=66 tumours, n=2800 genes). The AI-selected genes were then investigated in a second cohort (n=262 tumours) using immunohistochemistry. MEASUREMENTS: We compared the accuracy of AI and statistical approaches to identify tumour progression. RESULTS AND LIMITATIONS: AI identified 11 progression-associated genes (odds ratio [OR]: 0.70; 95% confidence interval [CI], 0.56-0.87; p=0.0004), and these were more discriminate than genes chosen using statistical analyses (OR: 1.24; 95% CI, 0.96-1.60; p=0.09). The expression of six AI-selected genes (LIG3, FAS, KRT18, ICAM1, DSG2, and BRCA2) was determined using commercial antibodies and successfully identified tumour progression (concordance index: 0.66; log-rank test: p=0.01). AI-selected genes were more discriminate than pathologic criteria at determining progression (Cox multivariate analysis: p=0.01). Limitations include the use of statistical correlation to identify 200 genes for AI analysis and that we did not compare regression identified genes with immunohistochemistry. CONCLUSIONS: AI and statistical analyses use different techniques of inference to determine gene-phenotype associations and identify distinct prognostic gene signatures that are equally valid. We have identified a prognostic gene signature whose members reflect a variety of carcinogenic pathways that could identify progression in non-muscle-invasive BCa.


23 citations in Web of Science®
25 citations in Scopus®
Google Scholar™



1 download since deposited on 29 Jan 2010
0 downloads since 12 months

Detailed statistics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:04 Faculty of Medicine > University Hospital Zurich > Institute of Surgical Pathology
Dewey Decimal Classification:610 Medicine & health
Deposited On:29 Jan 2010 11:03
Last Modified:05 Apr 2016 13:50
Publisher DOI:10.1016/j.eururo.2009.10.029
PubMed ID:19913990

Users (please log in): suggest update or correction for this item

Repository Staff Only: item control page