Paper Info
Title
An artificial neural network for analysing the survival of patients with colorectal cancer
Abstract
An internet/web based artificial neural network has been developed for use by practicing clinical oncologists and medical researchers as part of a programme to aid decision making and eventually, the management and treatment of individual patients with colorectal cancer. We have configured and implemented a Partial Likelihood Artificial Neural Network (PLANN) and trained it to predict cancer related survival in patients with confirmed colorectal cancer using a database provided by the Clinical Resource and Audit Group (CRAG) in Scotland. The reliability of the trained PLANN was evaluated against Kaplan- Meier (KM) actual survival plots and shows close agreement with them. We have applied artificial neural networks (ANNs) and their associated analytical techniques to healthcare, with special reference to patients suffering from common solid cancers. There is increasing complexity in the staging and management of these cancers, requiring specialist, multidisciplinary knowledge, and management. We believe that analytical systems such as these will become more readily available to clinicians with the emergence of web and grid-secure technology, which has the potential to link large clinical and scientific data sets of cancer patients from various sources and institutions. To date, ANNs of varying complexity and types have been used, mainly in clinical research rather than routine clinical oncology. Their usefulness has been investigated in the diagnosis, spread of the disease and prognosis in breast, ovarian, gastrointestinal, bronchial, prostatic and ovarian cancers (1-3). In breast and colorectal cancers, ANNs have been shown to be significantly more accurate in predicting survival than in predicting spread from the primary cancer site (4). To date, there have been no reported studies on the use of ANNs to formulate management plans for the treatment of patients with cancers, and this remains a long- term aim of the current interdisciplinary work by our group of oncologists in Dundee and physicists in Manchester. So far, we have trained the ANN by exposing it to sets of existing data on one type of solid cancer (colorectal), where the clinical outcome of the patients included in the data base is known over a 5-year follow-up period. This paper deals with the verification of the prediction of survival by our web-based system.
Year
Venue
Keywords
2005
ESANN
clinical research,artificial neural network,colorectal cancer,scientific data
Field
DocType
Citations 
Health care,Disease,Audit,Multidisciplinary approach,Computer science,Artificial intelligence,Clinical research,Medical physics,Stage (cooking),Colorectal cancer,Cancer,Machine learning
Conference
0
PageRank 
References 
Authors
0.34
7
6
Name
Order
Citations
PageRank
Rachel Bittern120.76
Alfred Cuschieri293.45
Sergey Dolgobrodov321.10
Robin Marshall420.76
Peter Moore520.76
Robert Steele652.57