𝔖 Bobbio Scriptorium
✦   LIBER   ✦

On the misuses of artificial neural networks for prognostic and diagnostic classification in oncology

✍ Scribed by Guido Schwarzer; Werner Vach; Martin Schumacher

Publisher
John Wiley and Sons
Year
2000
Tongue
English
Weight
210 KB
Volume
19
Category
Article
ISSN
0277-6715

No coin nor oath required. For personal study only.

✦ Synopsis

The application of arti"cial neural networks (ANNs) for prognostic and diagnostic classi"cation in clinical medicine has become very popular. In particular, feed-forward neural networks have been used extensively, often accompanied by exaggerated statements of their potential. In this paper, the essentials of feed-forward neural networks and their statistical counterparts (that is, logistic regression models) are reviewed. We point out that the uncritical use of ANNs may lead to serious problems, such as the "tting of implausible functions to describe the probability of class membership and the underestimation of misclassi"cation probabilities. In applications of ANNs to survival data, further di$culties arise. Finally, the results of a search in the medical literature from 1991 to 1995 on applications of ANNs in oncology and some important common mistakes are reported. It is concluded that there is no evidence so far that application of ANNs represents real progress in the "eld of diagnosis and prognosis in oncology.

πŸ“œ SIMILAR VOLUMES

Focusing on one component each timeβ€”comp
Focusing on one component each timeβ€”comparison of single and multiple component prediction algorithms in artificial neural networks for x-ray fluorescence analysis
✍ Liqiang Luo; Ang Ji; Guangzu Ma; Changlin Guo πŸ“‚ Article πŸ“… 1998 πŸ› John Wiley and Sons 🌐 English βš– 438 KB πŸ‘ 2 views

An algorithm of single component prediction based on backward error propagation is proposed, in which only one component concentration in a multivariate system is predicted each time. The algorithm was compared with a multiple component prediction model. In general, the predictive accuracy of the si

Use of artificial neural networks in eva
Use of artificial neural networks in evaluating prognostic factors determining the response to dendritic cells pulsed with PSMA peptides in prostate cancer patients
✍ Murphy, G.P.; Snow, P.; Simmons, S.J.; Tjoa, B.A.; Rogers, M.K.; Brandt, J.; Hea πŸ“‚ Article πŸ“… 2000 πŸ› John Wiley and Sons 🌐 English βš– 138 KB πŸ‘ 2 views

## BACKGROUND. Our purpose was to compare the importance of over 22 measurements used in evaluating the clinical responses of patients with metastatic or locally recurrent prostate cancer, treated by dendritic cell (DC) infusions with prostate-specific membrane antigen (PSMA) peptides. METHODS. Art