Artificial neural networks estimating survival probability after treatment of choroidal melanoma.

PURPOSE To describe neural networks predicting survival from choroidal melanoma (i.e., any uveal melanoma involving choroid) and to demonstrate the value of entering age, sex, clinical stage, cytogenetic type, and histologic grade into the predictive model. DESIGN Nonrandomized case series. PARTICIPANTS Patients resident in mainland Britain treated by the first author for choroidal melanoma between 1984 and 2006. METHODS A conditional hazard estimating neural network (CHENN) was trained according to the Bayesian formalism with a training set of 1780 patients and evaluated with a test set of another 874 patients. Conditional hazard estimating neural network-generated survival curves were compared with those obtained with Kaplan-Meier analyses. A second model was created with information on chromosome 3 loss, using training and test sets of 211 and 140 patients, respectively. MAIN OUTCOME MEASURES Comparison of CHENN survival curves with Kaplan-Meier analyses. Representative results showing all-cause survival and inferred melanoma-specific mortality, according to age, sex, clinical stage, cytogenetic type, and histologic grade. RESULTS The predictive model plotted a survival curve with 95% credibility intervals for patients with melanoma according to relevant risk factors: age, sex, largest basal tumor diameter, ciliary body involvement, extraocular extension, tumor cell type, closed loops, mitotic rate, and chromosome 3 loss (i.e., monosomy 3). A survival curve for the age-matched general population of the same sex allowed estimation of the melanoma-related mortality. All-cause survival curves generated by the CHENN matched those produced with Kaplan-Meier analysis (Kolmogorov-Smirnov, P<0.05). In older patients, however, the estimated melanoma-related mortality was lower with the CHENN, which accounted for competing risks, unlike Kaplan-Meier analysis. Largest basal tumor diameter was most predictive of mortality in tumors showing histologic and cytogenetic features of high-grade malignancy. Ciliary body involvement and extraocular extension lost significance when cytogenetic and histologic data were included in the model. Patients with a monosomy 3 melanoma of a particular size were predicted to have shorter survival if their tumor showed epithelioid cells and closed loops. CONCLUSIONS Estimation of survival prognosis in patients with choroidal melanoma requires multivariate assessment of age, sex, clinical tumor stage, cytogenetic melanoma type, and histologic grade of malignancy.

[1]  J. Gamel,et al.  Modifications of Callender's classification of uveal melanoma at the Armed Forces Institute of Pathology. , 1983, American journal of ophthalmology.

[2]  B. Damato,et al.  Psychological aspects of cytogenetic testing of uveal melanoma: preliminary findings and directions for future research , 2009, Eye.

[3]  N. Bornfeld,et al.  Prognostic implications of monosomy 3 in uveal melanoma , 1996, The Lancet.

[4]  T. Kivelä,et al.  Very long-term prognosis of patients with malignant uveal melanoma. , 2003, Investigative ophthalmology & visual science.

[5]  J. Gall,et al.  Nucleic acid hybridization to the DNA of cytological preparations. , 1975, Methods in cell biology.

[6]  B. Damato,et al.  Cytogenetics of uveal melanoma: a 7-year clinical experience. , 2007, Ophthalmology.

[7]  Tero Kivelä,et al.  Tumor, node, metastasis classification of malignant ciliary body and choroidal melanoma evaluation of the 6th edition and future directions. , 2005, Ophthalmology.

[8]  Roberto Tagliaferri,et al.  A novel neural network-based survival analysis model , 2003, Neural Networks.

[9]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[10]  Paulo J. G. Lisboa,et al.  Double-blind evaluation and benchmarking of survival models in a multi-centre study , 2007, Comput. Biol. Medicine.

[11]  S. Azen,et al.  Prognosis in uveal melanoma with extrascleral extension. , 1980, Archives of ophthalmology.

[12]  Paulo J. G. Lisboa,et al.  The Use of Artificial Neural Networks in Decision Support in Cancer: a Systematic Review , 2005 .

[13]  T. Hakulinen,et al.  Recent Developments in Relative Survival Analysis , 2007 .

[14]  B. Damato,et al.  Proton beam radiotherapy of choroidal melanoma: the Liverpool-Clatterbridge experience. , 2005, International journal of radiation oncology, biology, physics.

[15]  U. Ringborg,et al.  Uveal melanoma survival in Sweden from 1960 to 1998. , 2003, Investigative ophthalmology & visual science.

[16]  P. Meltzer,et al.  Vascular channel formation by human melanoma cells in vivo and in vitro: vasculogenic mimicry. , 1999, The American journal of pathology.

[17]  D. Hosmer,et al.  A review of goodness of fit statistics for use in the development of logistic regression models. , 1982, American journal of epidemiology.

[18]  J. Overgaard,et al.  Prognostic factors for survival after enucleation for choroidal and ciliary body melanomas. , 2004, Acta ophthalmologica Scandinavica.

[19]  F. Harrell,et al.  Evaluating the yield of medical tests. , 1982, JAMA.

[20]  R. L. Font,et al.  Tumors of the Eye and Ocular Adnexa , 2006 .

[21]  Mordechai Rosner,et al.  Forecasting the prognosis of choroidal melanoma with an artificial neural network. , 2005, Ophthalmology.

[22]  Anthony C Fisher,et al.  Modelling survival after treatment of intraocular melanoma using artificial neural networks and Bayes theorem. , 2004, Physics in medicine and biology.

[23]  D. Ruiter,et al.  Multiplex Ligation-Dependent Probe Amplification for the Detection of Chromosomal Gains and Losses in Formalin-Fixed Tissue , 2005, Diagnostic molecular pathology : the American journal of surgical pathology, part B.

[24]  T. Kivelä,et al.  Microvascular loops and networks in uveal melanoma. , 2004, Canadian journal of ophthalmology. Journal canadien d'ophtalmologie.

[25]  A. Schachat,et al.  The COMS randomized trial of iodine 125 brachytherapy for choroidal melanoma, III: initial mortality findings. COMS Report No. 18. , 2001, Archives of ophthalmology.

[26]  R. Folberg,et al.  The morphologic characteristics of tumor blood vessels as a marker of tumor progression in primary human uveal melanoma: a matched case-control study. , 1992, Human pathology.

[27]  James A. Koziol,et al.  Goodness-of-fit tests for randomly censored data , 1980 .

[28]  B. Hawkins.  The COMS randomized trial of iodine 125 brachytherapy for choroidal melanoma: V. Twelve-year mortality rates and prognostic factors: COMS report No. 28. , 2006, Archives of ophthalmology.