Gerardo Sanz

The use of neural networks and logistic regression analysis for predicting pathological stage in men undergoing radical prostatectomy: a population based study.

PURPOSE Clinical under staging occurs in 40% to 60% of patients who undergo radical prostatectomy for prostate cancer. To decrease under staging several methods of predicting pathological stage preoperatively have been developed based on statistical logistic regression analysis and neural networks. To our knowledge none has been validated in our homogeneous regional patient population to date. We created logistic regression and neural network models, and implemented and adapted them into our practice. We also compared the 2 methods to determine their value and practicality in daily clinical practice. We present the results of our novel approach for predicting pathological staging of prostate adenocarcinoma. MATERIALS AND METHODS Between 1986 and 1999, 600 white men from the Aragon region of Spain underwent surgery for prostate cancer; of whom 468 were selected for study. Predictive study variables included patient age, clinical stage, biopsy Gleason score and preoperative prostate specific antigen (PSA). The predicted result included in analysis was organ confined or nonorgan confined disease. Data were analyzed by multivariate logistic regression and a supervised neural network (multilayer perceptron and radial basis function). Results were compared by comparing the areas under the receiver operating characteristics curves. RESULTS We generated 5 logistic regression models. The model created with clinical staging, Gleason biopsy score and PSA distributed in 5 categories (p <0.001) with an area under the receiver operating characteristics curve of 0.840 proved to be most predictive of pathological stage. Similarly of the 6 neural network models evaluated the radial basis function model, which included age, clinical stage, Gleason biopsy score and preoperative PSA distributed in 5 categories with an area under the curve of 0.882, proved the most predictive but not superior to the logistic regression model. The difference in the area under the curves in the 2 chosen models was 0.042 (p = 0.1). CONCLUSIONS It is possible to generate useful predictive models of organ confined disease using logistic regression or neural networks with high indexes of clinical and statistical validity. However, using these variables neural networks did not prove to be better than logistic regression analysis. Therefore, better predictive variables must be identified, preferably nonlinear characteristics with respect to the probability of organ confined tumor, to generate better predictive models using neural networks.

Genetic predisposition to early recurrence in clinically localized prostate cancer.

Currently available nomograms to predict preoperative risk of early biochemical recurrence (EBCR) after radical prostatectomy are solely based on classic clinicopathological variables. Despite providing useful predictions, these models are not perfect. Indeed, most researchers agree that nomograms can be improved by incorporating novel biomarkers. In the last few years, several single nucleotide polymorphisms (SNPs) have been associated with prostate cancer, but little is known about their impact on disease recurrence. We have identified four SNPs associated with EBCR. The addition of SNPs to classic nomograms resulted in a significant improvement in terms of discrimination and calibration. The new nomogram, which combines clinicopathological and genetic variables, will help to improve prediction of prostate cancer recurrence.

Asymptotic normality for the counting process of weak records and δ-records in discrete models

Let

Implementing the use of nomograms by choosing threshold points in predictive models: 2012 updated Partin Tables vs a European predictive nomogram for organ-confined disease in prostate cancer.

\{X_n,n\ge1\}

Central limit theorems for the number of records in discrete models

be a sequence of independent and identically distributed random variables, taking non-negative integer values, and call

Stochastic comparisons for general probabilistic cellular automata (

X_n

Stochastic comparisons and couplings for interacting particle systems

a

On geometric records: rate of appearance and magnitude

\delta

Records from stationary observations subject to a random trend

-record if

Central Limit Theorem for the Number of Near-Records

X_n>\max\{X_1,...,X_{n-1}\}+\delta