The Use of Neural Networks and Logistic Regression Analysis for Predicting Pathological Stage in Men Undergoing Radical Prostatectomy: A Population Based Study

Borque, Á.; Sanz, Gerardo; Allepuz, C.; Plaza, L.; Álvarez, Pedro Gil; Rioja, L.A.

doi:10.1016/s0022-5347(05)65651-0

Cited by 28 publications

(12 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In our experience the endoscopic outcome of treating VUR was similar to those in other series treating primary and secondary VUR [16]. Neural networks have been proposed as useful aids for decision‐making in various medical fields [8,11,13,17,18] but they have not yet been applied to VUR.…”

Section: Discussionsupporting

confidence: 72%

The use of neural networks for predicting the result of endoscopic treatment for vesico‐ureteric reflux

et al. 2004

View full text Add to dashboard Cite

the endoscopic findings, and the type of cystography used. In all, 174 cases were used as training samples for the ANN and 87 to validate it. We calculated the sensitivity, specificity, positive (PPV) and negative predictive values (NPV), and the success rate (%) of the system. RESULTSIn the training group the ANN gave a sensitivity of 86.4%, a specificity of 89.5%, a PPV of 76% and NPV of 94%, with a success rate of 88.6%. In the same training group logistic regression (LR) gave respective values of 68.2%, 58.8%, 39%, 82.7% and 61.4%. In the validation group the respective values for the ANN were 71.4%, 81.6%, 58.8%, 88.6% and 78.9%, and in the same validation group the LR gave 64.4%, 50%, 32.1%, 79.2% and 53.9%. The Wilcoxon test confirmed the independence of both methods ( P < 0.001). CONCLUSIONThe ANN is an effective tool for assisting the urologist in indicating and applying endoscopic treatments for VUR.

show abstract

Section: Discussionsupporting

confidence: 72%

The use of neural networks for predicting the result of endoscopic treatment for vesico‐ureteric reflux

et al. 2004

View full text Add to dashboard Cite

show abstract

“…Approaches to KDD include traditional probabilistic techniques, 20 Bayesian analyses 21 and Artificial Intelligence-based (AI) methods. [22][23][24] The central insight is that knowledge emerges not from single analysis, but from replication of the analyses in multiple databases and in other studies. KDD is indifferent to the nature of the variable, which allows social, clinical and biological variables to be aggregated for joint analysis.…”

Section: The Role and Nature Of Models In Understanding Frailtymentioning

confidence: 99%

Some mathematical models of frailty and their clinical implications

Rockwood

Mitnitski

MacKnight

2002

Rev. Clin. Gerontol.

122

View full text Add to dashboard Cite

Frailty is a term that is used often, but commonly not defined precisely. As reviewed elsewhere most definitions share several features. Typically, older adults who are frail have a greater rate of dependence on others, so-called ‘loss of physiological reserve’ and multiple diseases. A dynamic component is often included (e.g. ‘loss of reserve’ and such synonyms as ‘unstable disability’ and ‘impaired homeostenosis’) and is manifest when, over time, patients respond less well to stress, or when those with given levels of frailty have higher rates of adverse outcomes. Still, the imprecision of the term frailty has led some to question its merit, and either to develop alternative means of classification or to stay with the concept of function and disability. Alternative methods of classification are either broadly or narrowly focussed.

show abstract

“…Or A. Borque neural network for predicting pathological stage in men undergoing radical prostatectomy. (22) Prognostic nomograms: are tools that estimate the probability of success in applying a certain treatment to analyze different variables. The most famous and globally applied is Kattan nomogram (23).…”

Section: Defining High Risk Prostate Cancermentioning

confidence: 99%