Artificial neural network model for the assessment of lymph node spread in patients with clinically localized prostate cancer

Prostate cancer nomograms and their application in Asian men: a review

Nomograms help to predict outcomes in individual patients rather than whole populations and are an important part of evaluation and treatment decision making. Various nomograms have been developed in malignancies to predict and prognosticate clinical outcomes such as severity of disease, overall survival, and recurrence-free survival. In prostate cancer, nomograms were developed for determining need for biopsy, disease course, need for adjuvant therapy, and outcomes. Most of these predictive nomograms were based on Caucasian populations. Prostate cancer is significantly affected by race, and Asian men have a significantly different racial and genetic susceptibility compared to Caucasians, raising the concern in generalizability of these nomograms. We reviewed the existing literature for nomograms in prostate cancer and their application in Asian men. There are very few studies that have evaluated the applicability and validity of the existing nomograms in these men. Most have found significant differences in the performance in this population. Thus, more studies evaluating the existing nomograms in Asian men or suggesting modifications for this population are required.

A systematic review of the applications of Expert Systems (ES) and machine learning (ML) in clinical urology

BACKGROUND

Testing a hypothesis for 'factors-outcome effect' is a common quest, but standard statistical regression analysis tools are rendered ineffective by data contaminated with too many noisy variables. Expert Systems (ES) can provide an alternative methodology in analysing data to identify variables with the highest correlation to the outcome. By applying their effective machine learning (ML) abilities, significant research time and costs can be saved. The study aims to systematically review the applications of ES in urological research and their methodological models for effective multi-variate analysis. Their domains, development and validity will be identified.

METHODS

The PRISMA methodology was applied to formulate an effective method for data gathering and analysis. This study search included seven most relevant information sources: WEB OF SCIENCE, EMBASE, BIOSIS CITATION INDEX, SCOPUS, PUBMED, Google Scholar and MEDLINE. Eligible articles were included if they applied one of the known ML models for a clear urological research question involving multivariate analysis. Only articles with pertinent research methods in ES models were included. The analysed data included the system model, applications, input/output variables, target user, validation, and outcomes. Both ML models and the variable analysis were comparatively reported for each system.

RESULTS

The search identified n = 1087 articles from all databases and n = 712 were eligible for examination against inclusion criteria. A total of 168 systems were finally included and systematically analysed demonstrating a recent increase in uptake of ES in academic urology in particular artificial neural networks with 31 systems. Most of the systems were applied in urological oncology (prostate cancer = 15, bladder cancer = 13) where diagnostic, prognostic and survival predictor markers were investigated. Due to the heterogeneity of models and their statistical tests, a meta-analysis was not feasible.

CONCLUSION

ES utility offers an effective ML potential and their applications in research have demonstrated a valid model for multi-variate analysis. The complexity of their development can challenge their uptake in urological clinics whilst the limitation of the statistical tools in this domain has created a gap for further research studies. Integration of computer scientists in academic units has promoted the use of ES in clinical urological research.

Diagnosis of Common Headaches Using Hybrid Expert-Based Systems

Background:

Headache is one of the most common forms of medical complaints with numerous underlying causes and many patterns of presentation. The first step for starting the treatment is the recognition stage. In this article, the problem of primary and secondary headache diagnosis is considered, and we evaluate the use of intelligence techniques and soft computing in order to predict the diagnosis of common headaches.

Methods:

A fuzzy expert-based system for the diagnosis of common headaches by Learning-From-Examples (LFE) algorithm is presented, in which Mamdani model was used in fuzzy inference engine using Max–Min as Or–And operators, and the Centroid method was used as defuzzification technique. In addition, this article has analyzed common headache using two classification techniques, and headache diagnosis based on a support vector machine (SVM) and multilayer perceptron (MLP)-based method has been proposed. The classifiers were used to recognize the four types of common headache, namely migraine, tension, headaches as a result of infection, and headaches as a result of increased intra cranial presser.

Results:

By using a dataset obtained from 190 patients, suffering from primary and secondary headaches, who were enrolled from a medical center located in Mashhad, the diagnostic fuzzy system was trained by LFE algorithm, and on an average, 123 pieces of If-Then rules were produced for fuzzy system, and it was observed that the system had the ability of correct recognition by a rate of 85%. Using the headache diagnostic system by MLP- and SVM-based decision support system, the accuracy of classification into four types improved by 88% when using the MLP and by 90% with the SVM classifier. The performance of all methods is evaluated using classification accuracy, precision, sensitivity, and specificity.

Conclusion:

As the linguistic rules may be incomplete when human experts express their knowledge, and according to the proximity of common headache symptoms and importance of early diagnosis, the LFE training algorithm is more effective than human expert system. Favorable results obtained by the implementation and evaluation of the suggested medical decision support system based on the MLP and SVM show that intelligence techniques can be very useful for the recognition of common headaches with similar symptoms.

Risk prediction models for biochemical recurrence after radical prostatectomy using prostate-specific antigen and Gleason score

Many computer models for predicting the risk of prostate cancer have been developed including for prediction of biochemical recurrence (BCR). However, models for individual BCR free probability at individual time-points after a BCR free period are rare. Follow-up data from 1656 patients who underwent laparoscopic radical prostatectomy (LRP) were used to develop an artificial neural network (ANN) to predict BCR and to compare it with a logistic regression (LR) model using clinical and pathologic parameters, prostate-specific antigen (PSA), margin status (R0/1), pathological stage (pT), and Gleason Score (GS). For individual BCR prediction at any given time after operation, additional ANN, and LR models were calculated every 6 months for up to 7.5 years of follow-up. The areas under the receiver operating characteristic (ROC) curve (AUC) for the ANN (0.754) and LR models (0.755) calculated immediately following LRP, were larger than that for GS (AUC: 0.715; P = 0.0015 and 0.001), pT or PSA (AUC: 0.619; P always <0.0001) alone. The GS predicted the BCR better than PSA (P = 0.0001), but there was no difference between the ANN and LR models (P = 0.39). Our ANN and LR models predicted individual BCR risk from radical prostatectomy for up to 10 years postoperative. ANN and LR models equally and significantly improved the prediction of BCR compared with PSA and GS alone. When the GS and ANN output values are combined, a more accurate BCR prediction is possible, especially in high-risk patients with GS ≥7.

Artificial neural networks and prostate cancer--tools for diagnosis and management

Artificial neural networks (ANNs) are mathematical models that are based on biological neural networks and are composed of interconnected groups of artificial neurons. ANNs are used to map and predict outcomes in complex relationships between given 'inputs' and sought-after 'outputs' and can also be used find patterns in datasets. In medicine, ANN applications have been used in cancer diagnosis, staging and recurrence prediction since the mid-1990s, when an enormous effort was initiated, especially in prostate cancer detection. Modern ANNs can incorporate new biomarkers and imaging data to improve their predictive power and can offer a number of advantages as clinical decision making tools, such as easy handling of distribution-free input parameters. Most importantly, ANNs consider nonlinear relationships among input data that cannot always be recognized by conventional analyses. In the future, complex medical diagnostic and treatment decisions will be increasingly based on ANNs and other multivariate models.

Role of pelvic lymph node dissection in prostate cancer treatment

Pelvic lymph node dissection (PLND) is the most accurate and reliable staging procedure for detecting lymph node invasion (LNI) in prostate cancer. Recently, [(11)C]-choline positron emission tomography imaging and magnetic resonance imaging with lymphotropic superpara-magnetic nanoparticles have shown potential for detecting LNI but are still under investigation. The risk of LNI in low-risk groups could be underestimated by use of the current nomograms, which rely on data collected from patients who underwent only limited PLND. Extended PLND (ePLND) shows higher lymph node yield, which leads to the removal of more positive nodes and fewer missed positive nodes. It may be possible to refrain from performing PLND on low-risk patients with a prostate-specific antigen value <10 ng/ml and a biopsy Gleason score ≤6, but the risk of biopsy-related understaging should be kept in mind. Theoretically, meticulous ePLND may also impact prostate cancer survival by clearing low-volume diseases and occult micrometastasis even in pN0. The therapeutic role of PLND in prostate cancer patients is still an open question, especially in individuals with low-risk disease. Patients with intermediate- to high-risk disease are more likely to benefit from ePLND.

Critical review of prostate cancer predictive tools

Prostate cancer is a very complex disease, and the decision-making process requires the clinician to balance clinical benefits, life expectancy, comorbidities and potential treatment-related side effects. Accurate prediction of clinical outcomes may help in the difficult process of making decisions related to prostate cancer. In this review, we discuss attributes of predictive tools and systematically review those available for prostate cancer. Types of tools include probability formulas, look-up and propensity scoring tables, risk-class stratification prediction tools, classification and regression tree analysis, nomograms and artificial neural networks. Criteria to evaluate tools include discrimination, calibration, generalizability, level of complexity, decision analysis and ability to account for competing risks and conditional probabilities. The available predictive tools and their features, with a focus on nomograms, are described. While some tools are well-calibrated, few have been externally validated or directly compared with other tools. In addition, the clinical consequences of applying predictive tools need thorough assessment. Nevertheless, predictive tools can facilitate medical decision-making by showing patients tailored predictions of their outcomes with various alternatives. Additionally, accurate tools may improve clinical trial design.

Epidemiology and statistical methods in prediction of patient outcome

Substantial gaps exist in the data of the assessment of risk and prognosis that limit our understanding of the complex mechanisms that contribute to the greatest cancer epidemic, prostate cancer, of our time. This report was prepared by an international multidisciplinary committee of the World Health Organization to address contemporary issues of epidemiology and statistical methods in prostate cancer, including a summary of current risk assessment methods and prognostic factors. Emphasis was placed on the relative merits of each of the statistical methods available. We concluded that: 1. An international committee should be created to guide the assessment and validation of molecular biomarkers. The goal is to achieve more precise identification of those who would benefit from treatment. 2. Prostate cancer is a predictable disease despite its biologic heterogeneity. However, the accuracy of predicting it must be improved. We expect that more precise statistical methods will supplant the current staging system. The simplicity and intuitive ease of using the current staging system must be balanced against the serious compromise in accuracy for the individual patient. 3. The most useful new statistical approaches will integrate molecular biomarkers with existing prognostic factors to predict conditional life expectancy (i.e. the expected remaining years of a patient's life) and take into account all-cause mortality.

Inventory of prostate cancer predictive tools

PURPOSE OF REVIEW

We created an inventory of current predictive tools available for prostate cancer. This review may serve as an initial step toward a comprehensive reference guide for physicians to locate published nomograms that apply to the clinical decision in question. Using MEDLINE a literature search was performed on prostate cancer predictive tools from January 1966 to November 2007. We describe the patient populations to which they apply and the outcomes predicted, and record their individual characteristics.

RECENT FINDINGS

The literature search generated 111 published prediction tools that may be applied to patients in various clinical stages of disease. Of the 111 prediction tools, only 69 had undergone validation. We present an inventory of models with input variables, prediction form, number of patients used to develop the prediction tools, the outcome being predicted, prediction tool-specific features, predictive accuracy, and whether validation was performed.

SUMMARY

Decision rules, such as nomograms, provide evidence-based and at the same time individualized predictions of the outcome of interest. Such predictions have been repeatedly shown to be more accurate than those of clinicians, regardless of their level of expertise. Accurate risk estimates are also required for clinical trial design, to ensure homogeneous high-risk patient groups for whom new cancer therapeutics will be investigated.

Application of artificial intelligence to the management of urological cancer

PURPOSE

Artificial intelligence techniques, such as artificial neural networks, Bayesian belief networks and neuro-fuzzy modeling systems, are complex mathematical models based on the human neuronal structure and thinking. Such tools are capable of generating data driven models of biological systems without making assumptions based on statistical distributions. A large amount of study has been reported of the use of artificial intelligence in urology. We reviewed the basic concepts behind artificial intelligence techniques and explored the applications of this new dynamic technology in various aspects of urological cancer management.

MATERIALS AND METHODS

A detailed and systematic review of the literature was performed using the MEDLINE and Inspec databases to discover reports using artificial intelligence in urological cancer.

RESULTS

The characteristics of machine learning and their implementation were described and reports of artificial intelligence use in urological cancer were reviewed. While most researchers in this field were found to focus on artificial neural networks to improve the diagnosis, staging and prognostic prediction of urological cancers, some groups are exploring other techniques, such as expert systems and neuro-fuzzy modeling systems.

CONCLUSIONS

Compared to traditional regression statistics artificial intelligence methods appear to be accurate and more explorative for analyzing large data cohorts. Furthermore, they allow individualized prediction of disease behavior. Each artificial intelligence method has characteristics that make it suitable for different tasks. The lack of transparency of artificial neural networks hinders global scientific community acceptance of this method but this can be overcome by neuro-fuzzy modeling systems.

Anatomical Extent of Pelvic Lymphadenectomy in Patients Undergoing Radical Prostatectomy

OBJECTIVES

The rationale for locoregional staging lymphadenectomy in prostate cancer (pCA) lies in the accurate diagnosis of occult micrometastases to stratify patients who might benefit from adjuvant therapeutic measures. In pCA, the issues of the necessity and the therapeutic advantage of pelvic lymphadenectomy (PLND]) in patients with low-, intermediate-, and high-risk disease are still discussed controversially. The aim of this review manuscript is to critically evaluate the current status on PLND in pCA.

METHODS

A review of the literature was performed concerning radical prostatectomy and PLND with respect to anatomical extent, oncological outcome, and associated complications.

RESULTS

The anatomical lymphatic drainage of the prostate includes the obturator fossa, and the external and internal iliac arteries; therefore, at least these areas should be included in PLND. According to the current clinical studies, extended PLND (ePLND) significantly increases the yield of both total lymph nodes and lymph node metastases independent of the risk classification of pCA. Lymph node metastases will be detected in about 5-6%, 20-25%, and 30-40% of low-, intermediate-, and high-risk pCA, respectively. Exclusively 25% of all positive lymph nodes are located in the area around the internal iliac artery. With regard to progression-free and cancer-specific survival, retrospective analysis of the SEER data and additional case-control studies indicate a direct positive relationship between the number of removed lymph nodes and long-term oncological outcome in patients with limited lymph node involvement or negative lymph nodes. In these patients, cancer-specific survival is improved by about 15-20%. On the basis of results of large case-control studies, complication rates of ePLND are not significantly increased.

CONCLUSIONS

On the basis of current data, the following conclusions can be drawn: (1) If performed, PLND has to be done in the extended, anatomically adequate variant. (2) The frequency of lymph node metastases in low-risk pCA is low, and the issue of PLND has to be discussed with the patient. (3) If radical prostatectomy is performed in intermediate- and high-risk pCA, an ePLND should be option of choice. For the future, ongoing prospective trials have to demonstrate a benefit in terms of biochemical-free and cancer-specific survival.

Validation of a Nomogram Predicting the Probability of Lymph Node Invasion among Patients Undergoing Radical Prostatectomy and an Extended Pelvic Lymphadenectomy

INTRODUCTION

Our goal was to develop and internally validate a nomogram for prediction of lymph node invasion (LNI) in patients with clinically localized prostate cancer undergoing extended pelvic lymphadenectomy (ePLND).

METHODS

602 consecutive patients (mean age 65.8 years) underwent an ePLND, where 10 or more nodes were removed. PSA was 1.1-49.9 (median 7.2). Clinical stages were: T1c in 55.6%, T2 in 41.4% and T3 in 3%. Biopsy Gleason sums were: 6 or less in 66%, 7 in 25.4%, 8-10 in 8.6%. Multivariate logistic regression models tested the association between all of the above predictors and LNI. Regression-based coefficients were used to develop a nomogram predicting LNI and 200 bootstrap resamples were used for internal validation.

RESULTS

Mean number of lymph nodes removed was 17.1 (range 10-40). LNI was detected in 66 patients (11.0%). Univariate predictive accuracy for total PSA, clinical stage and biopsy Gleason sum was 63%, 58% and 73%, respectively. A nomogram based on clinical stage, PSA and Biopsy Gleason sum demonstrated bootstrap-corrected predictive accuracy of 76%.

CONCLUSIONS

A nomogram based on pre-treatment PSA, clinical stage and biopsy Gleason sum can highly accurately predict LNI at ePLND.

Computer technology in detection and staging of prostate carcinoma: A review

After two decades of increasing interest and research activity, computer-assisted diagnostic approaches are reaching the stage where more routine deployment in clinical practice is becoming a possibility [Kruppinski, E.A., 2004. Computer-aided detection in clinical environment: Benefits and challenges for radiologists. Radiology 231, 7-9]. This is particularly the case in the analysis of mammographic images [Helvie, M.A., Hadjiiski, L., Makariou, E., Chan, H.P., Petrick, N., Sahiner, B., Lo, S.C., Freedman, M., Adler, D., Bailey, J., Blane, C., Hoff, D., Hunt, K., Joynt, L., Klein, K., Paramagul, C., Patterson, S.K., Roubidoux, M.A., 2004. Sensitivity of noncommercial computer-aided detection system for mammographic breast cancer detection: pilot clinical trial. Radiology 231, 208-214] and in the detection of pulmonary nodules [Reeves, A.P., Kostis, W.J., 2000. Computer-aided diagnosis for lung cancer. Radiol. Clin. North Am. 38, 497-509]. However, similar approaches can be applied more widely with the promise of increasing clinical utility in other areas. We review how computer-aided approaches may be applied in the diagnosis and staging of prostatic cancer. The current status of computer technology is reviewed, covering artificial neural networks for detection and staging, computerised biopsy simulation and computer-assisted analysis of ultrasound and magnetic resonance images.

Is pelvic lymph node dissection necessary in patients with a serum PSA<10ng/ml undergoing radical prostatectomy for prostate cancer?

OBJECTIVE

Controversy persists concerning the role of pelvic lymph node dissection (PLND) in patients with preoperative PSA values <10ng/ml undergoing treatment for prostate cancer with a curative intent. The aim of this study was to determine the incidence of lymph node metastasis in this subgroup of patients.

METHODS

Patients with clinically localized prostate cancer and a serum PSA<10ng/ml, without neoadjuvant hormonal or radiotherapy, with negative staging examinations who underwent radical retropubic prostatectomy with bilateral extended PLND and with >/=10 lymph nodes detected by the pathologist in the surgical specimen, were included in the study.

RESULTS

A total of 231 patients with a median serum PSA of 6.7ng/ml (range 0.4-9.98) and a median age of 62 years (range 44-76) were evaluated. A median of 20 (range 10-72) nodes were removed per patient. Positive nodes were found in 26 of 231 patients (11%), the majority of which (81%) had a Gleason score >/=7 in the surgical specimen. Of the patients with a Gleason score >/=7 in the prostatectomy specimen 25% had positive nodes, whereas only 3% with a Gleason score </=6 were node positive.

CONCLUSIONS

The incidence of positive nodes in patients with clinically localized prostate cancer, a serum PSA<10ng/ml and a Gleason score >/=7 in the prostatectomy specimen was 25% after extended PLND. It seems that in this patient group extended PLND, including removal of nodes along the internal iliac vessels, is warranted.

A novel approach for accurate prediction of spontaneous passage of ureteral stones: Support vector machines

The objective of this study was to optimally predict the spontaneous passage of ureteral stones in patients with renal colic by applying for the first time support vector machines (SVM), an instance of kernel methods, for classification. After reviewing the results found in the literature, we compared the performances obtained with logistic regression (LR) and accurately trained artificial neural networks (ANN) to those obtained with SVM, that is, the standard SVM, and the linear programming SVM (LP-SVM); the latter techniques show an improved performance. Moreover, we rank the prediction factors according to their importance using Fisher scores and the LP-SVM feature weights. A data set of 1163 patients affected by renal colic has been analyzed and restricted to single out a statistically coherent subset of 402 patients. Nine clinical factors are used as inputs for the classification algorithms, to predict one binary output. The algorithms are cross-validated by training and testing on randomly selected train- and test-set partitions of the data and reporting the average performance on the test sets. The SVM-based approaches obtained a sensitivity of 84.5% and a specificity of 86.9%. The feature ranking based on LP-SVM gives the highest importance to stone size, stone position and symptom duration before check-up. We propose a statistically correct way of employing LR, ANN and SVM for the prediction of spontaneous passage of ureteral stones in patients with renal colic. SVM outperformed ANN, as well as LR. This study will soon be translated into a practical software toolbox for actual clinical usage.

Forecasting the Prognosis of Choroidal Melanoma with an Artificial Neural Network

PURPOSE

To develop an artificial neural network (ANN) that will forecast the 5-year mortality from choroidal melanoma.

DESIGN

Retrospective, comparative, observational cohort study.

PARTICIPANTS

One hundred fifty-three eyes of 153 consecutive patients with choroidal melanoma (age, 58.4+/-14.6 years) who were treated with ruthenium 106 brachytherapy between 1988 and 1998 at the Department of Ophthalmology, Hadassah University Hospital, Jerusalem, Israel.

METHODS

Patients were observed clinically and ultrasonographically (A- and B-mode standardized ultrasonography). Metastatic screening included liver function tests and liver imaging. Backpropagation ANNs composed of 3 or 4 layers of neurons with various types of transfer functions and training protocols were assessed for their ability to predict the 5-year mortality. The ANNs were trained on 77 randomly selected patients and tested on a different set of 76 patients. Artificial neural networks were compared based on their sensitivity, specificity, forecasting accuracy, area under the receiver operating curves, and likelihood ratios (LRs). The best ANN was compared with the results of logistic regression and the performance of an ocular oncologist.

MAIN OUTCOME

The ability of the ANNs to forecast the 5-year mortality from choroidal melanoma.

RESULTS

Thirty-one patients died during the follow-up period of metastatic choroidal melanoma. The best ANN (one hidden layer of 16 neurons) had 84% forecasting accuracy and an LR of 31.5. The number of hidden neurons significantly influenced the ANNs' performance (P<0.001). The performance of the ANNs was not significantly influenced by the training protocol, the number of hidden layers, or the type of transfer function. In comparison, logistic regression reached 86% forecasting accuracy, with a very low LR (0.8), whereas the human expert forecasting ability was <70% (LR, 1.85).

CONCLUSIONS

Artificial neural networks can be used for forecasting the prognosis of choroidal melanoma and may support decision-making in treating this malignancy.

Classification of bacterial species from proteomic data using combinatorial approaches incorporating artificial neural networks, cluster analysis and principal components analysis

MOTIVATION

Robust computer algorithms are required to interpret the vast amounts of proteomic data currently being produced and to generate generalized models which are applicable to 'real world' scenarios. One such scenario is the classification of bacterial species. These vary immensely, some remaining remarkably stable whereas others are extremely labile showing rapid mutation and change. Such variation makes clinical diagnosis difficult and pathogens may be easily misidentified.

RESULTS

We applied artificial neural networks (Neuroshell 2) in parallel with cluster analysis and principal components analysis to surface enhanced laser desorption/ionization (SELDI)-TOF mass spectrometry data with the aim of accurately identifying the bacterium Neisseria meningitidis from species within this genus and other closely related taxa. A subset of ions were identified that allowed for the consistent identification of species, classifying >97% of a separate validation subset of samples into their respective groups.

AVAILABILITY

Neuroshell 2 is commercially available from Ward Systems.

Biochemical recurrence and survival prediction models for the management of clinically localized prostate cancer

A number of new predictive modeling techniques have emerged in the past several years. These methods, which have been developed in fields such as artificial intelligence research, engineering, and meteorology, are now being applied to problems in medicine with promising results. This review outlines our recent work with use of selected advanced techniques such as artificial neural networks, genetic algorithms, and propensity scoring to develop useful models for estimating the risk of biochemical recurrence and long-term survival in men with clinically localized prostate cancer. In addition, we include a description of our efforts to develop a comprehensive prostate cancer database that, along with these novel modeling techniques, provides a powerful research tool that allows for the stratification of risk for treatment failure and survival by such factors as age, race, and comorbidities. Clinical and pathologic data from 1400 patients were used to develop the biochemical recurrence model. The area under the receiver operating characteristic curve for this model was 0.83, with a sensitivity of 85% and specificity of 74%. For the survival model, data from 6149 men were used. Our analysis indicated that age, income, and comorbidities had a statistically significant impact on survival. The effect of race did not reach statistical significance in this regard. The C index value for the model was 0.69 for overall survival. We conclude that these methods, along with a comprehensive database, allow for the development of models that provide estimates of treatment failure risk and survival probability that are more meaningful and clinically useful than those previously developed.

Artificial neural networks for predictive modeling in prostate cancer

Artificial neural networks (ANNs) represent a relatively new methodology for predictive modeling in medicine. ANNs, a form of artificial intelligence loosely based on the brain, have a demonstrated ability to learn complex and subtle relationships between variables in medical applications. In contrast with traditional statistical techniques, ANNs are capable of automatically resolving these relationships without the need for a priori assumptions about the nature of the interactions between variables. As with any technique, ANNs have limitations and potential drawbacks. This article provides an overview of the theoretical basis of ANNs, how they function, their strengths and limitations, and examples of how ANNs have been used to develop predictive models for the management of prostate cancer.

Use of algorithms as determinants for individual patient decision making: national comprehensive cancer network versus artificial neural networks

The National Comprehensive Cancer Network (NCCN) developed a series of algorithms based on expert opinion to guide the treatment of patients with prostate cancer. These algorithms define acceptable treatment options according to the risk of disease recurrence and the life expectancy of the patient. However, practicing clinicians are expected to use medical judgment when making actual treatment decisions. Many clinical and pathologic variables affect patient prognosis, which, in turn, influences the treatment and surveillance of patients. Artificial neural networks (ANNs) offer promise for improving the predictive value of traditional statistical modeling. ANN models have been designed that predict risk of lymph node spread and capsular involvement during disease staging, risk of disease recurrence after prostatectomy, and overall and cause-specific survival. This article provides a review of guidelines, such as NCCN and ANN, used for the management of prostate cancer and suggests that group-level recommendations based on these algorithms or other decision trees may misrepresent individual patient preferences for treatment. Patients and their clinicians need to consider available prognostic information, including clinical status, pathologic variables, and comorbidities, and then select a reasonable treatment approach that maximizes outcome and quality of life according to the preferences of each patient.

The Predictors of Pelvic Lymph Node Metastasis at Radical Retropubic Prostatectomy

PURPOSE

We studied preoperative variables in a contemporary series of patients who underwent radical retropubic prostatectomy (RRP) to determine which variables were associated with lymph node metastasis.

MATERIALS AND METHODS

Between January 1995 and November 1999, 1,091 men underwent RRP, 695 of whom underwent bilateral pelvic lymph node dissection without any prior therapy. We evaluated biopsy Gleason score, maximum tumor length and maximum percentage of tumor in the positive core(s), location and number of positive cores, and total prostate specific antigen before surgery in 295 of these patients. We also developed a classification and regression tree analysis algorithm to segregate the risk of positive lymph node metastasis. Stepwise logistic regression analyses were used to determine independent predictors of lymph node metastasis.

RESULTS

Of the 695 patients 19 (2.7%) had lymph node metastasis. Clinical stage, Gleason score, positive basal core, greatest percentage of tumor on positive cores and maximum tumor length in positive core were significant predictors of lymph node metastasis in the Mann-Whitney U test and chi-square test. Classification and regression trees analysis revealed that 4 or more positive cores with any Gleason grade 4 or 5, serum prostate specific antigen 15.0 ng/ml or greater, or the presence of dominant Gleason 4 or 5 were independent predictors of lymph node metastasis. Our algorithm had a significantly higher diagnostic performance than the Hamburg algorithm (p = 0.002).

CONCLUSIONS

Our algorithm may be a valid tool for the prediction of lymph node metastasis and may help to select men who do not need to undergo bilateral pelvic lymph node dissection with RRP.

Frequency of lymphoceles after open and laparoscopic pelvic lymph node dissection in patients with prostate cancer

OBJECTIVE

To compare the frequencies of pelvic lymphocele formation after laparoscopic and open pelvic lymph node dissection in patients with prostate cancer.

MATERIAL AND METHODS

A total of 132 patients operated on with pelvic lymph node dissection (PLND) underwent CT scanning of the abdomen and pelvis at a median of 29 days postoperatively. Open pelvic lymph node dissection (OPLND) was performed in 94 patients (71%) and 38 patients (29%) were operated on using a laparoscopic technique (LPLND). The frequency and size of pelvic lymphoceles were registered. Lymphoceles with a horizontal diameter of </=4.9 cm were classified as small and those with a horizontal diameter of >/=5.0 cm were classified as large.

RESULTS

The overall frequency of lymphoceles was 54%. The frequencies in the OPLND and LPLND groups were 61% and 37%, respectively. A total of 27% of the OPLND patients had large lymphoceles, compared to 8% of the LPLND patients. Three patients (2.3%), all in the OPLND group, had clinically significant lymphoceles.

CONCLUSIONS

Although the overall frequency of lymphocele formation was high, clinically significant lymphoceles were scarce. LPLND was associated with a statistically significant lower frequency of lymphocele formation compared to OPLND.

Artificial neural networks for decision-making in urologic oncology

The authors are presenting a thorough introduction in Artificial Neural Networks (ANNs) and their contribution to modern Urologic Oncology. The article covers a description of Artificial Neural Network methodology and points out the differences of Artificial Intelligence to traditional statistic models in terms of serving patients and clinicians, in a different way than current statistical analysis. Since Artificial Intelligence is not yet fully understood by many practicing clinicians, the authors have reviewed a careful selection of articles in order to explore the clinical benefit of Artificial Intelligence applications in modern Urology questions and decision-making. The data are from real patients and reflect attempts to achieve more accurate diagnosis and prognosis, especially in prostate cancer that stands as a good example of difficult decision-making in everyday practice. Experience from current use of Artificial Intelligence is also being discussed, and the authors address future developments as well as potential problems such as medical record quality, precautions in using ANNs or resistance to system use, in an attempt to point out future demands and the need for common standards. The authors conclude that both methods should continue to be used in a complementary manner. ANNs still do not prove always better as to replace standard statistical analysis as the method of choice in interpreting medical data.

Decision making using hybrid rough sets and neural networks

A methodology for using rough sets theory for preference modeling in decision problem is presented in this paper. We will introduce a new method where neural network systems and rough sets theory are completely integrated into a hybrid system and are used cooperatively for decision and classification support. At the first glance, the two methods we discuss have not much in common. But, in spite of the differences between them, it is interesting to try to incorporate both into one combined system, and apply it in the building of a decision support system.

Validation of a biopsy-based pathologic algorithm for predicting lymph node metastases in patients with clinically localized prostate carcinoma

BACKGROUND

The authors validated an algorithm for the preoperative prediction of lymph node (LN) metastases in patients with clinically localized prostate carcinoma. The algorithm was applied to sextant biopsy material and radical retropubic prostatectomy (RRP) stage obtained from a cohort of men who were treated at the authors' institution.

METHODS

Four hundred forty-three patients underwent systematic sextant biopsy and RRP with staging lymphadenectomy. The original algorithm was based on systematic sextant biopsy data and classified patients into three risk groups for LN metastases based on the biopsy result. If > or = 4 of 6 biopsies contained any Gleason Pattern 4 disease, then the patient was at high risk for LN metastases (45%). Patients with > or = 1 of 6 biopsies with dominant Gleason Pattern 4 disease (excluding high-risk patients) had an intermediate predicted risk (19%) of LN metastases. All other patients had a low predicted risk of LN metastases (2.2%). The authors assed the percentage of patients who were positive and negative for LN metastases and calculated the specificity and negative predictive value in the series when patients were classified according to the original algorithm.

RESULTS

Twenty of 443 patients had intraoperative LN metastases. When applied to the current data, the Hamburg algorithm classified 404 patients in the low-risk group, 30 patients in the intermediate-risk group, and 9 patients in the high risk group. The incidence of LN metastases was 2.47% in the low-risk group, 20% in the intermediate-risk group, and 44.4% in the high-risk group. The negative predictive value for the low-risk group was 97.52%, and the specificity was 94.14%.

CONCLUSIONS

The Hamburg algorithm proved a valid tool for the prediction of lymphatic spread in this validation study on data from the authors' institution. The algorithm may serve as a tool to select patients who do not need to undergo pelvic lymphadenectomy at the time they undergo RRP, hence reducing morbidity and expense. More importantly, with the increasing numbers of men undergoing treatment options in whom LN dissection is not performed, this validated algorithm provides an important selection basis regarding the appropriateness of a therapy that does not routinely include LN staging.

Biological selection criteria for radical prostatectomy

Tumors clinically confined to the prostate gland (T1-2) are heterogeneous with respect to pathological staging and outcome after definitive radical surgery (radical prostatectomy). The preoperative prognostic factors that could predict pathological stage and outcome of individual patients with clinically localized prostate cancer are reviewed. New preoperative factors have been identified by histological analysis of needle biopsy prostate specimens in addition to Gleason grading score, serum markers (PSA), and clinical staging. These factors are related to tumor volume, zonal origin of the tumor, and spread into the gland and surrounding tissues. Other biological factors are identified by molecular and immunohistochemical analysis (neuroendocrine differentiation, DNA content, microvessel density, and perineural invasion). Biomolecular factors can also be assessed preoperatively on serum samples (free/total PSA ratio, PSA RT-PCR). Although only a few of these factors have a role in predicting treatment failure and/or disease recurrence, the neural network analysis seems to be the most important tool for identifying patients with more aggressive disease. A combination of these new factors, also using neural networks, could be relevant in the preoperative management of patients with prostate cancer to identify those with confined disease and to select those suitable for a "nerve sparing radical prostatectomy" to preserve sexual function and to achieve definitive cancer control.

Use of artificial neural networks in prostate cancer

Artificial neural networks (ANNs) are a type of artificial intelligence software inspired by biological neuronal systems that can be used for nonlinear statistical modeling. In recent years, these applications have played an increasing role in predictive and classification modeling in medical research. We review the basic concepts behind ANNs and examine the role of this technology in selected applications in prostate cancer research.

Computer-assisted diagnostics: application to prostate cancer

Artificial neural networks (ANNs) have only recently been applied to solve problems in the diagnosis, staging, and prediction of treatment outcome in prostate cancer. A literature search provided information on 10 published journal articles that were selected for review and analysis. In all but one of the studies that compared the ANN output with logistic regression modeling, the ANN performed better. Specific training issues for neural networks are discussed and examples provided. We conclude that the continued development and refinement of computer-assisted diagnostic methodology are warranted to enhance conventional statistical approaches to the classification and pattern recognition found in data sets from men either suspected of having or known to have prostate cancer.

Artificial neural network model to predict biochemical failure after radical prostatectomy

BACKGROUND

Biochemical failure, defined here as a rise in the serum prostate specific antigen (PSA) concentration to >0.3 ng/mL or the initiation of adjuvant therapy, is thought to be an adverse prognostic factor for men who undergo radical prostatectomy (RP) as definitive treatment for clinically localized cancer of the prostate (CAP). We have developed an artificial neural network (ANN) to predict biochemical failure that may benefit clinicians and patients choosing among the definitive treatment options for CAP.

MATERIALS AND METHODS

Clinical and pathologic data from 196 patients who had undergone RP at one institution between 1988 and 1999 were utilized. Twenty-one records were deleted because of missing outcome, Gleason sum, PSA, or clinical stage data. The variables from the 175 remaining records were analyzed for input variable selection using principal component analysis, decision tree analysis, and stepped logistic regression. The selected variables were age, PSA, primary and secondary Gleason grade, and Gleason sum. The records were randomized and split into three bootstrap training and validation sets of 140 records (80%) and 35 records (20%), respectively.

RESULTS

Forty-four percent of the patients suffered biochemical failure. The average duration of follow up was 2.5 years (range 0-11.5 years). Forty-two percent of the patients had pathologic evidence of non-organ-confined disease. The average area under the receiver operator characteristic (ROC) curve for the validation sets was 0.75 +/- 0.07. The ANN with the highest area under the ROC curve (0.80) was used for prediction and had a sensitivity of 0.74, a specificity of 0.78, a positive predictive value of 0.71, and a negative predictive value of 0.81.

CONCLUSION

These results suggest that ANN models can predict PSA failure using readily available preoperative variables. Such predictive models may offer assistance to patients and physicians deciding on definitive therapy for CaP.