Artificial neural network model to predict biochemical failure after radical prostatectomy

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.

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.

ARTIFICIAL INTELLIGENCE FOR THE PREDICTION OF BLADDER CANCER

New techniques for the prediction of tumour behaviour are needed as statistical analysis has a poor accuracy and is not applicable to the individual. Artificial intelligence (AI) may provide these suitable methods. We have previously shown that the predictive accuracies of neuro-fuzzy modelling (NFM) and artificial neural networks (ANN), two methods of AI, are superior to traditional statistical methods for the behaviour of bladder cancer (Catto et al, 2003). In this paper, we explain the AI techniques required to produce these predictive models. We used 9 parameters, which were a combination of experimental molecular biomarkers and conventional clinicopathological data, to predict the risk of tumour progression in a population of 109 patients with bladder cancer, NFM, using fuzzy logic to model data, achieved similar or superior predictive accuracy to ANN, which required cross-validation. However, unlike the impenetrable opaque structure of neural networks, the rules of NFM are transparent, enabling validation from clinical knowledge and the manipulation of input variables to allow exploratory predictions.

[Time-influencing factors for biochemical progression following radical prostatectomy]

INTRODUCTION

We assessed the time-influencing clinical-pathological factors for biochemical progression of an equal series of patients from a single institution.

MATERIALS AND METHODS

Retrospective analysis of 278 patients with biochemical progression following prostatectomy. We considered biochemical progression to be PSA>0.4 ng/ml. We performed the trial using the Cox model (univariate and multivariate) and using the Student's t-test to compare averages.

RESULTS

With a mean follow-up of 4 (±3 DE) years, the univariate study showed a mean until progression for the Gleason score 2-6 in the biopsy of 824 days and 543 for the Gleason score 7-10 (p=0.003). For negative surgical margins, the mean was 920 days and 545 for positive margins (p=0.0001). In the case of a Gleason score 2-7 in the specimen, the mean was 806 days and 501 for a Gleason score 8-10 (p=0.001). Lastly, the mean for the cases with Ki-67 negative in the specimen (< 10%) was 649 days and 345 for Ki-67 positive (> 10%) (p=0.003). In the multivariate study, Ki-67 (OR 1.028; IC 95% 1-1.01; p=0.0001) and Gleason score 8-10 (OR 1.62; IC 95% 1.5-2.45; p=0.026) in the specimen, and initial PSA >10 ng/ml (OR 1.02; IC 95% 1.01-1.04; p=0.0001) were independent variables. Using these variables, we designed a predictive model with three groups. The time until the progression of each group was 1,081, 551 and 218 days respectively.

CONCLUSION

The Gleason score 7-10 in the prostate biopsy, the presence of Ki-67, the positive margins and the Gleason score 8-10 in the specimen, and the initial PSA > 10 ng/ml are time-influencing factors until biochemical progression. Pathological Gleason score 8-10, PSA > 10 ng/ml and Ki-67 are independent factors.

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.

Prognostic accuracy of an artificial neural network in patients undergoing radical cystectomy for bladder cancer: a comparison with logistic regression analysis

OBJECTIVE

To compare the prognostic performance of an artificial neural network (ANN) with that of standard logistic regression (LR), in patients undergoing radical cystectomy for bladder cancer.

PATIENTS AND METHODS

From February 1982 to February 1994, 369 evaluable patients with non-metastatic bladder cancer had pelvic lymph node dissection and radical cystectomy for either stage Ta-T1 (any grade) tumour not responding to intravesical therapy, with or with no carcinoma in situ, or stage T2-T4 tumour. LR analysis based on 12 variables was used to identify predictors of overall 5-year survival, and the ANN model was developed to predict the same outcome. The LR analysis, based on statistically significant predictors, and the ANN model were the compared for their accuracy in predicting survival.

RESULTS

The median age of the patients was 63 years, and overall 201 of them died. The tumour stage and nodal involvement (both P<0.001) were the only statistically independent predictors of overall 5-year survival on LR analysis. Based on these variables, LR had a sensitivity and specificity for predicting survival of 68.4% and 82.8%, respectively; corresponding values for the ANN were 62.7% and 86.1%. For LR and ANN, the positive predictive values were 78.6% and 76.2%, and the negative predictive values were 73.9% and 76.5%, respectively. The index of diagnostic accuracy was 75.9% for LR and 76.4% for ANN.

CONCLUSIONS

The ANN accurately predicted the survival of patients undergoing radical cystectomy for bladder cancer and had a prognostic performance comparable with that of LR. As ANNs are based on easy-to-use software that can identify nonlinear interactions between variables, they might become the preferred tool for predicting outcome.

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 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.

PSA progression following radical prostatectomy and radiation therapy: new standards in the new Millennium

Prostate-specific antigen (PSA) progression following radical treatments of clinically localized prostate cancer is a common problem facing both the patient and the urologist. Not all patients with relapsing disease have an equal risk of death due to prostate cancer. After surgery, biochemical failure can be defined as persisting detectable levels of PSA after radical prostatectomy or a PSA rise after a period of normalization. On the other hand, definitions of PSA progression after radiation therapy vary and no clear consensus can be found. This review of the recent international literature updates the knowledge about the diagnostic procedures used in relapsing patients. Predictors of progression are precised leading to a better patient selection, based on currently available tables and nomograms. Indeed, identification of high risk patients may allow a more appropriate treatment decision. After radical treatment, the analysis of time to recurrence, PSA doubling time, PSA kinetics combined to modern imaging techniques such as 111In capromab penditide scan may allow a better identification of the recurrence site. Thus, an optimal treatment strategy may be envisaged such as local irradiation, salvage surgery, hormone therapy or combinations for which indications and results are provided. Alternative options such as cryotherapy still need further investigation. At last, the use of artificial neural networks will certainly enhance the selection of patients submitted to radical treatments as well as the selection of relapsing patients to allow a more appropriate adjuvant therapy.