Theodore Anagnostou

An artificial neural network to predict the outcome of repeat prostate biopsies

OBJECTIVES To develop an advanced artificial neural network (ANN) to predict the presence of prostate cancer (PCa) and to predict the outcome of repeat prostate biopsies. The predictive accuracy was compared with the accuracy obtained using standard cutoffs for the free/total (f/t) prostate-specific antigen (PSA) ratio, PSA density (PSAD), PSA density of the transition zone (PSA-TZ), and the total and transition zone volumes. Clinical and biochemical diagnostic tests have been shown to improve PCa detection. When these tests are combined using an ANN, significant increases in specificity at high sensitivity are observed. METHODS The Vienna-based multicenter European referral database for early PCa detection of 820 men with a PSA level between 4 and 10 ng/mL was used. The presence of PCa was determined using transrectal ultrasound-guided octant needle repeat biopsy. Variables in the database consisted of age, PSA, f/t PSA ratio, digital rectal examination findings, PSA velocity, and the transrectal ultrasound-guided variables of prostate volume, transition zone volume, PSAD, and PSA-TZ. The ANN used in the analysis was an advanced multilayer perceptron selected for accuracy by a genetic algorithm. RESULTS The repeat biopsy PCa detection rate was 10% (n = 83). At 95% sensitivity, the specificity for ANN was 68% compared with 54%, 33.5%, 21.4%, 14.7%, and 8.3% for multivariate logistic regression analysis, f/t PSA ratio, PSA-TZ, PSAD, and total PSA, respectively. The ANN reduced unnecessary repeat biopsies by 68% in this study. The area under the curve was 83% for the ANN versus 79%, 74.5%, 69.1%, 61.8%, and 60.5% for multivariate analysis, f/t PSA ratio, PSA-TZ, PSAD, and total PSA, respectively. CONCLUSIONS The current ANN found a strong pattern predictive of PCa in patients with a negative initial biopsy. By combining the individual clinical and biochemical markers into the ANN, 68% specificity at 95% sensitivity was achieved. The ANN allows more accurate and individual counseling of patients with a negative initial biopsy.

Sixteen Years of Experience with Stone Management in Horseshoe Kidneys

Introduction: Horseshoe kidney is the commonest congenital renal fusion anomaly, and is often complicated by urolithiasis. We focus on our 16 years of experience with stone management in horseshoe kidneys. Materials and Methods: We reviewed the progress of 44 patients treated between 1987 and 2002. Shock wave lithotripsy (SWL) was used in 25 patients; the average stone surface area was 91 (range 10–1,600) mm2 and average follow-up was 36.5 (range 1–91) months. 19 patients underwent percutaneous nephrolithotomy (PCNL); the average stone surface area was 197 (range 6–2,400) mm2. Follow-up data are available for 8 patients and the average follow-up was 42.3 (range 3–144) months. Results: In the SWL group the 3-month stone-free rate (SFR) was only 31%. In the PCNL group the SFR was 75% on the postoperative day-1 KUB. Complications occurred in 9 patients. Conclusions: Stone management in horseshoe kidneys is challenging: PCNL produces a higher SFR with minimal major complications and failed access. PCNL thus appears to be the preferred management option in patients with urolithiasis in horseshoe kidneys.

Safety and Outcome of Percutaneous Nephrolithotomy in the Elderly: Retrospective Comparison to a Younger Patient Group

AIM To evaluate whether the overall safety and efficacy profile of percutaneous surgery for urinary stone disease in older (>70 years) patients might influence the decision for the procedure in the elderly. MATERIALS AND METHODS A large database was created from our patients (n = 1058) who underwent percutaneous surgery for stone disease between 1991 and 2003 in the Scottish Lithotriptor Centre, including clinical and operation details for each case. Only percutaneous nephrolithotomy cases with full details were studied (n = 779) and were grouped into two age groups: (1) between 17 and 69 years and (2) over 70 years. Statistical analysis evaluated differences in terms of operation-related adverse events, stone-free success rates, and clinical success rates (including stone-free cases and cases with residual fragments <4 mm). Further analysis was performed for the same endpoints after stratification of the patients by (1) previous stone procedures and (2) special clinical features. RESULTS In the overall database, no statistically important differences were found between the two groups in terms of stone burden before surgery, adverse events rates, complete stone-free rates, and clinical success rates. However, a statistical trend toward higher clinical success rates in favor of the younger group was seen (P = 0.051). Stratification of our database according to previous stone disease procedures or special clinical or anatomic characteristics has only shown a statistically important difference for clinical success rates in favor of the older group without special features (P = 0.01). CONCLUSION In experienced hands, age-related morbidity or age itself should not be a discouraging consideration when deciding on performing percutaneous nephrolithotomy, as the procedure is as equally feasible and safe in the elderly as in the younger patient population.