Artificial neural networks in urology: pro.
Explore the source record for details and available documents.
Humans↗
Biomedical subjects
J T Wei
Publications and source records attributed to J T Wei.
Comparison of direct hospital costs and length of stay for radical nephrectomy versus nephron-sparing surgery in the management of localized renal cell carcinoma.
OBJECTIVES: Recent work has demonstrated comparable surgical results and 5-year cancer-specific survival rates between radical nephrectomy and nephron-sparing surgery (NSS) in the treatment of patients with small (4 cm or smaller) solitary renal cell carcinomas (RCCs). However, differences exist in the intraoperative management and postoperative care of patients undergoing NSS versus radical nephrectomy, and we sought to compare direct hospital costs and length of stay (LOS) between these two groups to determine whether either treatment imparts a specific cost advantage. METHODS: Data were retrieved from medical records and administrative data sets containing billing encounters for all costs incurred during hospitalization at the Cleveland Clinic Foundation. Individual costs were grouped together using nine cost center categories encompassing every aspect of direct hospital care, including anesthesiology, laboratory, radiology, nursing, pharmaceutical, and emergency services, and medical care, surgical care, and miscellaneous costs. Each cost center was further subdivided, and a total of 52 cost subcategories were assessed. The total direct costs of hospitalization were compared using a multivariate regression model in which patient demographics and tumor characteristics, type and year of surgery, LOS, and cost center categories were assessed as single and interactive factors. Postoperative complication and cancer-specific survival rates were also compared to identify any potential therapeutic differences between the two groups. RESULTS: Between 1991 and 1995, 80 patients underwent surgery at the Cleveland Clinic Foundation for solitary RCCs 4 cm or smaller, including 52 partial and 28 radical nephrectomies. We found no difference in the postoperative complication rate or cancer-specific survival rate between the two surgical groups. Total direct hospital costs and LOS were not statistically different between the NSS and radical nephrectomy groups (P >0.05). This was further supported by our multivariate model, which accounted for 61% of the observed variance in the total costs (F = 12.11, P = 0.0001). The type of surgery was not associated with total cost when controlling for all other factors, including age, sex, year of surgery, tumor size, grade, and stage, and postoperative complications (P = 0.7). There was no significant interaction between the type of surgery and the LOS (P = 0.5). CONCLUSIONS: This study demonstrated that elective NSS can be performed with equivalent direct hospital costs and LOS when compared with patients undergoing radical nephrectomy for small solitary RCCs. These data have significant economic implications for the comparison of competing surgical treatment strategies for localized RCC.
Aged↗
Understanding artificial neural networks and exploring their potential applications for the practicing urologist.
Artificial neural networks (ANNs) are complex mathematical models that are distantly based on the human neuronal structure. They are capable of modeling elaborate biologic systems without making assumptions based on statistical distributions. Preliminary work has been reported on their application in urology. The initial results have been promising, particularly as an additional tool in the detection of early prostate cancer using the ProstAsure Index, which has been the most extensively studied urologic ANN to date. We review the basic concepts behind ANNs and examine currently existing and potential future applications of this new dynamic technology both in urology and in general clinical medicine.
Clinical Medicine↗
The influence of prostate size on cancer detection.
OBJECTIVES: To determine if cancer detection rates vary with prostate size using a sextant core biopsy pattern. METHODS: We reviewed 1021 transrectal ultrasound (TRUS)-guided sextant pattern prostate biopsies to determine if cancer detection varied based on prostate size. Prostate size was determined using a computer generated elliptical estimation method. Sextant core biopsies were taken, and the patients divided into groups based on estimated size of the prostate and biopsy outcome. Large prostates were those that were estimated by TRUS as 50 cc or more. Prostates were considered small if they were less than 50 cc. Groups were compared based on size and biopsy outcome. RESULTS: Adenocarcinoma was detected in 33% (334 of 1021) of the patients. Large prostates were noted in 34% (346 of 1021), of which 23% (80 of 346) had cancer detected by sextant biopsy. Small prostates were noted in 66% (675 of 1021), of which 38% (254 of 675) had cancer detected. The difference in cancer detection in large and small glands using a sextant pattern was statistically significant (P < 0.01). Patients with positive biopsies had significantly smaller prostate sizes (40 cc +/- 26) when compared with those with negative biopsies (51 cc +/- 33) (P < 0.01). Only 14% (8 of 58) of patients with gland sizes 100 cc or greater had positive sextant biopsies while 49% (118 of 239) with prostates 25 cc or less had cancer detected. Multivariate statistical analysis was used to control for differences in age, prostate-specific antigen (PSA), PSA density, TRUS findings, and digital rectal examination between the large and small prostate groups. The difference in cancer detection persisted (P < 0.05) CONCLUSIONS: Currently no evidence exists to support differing cancer rates based on gland size alone. Our cancer detection rate using a sextant pattern was higher in men with prostates less than 50 cc, and patients diagnosed with cancer had significantly smaller prostates than those with a negative sextant biopsy. Our data suggest that significant sampling error may occur in men with large glands, and more biopsies may be needed under these circumstances. The effects of tumor volume, focality, and specimen size in relation to overall gland size may contribute to these findings.
Adenocarcinoma↗
Volvulus of the ileal conduit: a late complication.
We report 2 cases of ileal conduit volvulus presenting as a late complication. The importance of early diagnosis and surgical intervention is discussed.
Adult↗
Mucolipidoses II and III variants with normal N-acetylglucosamine 1-phosphotransferase activity toward alpha-methylmannoside are due to nonallelic mutations.
Normal N-acetylglucosamine 1-phosphotransferase activity toward mono- and oligosaccharide acceptor substrates was detected in cultured skin fibroblasts from mucolipidoses II and III patients who were designated as variants (one of four mucolipidosis II and three out of six mucolipidosis III patients examined). The activity toward natural lysosomal protein acceptors was absent or deficient in cell preparations from all patients with classical as well as variant forms of mucolipidoses II and III. Complementation analysis, using fused and cocultivated mutant fibroblast combinations, revealed that, while cell lines with variant mucolipidosis III constituted a complementation group distinct from that of classical forms of mucolipidoses II and III, the variant mucolipidosis II cell line belonged to the same complementation group as did the classical forms. In contrast to the mutant enzyme from variant mucolipidosis III patients that failed to recognize lysosomal proteins as the specific acceptor substrates, the activity toward alpha-methylmannoside in the variant mucolipidosis II patient could be inhibited by exogenous lysosomal enzyme preparations (bovine beta-glucuronidase and human hexosaminidase A). These findings suggest that N-acetylglucosamine 1-phosphotransferase is composed of at least two distinct polypeptides: (1) a recognition subunit that is defective in the mucolipidosis III variants and (2) a catalytic subunit that is deficient or altered in the classical forms of mucolipidoses II and III as well as in the mucolipidosis II variant.
Alleles↗