Computational models for detection of endocrinopathy in subfertile males.

The observation that men with sperm density greater than 10 million/ml had low probability of endocrinopathy led to a refinement in the evaluation of subfertility. Using statistical methods, we sought to provide a more accurate prediction of which patients have an endocrinopathy, and to report the outcome as the odds of having disease. In addition, by examining the parameters that influenced the model significantly, the underlying pathophysiology might be better understood. Records of 1035 men containing variables including testis volume, sperm density, motility as well as the presence of endocrinopathy were randomized into 'training' and 'test' data sets. We modeled the data set using linear and quadratic discriminant function analysis, logistic regression (LR) and a neural network. Wilk's regression analysis was performed to determine which variables influenced the model significantly. Of the four models investigated, LR and a neural network performed the best with receiver operating characteristic areas under the curve of 0.93 and 0.95, respectively, correlating to a sensitivity of 28% and a specificity of 99% for the LR model, and a sensitivity and specificity of 56 and 97% for the neural network model. Reverse regression yielded P-values for the testis volume and sperm density of <0.0001. The neural network and LR models accurately predicted the probability of an endocrinopathy from testis volume, sperm density and motility without serum assays. These models may be accessed via the Internet, allowing urologists to select patients for endocrinologic evaluation at http://www.urocomp.org.

Diagnostic value of nitric oxide, lipoprotein(a), and malondialdehyde levels in the peripheral venous and cavernous blood of diabetics with erectile dysfunction.

Diabetes mellitus (DM) is the single most common cause of erectile dysfunction (ED) seen in clinical practice. Evaluation of penile arterial insufficiency in diabetic patients currently entails expensive and invasive testing. We assessed the diagnostic value of certain peripheral and cavernous blood markers as predictors of penile arterial insufficiency in diabetic men with ED. This study was conducted on a total of 51 subjects in three groups: 26 impotent diabetics, 15 psychogenic impotent men and 10 normal age matched control males. All subjects underwent standard ED evaluation including estimation of postprandial blood sugar and serum lipid profile. Peripheral venous levels of nitric oxide (NO), lipoprotein(a) (LP(a)), malondialdehyde (MDA) and glycosylated hemoglobin (HbA1c) were obtained in all subjects. Patients in the two impotent groups underwent additional measurement of NO, LP(a) and MDA levels in cavernous blood. They also underwent intracavernosal injection (ICI) of a trimix (papaverine, prostaglandin E1 and phentolamine mixture) and pharmaco-penile duplex ultrasonography (PPDU). Compared to patients in the psychogenic group, diabetic men had significantly lower erectile response to ICI (P<0.001), lower peak systolic velocity (PSV) (P<0.001), and smaller increase in cavernosal artery diameter (CAD) (P<0.001). Peripheral and cavernous levels of both LP(a) and MDA were higher in the diabetic group as compared to the psychogenic ED group (P<0.001), while the values of peripheral venous and cavernous NO were lower (P<0.001) in the diabetic men. Comparison of biochemical marker assays with the PPDU results showed a significant negative correlation between both venous and cavernous LP(a) and MDA levels on the one hand, and PSV, and the percentage of CAD increase on the other. At the same time, peripheral and cavernous NO levels had a significant positive correlation with the same parameters. Lipoprotein(a), MDA and NO levels were better predictors of low PSV than HbA1c, cholesterol or triglyceride levels. The finding of high levels of LP(a) and MDA with low levels of NO in the peripheral and cavernous venous blood of diabetic men with ED correlates strongly with severity of ED as measured by PPDU. This provides a rationale for further studies of biochemical markers as a surrogate for traditional invasive testing in the diagnosis of penile arterial insufficiency.

Surgical sperm retrieval for assisted reproduction.

Intra-cytoplasmic sperm injection (ICSI) has revolutionized the treatment of male infertility by requiring only a single sperm to allow men whose infertility was previously considered to be uncorrectable to father a biological offspring. As a result, surgical sperm retrieval for assisted reproduction has developed to support this therapy. Microsurgical techniques have been applied to either identify areas of active spermatogenesis within the testis or to aspirate sperm-containing fluid or tissue. The combination of these techniques with in vitro fertilization (IVF)/ICSI has been shown to be a powerful approach to the treatment of azoospermic men. The availability of sperm cryopreservation offers an additional advantage, negating the need for synchronization of sperm retrieval and ovulation. Thus, the advanced methods for sperm retrieval discussed in this review also provide therapeutic options, as compared the traditional diagnostic testicular biopsy.

Artificial neural networks in pediatric urology: prediction of sonographic outcome following pyeloplasty.

PURPOSE: Computerized artificial neural networks are analogous to biological neuronal systems. Since they may be trained to recognize the relevance of complex patterns in data, neural networks may be useful for decision making in the multifactorial management of ureteropelvic junction obstruction. We determine the ability of a customized neural network to predict sonographic outcome after pyeloplasty in children with ureteropelvic junction obstruction. MATERIALS AND METHODS: A data set was constructed with 242 demographic, clinical, radiological and surgical elements. We analyzed the available retrospective data in 100 consecutive children who underwent unilateral pyeloplasty for ureteropelvic junction obstruction chosen from all 144 surgically treated for ureteropelvic junction obstruction between 1993 and 1995. One radiologist reviewed all film data and provided a final sonographic outcome designation in each case. We wrote a set of computer programs to construct a neural network. A composite 4-layer network was built with output nodes representing 4 possible sonographic outcomes. The 100 patient data set was randomly divided into 84 training and 16 testing examples. RESULTS: The neural network correctly predicted all 5 of 5 significantly improved, 7 of 7 improved, 2 of 2 same and 2 of 2 worse sonogram results after pyeloplasty. Therefore, sensitivity and specificity were 100% for all 4 outcomes. Linear regression analysis of the data yielded inferior sensitivity and specificity values (52 to 94%), confirming that ureteropelvic junction obstruction is a nonlinear data analysis problem. CONCLUSIONS: The 100% accuracy, sensitivity and specificity of our neural network in this pilot study provide evidence of the value of the neural computational approach for the modern exploration and modeling of the clinical problem of pediatric ureteropelvic junction obstruction.

Use of a neural network to predict stone growth after shock wave lithotripsy.

OBJECTIVES: To determine whether a neural network is superior to standard computational methods in predicting stone regrowth after shock wave lithotripsy (SWL) and to determine whether the presence of residual fragments, as an independent variable, increases risk. METHODS: We reviewed the records of 98 patients with renal or ureteral calculi treated by primary SWL at a single institution and followed up for at least 1 year; residual stone fragment growth or new stone occurrence was determined from abdominal radiographs. A neural network was programmed and trained to predict an increased stone volume over time utilizing input variables, including previous stone events, metabolic abnormality, directed medical therapy, infection, caliectasis, and residual fragments after SWL. Patient data were partitioned into a training set of 65 examples and a test set of 33. The neural network did not encounter the test set until training was complete. RESULTS: The average follow-up period was 3.5 years (range 1 to 10). Of 98 patients, 47 had residual stone fragments 3 months after SWL; of these 47, 8 had increased stone volume at last follow-up visit. Of 51 patients stone free after SWL, 4 had stone recurrence. Coexisting risk factors were incorporated into a neural computational model to determine which of the risk factors was individually predictive of stone growth. The classification accuracy of the neural model in the test set was 91%, with a sensitivity of 91%, a specificity of 92%, and a receiver operating characteristic curve area of 0.964, results significantly better than those yielded by linear and quadratic discriminant function analysis. CONCLUSIONS: A computational tool was developed to predict accurately the risk of future stone activity in patients treated by SWL. Use of the neural network demonstrates that none of the risk factors for stone growth, including the presence of residual fragments, is individually predictive of continuing stone formation.

Predictors of general quality of life in patients with benign prostate hyperplasia or prostate cancer.

PURPOSE: Studies in disease specific populations have emphasized disease specific quality of life with little study of general quality of life. Furthermore, studies of general quality of life in disease specific populations have mostly examined the importance of disease specific variables, and have generally yielded poor correlations of such variables and general quality of life. We attempted to model the emotional component of general quality of life in patients with prostate disease. MATERIALS AND METHODS: We integrated prospectively collected disease specific and nonspecific clinical and self-reported patient data. We also applied neural network and more conventional statistical tools to examine the relative use of various available analytical methodologies in modeling general quality of life. RESULTS: Neural networks created reasonably good models of the emotional component of general quality of life. Logistic regression analysis also created reasonably good models and, given current computational schemes, allowed for identification of significant inputs in the models more readily than did the feed-forward, back propagation neural networks. All models of general quality of life relied primarily on disease nonspecific inputs, including social support, activities of daily living and coping. CONCLUSIONS: Our observations suggested that efforts to optimize general quality of life in patients with prostate disease must integrate disease nonspecific variables.

Use of a moderated international Internet information exchange in the study of male reproduction.

It is clear that modern information technology is having a profound impact on the way researchers and clinicians exchange information. Use of the Internet is one example of how such change can be translated into scientific progress and improved patient care. Androlog, a moderated international information exchange, has proven to be very useful in the transfer of information pertaining to the study and treatment of male reproductive disorders. Allowing instantaneous dispersal of messages to members in 27 countries, this system has become a valuable source of scientific information, as well as an excellent forum for the discussion of a broad range of clinical and laboratory topics. Moderated-user groups such as Androlog are highly applicable to many other areas of urology. Establishment of such an information exchange requires only a modest investment in computer hardware and software and moderators who are willing to perform the necessary tasks of system administration and message review. Given the unique advantages provided by this method of communication, there is little doubt that systems such as Androlog will flourish in the future, providing a valuable tool in the advance of medical science.

Animal models that mimic human male reproductive defects.

All stages of male reproductive development and function are highly regulated, not only by the gonadotropins FSH, LH, and testosterone, but also by local control signals regulating cell function, mitosis, meiosis, and differentiation. The present approach to the treatment of many types of male infertility focuses on the use of suboptimal or defective sperm with protocols designed to overcome specific abnormalities. Elucidation of the molecular events required for normal male reproduction using animal model systems will eventually permit the design of new diagnostic procedures and therapeutic modalities. These advances may lead to enhancement or restoration of fertility in previously sterile men.

Tests of sperm function for evaluation of the male: Penetrak and Tru-Trax.

OBJECTIVE: To evaluate the Penetrak (Serono Laboratories, Norwell, MA) and Tru-Trax (Humagen, Charlottesville, VA) bovine cervical mucus (CM) penetration assays and to correlate results to parameters of semen analysis and male factor diagnosis. DESIGN: Prospective, nonrandomized, controlled study. PARTICIPANTS: Two hundred thirty-six males undergoing evaluation for male factor infertility and 37 fertile semen donors. MAIN OUTCOME MEASURES: Human sperm penetration in bovine CM measured by the Penetrak and Tru-Trax assay systems correlated to sperm density, motility, forward progression, and clinical diagnosis. RESULTS: Two parameters of semen analysis, motility and density were correlated to the distance traversed by the vanguard sperm in both Penetrak and Tru-Trax assays. Penetrak results were significantly correlated to male factor infertility diagnosis. CONCLUSIONS: Both assays were reliable and highly reproducible, and the Tru-Trax assay was correlated to its predecessor, Penetrak. Although Penetrak and Tru-Trax were correlated to motility and density, no correlation coefficient was > 0.6, suggesting that these assays measure a facet of sperm function that is independent of semen analysis.

A neural network to analyze fertility data.

OBJECTIVE: To program an artificial intelligence system, a neural network, and use it to predict results of sperm penetration in bovine cervical mucus (Penetrak assay; Serono Laboratories, Norwell, MA) and zona-free hamster egg penetration from the semen analysis. DESIGN: Results of 139 Penetrak assays, 1,416 zona-free hamster egg penetration assays, and the corresponding semen analyses were retrospectively analyzed by an artificial neural network. MAIN OUTCOME MEASURES: Classification errors of the neural network were compared with those of linear and quadratic discriminant function analyses. RESULTS: Data were separated into training and test sets. For the Penetrak result, linear and quadratic discriminant function analysis correctly predicted 58% and 74% of the training set results and only 64.1% and 69.2% of the test data, respectively. The neural network correctly predicted 92% of training set results and 80% of test set results. For the zona-free hamster egg penetration assay outcome, linear and quadratic discriminant function analysis correctly classified 66.3% and 46.0% of the training set and 64.9% and 44.7% of the test set, respectively. The neural network correctly classified 75.7% of the training data and 67.8% of the test data. CONCLUSIONS: Using the semen analysis, the neural network correctly classified 67.8% of zona-free hamster egg penetration assay results and 80% of Penetrak results it had not encountered previously, suggesting that this method of data analysis may be successfully employed to predict fertility potential.

Primary malignant melanoma of urinary bladder.

We report a case of primary malignant melanoma of the urinary bladder. Exclusion of other sites of melanoma confirmed the primary character of the tumor, and careful histologic examination proved it to be malignant melanoma. Six previously reported cases of bladder melanoma are reviewed. Therapy and prognosis are discussed.

Paracrine factors and the regulation of spermatogenesis.

MAIN PROBLEM: Although the gonadotropins and testosterone are required for normal spermatogenesis, it is believed that local control factors regulate spermatogenesis. For many years these regulatory factors had not been identified. Over the past five years, a number of growth factors have been identified in testis or isolated testicular cell types or secretions. Growth factors are key regulatory molecules which affect cell proliferation, meiosis, and differentiated function. These factors usually act in an autocrine (acting upon the cell which secreted it) or paracine (affecting another cell) manner and thus are involved in intercellular communications. METHODS: Growth factor secretion by testicular cell types or testis tissue has been analyzed using a variety of assays measuring cell proliferation in vitro, as well as assays using immunocytochemicals. Growth factor gene expression in testis has been analyzed by Northern blot analysis and in situ hybridization, which gives information concerning the stage and cell specific expression of the gene. Inbred strains of mice with mutations of deletions in a growth factor gene has been used to suggest the function of two specific factors in testicular development and growth. RESULTS: Among the growth factors expressed or secreted by testicular cell types, most are common to some other cell types in the body, such as transforming growth factors alpha and beta, epidermal growth factor, fibroblast-like growth factors, insulin-like growth factors, interleukins, endorphins, inhibin and activin, while others may be more testis specific such as mullerian inhibiting substance (anti-mullerian hormone) and Sertoli cell secreted growth factor.(ABSTRACT TRUNCATED AT 250 WORDS)

Artificial intelligence in medicine and male infertility.

MAIN PROBLEM: fertility data is inadequately assessed by traditional statistical methods for a variety of reasons. First, the principal test of male fertility potential, the Semen Analysis (SA) is a composite of several dissimilar parameters, and the SA and other laboratory tests of fertility potential reflect physiological mechanisms that interact in complex ways. Second, patient data is often fragmented, obtained from multiple sources. Importantly, 2 patients are required for the final result. METHODS: Novel and powerful computational method, the neural network, was explored to analyze fertility data. An integrated series of programs was written in the C computer language to implement a back propagation algorithm. A model data analysis system was chosen, predicting the penetration of zona-free hamster ova by sperm (Sperm Penetration Assay (SPA)) and the distance travelled by the farthest swimming sperm (Penetrak Assay) from the SA, for these 2 assays are generally believed by the reproductive medical community to be independent of the SA. The classification accuracy of the neural network was compared to 2 standard statistical methods, linear discriminant function analysis (LDFA) and quadratic discriminant function analysis (QDFA). RESULTS: A neural network could be trained to correctly predict the Penetrak result in over 80% of assays it had not previously encountered, and another network could predict the SPA outcome in nearly 70%. The neural network was superior to LDFA and QDFA in predicting both assay outcomes (for Penetrak: LDFA = 64%, QDFA = 69%; for SPA: LDFA = 65%, QDFA = 45%).(ABSTRACT TRUNCATED AT 250 WORDS)

A local direct effect of pituitary graft on growth of the lateral prostate in rats.

Prolactin and testosterone are synergistic in stimulating growth of the rat prostate. The lateral lobe is more sensitive to this synergism than the ventral and dorsal lobes. To investigate whether prolactin acts directly in the rat prostate or indirectly through another systemic mediator, anterior pituitary grafts (1 mm3) were implanted in the lateral prostate of castrated Sprague-Dawley rats in whom a 0.5 cm or 1.0 cm testosterone-filled silastic tubing was implanted subcutaneously at the same time. Rats were randomly assigned to receive either the pituitary or a muscle chip of similar size grafted beneath the fascia lateral to the lateral prostate. Twenty-one days later, serum prolactin levels were not elevated in pituitary-grafted animals and were not significantly different from those in muscle-grafted rats. The mean lateral prostate weight on the grafted side in pituitary-implanted rats with 1.0 cm testosterone tubing was 43% heavier than either that of the contralateral side or the corresponding weights in muscle-implanted rats. In pituitary-implanted rats with 0.5 cm testosterone tubing, the mean lateral prostate weight on the grafted side was 60% heavier than either that of the contralateral side or that of the corresponding weights in muscle-implanted rats. The weight of the ventral and dorsal lobes of the prostate was not significantly affected by the presence of pituitary grafts in one of the lateral lobes. The local effect of prolactin on the lateral prostate was further demonstrated by an overall decline in tissue concentrations of dihydrotestosterone in the grafted side. These results provided evidence to indicate that there was a direct effect of prolactin on growth of the lateral prostate in rats.