Predicting hypogonadism in men based upon age, presence of erectile dysfunction, and depression

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.

Orthodontic Treatment Planning based on Artificial Neural Networks

In this study, multilayer perceptron artificial neural networks are used to predict orthodontic treatment plans, including the determination of extraction-nonextraction, extraction patterns, and anchorage patterns. The neural network can output the feasibilities of several applicable treatment plans, offering orthodontists flexibility in making decisions. The neural network models show an accuracy of 94.0% for extraction-nonextraction prediction, with an area under the curve (AUC) of 0.982, a sensitivity of 94.6%, and a specificity of 93.8%. The accuracies of the extraction patterns and anchorage patterns are 84.2% and 92.8%, respectively. The most important features for prediction of the neural networks are “crowding, upper arch” “ANB” and “curve of Spee”. For handling discrete input features with missing data, the average value method has a better complement performance than the k-nearest neighbors (k-NN) method; for handling continuous features with missing data, k-NN performs better than the other methods most of the time. These results indicate that the proposed method based on artificial neural networks can provide good guidance for orthodontic treatment planning for less-experienced orthodontists.

Identification of late-onset hypogonadism in middle-aged and elderly men from a community of China

In this study, we investigated the essential criteria for late-onset hypogonadism (LOH) syndrome based on the presence of symptoms associated with low testosterone levels in Han Chinese men. Blood tests for total testosterone (TT) and sex hormone–binding globulin (SHBG) were performed, and the aging male symptoms (AMS) questionnaire was conducted in a randomly selected cohort composed of 944 Chinese men aged 40 to 79 years from nine urban communities. Three sexual symptoms (decreased ability/frequency of sexual activity, decreased number of morning erections, and decreased libido) were confirmed to be related to the total and free testosterone levels. The thresholds for TT were approximately 12.55 nmol l⁻¹ for a decreased ability/frequency to perform sex, 12.55 nmol l⁻¹ for decreased frequency of morning erections, and 14.35 nmol l⁻¹ for decreased sexual desire. The calculated free testosterone (CFT) thresholds for these three sexual symptoms were 281.14, 264.90, and 287.21 pmol l⁻¹, respectively. TT <13.21 nmol l⁻¹ (OR = 1.4, 95%CI: 1.0–1.9, P = 0.037) or CFT <268.89 pmol l⁻¹ (OR = 1.5, 95%CI: 1.1–20, P = 0.020) was associated with an increase in the aforementioned three sexual symptoms. The prevalence of LOH was 9.1% under the criteria, including all three sexual symptoms with TT levels <13.21 nmol l⁻¹ and CFT levels <268.89 pmol l⁻¹. Our results may improve the diagnostic accuracy of LOH in older men.

Efficacy and safety of two different testosterone undecanoate formulations in hypogonadal men with metabolic syndrome

AIM

To investigate efficacy and safety of two different preparations of testosterone undecanoate (TU) in 52 hypogonadal men [mean age 57 yr and mean testosterone (T) < 320 ng/dl] with metabolic syndrome (MS).

SUBJECTS AND METHODS

Randomized, double-blind, double-dummy study with three parallel treatment arms [oral TU; transdermal placebo gel (P); im TU] administration for 12 months (mo). Each subject was randomized (1:1:3) to receive either oral TU (2 capsules of 40 mg/twice per day at breakfast and dinner, equalling a total dose of 160 mg/day; no.=10) for 6 mo and continued with im TU for further 6 mo, or P (3-4 g/day; no.=10) and im TU (1000 mg/12 weeks from week 6; no.=32) for 12 mo.

RESULTS

After 6 mo, im TU increased T and free- T levels (p<0.0001), and improved metabolic parameters [reduction in Homeostasis Model Assessment (HOMA) index, p<0.0001; waist circumference and fat mass, p<0.001, respectively], in International Index of Erectile Function-5 and Aging Males' Symptoms scores (p<0.01, respectively). After 12 months, im TU produced further increases in T and free- T levels (p<0.0001) and metabolic parameters (reduction in HOMA-index, p<0.0001; waist circumference p<0.0001; fat mass, p<0.001). No major adverse event due to T treatment occurred.

CONCLUSIONS

Clinical efficacy of T replacement therapy in hypogonadal men with MS is reached when its plasmatic levels approach into the medium-high range of normality (>5 ng/ml), although subjective threshold values may be different. Administration of im TU was more effective than oral TU to reach the target for T levels and to improve MS parameters. TU was safe over 12 months and discontinuation rates were similar to placebo.

Androgens and male aging: Current evidence of safety and efficacy

Many signs of aging, such as sexual dysfunction, visceral obesity, impaired bone and muscle strength, bear a close resemblance to features of hypogonadism in younger men. The statistical decline of serum testosterone in aging men is solidly documented. It has been presumed that the above features of aging are related to the concurrent decline of androgens, and that correction of the lower-than-normal circulating levels of testosterone will lead to improvement of symptoms of aging. But in essence, the pivotal question whether the age-related decline of testosterone must be viewed as hypogonadism, in the best case reversed by testosterone treatment, has not been definitively resolved. Studies in elderly men with lower-than-normal testosterone report improvement of features of the metabolic syndrome, bone mineral density, of mood and of sexual functioning. But as yet there is no definitive proof of the beneficial effects of restoring testosterone levels to normal in elderly men on clinical parameters. Few of these studies meet as yet rigorous standards of scientific enquiry: double-blind, placebo-controlled design of the study. The above applies also to the assessment of safety of testosterone administration to elderly men. There is so far no convincing evidence that testosterone is a main factor in the development of prostate cancer in elderly men and guidelines for monitoring the development of prostate disease have been developed. It is of note that there are presently no long-term safety data with regard to the prostate. Polycythemia is another potential complication of testosterone treatment. It is dose dependent and can be managed with dose adjustment.

Hypogonadism is associated with overt depression symptoms in men with erectile dysfunction

Depression and hypogonadism are associated with erectile dysfunction (ED). We evaluated the prevalence of both conditions in men presenting to an ED specialty clinic, and tested whether hypogonadism correlated with the presence of depressive symptoms using a validated questionnaire. From July 2001 to June 2003, 157 men referred to an ED specialty clinic prospectively filled the Center for Epidemiologic Studies Depression Scale (CES-D), the abbreviated International Index of Erectile Function (IIEF-5) and had testosterone serum levels drawn. Median age was 53 (range=21-85 years). Hypogonadism, defined as serum T (testosterone)<300 mg/dl, was present in 36% of patients. This proportion was higher in men over the median age compared to younger patients (45 and 26%, respectively, P=0.002). Overt depression symptoms, defined as a CES-D> or =22, were found in 24% of men. Mean age of men with overt depression was 49.9+/-10.1 years vs 55.1+/-15.8 years for those with CES-D<22 (P=0.02). Hypogonadal men were more likely to have overt depression scores compared to eugonadal counterparts (35 vs 18%, P=0.02). This association was statistically stronger after correcting for age in a multivariate linear model (P=0.005). The relative risk of having overt depression was 1.94 times higher in men with hypogonadal testosterone level (95% confidence interval: 1.13 to 3.7). We conclude that in an ED referral population, symptoms of hypogonadism and depression symptoms are fairly prevalent, and that overt depression symptoms are strongly associated with hypogonadism. Clinicians should consider testosterone measurements in all men with high depression symptom scores.

Association of specific symptoms and metabolic risks with serum testosterone in older men

CONTEXT

Although attention and concern about health disorders in aging men have been growing, the structure of psychological and somatic complaints of actual patients, not population-based cohorts, has not been elucidated in relation to sex hormone patterns and metabolism.

OBJECTIVE

The objective of the study was investigation of factors influencing complaint structures in aging male patients.

DESIGN

This was a cross-sectional cohort study.

SETTING

The study was conducted in an andrological outpatient department.

PATIENTS

Subjects included 434 consecutive male patients aged 50-86 yr.

MAIN OUTCOME MEASURES

The following hypotheses were measured: 1) psychosomatic complaints and metabolic factors in aging male patients are related to sex hormone levels in a symptom-specific manner, and 2) patients form subcohorts.

RESULTS

A clear-cut threshold for late-onset hypogonadism was not found; rather, prevalence of psychosomatic symptoms and metabolic risk factors accumulated with decreasing androgen levels. For example, androgen-induced prevalence of loss of libido or vigor increased below testosterone concentrations of 15 nmol/liter (P < 0.001), whereas depression and diabetes mellitus type 2 (also in nonobese men) were significantly more present in men with testosterone concentrations below 10 nmol/liter (P < 0.001). Erectile dysfunction was identified as a composite pathology of metabolic risk factors, smoking, and depressivity, whereas only testosterone concentrations below 8 nmol/liter contributed to that symptom (P = 0.003). Cluster analysis revealed aging men to present within three independent groups characterized by psychosomatic complaints, metabolic disorders, and sexual health problems. These subgroups of patients exhibit distinct features in terms of androgen levels, age, and body mass index.

CONCLUSIONS

There is no evidence that a uniform structure of testosterone concentrations and complaints exists within the cohort of elderly male patients. Rather, in aging male patients, psychosomatic complaints and metabolic risk relate to testosterone in a symptom-specific manner.