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

Abstract

Hypogonadism, a disorder associated with aging, can cause significant morbidity. As clinical manifestations of hypogonadism can be subtle, the challenge and the burden of diagnosis remain the responsibility of the clinician. Four different analytic methods were used to predict hypogonadism in men based upon age, the presence of erectile dysfunction (ED) and depression. 218 men were classified by age, serum testosterone level, the presence of ED and depression. Depression was determined by the Center for Epidemiologic Studies Depression Scale (CES-D). ED was assessed by the Sexual Health Inventory for Men (SHIM). Hypogonadism was defined as a serum testosterone level o300 ng/dl. An artificial neural network (ANN) was programmed and trained to predict hypogonadism based upon age, SHIM, and CES-D scores. Subject data was randomly partitioned into a training set of 148 (67.9%) and a test set of 70 (32.1%). The ANN processed the test set only after the training was complete. The discrete predicted binary output was set to (0) if testosterone level was o300 ng/dl or (1) if 4300 ng/dl. The data was also analyzed by standard logistic regression (LR), linear and quadratic discriminant function analysis (LDFA and QDFA, respectively). Reverse regression (RR) analysis evaluated the statistical significance of each risk factor. The ANN can accurately predict hypogonadism in men based upon age, the presence of ED, and depression (receiver-operating characteristic ¼ 0.725). A four hidden node network was found to have the highest accuracy. RR revealed the depression index score to be most significant variable (P ¼ 0.0019), followed by SHIM score (P ¼ 0.00602), and then by age (P ¼ 0.015). Hypogonadism can be predicated by an ANN using the input factors of age, ED, and depression. This model can help clinicians assess the need for endocrinologic evaluation in men.

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

“…In fact, we have previously shown that depression scores can be used as a clinical aid to predict hypogonadism using an artificial neural network model. 24 The present study lends further support to this concept.…”

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

“…Sexual symptoms are therefore of diagnostic importance in elderly men but should suggest androgen deficiency only when testosterone levels are clearly sub-normal 325. The presence of multiple symptom-specific testosterone thresholds indicates that different functional thresholds exist for different androgen-dependent targets 326293031. Our study suggests that some symptoms of LOH may manifest at higher concentrations of androgens than other symptoms ( Table 2 ), which suggest that testosterone thresholds may be symptom-specific26 or that the phenotype upon which the symptoms of androgen deficiency are based does not apply in all respects to aging men 32.…”

Androgens and male aging: current evidence of safety and efficacy

“…On the basis of the above observations it is clear that the symptoms of testosterone deficiency are not uniformly and predictably related to values of blood testosterone, which may lead to different diagnostic criteria for testosterone deficiency. So, the conclusion seems inevitable that the clinical manifestations of hypogonadism are multifactorially determined and that the diagnosis should not only depend on the measurement of testosterone but proper assessment should comprise somatic and psychological npg aspects in addition to measurement of testosterone [29].…”