Cluster validity indices for mixture hazards regression models.

In the analysis of survival data, the problems of competing risks arise frequently in medical applications where individuals fail from multiple causes. Semiparametric mixture regression models have become a prominent approach in competing risks analysis due to their flexibility and easy interpretation of resultant estimates. The literature presents several semiparametric methods on the estimations for mixture Cox proportional hazards models, but fewer works appear on the determination of the number of model components and the estimation of baseline hazard functions using kernel approaches. These two issues are important because both incorrect number of components and inappropriate baseline functions can lead to insufficient estimates of mixture Cox hazard models. This research thus proposes four validity indices to select the optimal number of model components based on the posterior probabilities and residuals resulting from the application of an EM-based algorithm on a mixture Cox regression model. We also introduce a kernel approach to produce a smooth estimate of the baseline hazard function in a mixture model. The effectiveness and the preference of the proposed cluster indices are demonstrated through a simulation study. An analysis on a prostate cancer dataset illustrates the practical use of the proposed method.

Risk factors of urinary frequency among women aged 60 and older in Taiwan.

OBJECTIVE: To assess the associated risk factors for daytime urinary frequency among Taiwanese women aged = 60 years. MATERIALS AND METHODS: Daytime urinary frequency, defined by the International Continence Society, and its associated problems were evaluated, and medical history and sociodemographic variables were recorded. A total of 2,410 women were selected by a multistage random sampling method. The factors were assessed by frequency and Pearson's ?2 test using a significance level of < 0.05. RESULTS: A total of 621 women of those initially selected in the study died before completion of this study. Face-to-face interviews with 1,521 women were completed, producing a response rate of 85.0% (1,521/1,789 women). The prevalence of daytime urinary frequency was significantly related to body mass index (p = 0.018), diabetes mellitus (p = 0.017), hypertension (p = 0.015), previous drug allergy (p = 0.003), smoking (p = 0.005), hormone therapy (p = 0.019), parity (p = 0.019), and urinary incontinence (p = 0.000). However, there was no association between urinary frequency and previous gynecologic surgery, hysterectomy, alcohol consumption, marital status, childbirth, and age of menopause. CONCLUSION: The results of this study showed a relatively high risk of urinary frequency development in patients with urinary incontinence, diabetes mellitus, hypertension, obesity, and smoking that are preventable, modifiable, or controllable. Better quality of health education for these women, drawing their attention to the associated factors, may have an impact on the prevalence of urinary frequency.

Prevalence of urinary frequency among women aged 60 years and older in Taiwan.

OBJECTIVE: To evaluate the prevalence of daytime urinary frequency among Taiwanese women aged 60 years and older. MATERIALS AND METHODS: There were an estimated 1.25 million female residents aged 60 years and over in Taiwan in 2000. A sample of 2,410 women was selected using a multistage random sampling method. Face-to-face visits with 1,523 women were completed by trained professional interviewers within 3 months of the subjects selection. Questions about urinary frequency and other lower urinary tract symptoms, sociodemographics, reproduction, and medical and surgical histories were recorded. The factors were assessed by frequency and Pearson's Chi-squared test using a significance level of < 0.05. RESULTS: The prevalence of urinary frequency in Taiwanese women aged 60 years and over was 18.8% (286/1,521). The response rate was 85.0% (1,521/1,789). For those who complained of frequency, 45.8% voided 8-15 times a day, 37.8% voided 16-23 times a day, 1.7% voided 24-31 times and a day, and 14.7% voided more than 31 times a day. The prevalence of urinary frequency was significantly associated with age (p < 0.001). CONCLUSION: Urinary frequency is a common symptom in menopausal women and is significantly related to age. More than half of the women interviewed experienced intervals of < 1 hour between visits to the restroom during the day.