Event models for tumor classification with SAGE gene expression data

Serial Analysis of Gene Expression (SAGE) is a relatively new method for monitoring gene expression levels and is expected to contribute significantly to the progress in cancer treatment by enabling a precise and early diagnosis. A promising application of SAGE gene expression data is classification of tumors. In this paper, we build three event models (the multivariate Bernoulli model, the multinomial model and the normalized multinomial model) for SAGE data classification. Both binary classification and multicategory classification are investigated. Experiments on two SAGE datasets show that the multivariate Bernoulli model performs well with small feature sizes, but the multinomial performs better at large feature sizes, while the normalized multinomial performs well with medium feature sizes. The multinomial achieves the highest overall accuracy.

Sex talk? overcoming barriers about sex and contraception after childbirth

Anecdotal evidence tells professionals that childbirth is the best form of contraception. However, sexual health problems are the very common after childbirth with Barrett et al (2000) arguing that only 15% of women who have a postnatal sexual problem reported discussing it with a health professional. As health professionals with a predilection for the ‘clinical’ and the ‘prescriptive’ we organise antenatal classes to discuss bathing the baby and post partum reunions to recount birth stories, but often fail to address sexual health problems and contraception after birth.(Glazener 1997). Many women who have carefully used contraception for years prior to pregnancy are often not helped to re-engage with the issues following birth. This would seem to be a particular problem for the most vulnerable parents such as adolescent mothers and their partners (Social Exclusion Unit 1999, 2004) where some young women go on to have more than one baby in a short time period (Reeves 2003). The focus of this paper is to explore the apparent general failure of health professionals to discuss sex after childbirth and provide information regarding reliable contraception. Glazener (1997) tells us that health professionals are encouraged to educate and prepare patients antenatally, for example to be trained to identify problems and deal with them openly and sympathetically. What is brought into question is why this form of rigorous support is not extended to providing sexual health advice in the immediate and often vulnerable postnatal period and why this provision is not a priority for some groups. The paper will explore if this situation caused by a lack of training or is it a symptom of our culture and a British attitude towards sex and contraception.