Analysing stillbirth data using dynamic self organizing maps

Even with the presence of modern obstetric care, stillbirth rate seems to stay stagnant or has even risen slightly in countries such as England and has become a significant public health concern [1]. In the light of current medical research, maternal risk factors such as diabetes and hypertensive disease were identified as possible risk factors and are taken into consideration in antenatal care. However, medical practitioners and researchers suspect possible relationships between trends in maternal demographics, antenatal care and pregnancy information of current stillbirth in consideration [2]. Although medical data and knowledge is available appropriate computing techniques to analyze the data may lead to identification of high risk groups. In this paper we use an unsupervised clustering technique called Growing Self organizing Map (GSOM) to analyse the stillbirth data and present patterns which can be important to medical researchers.

Male sex and pre-existing diabetes are independent risk factors for stillbirth

AIM: To determine whether the risk of stillbirth is associated with male fetal sex, fetal growth and maternal factors in an Australian population. METHODS: A retrospective secondary data analysis of 16 445 singleton births was performed using a tertiary referral centre obstetric database (1995-1999). Univariate and multiple logistic regression analyses were performed. RESULTS: Stillbirth complicated 1% of the pregnancies in the study population, and 59% of stillbirths were associated with a male fetus. Significant characteristics associated with stillbirth were intrauterine growth restriction (IUGR), birth defects, gestational age, Aboriginal ethnicity, previous stillbirth, parity greater than three and placental abruption. Male stillbirths were more likely to occur at a later gestation (median gestation 30.5 weeks, range 20-43 weeks) compared to females (median 25 weeks, range 20-40 weeks), P = 0.01. Sixty per cent of IUGR fetuses were female (P < 0.001). Male sex (odds ratio (OR) 1.5, confidence interval (CI) 1.01, 2.17, P = 0.04) and maternal type 1 diabetes (OR 4.7, CI 1.58, 14.19, P = 0.006) were independently associated with stillbirth. CONCLUSION: Male fetal sex and pre-existing diabetes are independent risk factors for stillbirth. Diabetes remains a significant risk for stillbirth even with contemporary monitoring and clinical management. Those diabetic pregnancies where the fetus is male require appropriate monitoring and timely interventions to achieve an optimal outcome.

The challenges and future considerations regarding pregnancy-related outcomes in women with pre-existing diabetes

Ineffective management of blood glucose levels during preconception and pregnancy has been associated with severe maternal and fetal complications in women with pre-existing diabetes. Studies have demonstrated that preconception counseling and pre-pregnancy care can dramatically reduce these risks. However, pregnancy-related outcomes in women with diabetes continue to be less than ideal.

This review highlights and discusses a variety of patient, provider, and organizational factors that can contribute to these suboptimal outcomes. Based on the findings of studies reviewed and authors’ clinical and research experiences, recommendations have been proposed focusing on various aspects of care provided, including improved accessibility to effective preconception and pregnancy-related care and better organized clinic consultations that are sensitive to women’s diabetes and pregnancy needs.