A5003021584- Maternal and Perinatal Health Interventions
- Emergency and Acute Care Studies
- Nutritional Studies and Diet
- Child Nutrition and Water Access
- Family and Patient Care in Intensive Care Units
- Ethics in Clinical Research
- Machine Learning in Healthcare
- Maternal and fetal healthcare
- Artificial Intelligence in Healthcare and Education
- Simulation Techniques and Applications
- Food Security and Health in Diverse Populations
Edinburgh Cancer Research
2024-2025
University of Glasgow
2020
MRC/CSO Social and Public Health Sciences Unit
2020
Background: Identifying women at highest or lowest risk of perinatal intensive care unit (ICU) admission may enable clinicians to stratify antenatally so that enhanced elective ICU be considered excluded in birthing plans. We aimed develop a statistical model predict the maternal admission. Methods: studied 762,918 pregnancies between 2005 and 2018. Predictive models were constructed using multivariable logistic regression. The primary outcome was Additional analyses performed allow...
Factors increasing the risk of maternal critical illness are rising in prevalence maternity populations. Studies general care populations highlight that severe is associated with longer-term physical and psychological morbidity. We aimed to compare short- outcomes between women who required admission during pregnancy/puerperium those did not. This a cohort study including all delivering Scottish hospitals 01/01/2005 31/12/2018, using national healthcare databases. The primary exposure was...
Prediction models frequently face the challenge of concept drift, in which underlying data distribution changes over time, weakening performance. Examples can include predict loan default, or those used healthcare contexts. Typical management strategies involve regular model updates triggered by drift detection. However, these simple policies do not necessarily balance cost updating with improved classifier We present AMUSE (Adaptive Model Updating using a Simulated Environment), novel...
IntroductionMany early years interventions, e.g. UK’s Family Nurse Partnership, aim to provide additional support higher need families prevent poor health and development. Most prediction studies using cohort surveys have had limited success in identifying which target for such interventions. Objectives ApproachTo examine whether the breadth volume of information available linked administrative data can predict childhood overweight (defined International Obesity TaskForce cut-offs) at age 5...