Click here to watch this seminar
Presentation 1: Children’s Urgent Care Provided in the Right Place Every Time
By: Sam Relins
Abstract: Bradford is home to one of the country’s leading hospital-at-home services – the Ambulatory Care Experience or ACE. Children suffering with health problems, that may traditionally have been admitted to a hospital ward, can instead receive treatment at home. The familiar household setting reduces anxiety for child and parent and frees up much needed space and resources in hospitals. This project aims to use data analysis and machine learning to increase the accuracy of referrals and better inform decision making within ACE. Using anonymised data collected at the time a child is referred to the service, modern statistical methods can be used predict the most suitable treatment setting for each patient. In particular, the project aims to produce models that can not only predict the likelihood of successful treatment in the ACE service, but also the level of confidence (or lack thereof) in this prediction. This information can then be provided as a tool to clinicians, to aid them in making the best referral decision for every patient every time.
Presentation 2: Exploring the predictors of low birthweight between pre-austerity and austerity periods in the Bradford Better Start area.
By: Alex Dalton
Abstract: Low birthweight in Bradford is considerably higher than the rest of the UK, particularly in areas of Bradford suffering from high levels of material deprivation. The Born in Bradford cohort (2007-2011) and their Better Start cohort (2016-2020) allows low birthweight to be studied across a multi-ethnic community, and compared between the pre-austerity and austerity periods. The rich, longitudinal dataset enables gestational and socio-economic factors associated with low birthweight to be investigated.
This talk utilises data visualisations and statistical analysis to study and identify such associations, along with whether those associations have changed over time. Where factors are identified as predictors of low birthweight, the project aims to develop a predictive model.
Low birthweight has been linked to poor health outcomes and the nature of its role (whether causal or correlated) is heavily studied and debated. Thus, identifying any meaningful indicators for low birth weight is relevant to this debate and explores the feasibility of reducing the rate of low birth weight.
Presentation 3: Analysing and building cohorts in the OMOP common data model.
By: James Lazarus
Abstract: When conducting medical studies one of the most challenging aspects is obtaining the data with issues in privacy; the number of patients required; as well as research results needing be drawn from many disparate data sources and compared and contrasted. To extract data for analysis purposes traditionally requires strict data use agreements. Thus, a common data model is used to alleviate this need by eliminating this extraction step. However, retrieving these cohorts can be challenging. The aim of this project is to design and build a cohort building library, analysis scripts, along with written tutorials in order to make data retrieval and analysis from the common data model as easy and as fast as possible.
If you wish to ask the presenters any questions or offer feedback, please email LIDA