Current projects using the system-wide dataset for Bristol, North Somerset and South Gloucestershire
Systems Modelling project
Lack of availability of social care services is a recognised contributor to the pressures faced by hospitals. This project will model the flow of patients from acute discharge readiness through to longer-term domiciliary home visits and care home placements, with the aim of determining the optimal balance of capacity along this clinical pathway.
This project is part of the Health Data Research UK South Better Care Partnership
Lead: Richard Wood
Antimicrobial Resistance (AMR) project
Antibiotic drugs are a crucial part of modern medicine, but rising levels of resistance and lack of new drugs in development mean that we must use existing drugs carefully. Clinicians often lack information about their patients’ antibiotic history, and the drug susceptibility of patients’ infections. We will analyse data from the Bristol, North Somerset and South Gloucestershire (BNSSG) System-wide dataset of linked primary care, secondary care and laboratory records to optimise antibiotic choice for patients based on their individual history and clinical characteristics, as well as their and the population’s risk of resistance.
This project is part of the Health Data Research UK South Better Care Partnership.
RAPCI Project: Rapid COVID-19 Intelligence to improve general practice response
This project aims to understand how GP practices are coping with substantially increased demand combined with an immediate move to remote consultations (written, telephone and video) in response to the COVID-19 pandemic, and to rapidly share successful innovation across general practice.
This project is funded by NIHR School for Primary Care Research.
Lead: Dr Mairead Murphy
Understanding factors behind asthma attack and presentation at ICU
Identification of high risk asthma patients for ICU would enable early intervention. This project will investigate the care usage patterns and clinical attributes of patients with asthma who present at ICU (and A&E) and will thereafter assess whether GPs can better manage these patients in the primary care system.
Lead: Dr Jenny Cooper
Automated machine learning identification of clinical pathways
Identification of clinical pathways is not always straightforward. This project will examine use of machine learning methods to extract information on clinical pathways from routinely-collected data.
Lead: Dr Jenny Cooper
Forecasting the effects of Covid-19 on patient experience and service delivery for mental health care
This project is investigating the pressures that mental health services in BNSSG may face during the Covid-19 pandemic. A discrete-time simulation is being used to model patient flows around the various settings of care.
Lead: Ben Murch
Predicting “Did Not Attends”
This projected looked at what attributes, appointment details, and wider determinants were predictors of whether a patient would attend a scheduled outpatient appointment. Applications of the work could include a call based reminder service which was shown to be cost effective given the accuracy of the model.
Lead: Dr Adrian Pratt