Clinician and Clinical Decision Support

Lack of staff and training can be barriers to good care of critically ill patients. To support staff in low resource settings, VITAL is developing clinician support tools using machine learning, deep learning and data gathered from patient monitors and point-of-care Imaging.

Decision Support for Sepsis

We are developing a tool to allow early identification of septic shock, allowing medical staff to intervene early in treatment.

Leads: Louise Thwaites and David Clifton

Decision Support for Dengue

We are developing clinical decision support tools to predict patients at risk of severe dengue and dengue shock using data from patient monitors and specifically designed wearable monitors.

Leads: Pantelis Georgiou, Bernard Hernandez Perez and Sophie Yacoub

Decision Support for Tetanus

We are developing a clinical decision support tool to early identify autonomic nervous system instability in patients with tetanus.

Leads: Louise Thwaites and David Clifton

Decision Support for Imaging

VITAL is using deep learning technology to develop clinician support tools to
support inexperienced users carry out point-of-care ultrasound assessment of the heart and lungs.

Leads: Sophie Yacoub, Reza Razavi and Alberto Gomez, Marcus Schultz

Decision Support in TB Meningitis

We are creating a clinical decision support tool to predict patients likely to respond to treatment with TB meningitis, using deep learning methods.

Leads: Guy Thwaites and Marc Modat

Work Update

24 August 2020

Data scientists and biostatisticians are using data already collected in patients with dengue and tetanus to create predictive models of patients who will progress to severe disease. Our aim is to allow clinicians to predict which patients are likely to deteriorate as soon as they are admitted to hospital, allowing them to closely monitor these patients or intervene with specific treatments.  The implementation science team are working with doctors and nurses to work out how best these support systems will work in practice.