Themes

Blood film morphology

We aim to develop automated workflows for analysis of blood films.

Cardiovascular and cerebrovascular diseases

We are examining how Full Blood Count tests can be used to identify patients with heart and brain diseases earlier.

Federated Learning

We use Federated learning to ensure data privacy and security.

Haematological disorders

We are investigating how Full Blood Count data can be used to improve the diagnosis of blood disorders.

Iron deficiency

We are implementing a test for iron deficiency using the Full Blood Count.

Machine learning

We are developing sophisticated machine learning models for use with Full Blood Count data.

Malaria and other infectious diseases

Can our algorithms be applied to other infectious diseases, such as malaria?

New emerging outbreaks

Can we use our detection systems to identify new, unknown pandemics?

Pregnancy

We are exploring whether we can use Full Blood Count data to identify women at risk of serious complications during pregnancy.

Renal cancer

Can Full Blood Count data be used to identify individuals at high risk of renal cell carcinoma?

SARS-CoV-2

We have developed machine learning models which can detect the SARS-CoV-2 outbreak in Cambridge.

Sepsis

BloodCounts! Sepsis leverages detailed full blood count (FBC) data, electronic health records (EHRs), and advanced AI to detect immune response patterns associated with sepsis. By identifying signatures of the body’s response to infections, the project aims to improve the prediction, early detection, and personalised management of sepsis.