BloodCounts launches healthcare project utilizing artificial intelligence for blood tests
Research initiative BloodCounts launched a medical project in Singapore to build artificial intelligence models that analyse full blood count tests for early disease detection
SINGAPORE – 26 October 2026 – The Cambridge Centre for Advanced Research and Education in Singapore (CARES) has launched its inaugural healthcare project, BloodCounts!, in partnership with leading local hospitals National University Health System (NUHS) and SingHealth. Utilizing advanced analytics and artificial intelligence (AI), the project aims to uncover new patterns from complete blood count (CBC) tests and facilitate earlier disease detection across Singapore and the global healthcare landscape.
BloodCounts! is spearheaded by Professor Weisi Lin of Nanyang Technological University and Professor Michael Roberts of the University of Cambridge. By harnessing the vast amount of CBC data generated daily by healthcare systems, the initiative seeks to build sophisticated AI models capable of identifying subtle changes in blood cells associated with various diseases, ultimately improving early diagnosis, prognosis, and clinical decision-making.
The project brings together a global consortium of researchers and clinicians from Singapore, the UK, Belgium, The Gambia, Ghana, India, and the Netherlands. NUHS and SingHealth will provide anonymized CBC and clinical data, as well as scientific expertise in haematology, laboratory medicine, oncology, neurology, and biomedical informatics.
The research team will host a launch event on 29 October to introduce the project to researchers, clinicians, and partners. Supported by a $120 million National Research Foundation, Singapore (NRF) grant under the AI-for-Science (AI4S) initiative, BloodCounts! represents a significant step toward leveraging existing healthcare data to enhance patient outcomes through innovative AI-driven solutions.
Written by urgent.news from Vietnam Investment Review's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
