Join the club for FREE to access the whole archive and other member benefits.

AI model shows promise in speeding up cancer detection and diagnosis

Potential to fast-track patients to treatment and streamline CT scan analysis

30-Apr-2023

Key points from article :

AI model accurately identifies cancer, potentially speeding up diagnosis and treatment.

Developed by experts at the Royal Marsden NHS foundation trust, the Institute of Cancer Research, London, and Imperial College London.

Tool can identify if abnormal growths found on CT scans are cancerous.

Algorithm performs more efficiently and effectively than current methods.

AI model developed using CT scans of about 500 patients with large lung nodules and radiomics technique.

Results showed AI model could identify cancerous nodules with an AUC of 0.87, outperforming the Brock score and comparable to the Herder score.

AI model may help doctors make quicker decisions about patients with medium-risk abnormal growths.

Study, known as Libra, is in early stage, requiring more testing before introduction to healthcare systems.

Lung cancer is a major focus, as early detection significantly improves survival rates, but over 60% of lung cancers in England are diagnosed at late stages.

Study published in in Lancet's eBioMedicine journal.

Mentioned in this article:

Click on resource name for more details.

EBioMedicine

Medical journal covering all fields in the biomedical research

Imperial College London (ICL)

Public research university with an international reputation for excellence in teaching and research

The Institute of Cancer Research (ICR)

One of the world’s most influential cancer research organizations

Topics mentioned on this page:
AI in Healthcare, Cancer
AI model shows promise in speeding up cancer detection and diagnosis