Indian scientists apply AI for personalised cancer treatment

Scientists at the S. N. Bose National Centre for Basic Sciences have introduced an artificial intelligence (AI)-based system that may transform the traditional approach to cancer treatment. This is reported by IANS, a TV BRICS partner, citing India’s Ministry of Science and Technology.

In previous decades, doctors relied on assessing the size and extent of tumour spread. The new system evaluates the molecular individuality of the disease, which explains why two patients with the same stage of cancer may experience different disease progression, and enables a personalised approach to therapy selection.

“Cancer is not just a disease of growing tumours -- it is powered by a set of hidden biological programmes called the hallmarks of cancer. These hallmarks explain how healthy cells turn malignant: how they spread, evade the immune system, and resist treatment,” India’s Ministry of Science and Technology explained.

Using the new AI system, the research team analysed 3.1 million individual cells across 14 types of cancer and created synthetic ‘pseudo-biopsies’ that map tumour states driven by key characteristics. This extensive dataset enabled the AI to study how such critical features as metastasis, immune evasion and genomic instability interact to drive tumour growth and the development of therapy resistance.

“The method was validated on 20,000 real-world patient samples from eight major datasets. […] For the first time, scientists could actually visualise how hallmark activity rises with advancing cancer stage,” the Ministry stated.

The new artificial intelligence system can read the molecular ‘logic’ of a cancerous tumour and predict its behaviour. This will help clinicians select drugs that specifically target the active markers of an individual patient’s tumour, as well as identify aggressive forms of the disease at early stages.

Photo: gorodenkoff / iStock