News Excerpt:

A supercomputer and AI (iOncology AI), developed by researchers from the All India Institute of Medical Sciences (AIIMS) Delhi promises to identify the best cancer therapy for their patients.

• With iOncology AI, which employs a supercomputer in Pune and a high-capacity server called Charak I at the National Cancer Institute campus in Jhajjar, doctors are attempting to determine the most common type of genetic mutation in their patients, helping them narrow in on the best treatment option.

Objective of iOncology AI:

• iOncology AI aims to sequence the genomes of 3,000 cancer patients who are currently seeking treatment at AIIMS.
• It also aims to address a fundamental question: Does a patient’s genetic makeup correlate with the efficacy of diverse cancer therapies?

How does the AI tool work?

• The platform, developed with Pune’s Centre for Development of Advanced Computing, allows doctors to store cancer patients’ blood test and lab reports, scans and ultrasound reports and their history. 
• Along with collecting and collating data, the AI-enabled platform can also read the different types of datasets and help doctors make decisions.
• After studying the clinical data and genomic makeup of a couple of thousand cancer patients, the tool will help the doctors select the appropriate treatment for the next patient.
• This tool can also help in targeted treatments in resource-constrained settings where genomic studies might not be possible.
• When a scan or histopathology report is uploaded on the platform, the trained AI can automatically flag the ones with certain abnormalities. 
• For example, an extremely small tumour that a radiologist might miss at first. The AI will flag it. This can help in early detection of cancers in some cases.
• This data can help oncologists create their own prevention strategies and standard protocols.

Can the tool address all types of cancer?

• The research will focus on five types of cancers that are the most common, deadliest, or have immunotherapies available — breast, ovarian, head, and neck, colorectal, and two types of blood cancers. 
• At present, the platform is trained only for breast and ovarian cancer. 
• It already has various models for CT scan prediction, ultrasound image, histopath prediction, mammogram image prediction and detection and classification of the tumour.

AI and cancer care: The big shift

• Globally, there is an increasing interest in the use of AI for cancer treatment as it can help doctors – from developing new therapies to diagnosing patients at early stages of the disease and selecting appropriate treatments. 
• Studies have shown that certain AI-based models were able to identify individuals at high risk of developing pancreatic cancers up to three years earlier. 
  • This is game-changing considering that most get diagnosed only when the cancer has advanced or metastasised.
• Similar results have been observed for breast and lung cancers as well. 
  • For example, the AI tool being developed by the Harvard Medical School, which is similar to AIIMS but is specific for colon cancers.
• The model is being trained to predict survival accurately and provide insights for treatment response based on tumour pathology, radiology images, and genomic data.