Researchers from the Indian Institute of Technology Madras (IIT-Madras) recently developed PIVOT, an artificial intelligence (AI)-based tool that can predict cancer-causing genes. In a statement, the Institute said the tool will ultimately help devise personalised cancer treatment strategies.
Cancer is a leading cause of death across the world and accounted for nearly one in six deaths in 2020, according to data from the World Health Organisation. It is an uncontrolled growth of cells that can occur due to mutations in oncogenes, tumour suppressor genes, or both. However, not all mutations result in cancer. Therefore, it is important to identify genes that cause cancer to create appropriate, personalised cancer treatment strategies.
According to IIT-Madras’ statement, PIVOT predicts cancer-causing genes using a model that utilises information on mutations, expression of genes, and copy number variation in genes and perturbations in the biological network that results from an altered gene expression. The tool applies machine learning (ML) to classify genes as tumour suppressor genes, oncogenes, or neutral genes. PIVOT successfully predicted both the existing oncogenes and tumour-suppressor genes like TP53, and PIK3CA, among others, and new cancer-related genes such as PRKCA, SOX9, and PSMD4.
An expert explained that cancer, being a complex disease, cannot be dealt with in a one-treatment-fits-all fashion. As cancer treatment increasingly shifts towards personalised medicine, models like PIVOT, which aim at pinpointing differences between patients are very useful. Current cancer treatments are known to be detrimental to the overall health of the patient. Knowing the genes responsible for the initiation and progression of cancer in a patient can help determine the combination of drugs and therapy most suitable for their recovery.
Although there are tools currently available that identify personalised cancer genes, they use unsupervised learning and make predictions based on the presence and absence of mutations in cancer-related genes. This study, however, is the first to use supervised learning and considers the functional impact of mutations while making predictions.
IIT-Madras researchers have built AI prediction models for three types of cancer including breast invasive carcinoma, colon adenocarcinoma, and lung adenocarcinoma. The research team is working on a list of personalised cancer-causing genes that can help identify suitable drugs for patients based on their individual cancer profiles.
Technology in healthcare has not only been successful in treatment strategies but as a tool to connect citizens quickly and easily with medical professionals. In May, the National Health Authority (NHA), under its Ayushman Bharat Digital Mission (ABDM), launched the Ayushman Bharat Health Account (ABHA) mobile application, an upgraded version of the National Digital Health Mission (NDHM) health records application.
As OpenGov Asia reported, the updated version of the ABHA app has a new user interface and added functionalities that enable individuals to access their health records anywhere. Users can create an ABHA address that can be linked to a 14-digit randomly generated ABHA number. The application also allows users to link their health records created at ABDM-compliant health facilities and access them on their smartphones. Users can upload physical health records in ABDM-compliant health lockers and share digital health records (diagnostic reports, prescriptions, COVID-19 vaccination certificates) through the ABDM network.