30 Days to a Cancer Cure: How Artificial Intelligence Changed the Game
Artificial intelligence has developed a cure for an aggressive form of cancer in just 30 days and has shown that it can predict patient survival using doctors’ records.
The hacks were implemented through separate systems, but they show how the use of powerful technology goes beyond the creation of images and text.
University of Toronto researchers have been working with Insilico Medicine to develop a potential treatment for hepatocellular carcinoma (HCC) using an AI drug development platform called Pharma.
The AI has discovered a previously unknown healing pathway and has developed a “hit novel molecule” that can bind to that target. The system, which can also predict survival, was invented by scientists from the University of British Columbia.
Artificial intelligence has become a new weapon against deadly diseases, as the technology is able to analyze huge amounts of data, identify patterns and relationships, and predict the effects of treatments.
“While the world has been fascinated by generative AI developments in art and language, our generative AI algorithms have been able to develop powerful target inhibitors with an AlphaFold-derived structure,” said Alex Zavoronkov, founder and CEO of Insilico Medicine. in a statement.
The team used AlphaFold, an artificial intelligence (AI)-based protein structure database, to develop and synthesize a potential drug for the treatment of hepatocellular carcinoma (HCC), the most common type of primary liver cancer.
This feat was accomplished in just 30 days of target selection and after only seven vehicles had been built.
And in the second round of AI-assisted compounding, researchers have found an even more powerful molecule, although any potential drug still needs to pass clinical trials.
“AlphaFold has opened up a new scientific framework for predicting the structure of all proteins in the human body,” said Feng Ren, Chief Scientist and Co-CEO of Insilico Medicine. “We at Insilico Medicine saw this as an incredible opportunity to take these structures and apply them to our comprehensive an artificial intelligence platform to create new treatments for diseases with high unmet need. This document is an important first step in this direction.”
The system used to predict life expectancy uses natural language processing (NLP) — a branch of artificial intelligence that understands complex human language — to analyze an oncologist’s records after an initial visit to a patient’s consultation.
The model identified the unique characteristics of each patient and predicted six-month, 36-month, and 60-month survival rates with over 80% accuracy.
The documents contain many details such as the patient’s age, type of cancer, underlying health conditions, past drug use, and family history.
And AI brings it all together to paint a complete picture of patient outcomes.
Traditionally, cancer survival rates have been calculated retrospectively and classified by only a few general factors such as cancer location and tissue type.
However, the model is able to capture unique clues in the patient’s initial consultation document to provide a more accurate estimate.
Source: Daily Mail
You must log in to post a comment.