By Stacy Liberatore For Dailymail.com 1:02 PM Mar 19, 2023, updated 1:26 PM Mar 19, 2023
Artificial intelligence has developed a treatment for an aggressive form of cancer in just 30 days and has shown it can predict a patient’s survival rate based on doctor’s notes.
The breakthroughs were made by separate systems, but demonstrate how the powerful technology can be used far beyond the generation of images and text.
University of Toronto researchers collaborated with Insilico Medicine to develop a potential treatment for hepatocellular carcinoma (HCC) using an AI drug discovery platform called Pharma.
HCC is a form of liver cancer, but AI discovered a previously unknown treatment route and designed a “novel hit molecule” that could bind to that target.
The system, which can also predict survival, is the invention of scientists at the University of British Columbia and BC Cancer, who found the model to be 80 percent accurate.
AI developed the cancer treatment (strain) in just 30 days after target selection and after synthesizing just seven compounds
AI is becoming the new weapon against deadly diseases due to the technology’s ability to analyze vast amounts of data, uncover patterns and connections, and predict the effects of treatments.
Alex Zhavoronkov, Founder and CEO of Insilico Medicine, said in a statement: “While the world has been mesmerized by advances in generative AI in art and language, our generative AI algorithms have succeeded in creating effective inhibitors of a target with an AlphaFold-derived structure to develop.”
The team used AlphaFold, an artificial intelligence (AI)-based protein structure database, to design and synthesize a potential drug to treat hepatocellular carcinoma (HCC), the most common type of primary liver cancer.
The feat was accomplished in just 30 days after target selection and after synthesizing just seven compounds.
In a second round of AI-assisted drug generation, the researchers discovered a more potent hit molecule — although any potential drug would still need to undergo clinical trials.
Feng Ren, Chief Scientific Officer and Co-CEO of Insilico Medicine, said: “AlphaFold broke new scientific ground by predicting the structure of all proteins in the human body.
“We at Insilico Medicine saw this as an incredible opportunity to take these structures and apply them to our end-to-end AI platform to develop novel therapeutics to address diseases with high unmet needs. This paper is an important first step in that direction.’
Another AI system identified unique characteristics for each patient and predicted survival at six months, 36 months and 60 months with more than 80 percent accuracy
In a real-world setting, machine learning-based software has greatly improved the identification of lung nodules on chest X-rays.
The system used to predict life expectancy used natural language processing (NLP) — a branch of AI that understands complex human language — to analyze the oncologist’s notes after a patient’s first consultation visit.
The model identified unique characteristics for each patient and predicted survival at six months, 36 months and 60 months with more than 80 percent accuracy.
John-Jose Nunez, a psychiatrist and clinical researcher at the UBC Mood Disorders Center and BC Cancer, said in a statement: “The AI reads the consultation document essentially as a human would read it.
“These documents contain many details such as the patient’s age, type of cancer, underlying health conditions, past substance use and family histories.
“The AI combines all of this to paint a complete picture of patient outcomes.”
Traditionally, cancer survival rates have been calculated retrospectively and categorized according to only a few generic factors such as cancer location and tissue type.
However, the model is able to pick up on unique cues in a patient’s initial consultation document to provide a more nuanced assessment.
The AI was trained and tested using data from 47,625 patients at all six BC Cancer sites across British Columbia.
“Because the model is trained on BC data, it is a potentially powerful tool for predicting provincial cancer survival,” Nunez said.
‘[But] The great thing about neural NLP models is that they are highly scalable and portable and do not require structured data sets. We can quickly train these models using local data to improve performance in a new region.”
