Artificial intelligence has developed a cure for aggressive forms cancer In just 30 days, it was demonstrated that doctors’ notes could be used to predict patient survival.
Breakthroughs were made by separate systems, but they demonstrate the use of powerful technology far beyond generating images and text.
Researchers at the University of Toronto collaborated with Insilico Medicine to develop a treatment for hepatocellular carcinoma (HCC). AI A drug discovery platform called Pharma.
HCC is a type of liver cancer, but AI has discovered a previously unknown therapeutic pathway and designed a “novel hit molecule” that can bind to its target.
This system, which can also predict survival, was devised by scientists at the University of British Columbia and BC Cancer, who found the model to be 80% accurate.
AI developed a cancer drug (stock) in just 30 days from target selection after synthesizing just seven compounds.
AI is becoming a new weapon against deadly diseases as it can analyze vast amounts of data, uncover patterns and relationships, and predict the effectiveness of treatments.
Alex Zhavoronkov, Founder and CEO of Insilico Medicine, said: statement: “While the world has been fascinated by generative AI advances in art and language, our generative AI algorithms have successfully designed potent inhibitors of targets with AlphaFold-derived structures.”
The team used AlphaFold, an artificial intelligence (AI)-powered protein structure database, to identify a potential drug for treating hepatocellular carcinoma (HCC), the most common type of primary liver cancer. designed and synthesized drugs.
This feat was accomplished in just 30 days from target selection and synthesis of just seven compounds.
In a second round of AI-powered compound generation, researchers have found more potent hit molecules, but potential drugs still need to undergo clinical trials.
Feng Ren, Chief Scientific Officer and Co-CEO of Insilico Medicine, said:
“At Insilico Medicine, we saw a great opportunity to apply these constructs to an end-to-end AI platform to generate new therapeutics to tackle diseases with high unmet need. , is an important first step in that direction.
Another AI system identified characteristics unique to each patient and predicted 6-, 36-, and 60-month survival rates with over 80% accuracy.
The system used to predict life expectancy uses natural language processing (NLP) — the branch of AI that understands complex human language — to capture the oncologist’s notes after a patient’s first clinical visit. Analyzed.
The model identified unique characteristics for each patient and predicted survival at 6, 36, and 60 months with greater than 80% accuracy.
John-Jose Nunez, a psychiatrist and clinical research fellow at the UBC Center for Mood Disorders and BC Cancer, said: statement: ‘The AI essentially reads the consultation document as a human reads it.
“These documents contain many details such as the patient’s age, type of cancer, underlying medical conditions, past drug use and family history.
“AI combines all of this to paint a complete picture of patient outcomes.”
Traditionally, cancer survival rates have been calculated retrospectively and categorized by several common factors, such as cancer site and tissue type.
However, the model can pick up its own cues from the patient’s initial medical documentation to provide a more nuanced assessment.
The AI was trained and tested using data from 47,625 patients from all six BC cancer sites in British Columbia.
“Because the model was trained on BC data, it could be a powerful tool for predicting cancer survival in the state,” said Nunez.
‘[But] The beauty of neural NLP models is that they are highly scalable, portable, and do not require structured data sets. You can quickly train these models using local data and improve their performance in new regions. ”
