The project is described in a study published July 3 in Scientific Reports. The algorithm compared the molecules of cancer-treating drugs to those found in foods to produce a map of 110 food-based molecules with seemingly similar effects to clinical cancer treatments.
The model concluded that plant-based foods including tea, carrots, celery, oranges, grapes, cilantro, cabbage and dill show the most similar treatment potential to cancer-treating drugs. “Food represents the single biggest modifiable aspect of an individual’s health and the machine learning strategy described here is a first step in realizing the potential role for ‘smart’ nutritional programs in the prevention and treatment of cancer,” the study’s authors wrote.
The model was powered by the DreamLab platform developed by international telecommunications company Vodafone and the Garvan Institute of Medical Research in Sydney. Users around the world can download the DreamLab app, which utilizes smartphones’ unused processing power to run applications to aid in cancer treatment, all while the idle phones are charging overnight.
More articles about AI:
AI algorithm predicts inpatient violence from clinical notes in EHRs
Kaiser Permanente researchers develop AI tool to predict HIV risk
In healthcare, ethical AI is a life-or-death issue: Q&A with AI Ethics Lab’s founder and director
