US researchers using AI to analyse more than 10,000 studies of cannabis and cancer have found a significant majority showed improved outcomes for patients using the medicine.
Published in Frontiers in Oncology, the team used ‘sentiment analysis’ to determine how many studies had positive, neutral or negative views on the medicine’s ability to treat cancer and its symptoms.
Lead author and research director at the Whole Health Oncology Institute (WHOI), Ryan Castle, told The Guardian: “Our goal was to determine the scientific consensus on the topic of medical cannabis, a field that has long been dominated by a war between cherrypicked studies.”
Funded by Cancer Playbook, which works with WHOI to collect, analyse and share data on patient-reported outcomes, the project examined data from observational studies on medical cannabis and cancer as well as laboratory research.
Castle said: “In order to move beyond bias – conscious or not – it was essential to use a large-scale, radically inclusive methodology based on mathematical reasoning. We wanted to analyse not just a handful, but nearly every major medical cannabis study to find the actual points of scientific agreement.”
While the team hoped to find “moderate consensus” about the potential of cannabis to ease cancer symptoms, Castle said they were surprised to find the results exceeded their “best-case scenario” of 55%.
“It wasn’t 55-45 [reporting improved outcomes], it was 75-25,” he said.
The findings supported the medicine as a treatment for cancer-related inflammation, appetite loss and nausea.
“That’s a shocking degree of consensus in public health research, and certainly more than we were anticipating for a topic as controversial as medical cannabis,” Castle added.
The Guardian said the study “also showed that cannabis has the potential to fight cancer cells themselves, by killing them and stopping their spread”, but acknowledged such claims remain controversial and unproven.
Castle said he hoped the findings would encourage the US Drug Enforcement Administration to complete the much-delayed process of reclassifying cannabis so it is no longer federally illegal, making clinical research easier.
“We are not arguing that the standards for adopting new cancer treatments should be lower,” he said. “We are arguing that medical cannabis meets or exceeds those standards, often to a greater extent than current pharmaceutical treatments.”
