Harvard Medical School's AI screening system could produce more accurate cancer treatment programs

An artificial intelligence screening system developed by scientists at Harvard Medical School in Cambridge, Mass., can identify homologous recombination deficiency, a cancer-causing genetic defect that often goes undetected, according to a press release. If integrated into widespread use, the AI system could expand treatment options for cancer patients with HR deficiency.

Most clinical genetic tests are unable to accurately detect HR deficiency, according to the release, which can be treated with PARP inhibitors, a type of medication used most commonly to treat breast cancer patients with BRCA mutations.

"We suspect there are many more patients without BRCA mutations who could benefit from PARP inhibitors, but doctors do not know which ones they are. Our approach could help close that gap," Peter Park, PhD, professor of biomedical informatics at HMS's Blavatnik Institute, said in a statement.

In tests, the new algorithm, called SigMA, correctly identified 74 percent of cell samples with HR deficiency, compared to other screening systems that typically identify HR-deficient cancer cells with only 30 to 40 percent accuracy.

"Pinpointing actionable genetic biomarkers and treating patients with drugs that specifically target the relevant cancer-driving pathways is at the heart of precision medicine. We believe our algorithm can greatly enhance physicians' ability to deliver such individualized therapy," Dr. Park said.

More articles on artificial intelligence:
Approving AI for medical use: 7 things to know
Google quietly disbands another AI advisory board
Partners HealthCare pledges to make AI tools accessible to clinicians, researchers

© Copyright ASC COMMUNICATIONS 2019. Interested in LINKING to or REPRINTING this content? View our policies by clicking here.

 

Top 40 Articles from the Past 6 Months