Scientists have created a new technique which has been proven to be more effective at detecting cervical pre-cancers than medical experts, according to a new report in the Journal of the National Cancer Institute. The new technique, called automated visual evaluation, was found to achieve 91% accuracy when detecting precancerous cells, beating human expert accuracy (69%) and pap smears (71%).
While cervical cancer is the fourth most common form of cancer found in women, medical advancements in both screening and vaccination have meant that women with access to quality healthcare are contracting the illness less often than ever. However, of the close to 600,000 women who develop cervical cancer every year, almost half die and the vast majority of them (90%) are from low-to-middle-income nations.
"Cervical cancer is now a disease of poverty, of low resources," commented the senior author of the report and the National Cancer Institute's Division of Cancer Epidemiology and Genetics doctor Mark Schiffman. "We are trying to find ways that are extremely cheap, extremely easy but very accurate, so that we can attack cervical cancer by vaccine and also a bit later through a simple technique that is cell-phone based or something like it."
Schiffman has been working on a cure for cervical cancer for more than 35 years. He and his team built the algorithm from 60,000 cervical images taken in Costa Rica using basic techniques involving a speculum, small light and a camera. The team aim to roll out the new technique over the next three to five years and in the meanwhile, will carry on enrolling new patients from all over the world for further clinical trials.
The results so far have been very promising and, with the help of a philanthropic group, Schiffman are leaving the new AI unpatented so it can remain as cheap as possible.
"I think now we have a possible tool that can go anywhere and not sacrifice scientific quality but actually offer a medically valid screen," Schiffman added.