FDA Approves Roche’s Biomarker Test for At-Risk HPV Infections

Earlier this week, Roche announced that the FDA approved its CINtec PLUS Cytology as the first biomarker-based triage test for women whose primary cervical cancer screening results are positive for the human papillomavirus (HPV).

The test uses the cobas 4800 HPV which simplifies clinical decision making by providing simple results so clinicians and women understand the additional steps to take.

“Despite being nearly 100 percent preventable, cervical cancer is still one of the most common cancers in women worldwide. To address this, Roche is dedicated to investing in next-generation biomarkers that will significantly advance screening strategies and support global efforts to eradicate this disease,” Thomas Schinecker, CEO of Roche, said in the announcement.

“We are committed to providing women with the protection and care they deserve.”

FDA looked at data from the Roche-sponsored registrational IMPACT trial which enrolled more than 35,000 women in the US to validate CINtec PLUS Cytology as a test in various scenarios.

Most of the time, HPV infections are treatable, but some women may develop pre-cancerous cervical lesions that, if left untreated, may progress to cervical cancer. Therefore, early identification is crucial.

The American Cancer Society highlighted that nearly 13,800 new cases of invasive cervical cancer will be diagnosed in the US in 2020. Of those women, 4,290 will die from the disease this year. Reoccurring infection with HPV is the main cause of cervical cancer in more than 99 percent of cervical cancers worldwide.

CINtec PLUS Cytology provides information about which HPV-positive women may need, from referrals to colonoscopy versus repeat testing. This system is a step in the right direction to individualize women’s care and prevent overtreatment and undertreatment.

Technology is gradually becoming a vital asset in the healthcare space, specifically for diagnoses and treatments.  

Last January, researchers from the National Cancer Institute (NCI) and Global Good launched an artificial intelligence tool to analyze more digital images of a woman’s cervix and identify any precancerous signs with notably more accuracy than human experts.

During a study in Costa Rica in 1990, researchers used more than 60,000 cervical images collected during cervical cancer screenings. The study consisted of more than 94,000 women and the follow-up lasted 18 years.

Researchers gained a significant amount of information on which cervical changes developed into pre-cancers and which didn’t through the tool. The AI outperformed all standard screening tests. It achieved an area under curve of 0.91, while human experts achieved 0.69 and conventional cytology received 0.71.

“Our findings show that a deep learning algorithm can use images collected during routine cervical cancer screening to identify precancerous changes that, if left untreated, may develop cancer,” said Mark Schiffman, MD, MPH, of NCI’s division of center epidemiology and genetics, and a senior author or the study.

“In fact, the computer analysis of the images was better at identifying precancer than a human expert reviewer of Pap tests under the microscope (cytology).”

The new method had the potential to improve cervical cancer screenings for various healthcare organizations, including those with limited resources or communities where women’s health experts may be hard to find.

The study further shows that artificial intelligence and other technologies have the ability to enhance and accelerate the performance of human clinicians.

“When this algorithm is combined with advanced in HPV vaccination, emerging HPV detection technologies and improvements in treatment, it is conceivable that cervical cancer could be brought under control, even in low-resource settings,” Maurizio Vecchione, executive vice president of Global Good concluded.