How cellphones may save black women from cervical cancer.
Our book review on 21 lessons for the 21st century hinted at the future of A.I. in the health industry. Today
An algorithm from 20-year-old photos was designed to detect pre-cancerous behaviors in the cervix. in the photos, the algorithm proved more accurate than human expert reviewers and all standard screening tests in detecting pre-cancerous changes. after training the computer to read images, the computer was trained to detect a healthy cervix, a worrisome cervix and a pre cancerous cervix.over 60,000 photos were used from a 1990’s Costa Rican study in which of 9,400 women participate.
The AI technique, called automated visual evaluation, found precancerous cells with 91 percent accuracy. According to a report published in the Journal of the National Cancer Institute. In comparison, a human expert review found 69 percent of pre-cancers, while lab tests like Pap smears found 71 percent.
The algorithm was more accurate among women aged 25-49, who face the highest risk of cervical cancer. the AI algorithm was even more accurate, finding 97.7 percent of pre-cancerous cells.
The highest rate of cervical cancer is older black women ages 60-85. However, with older people having less usage of cell phones, will they even benefit or believe that this can help them? How will the public health market this to an aging population that feels modern technology is too complicated?
Furthermore, access to screenings plagues many African American women, Especially in Alabama. In November of 2018 the human rights report titled “it should not happen” exposed black women dying from cervical cancer. There’s a black belt of counties in Alabama which is historically poor high African American population. Out of the 17 counties, only 4 have at least one obstetrician-gynecologist.
57 year- old Darcy C. has to pay $150 for a 2.5 hour trip for her screening, despite a $700 a month income. In Alabama, women are dying at a higher rate of cervical cancer than anywhere else in the world.
This barrier to healthcare for cervix screenings maybe solved with A.I. usage of screening saving thousands of lives. The problem may not be the technology however but the aging population perception of it.