Poonam Pandey may not have lost her life due to cervical cancer, but every year, more than 70,000 Indian women succumb to cervical cancer.

Pandey's tactics to draw attention to the condition is abhorrent and disrespectful to say the least, but the reality is that cervical cancer is the second leading cause of cancer among women between ages 15-44 in India. It is not only highly preventable but also highly treatable when detected timely. Yet, cervical cancer, like other women's health issues, remains low on the priority list for technological disruption and funding. (Also read: Poonam Pandey's death stunt puts spotlight on cervical cancer)

There are more than 200 strains of human papillomavirus (HPV) and most infections caused by HPV are actually harmless and go away on their own. However, about 12 strains result in a majority of cancer cases of the vulva, vagina, cervix, penis, anus, mouth and throat. The sad reality is that HPV is actually the most prevalent sexually transmitted disease and nearly everyone will get exposed to and infected by one of the strains of HPV at some point in their lives.

While the statistics seem intimidating, the good news is that there is hope. Because cervical cancer is virus driven, as opposed to other cancers which are caused by internal cell replication issues, it's also easier to immunize and prevent against HPV. Merck’s Gardasil vaccine, till very recently, was the only vaccination available widely in the market. However, its costs were prohibitive.

Now, the good news is that India’s own Serum Institute of India has developed a vaccine for HPV called Cervavac which is now being made available at 1/10th of the price. In fact, there is talk in the proposed union budget to make it a part of the government vaccination program as well. This is an incredibly welcome move. In many countries, HPV is a part of national immunization programs including Bhutan (in 2010), Thailand (2017), Sri Lanka (2017), and the Maldives (2019).

Another great news is that if cervical cancer is detected early, there is an excellent treatment and recovery outcome. However, here is where the good news ends. While we have moved ahead significantly in efforts to prevent cervical cancer, technology to predict risk, identify HPV, and treat it, still lags behind.

Firstly, the current process of identifying cervical cancer, a pap smear, is not designed to be scalable. Getting a pap smear involves a gynecologist scraping off a few cells from the cervix of a woman and sending it for an analysis. This method is intrusive and while most women don’t experience pain, many avoid it due to discomfort or embarrassment.

Secondly, there are only 70,000 gynecologists in India for nearly 360 million women of reproductive age. Pap smears are usually performed in a gynecologist’s clinic or a hospital, therefore making it inaccessible to most.

Thirdly, pap smears rely on visual examination and are therefore prone to human error and prevent detection at very early states.

A lot of young and unmarried women hesitate to ask their gynecologists about pap smears due to the social stigmas and taboos that may surround the test. The World Health Organisation has recognised these issues and has recommended a more recent technology, the DNA test for HPV. However, in India, the costs for this test are prohibitive.

AI/ML based predictive models have a lot of potential to break barriers of invasiveness, over reliance on human input, and cost. There are many factors which can drive HPV prediction including behavioral, socio-economic, and demographic in addition to reported symptoms and medical history. Some of these include having multiple sex partners, being sexually active at a young age, belonging to a lower socio-economic class, smoking, having a history of herpes, HIV or chlamydia and so on.

Symptomatically also, irregular bleeding like brownish discharge, spotting, bloody discharge with an unusual smell etc., are factors that can enable quick triage and detection. This is a small sample set from a very extensive list. We have built a predictive model that not only diagnoses current conditions but predicts issues like HPV and cervical cancer risk based on some of these variables.

Using AI/ML based technology, symptoms and medical history can get instantly diagnosed and this can play a large role in not only detecting their current issue but also in predicting issues in the future like cervical cancer. Such models using AI for inspection of cervical cancer cells can greatly help improve early detection of cervical cancer and the avoidance of unnecessary deaths.

Poonam Pandey’s methods to draw attention to cervical cancer cannot be endorsed. However, now that we are talking about cervical cancer, let’s focus not on the theatrics of it but on improving vaccine availability and technologies for early detection where AI/ML does bear a lot of promise.

(Divya Kamerkar is a Biologist and Global Health fellow from Yale University and CEO of Pinky Promise, an AI/ML based women's health platform; Dr Reema Shah is an Obstetrician and Gynecologist and Medical Director of Pinky Promise; Akanksha Vyas is an engineer and mathematician with 15+ years of AI/ML work and the CTO of Pinky Promise)