World Health Day 2019: Maternal & child health are priority areas for AI in India

AI can go a long way in helping India attain a crucial sustainable development goal in health care.

The honorable interim finance minister Shri Piyush Goyal has made an allocation in the interim budget for a National Center for Artificial Intelligence (AI) and a National AI portal. This will have far-reaching implications in many fields — the biggest in the field of healthcare if AI is used effectively.

In fact, the buzz words in healthcare of late are machine learning (ML) and AI. Both these technologies have gained significant interest in the healthcare space in India and around the world.

In my opinion, we are yet to scratch the surface of the uses of AI and ML and should take a page from the finance minister's faith in the technology to make the best use of it in healthcare. Of the many specialties in healthcare and medicine in India, AI has a whole lot to offer in maternal and child healthcare, where it is also required more than most others.

Meeting Developmental Goals for 2030

The current healthcare indices in maternal and child health are far from desirable in India. India ranks 128th in terms of meeting the United Nations’ (UN) health-related Sustainable Development Goals (SDGs) by 2030, with low scores on air pollution, sanitation, hepatitis B and child wasting. India is home to 46.6 million stunted children, a third of the world's total. With 46.6 million children who are stunted, India tops the list of countries followed by Nigeria (13.9 million) and Pakistan (10.7 million). One-third of all women of reproductive age in India have anemia. India tops the list of 10 nations contributing 60 percent of the world’s premature deliveries.

The Sustainable Developmental Goals envisioned for 2030. Image: United Nations

The Sustainable Developmental Goals envisioned for 2030. Image: United Nations

The SDG targets for 2030 are to reduce the global maternal mortality ratio to less than 70 per 100,000 live births. By 2030, end preventable deaths of newborns and children under 5 years of age, with all countries aiming to reduce neonatal mortality to at least as low as 12 per 1,000 live births and under-5 mortality to at least as low as 25 per 1,000 live births. It is very clear from the data above that maternal and child health should be high up in the priority list for the long-term benefits it offers. It will ensure that the future of our country stays healthy by having the best outcomes for mothers and their babies.

Clear Protocol

Healthy mothers are key to birthing an entire population that is healthy. AI as a tool in maternal and child health care will benefit individuals and communities across the country. It will go a long way in helping us (and other countries around the world) attaining one of the most important sustainable development goals in healthcare.

There are many reasons why maternal and child health lends itself to artificial intelligence. The entire period from pregnancy to childbirth to preventive care for mother and child is defined: it extends from preconception to when the child is 5 years of age. The period of pregnancy has very clear protocols for the number of visits, the lab and radiology investigations that need to be done, the medications that need to be taken, the complications that need to be looked for and a definite endpoint which is the birth of the child.

Representational image. Image courtesy: HealthX

Representational image. Image courtesy: HealthX

Similarly, the care of the child is also dictated by protocols in both the immediate care after birth and preventive care for 5 years until the immunizations are completed. The data for the above touch points are available in many settings of maternal and child care like Government clinics and hospitals, NGOs, insurance companies and private health care organizations.

What does India need to do? 

  • Identify use cases & questions to be answered where AI will give us the best bang for our buck, and gather data needed for those use cases
  • Find out where we can get the retrospective data from and how. This will be needed to enable machine learning
  • Find a method of collecting prospective data to enable both, machine learning and artificial intelligence
  • Computing power and technology to put all this information to use in the most practical manner
  • Write algorithms to help us solve real-world problems
  • Implement solutions that are AI-generated to help improve maternally and child health

After having identified the 'why' and 'what' as mentioned above, we need to have a plan for how we can accomplish this. We need to have key thought and opinion leaders identifying use cases and pointing out weaknesses and areas that need addressing. There should be representation from health care providers from a wide cross-section of providers in the maternal and child health field. Data required for the use of AI in healthcare should be identified by subject matter experts. We will then have to identify suitable sources of data to find the best way of refining and collating it. For the data to be used meaningfully by the system, we need to create a data ingestion tool that helps machine learning.

A pregnant woman lies on an examination table as a nurse places her hands on her stomach during a check up at a community health centre in Chharchh. Reuters

A pregnant woman lies on an examination table as a nurse places her hands on her stomach during a check-up at a community health center in Chharchh. Reuters

Algorithms will need to be prepared by medical and technology experts working closely together. These algorithms should help us identify high-risk pregnancies, women at risk for anemia, pregnancies that may lead to preterm deliveries, infants and toddlers at risk for being unimmunized, babies in the neonatal intensive care units that are at risk for sepsis and poor outcomes.

With huge volumes of data, ML and AI can actually even suggest methods of improving outcomes. Once we have solutions suggested by artificial intelligence, we need to have a concerted and coordinated effort by all stakeholders to implement them on the ground in a practical and realistic manner to improve maternal and child health.

Devil is in the data

The allure of AI is great and I believe it will help us solve many problems faster than we ever imagined we could. However, while the cliché is that the “devil is in the details” but in this case "the devil is in the data"! There can be no machine learning or AI without data. Unfortunately, this is oft forgotten in many discussions.

Representational image.

Representational image.

Medical data is pleomorphic — it comes in many shapes and forms. Unfortunately, these forms include unstructured, fragmented, unreliable, illegible, written, digital, inaccessible data. It will undoubtedly take a humongous effort to compile the data required in the manner required to enable ML and AI. This alone will require a number of stakeholders to work together. It will include patients, too, whose data will be needed to get the ball rolling.

The Government will have to give the necessary impetus by framing the rules to enable the easy availability of data for the greater good. All agencies, private and public, will need to feed data into a common data ingestion tool. There needs to be a collaboration with the Government, teaching hospitals, WHO, Gates Foundation, UNICEF and health insurance providers for getting as much as data as possible. Agencies like Nasscom should be liaisons between data sources and technology companies to optimize ML and AI.

These steps are common to the use of ML and AI in any healthcare specialties and not just maternal and child health. It will no doubt be difficult, but not impossible. Being an eternal optimist and supporter of the technology, I would bet on AI and ML making a massive, welcome change in healthcare systems.

Given the importance and impact it can have on maternal and child health, I hope it happens sooner rather than later.


The author is the Director of Medical Services at Cloudnine Group of Hospitals, and a mentor and advisor to the Life Sciences and Health Care Innovation Forum at NASSCOM. Views expressed are personal.

Find latest and upcoming tech gadgets online on Tech2 Gadgets. Get technology news, gadgets reviews & ratings. Popular gadgets including laptop, tablet and mobile specifications, features, prices, comparison.