India’s healthcare challenges are well known. The issues plaguing the system garnered even more attention when India faced the brunt of the Covid-19 pandemic. It revealed gaps in our healthcare infrastructure, sparking a conversation on how India can be better equipped to deal with such contingencies in the future.
This article also intends to start a similar conversation. It talks about how a specific branch of technology can be implemented to benefit the most underserved people of this country — the rural populace.
For a country of our size and diversity, developing a system that can provide adequate healthcare to each person is no easy task. The different areas of the country have different healthcare needs; sickle cell disease, for example, is a major health concern in central India () while non-communicable diseases are a concern in Kerala.
States like Andhra Pradesh and Uttar Pradesh have to deal with the highest number of deaths due to heatstroke (). Accordingly, the type of healthcare needed by the citizens, and the state’s healthcare priority, differs as well.
Some states are well served while some others are not. In the SDG India Index 2020-21 report by NITI Aayog, against a target of 45 health workers for every 10,000 population, several states have very low numbers. Jharkhand has four and Telangana has 10. On the other hand, states like Karnataka, Andhra Pradesh, and Kerala are way ahead, with 70, 95, and 115 health workers per 10,000 population respectively.
On the supply side, India does not have adequate healthcare providers. According to the Fifteenth Finance Commission, we have one allopathic doctor for every 1,511 people, and one nurse for every 670 people, while the World Health Organization (WHO) recommends a ratio of 1:1,000 and 1:300 respectively.
Training doctors is resource-intensive, expensive, and requires hands-on training. Even if the government multiplies its efforts to reach the market, it is not certain when we will be able to meet our growing demands.
The natural question that comes up is, what should we do in this situation? Improvements in mortality rates, healthcare coverage, and manpower take time. Perhaps, there is something that can be deployed with relative speed.
Of course, buzzwords like artificial intelligence (AI), machine learning, and big data get thrown around often. Most people have heard of AI being the next big thing, but how can it help us find practical solutions to the problems we face today?
First, the basics.
Artificial intelligence is, as we can intuitively understand from the term, the replication of human intelligence. In a sense, we are using computers and machines to perform tasks that were once only possible with the help of a human being.
The advantage of artificial intelligence is that while we humans have limited memory and abstraction ability, machines have a near-permanent and infinite memory. This makes them suitable for recognising complex patterns and making decisions when there are a large number of variables involved. Therefore, it is uniquely apt for the healthcare paradigm.
How? We will now talk about some use cases that illustrate how AI can transform a village resident’s experience with healthcare.
The heart of the health issue lies in the lack of quality and quantity of the healthcare provided that works in rural communities. A recent study () has shown that, according to the National Sample Survey Office (NSSO), rural India constitutes approximately 66 per cent of the total population, but only 33 per cent of all health workers are practising in rural facilities. This is not only because of the general lack of healthcare personnel in the country, but also because most healthcare providers move to regions where their professional and financial incentives are higher — larger cities and metros.
Healthcare professionals that are left behind to serve in rural areas often lack networks and exposure to the latest treatment options, which negatively impacts their careers and the service they can provide. How to incentivise healthcare professionals to work in rural areas is a multi-dimensional question, which is another conversation in itself. However, AI can improve the quality of healthcare given to patients.
A system that could be useful in this scenario is called CDSS — Clinical Decision Support System. These are AI algorithms that have been trained using data sets of confirmed cases and work based on recognising patterns. For example, an algorithm that has been trained to examine x-ray scans of human lungs can help inexperienced doctors notice peculiarities in a scan they might have missed otherwise, guiding them towards the correct diagnosis. This reduces the need for constant mentorship while increasing the quality of healthcare provided.
However, either due to lack of accessibility or financial troubles, people in rural regions avoid going to the doctor until the matter becomes unmanageable. That is where ASHAs, that is, accredited social health activists, come in.
ASHAs are not medical professionals, but they are the first link between a family and the healthcare system of the country. They have limited knowledge, and keeping every worker up to date with the latest emerging health problems is another concern. An application based on an AI system that would take into account the statistics of the local incidence of specific health issues can help ASHAs give preliminary care to patients while more suitable care is on the way.
ASHAs that are trained to work on a digital platform can thus ensure that proper care is provided to every person in the country. This preliminary analysis done by AI could be used by the consulting doctor to speed up the diagnosis and treatment process, which increases the efficiency of medical staff.
Once the disease has been determined, and treatment provided, we have to deal with another stumbling block. For certain diseases like tuberculosis, which require continuous treatment over several months, an AI algorithm can be used to identify patients that are at the most risk of being unable to follow the treatment regime, either due to lack of literacy, poor economic status, or remoteness. This can help government and healthcare personnel direct their limited resources to the site at which they can make the most impact or save most lives.
On the other hand, what if it is a disease for which there is no accessible cure or treatment available?
Rural Indians often suffer from a high case load of neglected tropical diseases or NTDs. These diseases include chikungunya, dengue, and rabies, which are often found in the poorer populace, living in underdeveloped regions of the world. Pharmaceutical companies lack economic incentives to focus on researching these diseases, leaving them ‘neglected’. Artificial intelligence can help decrease the development cost of the cure by accelerating and automating the process of drug discovery.
AI has already been used to ascertain potential causes and cures for schistosomiasis (), an NTD from sub-Saharan Africa that affects 220 million people around the world. Similar efforts have been made for leishmaniasis, malaria, and tuberculosis (). Therefore, the introduction of AI in these fields can drastically change the quality of life of people living in rural regions.
That’s not all — we can prevent illness altogether with the help of AI systems. Artificial intelligence frameworks can deduce patterns; for example, seeing commonalities in symptoms among the patients of a region can reveal the hidden conditions that might be plaguing a community before they become a major problem. This can detect not only epidemics of communicable diseases such as flu and chickenpox, but also health concerns such as water contamination.
Such an early warning system can allow the government to take prompt action before the situation gets worse. It will enable the government to redirect the manpower needed to deal with the health issue at the place of incidence rapidly.
Of course, these applications need standardised electronic databases as well as interconnected systems in place to allow researchers, government executives, as well as the private sector access to this data, so that they can figure out viable models and neural networks, which can be applied in various scenarios. This would require a focus on designing multi-disciplinary courses to train people in the system to work in both the healthcare and digital landscape.
Another point of concern is that AI algorithms learn iteratively, which means that they improve with time. This might require constant monitoring of AI systems because we are dealing with a sensitive domain.
So, while AI technology has huge potential, it also requires continuous government encouragement and private sector enterprise. The challenges are immense but not insurmountable, and this article has been written with the asha, or hope, that with combined effort and investment, we can use this seemingly elusive technology to improve the lives of people who need this intervention the most.
This article has been published as part of Swasti 22, the Swarajya Science and Technology Initiative 2022. Read other Swasti 22 submissions.
As you are no doubt aware, Swarajya is a media product that is directly dependent on support from its readers in the form of subscriptions. We do not have the muscle and backing of a large media conglomerate nor are we playing for the large advertisement sweep-stake.
Our business model is you and your subscription. And in challenging times like these, we need your support now more than ever.
We deliver over 10 - 15 high quality articles with expert insights and views. From 7AM in the morning to 10PM late night we operate to ensure you, the reader, get to see what is just right.
Becoming a Patron or a subscriber for as little as Rs 1200/year is the best way you can support our efforts.