The need and lack of healthcare information in India

This article was first published in my Times of India Blog Staying Wired.

In my previous post I had mentioned about the importance of Artificial Intelligence and Machine Learning in healthcare specially for countries like India where the population is large and availability of skilled medical professionals is scarce. But is the healthcare infrastructure of India in a state from where it can take this great leap forward.

The primary requirement to be met for being able to utilize the fruits of AI and ML, is the availability of data which can be fed into the systems to make them learn. As we humans learn by reading so do these machines. They can gobble up volume of medical data, sift through them, learn, and generate more meaningful output during diagnoses.

However, there must be context to the data. We cannot train an algorithm by feeding it medical data from Europe and expect them to yield meaningful results in a tropical country like India. With different environmental and weather conditions, there is difference in the nature of diseases and the agents which cause them.

However, the question is whether India is well equipped with the health data of its citizens which can be used for the purpose of training these models. The answer would be a resounding ‘no’. Apart from a few top tier public sector hospitals like AIIMS basic IT infrastructure is lacking in most places. In private sector though some of the big names have provisions for Electronic Medical Records (EMR) the same cannot be said for other small nursing homes and hospitals operating throughout the country.

From personal experience even in a leading private hospital in Kolkata I never got to access EMRs online. They seemed to have an online portal, but no one in the hospital knew how, from whom and where to get access.

Moreover, an EMR in most cases doesn’t translate in to a meaningful Electronic Health Record (EHR). In retail a well-used term is the ‘One Customer View’ through which a retailer knows his customer holistically; what he buys, which brand he likes, how much he spends, what are his/her dislikes and most of the other relevant preferences.

EHR should be able to provide healthcare agencies similar holistic view of a patient’s entire health history, so that in time of need or emergency there is no scrambling around looking for allergies etc. Transparent sharing of EHR across hospitals would also make it easier for patients to continue the correct course of treatment while shifting from one city to another.

Worldwide the adoption of EHR has been rapidly progressing. In most of the developed European nations the adoption rate is more than 90%. In USA as of 2014, 76% of hospitals and 97% of acute care hospitals had adopted for EHR. For India no certified figures could be found, some resources point the adoption to be in the region of 20-30% only.

Despite some recent advances with public healthcare spending in India below 1.5% of GDP not much change can be expected to take place. Globally most countries have understood the important part IT is to play in the healthcare domain. By 2020, the global healthcare expenditure is expected to reach $9 trillion out of which $1.7 trillion will be in technology; almost reaching one-fifth of the total.

It is quite a contradiction that India being home to some of most prominent names in information technology industry, is lagging poorly in revamping its own healthcare. There are multiple healthcare schemes launched by successive governments but all this while the allocation for health never reached 2% of the GDP. Even considering the emerging countries of the BRICS group, India stands out at the bottom when it comes per capita healthcare expenditure; just $75 for India as against $947 for Brazil at the top.

None of the fruits of new age technologies could be availed till this apathy towards healthcare is corrected to the core. Having a comprehensive EHR for all citizens would be a goldmine which is to be protected with an equivalent zeal. The data so far available is scant, scattered and localized.

About 72% of the rural and 79% of the urban residents today avail private sector services for healthcare. But over reliance on private sector would make it hard to realize the requirements of an integrated EHR framework. Government needs step in with the initial necessary capital investment, policy formulation and provide the necessary governance framework; since it is necessary that the information is not put to rogue use. Once the integration is achieved the benefits would just be exponential.

Artificial Intelligence and the future of healthcare

This article was first published in my Times of India Blog Staying Wired.

Anyone reading this post would know how predominant has been the terms ‘Artificial Intelligence’ and ‘Machine Learning’ in this millennium. Though these fields have been under the research radar of scientists from a much earlier period, it is only in the last few decades that AI and ML have matured out of the test-tubes to face real-world challenges. And healthcare is one field which stands to gain from that.

It would not be too far-fetched to predict that the advances in medical science like vaccination and genetics which helped to further human longevity, Artificial Intelligence would bring about the next quantum leap. And as we discuss multiple instances of applications of AI and ML have already started coming to the forefront.

In the detection of cancer, metastasis pathologists are faced with the time-consuming task of reviewing slides of high-resolution images covering every tissue under investigation. The images are in the magnitude of 10 gigapixels and a pathologist must go through each pixel to ensure that he isn’t missing anything important.

AI algorithms reading the visual patterns are expected to be between 5-10% more accurate than pathologists with unlimited time studying the same images. And since being machines they are expected to be more consistent as well. This increased accuracy and consistency can strongly fight off misdiagnoses.

In another brilliant example, Madurai based Arvind Eye Hospital has started testing a Google AI based interface which can provide early against diabetic retinopathy, which if untreated can lead to permanent blindness. However, with just 11 ophthalmologists for 10 lakh people, not everyone is expected to undergo regular eye checkups in India. Such AI interfaces, providing preliminary examination results fast and at low cost, can go a long way to bridge the gap w.r.t availability and reach of doctors.

AI systems have found extensive usage in diagnoses of common ailments along with predicting how long a patient would stay in hospital or chances of readmission and even death.

In China studies conducted on a wide base of patients have shown amazing results. AI systems diagnosed asthma with 90% accuracy as against physicians whose accuracy ranged from 80% to 94%. For gastrointestinal diseases, AI systems were 87% accurate while physicians were in the 82-90% bracket. Thus AI systems can be overwhelmingly reliable in terms of generating a consistently accurate outcome. And hopefully, with further proliferation, it will be cheap and maybe even open source sometime in future.

But that doesn’t mean there are no pitfalls. Anyone with access can fudge the medical records to fool AI systems. And many scientists have already proved so my performing tricks with AI systems which made these machines fall flat. So it can be well said that the introduction of AI will no way reduce the importance of the work a physician or a pathologist does. It only shifts the nature of work.

Pathologists and doctors can let AI systems perform the preliminary investigation while they get look at exceptions and outliers. For the patients, especially in countries like India where competent doctors are scarce to be found, AI systems could be the first line of the interface at primary healthcare facilities where preliminary diagnoses can take place.

We should be aiming at an augmented Healthcare system where physicians and AI can work hand in hand providing the best possible outcome for the patient. With the growing population and ever new complications in diseases arising, the field where humanity needs to embrace the combined might of Machine Learning and Artificial Intelligence most are not self-driving cars or productivity enhancing robots but healthcare.