Shahid Akhter, editor of ETHealthworld, spoke with Dr. Vikram Venkateswaranco-chair of the health care task force of the IET Future Technology Panelto discover the role of technology in disease surveillance that can culminate in identifying the spread of disease well in advance.
Disease Surveillance: Trends
Disease surveillance is probably the most important aspect evolving in the global healthcare industry. We look at data today that has proliferated across all media, especially digital media, and there is a huge opportunity to use that data to not only prevent disease but also to predict the next outbreak. These data have been used sporadically, such as in the fight against Ebola or HIV in certain cases, but the pandemic has given a new twist to this whole panorama. Today we have the opportunity not only to collect the data at the source, but also to have a high level of computing available in technologies like the cloud, which can be leveraged to predict the next epidemic. Although we caught up late during the COVID pandemic, the lessons learned globally have been that we can accelerate this development and use it very effectively to identify and combat the next pandemic.
Disease Surveillance Program: Idea and Inspiration
The disease surveillance program we are piloting as part of our IET Healthcare working group was inspired by similar attempts by researchers around the world to understand the spread of disease. A simple infectious disease use case, especially during the monsoon season in India, was a good opportunity to not only see how far we have progressed in our technology adoption, but also to see if this could be used in a real world scenario. like predicting the next epidemic or the next spread of the disease. The idea was to capture the information at the source, classify it, pinpoint exact locations, and see if we can triangulate where these mentions and data sources were coming from and if local authorities could be alerted to the spread of infection.
social analytics for the Rapid Transformation of Health for India (SARTHI) project
We call this pilot “SARTHI” which is “Social Analysis for Rapid Transformation in Health for India”. What we have done is look at publicly available data sources, this includes consumer forums, blogs, news websites, as well as social media data sources such as Twitter and Facebook, whenever there is an API available, we connect it to this system. Then we’ve written queries to suppress all the false positives, called junk information, to get to the actual key information that provides information. This is then processed in a front-end application called Flutterwhich is then visible to the user as dashboards, which not only show you locations or where diseases are spreading, but also give you the numbers of exactly where and how the trend has been for the last six months.
Disease Surveillance Program: Challenges
Some of the opportunities or challenges that, as you can tell, we ran into along the way were: one was, did we have the informed consent of the patients? Now consent is a big part of privacy and as you can see the new data privacy bill talks a lot about consent too. As IET operates under GDPR, it was very important to have informed consent from patients to use their data. We overcome that by using publicly available data sources instead of data sources where patient consent was required. The second challenge we ran into was the volume of data. So the volume was high, and much of it was not relevant data; what we called into the system was misleading data, false positives, or noise, and we overcome that by writing specific pull queries, where we identify false positives and write queries to reduce them. The last aspect was about languages. India does not use a single language; We use a variety of languages, so we have chosen the ten most widely spoken languages in India.
Connect data with predictive analytics
What we’ve done now is take a few use cases and correlate them with local vector-borne information data released by various state governments. We have done so in three cases: Delhi, Uttar Pradesh and Karnataka. But what we’re going to do next is use our partnership with organizations like CHRI, who are also participating in this project. To do analysis, to correlate the data that we have on the digital platform with what they are seeing in the local primary health centers and that way we want to see the correlation and see what the percentage of that correlation is. That validation at ground level is the most important step.
The next step on top of what we’re doing is we’re going to start exploring avenues to do predictive analytics. To see, can I predict trends, can I predict patterns, can I give you an analysis that if you are coming to Bangalore in November 2023 should you take your water bottle or should you take mosquito repellent, because that is the infection? What are you going to face? So that will be our next step, and the last step will obviously be to add more data sources. Now one of the most interesting data sources available in India which is not explored much is weather data. Most of these infectious diseases are very weather based. For example, dengue only occurs with fresh water, and malaria occurs with standing water. So, monsoons play an important role in the spread of these infectious diseases.
Disease Surveillance Program: ENT and Mental Health
The other challenge we face in India, if we move away from infectious diseases like tuberculosis, dengue fever and malaria, is non-communicable diseases. Today we see a huge increase in cases of hypertension and diabetes, which are not diseases in themselves, but conditions that lead to the spread of other diseases and conditions.
I think in the future we will have to look at non-communicable diseases. The last aspect is mental health. I think the COVID pandemic has exposed us to the gaps that we have in our mental health framework, and today we have programs, both nationally and regionally run by states, that look at things like suicide prevention and depression. But I think, as the Hon. ex-minister, Suresh Prabhu said, these are conversations that give you the symptoms, and although it will take a while for the symptoms to register in a hospital. This gives us the opportunity to intervene in this case just before the person becomes a patient. So we’re looking at healthcare consumers and supporting them so they don’t even have to go into the hospital in a certain condition. So there is huge scope for this, and the impact on both society and the healthcare community can be immense. And what we need is collaboration: building the ecosystem together as we have done in this case.
