The Hindu Explains | How will a centralised electronic medical records tool help to monitor trends about COVID-19?

Why do we need a centralised EMR tool? What does the tool do?

Updated - August 23, 2020 02:02 pm IST

Published - August 23, 2020 01:02 am IST

The story so far: The COVID-19 pandemic has been the start of a great spurt in innovation in the health-care industry. The rush has not only been to find safe and efficacious cures and vaccines but also to tweak every aspect of medical care in order to serve issues arising from the pandemic and beyond. Last week, researchers, as part of an international consortium, reportedly created an agile analytic tool for rapid disease insights, working with medical records of patients with COVID-19 in five countries. They put together a centralised electronic medical records (EMR) tool that would help them gather, monitor, analyse clinical trends in COVID-19 across multiple countries.

Why do we need a centralised EMR tool?

While EMRs were supposed to make things easier in terms of access across platforms, they did not turn out to be such a big boon after all, because the data was locked in on local platforms. Researchers realised “the paucity of relevant clinical information to drive response at the clinical and population levels”.

Also read | Digital Health Mission a voluntary, central repository of records: Health Ministry

Further, the researchers argued in a paper International electronic health record-derived COVID-19 clinical course profiles: the 4CE consortium in Nature Digital Medicine : “Even in an information technology-dominated era, fundamental measurements to guide public health decision-making remain unclear... data that should be widely available in electronic health records (EHRs) have not yet been effectively shared across clinical sites, with public health agencies, or with policy makers.”

In order to resolve this basic conundrum, researchers who were part of the Consortium for Clinical Characterization of COVID-19 by EHR (4CE) rapidly set up an ad hoc network to harmonise data, produce analytics and better visualisations to “begin to answer some of the clinical and epidemiological questions around COVID-19”.

What does the tool do?

The team fashioned its tool on open source and a free i2b2 (Informatics for Integrating Biology and the Bedside) toolkit, to use data generated from EHRs, in a move to get them to ‘talk’ to each other. The final product was a model, the team claims, that demonstrates the possibility of centralising data held in various EHR and uses it fairly quickly to determine disease trajectories.

Also read | COVID-19 enhances reliance on telemedicine

Over a span of three weeks, 96 hospitals — the United States (45), France (42), Italy (5), Germany (3), and Singapore (1) — contributed data to the consortium. This was represented by 23 data collaboratives across these five countries. A total of 27,584 patients with COVID-19 diagnosis were included in the data set, with data covering January 1, 2020 through April 11, 2020. Researchers collected a whopping 187,802 laboratory values to harmonise them across sites.

Among other things, the team tracked the total number of COVID-19 patients, intensive care unit admissions and discharges, daily death toll, demographic details of patients and laboratory tests to assess various health parameters.

In the Nature paper, the team argued that the initial report sought to establish that EMR data for COVID-19 patients was accessible, learn about the clinical trajectories, facilitate evaluation and communication of the various tests and therapies, and contribute data, and learnings to a global network, and the public.

Also read | Gaps in our knowledge of coronavirus origin need fulfilment: Study

The team claimed the “sources of the data and the mechanism established for sharing them are sound, reproducible, and scalable”. A paper, Portrait of a virus , in the Science Daily dated August 19, 2020 quotes Isaac Kohane, senior author on the research and chair of the Department of Biomedical Informatics in the Blavatnik Institute at Harvard Medical School: “The new platform we have created shows that we can, in fact, overcome some of these challenges and rapidly collect critical data that can help us confront the disease at the bedside and beyond... Our efforts establish a framework to monitor the trajectory of COVID-19 across different categories of patients and help us understand response to different clinical interventions.”

The new ‘network designed to be a highly scalable system, is now being implemented at 23 sites’.

What lies ahead?

While the wisdom of quickly aggregating data for drawing conclusions that will guide treatment cannot be ignored, it is also necessary to exercise some caution while dealing with machine learning.

The researchers themselves acknowledged that the ‘early data are incomplete and are subject to many biases and limitations, which constrain the conclusions we can currently draw’.

Also read | Microsoft launches text analytics to organise a deluge of healthcare data

The Science Daily article quotes from an accompanying editorial on the issue: “The new platform underscores the value of such agile analytics in the rapid generation of knowledge, particularly during a pandemic that places extra urgency on answering key questions, but such tools must also be approached with caution and be subject to scientific rigour.”

0 / 0
Sign in to unlock member-only benefits!
  • Access 10 free stories every month
  • Save stories to read later
  • Access to comment on every story
  • Sign-up/manage your newsletter subscriptions with a single click
  • Get notified by email for early access to discounts & offers on our products
Sign in


Comments have to be in English, and in full sentences. They cannot be abusive or personal. Please abide by our community guidelines for posting your comments.

We have migrated to a new commenting platform. If you are already a registered user of The Hindu and logged in, you may continue to engage with our articles. If you do not have an account please register and login to post comments. Users can access their older comments by logging into their accounts on Vuukle.