Using Patient Registries as a Tool in the Battle Against COVID-19

General Blog Banner
Deep 6 AI Blog

Deep 6 AI Blog

Get insights about clinical trials, patient identification, health IT, data science, machine learning, and more.

Being in the midst of a pandemic, it is more important than ever for hospitals and health care providers to be able to easily manage and sort through patient data. One method of doing this in healthcare is through the use of registries. A registry is used to collect uniform patient data for observational studies that surround a certain population, such as those who have a specific disease. While some may be used simply to collect information about that population, others may be geared towards identifying patients for prospective research studies. Today, the most relevant and critical types of registries are those of people who have tested positive for COVID-19.


The Importance of Registries Today


As our response to COVID-19 progresses, hospitals and medical facilities will need a way to track those who have contracted the virus, along with all the specificities of their symptoms, due to the fact that the way this virus presents itself varies greatly from person to person. The presentations of those infected can range from asymptomatic carriers to mild flu-like symptoms to long-term health issues to death. This makes tracking and carefully monitoring each known case using registries crucial for many reasons. It allows researchers to find trends in the prevalence of certain symptoms over others, to determine severity of certain disease presentations over others, and to establish the most effective current standard of care until clinical trials for treatments and vaccines conclude. The registry then can be used to identify the best matching patients for certain clinical trials, for example, looking at those who present with a certain symptom and a drug meant to treat that symptom. The Infectious Disease Society of America currently has over 40 listed registries related to COVID-19. One example was created by the American Society of Clinical Oncology (ASCO) called the Survey on COVID-19 in Oncology Registry (ASCO Registry). According to an article by Avalere, the ASCO Registry sets out “to identify patterns of symptoms and severity of COVID-19 among patients with cancer, as well as how the pandemic is impacting the delivery of cancer care and patient outcomes.”


The process to creating a registry is a lengthy and detailed one. These ten steps are outlined in “Registries for Evaluating Patient Outcomes: A User’s Guide [Internet]. 3rd edition:” “(1) articulate the purpose of the registry; (2) determine if a registry is an appropriate means to achieve the purpose; (3) identify key stakeholders; and (4) assess the feasibility of a registry. Once a decision is made to proceed, the next considerations in planning are to (5) build a registry team; (6) establish a governance and oversight plan; (7) define the scope and rigor needed; (8) define the data set, patient outcomes, and target population; (9) develop a study plan or protocol; and (10) develop a project plan.” These steps can occur in parallel to each other but the registry must be continuously revisited and revised to ensure the patient data is always up to date.


How Deep 6 AI Simplifies Registry Making


While primarily being a tool that consolidates the data within electronic medical records to help match patients to clinical trials, Deep 6 AI is currently helping our users expand upon the software’s typical functionalities of trial recruitment and management to address the needs of healthcare workers following the outbreak of the novel coronavirus. One of these new needs is creating registries. As institutions were forced to pause or suspend hundreds of clinical trials to shift the focus to the virus, many researchers were able to start applying Deep 6 AI to this use case. The tool is able to quickly and effectively search the unstructured data in a health system’s electronic medical records (EMR), a process that is typically confined to manual chart reviews. Currently, symptoms relating to COVID-19 and a positive diagnosis are still confined to existing within the physician notes. Without a tool that reads through unstructured data, the process to manually review thousands of patient charts and consolidate it into a registry would be tedious and time-consuming. The alternative, using separate survey functionality to collect information about COVID patients in another database, is duplicative and can risk losing important contextual information.


Pulling up patient counts for feasibility when running a clinical trial is simple in the Deep 6 AI platform, and the same concept applies to creating a registry. Researchers can use Deep 6 AI to search for patients who have had COVID-19 present with specific symptoms, such as a cough or diarrhea, and receive accurate counts of how many patients present with each of those symptoms. Further, patients go in for care through different routes, whether the emergency department, private clinics, and so on. The Deep 6 AI software can pull data from any source, even external to the hospital, making it easier to compile all of the different symptoms around COVID-positive patients. Having all this data surrounding COVID-19 symptoms, healthcare experts can draw conclusions of patient outcomes based on the numerous possibilities of how the virus may express itself. The power of the Deep 6 AI platform is in being able to search physician notes and other unstructured data to search symptoms and tie them with a COVID positive diagnosis. Additionally, the need to constantly go back and check that the data is current and accurate is a process on its own that would normally take hours of manual review. With Deep 6 AI, cohorts are saved within the system, so one would only need to refresh the search to see if anything has changed.


With floods of patients coming in for emergent intensive care, it has become increasingly difficult to organize the information surrounding their illness. And because the details of the virus are constantly changing, symptoms and diagnoses may be unclearly documented. With Deep 6 AI’s ability to quickly search the unstructured data that lies in physician notes, researchers have been able to efficiently categorize patients who belong on a registry, and then use the registry to conduct the diverse range of observational studies that are being done to fully understand and overcome the COVID-19 pandemic.


See our platform’s capabilities in action by requesting a demo. We’ll be discussing more interesting use cases for the Deep 6 AI platform in the coming weeks. Sign up for our newsletter so you don’t miss the next one!


About the Author: Nour Malki


Nour Malki is a business development representative at Deep 6 AI, which uses AI and NLP to allow clinical researchers to find patients that fit any set of complex criteria in real time. Nour works to facilitate clinical and academic partnerships between Deep 6 AI and research institutions nationwide. She has a background in biotechnology and the healthcare field, previously holding various positions centered around technology transfer and clinical research in cancer hospitals, academic medical centers, as well as small clinics.



Share this post

Share on linkedin
Share on facebook
Share on twitter
Share on print
Share on email