Your entire medical journey takes place in digital health records, but how do you know if these records are wrong, incomplete, or if important information is missing? That’s the focus of research by Varadraj Gurupur, an associate professor in UCF’s School of Global Health Management and Informatics.
His latest project has created an algorithm that can predict and measure the incompleteness of electronic health records – in everything from lab results to disease diagnoses, medical history to prescription records.
Missing information in electronic health records (EHRs) kept by hospitals and doctors’ offices is like a leaky pipe, he says. If you don’t know where the leak is, you can’t fix it and soon the house may be flooded. The same dangers can arise in the field of health. A recent Gurupur study found that a critical percentage of digital health records contained missing information.
Its algorithm uses math and computer science to answer, “Where is the leaking water?” he says. The analysis performed by Gurupur and his team revealed that the level of incompleteness per year varies and there is no pattern of where missing data occurs. Its algorithm helps identify attributes that have a greater tendency to be incomplete – areas of the water pipe that are more vulnerable and may break more frequently.
His previous studies have shown that the main reasons for lack of health information are communication and education. Communication between patients and their providers is not always clear, especially if the patient is interacting with a healthcare professional who does not speak their native language. Cultural barriers can prevent patients from sharing important information with their providers. Digital technology also creates its own challenges. Providers may not complete electronic records until the end of the day and forget what the patient said or may not have it correctly in their notes. Hospitals and clinics are switching electronic health record systems, which requires extensive new training that creates a learning curve for providers. Some healthcare workers, especially those who have not grown up with technology, may not be adept at using EHRs.
“Missing health information can sometimes be as simple as someone not knowing which button to press in the new system,” says Gurupur.
Ayan Nasir ’20MD is completing his residency in internal medicine at the Mayo Clinic in Jacksonville, Florida. As an undergraduate and medical student at UCF, Nasir researched with Gurupur on health informatics. Before entering the medical field, Nasir worked in finance and says he was amazed by the difference in quality control and data accuracy between banking and medical records. These discrepancies inspired him to make improving health informatics the subject of his two-year Focused Inquiry and Research Experience (FIRE) project at medical school, where Gurupur served as his research mentor.
His residency reinforced his passion for improving health informatics.
“When I see a patient, what I put in the electronic health record reflects an episode of their care,” he says. “But this information will guide every future medical decision. That’s why electronic records need to be complete.”
Gurupur gave this example to highlight the impact of incomplete data on health. A patient with limited English skills sees a new provider who does not speak the patient’s native language. With his communication problems and the rush of a clinical practice, the patient forgets to mention that he is taking a particular medication for type 2 diabetes. There is nothing about the previous diabetes treatment in the health record electronic, so the provider prescribes a standard drug at a standard dosage for this condition. Now the patient can receive double the recommended amount.
Medicine is looking for ways to use more big data – artificial intelligence – to diagnose and provide more evidence-based treatments. But this computer analysis relies on comprehensive patient data, Nasir points out.
“When it comes to medicine, you are only as good as your data,” he says.
Gurupur says developing reliable algorithms for missing data is also important for healthcare systems. Recent studies have shown that hospitals can lose an average of $5-8 million per year due to missing data that impacts their insurance reimbursement rates. Thanks to the algorithm, hospital managers can know exactly where the missing information comes from – a floor, a department, a particular department – and fix it.
Gurupur and Nasir believe health informatics is at a critical juncture. Health systems rely on electronic records, but need to develop ways to ensure that all the information they collect is complete and accurate. Nasir is earning his master’s degree in health informatics from Northwestern University and points out that these graduate medical education programs show the growing importance of using data to better care for patients. He believes future health technology will improve care even further – computers will translate conversations between providers and patients directly into the electronic record, reducing the need for providers to manually enter data after each visit, for example. .
“We are only at the beginning of this transformation,” he says. “It’s exciting to be part of this work.”
Source of the story:
Material provided by University of Central Florida. Original written by Wendy Sarubbi. Note: Content may be edited for style and length.