Health Life

COVID-19 symptom tracker ensures privacy during isolation

Credit: CC0 Public Domain

An online COVID-19 symptom tracking tool developed by researchers at Georgetown University Medical Center ensures a person’s confidentiality while being able to actively monitor their symptoms. The tool is not proprietary and can be used by entities that are not able to develop their own tracking systems.

Identifying and monitoring people infected with COVID-19, or exposed to people with infection, is critical to preventing widespread transmission of the disease. Details of the COVID19 Symptom Tracker and a pilot study were published August 13, 2020, in the Journal of Medical Information Research (JMIR).

“One of the major impediments to tracking people with, or at risk of, COVID-19 has been an assurance of privacy and confidentiality,” says infectious disease expert Seble G. Kassaye, MD, MS, lead author and associate professor of medicine at Georgetown University Medical Center. “Our online system provides a method for efficient, active monitoring of large numbers of individuals under quarantine or home isolation, while maintaining privacy.”

The Georgetown internet tool assigns a unique identifier as people enter their symptoms and other relevant demographic data. One function in the system allows institutions to generate reports about items on which people can act, such as symptoms that might require medical attention. Additionally, people using the system are provided with information and links to Centers for Disease Control and Prevention COVID-19 recommendations and instructions for how people with symptoms should seek care.

Development of the system was rapid—it took five days to design. The joint project included Georgetown University’s J.C. Smart, Ph.D., chief scientist of AvesTerra, a knowledge management environment that supports and synthesis to identify actionable events and maintain privacy, and Georgetown’s vice president for research and chief technology officer, Spiros Dimolitsas, Ph.D.

“We knew that time was of the essence and the challenges

Health Life

Combining genetic information with EMRs to pinpoint childhood epilepsies

Credit: CC0 Public Domain

A team of researchers at Children’s Hospital of Philadelphia (CHOP) affiliated with the CHOP Epilepsy Neurogenetics Initiative (ENGIN) further bridged the gap between genomic information and clinical outcome data by systematically linking genetic information with electronic medical records, focusing on how genetic neurological disorders in children develop over time. The findings were published today in the journal Genetics in Medicine.

Over the last decade, more than 200 genetic causes of epilepsy have been identified. Genetic changes can be found in up to 30% of Developmental and Epileptic Encephalopathies (DEE), severe brain disorders that can cause aggressive seizures, cognitive and neurological impairment and, in some cases, early death. Identifying a causative gene is often the first step of improving treatment, since many children with these conditions do not respond to current treatment methods.

Even though collectively common, each causal gene is only found in 1% or less of the overall patient population, often making it difficult to generate enough to provide families and their providers with reliable on how these conditions develop over time. Additionally, while genomic data is gathered in a standardized manner, the patient’s phenotype—a set of clinical finding that may include seizures or developmental disabilities—has historically not been collected in the same way.

Large initiatives to link genomic data with (EMR) are already underway to determine how existing can be linked to a lack of information about clinical outcomes. However, since these initiatives are relatively new, the role of EMRs in studying how disease-causing genetic changes can impact patients over longer periods of time has not been explored.

“Our study is the first example in childhood neurological orders to systematically connect with the medical records,” says Ingo Helbig, MD, attending physician at CHOP’s

Health Life

New prediction model can forecast personalized risk for COVID-19-related hospitalization

Credit: Unsplash/CC0 Public Domain

Cleveland Clinic researchers have developed and validated a risk prediction model (called a nomogram) that can help physicians predict which patients who have recently tested positive for SARS-CoV-2, the virus that causes COVID-19, are at greatest risk for hospitalization.

This new , published in PLOS One, is the second COVID-19-related nomogram that the research team—led by Lara Jehi, M.D., chief research information officer at Cleveland Clinic, and Michael Kattan, Ph.D., chair of Lerner Research Institute’s Department of Quantitative Health Sciences—has developed. Their earlier model forecasts an individual patient’s likelihood of testing positive for the virus.

“Ultimately, we want to create a suite of tools that physicians can use to help inform personalized care and resource allocation at many time points throughout a patient’s experience with COVID-19,” said Dr. Jehi, corresponding author on the study.

The team’s newest model was developed and validated using retrospective patient data from more than 4,500 patients who tested positive for COVID-19 at Cleveland Clinic locations in Northeast Ohio and Florida during a three-month time period (early March to early June). Data scientists used statistical algorithms to transform data from registry patients’ electronic medical records into the risk prediction model.

Comparing characteristics between those patients who were and were not hospitalized due to COVID-19 revealed several previously undefined hospitalization risk factors, including:

  • Smoking. Former smokers were more likely to be hospitalized than current smokers.
  • Taking certain medications. Using univariable analysis, patients taking Angiotensin Converting Enzyme (ACE) inhibitors or angiotensin II type-I receptor blockers (ARBs) were more likely to be hospitalized than patients not taking those drugs.
  • Race. African American patients were more likely to be hospitalized than patients of other races.

Dr. Kattan, an expert in developing and validating prediction models for medical decision making, cautions that additional studies will

Health Life

Artificial intelligence could improve CT screening for COVID-19 diagnosis

Credit: Pixabay/CC0 Public Domain

Researchers at the University of Notre Dame are developing a new technique using artificial intelligence (AI) that would improve CT screening to more quickly identify patients with the coronavirus. The new technique will reduce the burden on the radiologists tasked with screening each image.

Testing challenges have led to an influx of patients hospitalized with COVID-19 requiring CT scans which have revealed visual signs of the disease, including ground glass opacities, a condition that consists of abnormal lesions, presenting as a haziness on images of the lungs.

“Most patients with coronavirus show signs of COVID-related pneumonia on a chest CT but with the large number of suspected cases, radiologists are working overtime to screen them all,” said Yiyu Shi, associate professor in the Department of Computer Science and Engineering at Notre Dame and the lead researcher on the project. “We have shown that we can use —a field of AI—to identify those signs, drastically speeding up the screening process and reducing the burden on radiologists.”

Shi is working with Jingtong Hu, an assistant professor at the University of Pittsburgh, to identify the visual features of COVID-19-related pneumonia through analysis of 3-D data from CT scans. The team is working to combine the analysis software with off-the-shelf hardware for a light-weight mobile device that can be easily and immediately integrated in clinics around the country. The challenge, Shi said, is that 3-D CT scans are so large, it’s nearly impossible to detect specific features and extract them efficiently and accurately on plug-and-play mobile devices.

“We’re developing a novel method inspired by Independent Component Analysis, using a statistical architecture to break each image into smaller segments,” Shi said, “which will allow to target COVID-related features within large 3-D images.”

Shi and Hu are