Department of Biomedical Informatics In the News

Patient-Centered Outcomes Research Institute

Develop Novel Methods to Identify and Characterize Family Relationships from Electronic Health Data

news outletPatient-Centered Outcomes Research Institute
Publish DateNovember 21, 2022

Understanding household and family memberships has always been important in distinguishing the influence of shared genetics and environments on clinical risks and patient outcomes. Electronic health records (EHR) often include vast information about individuals that, if linked with that of their household or family members, could provide rich and detailed environmental and family history information to support scientific discovery, and patient-centered outcomes research.

Full Story
Science Direct

Artificial intelligence in echocardiography to diagnose congenital heart disease and fetal echocardiography

news outletScience Direct
Publish DateNovember 09, 2022

Echocardiography is the primary tool in pediatric cardiology for diagnosing and managing congenital heart disease (CHD). Accurate and reliable echocardiographic assessment is critical in clinical decision making. Artificial intelligence (AI), in particular deep learning, has the potential to reduce labor and provide automated assessment of CHD. 

Full Story
Nature Communications

Systematic tissue annotations of genomics samples by modeling unstructured metadata

news outletNature Communications
Publish DateNovember 08, 2022

There are currently >1.3 million human –omics samples that are publicly available. This valuable resource remains acutely underused because discovering particular samples from this ever-growing data collection remains a significant challenge. The major impediment is that sample attributes are routinely described using varied terminologies written in unstructured natural language.

Full Story
National Institutes of Health (NIH)

Advancing American Indian and Alaska Native Health Through Research, Training, and Engagement

news outletNational Institutes of Health (NIH)
Publish DateNovember 02, 2022

American Indian and Alaska Native (AI/AN) populations have long experienced health disparities such as higher rates of diabetes, certain cancers, and mental health conditions than those of other Americans. One contributing factor in these disparities is underrepresentation of AI/AN populations in biomedical science—as study participants, researchers, and health professionals.

Full Story
Cell Systems

Morphology and gene expression profiling provide complementary information for mapping cell state

news outletCell Systems
Publish DateOctober 28, 2022

Morphological and gene expression profiling can cost-effectively capture thousands of features in thousands of samples across perturbations by disease, mutation, or drug treatments, but it is unclear to what extent the two modalities capture overlapping versus complementary information.

Full Story
Laboratory Equipment

For Drug Discovery, the More Data Types, the Better

news outletLaboratory Equipment
Publish DateOctober 26, 2022

A new paper by researchers at the University of Colorado Anschutz Medical Campus expounds on the importance of using multiple data types in drug discovery. For the paper, published in Cell Systems, the researchers screened over 1,000 drugs tested in six doses. The results, according to the team, demonstrate that the two most popular methods—gene expression and cell morphology—should be used in tandem.

Full Story
The Conversation

Drugs – 4 essential reads on how they’re made, how they work and how context can make poison a medicine

news outletThe Conversation
Publish DateOctober 26, 2022

Pandemics and disease outbreaks put a spotlight on the hurdles researchers face to get a drug on the shelves. From finding prospective drug candidates to balancing time and financial pressures with ensuring safety and efficacy, there are many aspects of drug development that determine whether a treatment ever makes it out of the lab.

Full Story

A combined polygenic score of 21,293 rare and 22 common variants improves diabetes diagnosis based on hemoglobin A1C levels

news outletNature
Publish DateOctober 24, 2022

Joanne Cole, PhD, associate professor of biomedical informatics at the University of Colorado School of Medicine, has been published in Nature Genetics as an author of this study regarding diabetes diagnosis based on hemoglobin A1C levels.

Full Story

A combined polygenic score of 21,293 rare and 22 common variants improves diabetes diagnosis based on hemoglobin A1C levels

news outletNature
Publish DateOctober 24, 2022

Polygenic scores (PGSs) combine the effects of common genetic variants to predict risk or treatment strategies for complex diseases. Adding rare variation to PGSs has largely unknown benefits and is methodically challenging. 

Full Story

Data Assimilation Framework Sheds Light on Ventilator-induced Lung Injury

news outletSIAM News
Publish DateOctober 07, 2022

Acute respiratory distress syndrome (ARDS) occurs when fluid builds up in the air sacs of the lungs, preventing them from opening completely and depriving the body of necessary oxygen. The condition causes significant problems in clinical management and develops in roughly eight to 10 percent of patients in the intensive care unit. Most people with ARDS require intubation and mechanical ventilation in order to survive. “The problem is, when you put people on a mechanical ventilator, it inflates your lungs differently than your diaphragm does,” Jake Stroh of the University of Colorado Anschutz Medical Campus said. “So it increases the risk of ventilator-induced lung injury (VILI).” 

Full Story

2022 ACM SIGHPC Computational and Data Science Fellowship Winners

news outletSIGHPC
Publish DateOctober 05, 2022

ACM’s Special Interest Group on High Performance Computing (SIGHPC) has announced the eleven recipients of the ACM SIGHPC Computational and Data Science Fellowships for 2022. The fellowships are highly competitive, and are awarded after a rigorous merit review. The fellowship program, previously funded by Intel, is now funded exclusively by SIGHPC.

Full Story
National Institutes of Health (NIH)

Understanding Long-Term COVID-19 Symptoms and Enhancing Recovery

news outletNational Institutes of Health (NIH)
Publish DateOctober 04, 2022

Many people—potentially millions globally—are still living with the long-term effects of a COVID-19 infection, known as the post-acute sequelae of SARS-CoV-2 infection (PASC), including Long COVID. This is a public health issue that is in desperate need of answers. Research is essential to address the many puzzling aspects of Long COVID and guide us to effective responses that protect the nation’s long-term health.

Full Story
Mirage News

What Is Artificial Intelligence in Healthcare?

news outletMirage News
Publish DateSeptember 21, 2022

Casey Greene, PhD, chair of the University of Colorado School of Medicine’s Department of Biomedical Informatics, is working toward a future of “serendipity” in healthcare – using artificial intelligence (AI) to help doctors receive the right information at the right time to make the best decision for a patient.

Full Story
Health IT Analytics

Medical School Launches New Department to Enhance Patient Care Through AI

news outletHealth IT Analytics
Publish DateJuly 12, 2022

The University of Colorado (CU) School of Medicine has announced the launch of its new Department of Biomedical Informatics (DBMI), which will focus on addressing health disparities and improving healthcare quality using big data and artificial intelligence (AI).

Full Story
American Journal of Respiratory and Critical Care Medicine

Colocalization of Gene Expression and DNA Methylation with Genetic RiskVariants Supports Functional Roles of MUC5B and DSP in Idiopathic Pulmonary Fibrosis

news outletAmerican Journal of Respiratory and Critical Care Medicine
Publish DateJuly 11, 2022

Common genetic variants have been associated with idiopathic pulmonary fibrosis (IPF). We have established a relationship of the common IPF genetic risk variants rs35705950 and rs2076295 with respective changes in MUC5B and DSP expression and methylation. These results provide additional evidence that both MUC5B and DSP are involved in the etiology of IPF.

Full Story

Artificial intelligence may be used to identify benign thyroid nodules

news outletHealio
Publish DateJune 22, 2022

An ultrasound-based artificial intelligence classifier of thyroid nodules identified benign nodules with sensitivity similar to fine-needle aspiration, according to data presented at ENDO 2022.

Full Story

AI Tool Could Reduce Unnecessary Thyroid Biopsies

news outletMedscape
Publish DateJune 17, 2022

A machine-learning algorithm that analyzes thyroid-nodule ultrasound images correctly identifies likely cancerous nodules 97% of the time - which is on par with thyroid biopsy with fine-needle aspiration, according to research presented at the Endocrine Society annual meeting.

Full Story
Denver 7

Study shows AI deep learning models can detect race in medical imaging

news outletDenver 7
Publish DateMay 24, 2022

Most of us have experienced some form of medical imaging, whether it was at an eye appointment or after a broken bone. These images might contain more information than meets the eye. Things artificial intelligence can detect.

Full Story
National Center for Advancing Translational Sciences

Researchers Use Cutting-Edge EHR Data Resource to Find Risk Factors for Severe COVID-19 in Children

news outletNational Center for Advancing Translational Sciences
Publish DateMay 13, 2022

Children with COVID-19 often get less sick than adults, but some are at risk for serious illness or even death. In a recent study published in the journal JAMA Network Open, NCATS-supported researchers found traits that put children more at risk for severe COVID-19 complications. These traits can help doctors decide whether children diagnosed with COVID-19 should receive different treatment to avoid hospitalization.

Full Story

A study uses data from electronic health records to form a definition of long COVID

news outletUCHealth
Publish DateMarch 25, 2022

A study by researchers at the University of Colorado Anschutz Medical Campus used electronic health records to answer a still difficult question: just what is long COVID? The work also will help recruit patients for a major study of the condition.

Full Story