Informatics

Informatics

Our informatics faculty members actively develop new methodology in artificial intelligence, natural-language processing and machine learning. These methods make possible novel analyses of clinical data from electronic-health records and of data from population-based studies of common diseases, such as asthma and cancer.

Computational models of human health must take into account its complexity—how it is impacted by the interplay of demographic, environmental and genomic factors. The DBEI brings the informatics faculty’s work into close proximity and collaboration with cutting-edge research in biostatistics and epidemiology, connecting the questions we can ask about an individual with those we can ask at the population level.  We invite you to explore the latest findings here.  

Publications

Predicting Who’s at Risk: Electronic Health Records and a Polygenic Approach May Be Key

April 2020

Why do some people carry a disease like COVID-19 and remain asymptomatic, while others who have no underlying conditions may die from it? Genetics may be key—and an especially promising approach is the polygenic risk score, using data from biobank-linked electronic health records. But there are challenges.

Ruowang Li, Yong Chen, Marylyn D. Ritchie, Jason H. Moore

Learn more

How Our ‘Birth Environment’ Can Influence Our Health

January 2020

Some of our major health risks were actually predicted by environmental factors our mothers experienced while we were still in the womb—and some, such as temperature and humidity, can even affect the number of grandchildren we will have. This bigger picture is known as the “birth environment”—and its influence on health has long fascinated Mary Regina Boland, PhD.

Mary Regina Boland, PhD, and various team members authored this series of studies. See the each of the study links in this article for the full lists of authors.

Learn more

Estimating High-Order, Directional Drug Interactions: Study That Mines Effects on Myopathy Shows the Possibilities

October 2018

Many people in the U.S. take multiple prescription drugs, but very few studies have explored the relationships between these "high-order" drug combinations. The authors set out to make a general tool for quickly and accurately estimating drug-drug interactions, or DDIs, in cases where a patient already on a given drug adds a new one and three or more drugs are involved.

Danai Chasioti, Xiaohui Yao, Pengyue Zhang, Samuel Lerner, Sara K. Quinney, Xia Ning, Lang Li, Li Shen

Learn more

Dogs Born in Summer Are at Higher Risk of Heart Disease—Adding Weight to the Theory that Air Pollution Is a Culprit

May 2018

Does exposure to air pollution during early gestation increase our risk of heart disease? The answer appears to be yes—both for humans and for some of our closest animal companions—according to several studies led by Mary Regina Boland, PhD.

Mary Regina Boland, Marc S. Kraus, Eddie Dziuk, Anna R. Gelzer 

Learn more

Safe While Pregnant? A Machine-Learning Algorithm Helps Demystify "Category C" Drugs

October 2017

Pregnant women take some medications whose effects on the fetus are largely unknown. The authors sought to design a machine-learning method that uses big data housed in clinical records, coupled with information on the chemical properties of the drug, to determine if these "Category C" drugs were likely to be harmful or safe to the fetus.

Mary Regina Boland, Fernanda Polubriaginof, Nicholas P. Tatonetti

Learn more

For Women, Obesity and Smoking Pose Higher Asthma Risk

January 2017

We have long known that asthma occurs more frequently in adult women than in adult men; the reasons for this contrast are not completely understood. The authors sought to find out whether different demographic factors are associated with women's asthma than with men's.

Rebecca Greenblatt, Omar Mansour, Edward Zhao, Michelle Ross and Blanca E Himes

Learn more

Genetic Risk Factors of Disparate Diseases Share Similar Biological Underpinnings

May 2016

The investigators sought to reveal shared mechanisms by which certain genetic variants contribute downstream to a specific disease—and to reveal possible drug targets.

Haiquan Li, Ikbel Achour, Lisa Bastarache, Joanne Berghout, Vincent Gardeux, Jianrong Li, Younghee Lee, Lorenzo Pesce, Xinan Yang, Kenneth S Ramos, Ian Foster, Joshua C Denny, Jason Moore and Yves A Lussier

Learn more

Finding More Accurate Patterns in MRI for Alzheimer's Diagnosis

May 2016

The authors sought to improve the accuracy of magnetic resonance imaging for diagnosing Alzheimer's disease—a condition that is notoriously difficult to pin down.

Kristin A. Linn, Bilwaj Gaonkar, Theodore D. Satterthwaite, Jimit Doshi, Christos Davatzikos and Russell T. Shinohara

Learn more
Share this Content

About Us

To understand health and disease today, we need new thinking and novel science —the kind  we create when multiple disciplines work together from the ground up. That is why this department has put forward a bold vision in population-health science: a single academic home for biostatistics, epidemiology and informatics. MORE

© 2019 Trustees of the University of Pennsylvania. All rights reserved. | Disclaimer

Follow Us