Skip Navigation Bar

Grants and Funding: Extramural Programs (EP)

NLM Grantee Spotlight

Posted on July 27, 2012

Dr. Tanja Bekhuis and Dr. Diana Demner-Fushman

"Screening nonrandomized studies for medical systematic reviews: A comparative study of classifiers." Artificial Intelligence in Medicine: http://www.aiimjournal.com/article/S0933-3657(12)00062-0/abstract
In this study, Drs. Bekhuis and Demner-Fushman concluded that machine learning classifiers can help identify nonrandomized studies eligible for full-text screening by systematic reviewers. Optimization can markedly improve performance of classifiers. However, generalizability varies with the classifier. The number of citations to screen during a second independent pass through the citations can be substantially reduced.

This work was supported by NLM Grant R00LM010943.

Tanja C. Bekhuis, PhD
Screening Nonrandomized Studies for Inclusion in Systematic Reviews of Evidence
4 R00 LM010943-02
University of Pittsburgh at Pittsburgh
Top

 

Posted on July 27, 2012

Dr. Markus W. Covert

"A Whole-Cell Computational Model Predicts Phenotype from Genotype." Cell: http://www.cell.com/abstract/S0092-8674%2812%2900776-3
Dr. Markus Covert and his research team at Stanford University reported on July 20, 2012, in the journal Cell, on their breakthrough effort of completing the world’s first computational model of an organism. By encompassing the entirety of an organism in silico, the model allow researchers to address questions that aren’t practical to examine otherwise, representing a stepping-stone toward the use of computer-aided design in bioengineering and medicine.

This work was supported by NLM Grant DP1LM011510.

From NLM News & Events
NLM-Funded Investigator Creates First Complete Computerized Simulation of an Organism

Media Reports about this Study
Stanford University News Service: http://news.stanford.edu/pr/2012/pr-computer-model-organism-071812.html
New York Times: http://www.nytimes.com/2012/07/21/science/in-a-first-an-entire-organism-is-simulated-by-software.html?_r=2&ref=science

Markus W. Covert, PhD
A Gene-Complete Computational Model of Yeast
8DP1LM011510-04
Stanford University
Top

 

Posted on May 16, 2012

Dr. Jason H. Moore

Jason H. Moore, PhD, a bioinformatics methodologist, is the Third Century Professor and Director of the Institute for Quantitative Biomedical Sciences at Dartmouth College. Dr. Moore’s NLM-funded bioinformatics research program focuses on the development, evaluation and application of computational methods for characterizing gene interactions in studies of common human diseases.

Board of Regents Presentation: "Machine Learning Approaches to the Genetic Analysis of Complex Traits." The sequencing of the human genome has made it possible to identify millions of rare and common variants across the genome that can be used to carry out genome-wide association studies (GWAS). The availability of massive amounts of GWAS data has necessitated the development of new biostatistical methods for quality control and data analysis. This work has been successful and has enabled the discovery of new associations. However, it is now recognized that most SNPs discovered via GWAS have very small effects on disease susceptibility and thus may not be suitable for improving healthcare through genetic testing. One likely explanation for the mixed results of GWAS is that the current biostatistical analysis paradigm is by design agnostic or unbiased in that it ignores all prior knowledge about disease pathobiology. Further, the linear modeling framework that is employed in GWAS often considers only one SNP at a time thus ignoring their genomic and environmental context. There is now a shift away from the biostatistical approach toward a more holistic bioinformatics approach that recognizes the complexity of the genotype-phenotype relationship that is characterized by significant heterogeneity and gene-gene and gene-environment interaction. Machine learning has an important role to play in addressing the complexity of the underlying genetic basis of common human diseases.

This work is supported by NLM grant R01LM009012. An American Recovery and Reinvestment Act (ARRA) Summer Research Experience (SRE) Supplement allowed several high school students to participate in this novel genomic research.

Jason H. Moore, PhD
Machine Learning Prediction of Cancer Susceptibility
5 R01 LM009012-06
Dartmouth College
Top

 

Posted on April 24, 2012

Dr. John H. Holmes

Dr. John H. Holmes, an epidemiologist and medical-information specialist, is Associate Professor of Medical Informatics in Epidemiology at HUP, University of Pennsylvania Perelman SOM. When this study, called MICE for short, is completed, Dr. Holmes's team of researchers will have accessed more than one million message boards and Twitter feeds posted by breast-cancer and prostate-cancer patients who discuss the use and effects of herbal and nutritional supplements. This work is supported by NLM Grant RC1LM10342.

Media Reports about this Study
Wall Street Journal: http://online.wsj.com/article_email/SB10001424052702303404704577309794125038010-lMyQjAxMTAyMDIwMDEyNDAyWj.html?mod=wsj_share_email

John H. Holmes, PhD
Mining Internet Conversations for Evidence of Herbal-Associated Adverse Events
RC1LM010342
University of Pennsylvania
Top

 

Posted on April 24, 2012

Dr. Atul J. Butte

"Expression-based genome-wide association study links the receptor CD44 in adipose tissue with type 2 diabetes." Proceedings of the National Academy of Sciences: http://www.pnas.org/content/early/2012/04/10/1114513109.long
In a study published online April 9, Dr. Butte and his team combed through public databases storing huge troves of results from thousands of earlier experiments. They identified a gene never before linked to type-2 diabetes, a life-shortening disease that affects 4 percent of the world’s population. These findings have both diagnostic and therapeutic implications. This work was supported by NLM Grant R01LM9719.

Atul J. Butte, MD, PhD
Integrating Microarray and Proteomic Data by Ontology-based Annotation
5R01LM009719-04
Stanford University
Top

 

Posted on April 20, 2012

Dr. Xie George Xu

"Extension of RPI-adult male and female computational phantoms to obese patients and a Monte Carlo study of the effect on CT imaging dose." Physics in Medicine & Biology: http://iopscience.iop.org/0031-9155/57/9/2441/article
This study examines the effect of obesity on the calculated radiation dose to organs and tissues from CT using newly developed phantoms (models) representing overweight and obese patients. This set of new obese phantoms can be used in the future to study the optimization of image quality and radiation dose for patients of different weight classifications. This work was supported by NLM Grant R01LM009362.

Media Reports about this Study
RPI News and Events: http://news.rpi.edu/update.do?artcenterkey=3018&setappvar=page(1)
US News & World Report: http://health.usnews.com/health-news/news/articles/2012/04/13/ct-scans-deliver-more-radiation-to-obese-people-study

Xie George Xu, PhD
4D Visible Human Modeling for Radiation Dosimetry
5R01LM009362-04
Department of Mechanical, Aerospace, and Nuclear Engineering
Rensselaer Polytechnic Institute
Top

 

Posted on April 6, 2012

Dr. Peter J. Embi

Dr. Peter Embi received the inaugural Distinguished Paper Award at the American Medical Informatics Association (AMIA) 2012 Summit on Clinical Research Informatics. He was awarded this for his paper titled: "Evaluating Alert Fatigue and Response Patterns to EHR-based Clinical Trial Alerts: Findings from a Randomized, Controlled Study." The award is given "In recognition of research presented at the AMIA Clinical Research Informatics Summit that contributes to the state of knowledge and practice, is novel, and will impact future work through its dissemination." The full paper will appear in a special issue of the Journal of the American Medical Informatics Association, which will be dedicated to Clinical Research Informatics and is scheduled for publication in June 2012. This work was supported by NLM Grant R01LM009533.

Additional Information
http://www.nlm.nih.gov/ep/Embi.html

Peter J. Embi, MD
Evaluating EHR-based, Point-of-Care Trial Recruitment Across Clinical Settings
7R01LM009533-04
Ohio State University
Top