Biomedical Informatics Core, CTSI

The Biomedical Informatics Core of the Clinical and Translational Science Institute (CTSI) will establish a research data warehouse; develop and deploy user-friendly, web-based informatics tools such as a Cohort Discovery Tool, a Computable Phenotype Library, and a Data Transfer Tool; and develop and deploy a secure data analytic environment.

This work is funded by grant UL1 TR001857 from NCATS, NIH.

All of Us Research Program (Precision Medicine Initiative Cohort Program)

The University of Pittsburgh is funded as one of the Healthcare Provider Organizations for the national All of Us Research Program, which is a historic effort to gather data from 1 million people living in the United States. The goal of the program is to revolutionize how disease is prevented and treated based on individual differences in lifestyle, environment and genetics. The University of Pittsburgh's program, called the All of Us Pennsylvania Research Program, will enroll 150,000 participants.

This work is funded by grant UG3 OD023153 from the Office of the Director, NIH.

Accrual of patients to Clinical Trials (ACT) network

The Accrual of patients to Clinical Trials (ACT) network is a nationwide network of sites that share EHR data to significantly increase participant accrual to the nation’s highest priority clinical trials. It is funded by NCATS' Clinical and Translational Science Awards (CTSA) program that supports efforts to solve system-wide translational research problems to improve the success of U.S. clinical trials. The ACT network is built on existing platforms (i2b2/SHRINE) to create a federated network with common standards, data terminology and shared resources. The ACT investigators are focused on 1) data harmonization across EHR platforms, 2) technical needs assessment and implementation, 3) regulatory approaches to ensure compliance with protocols for data access and participant contact, and 4) governance development to establish proper agreements among institutions. More information is available at NCATS.

This work is funded by grant UL1 TR001857-01S1 from NCATS, NIH.

PaTH Clinical Data Research Network

PaTH is a Patient Centered Outcomes Research Institute (PCORI) Clinical Data Research Network project which is focused on building a Learning Health System (LHS) for the Mid-Atlantic region. It is comprised of Geisinger Health System, Johns Hopkins University, Johns Hopkins Health System, Penn State College of Medicine, Penn State Milton S. Hershey Medical Center, Temple Health System, Lewis Katz School of Medicine at Temple University, the University of Pittsburgh, UPMC, the University of Utah, and University of Utah Health Care. the University of Pittsburgh leads the informatics component of PaTH.

This work is funded by grant CDRN 1306-04912 from PCORI.

National Mesothelioma Virtual Bank (NMVB)

The National Mesothelioma Virtual Bank (NMVB) is a virtual biospecimen registry designed to support and facilitate basic science, clinical, and translational research that will advance understanding of mesothelioma pathophysiology with the goal of expediting the discovery of preventive measures, novel therapeutic interventions, and ultimately, cures for mesothelioma. The current participants in the virtual bank are University of Pittsburgh, University of Pennsylvania, NYU Langone Medical Center, Roswell Park Cancer Institute and University of Maryland.

This work is funded by grant U24 OH010873 from NIOSH, NIH.

The TIES Cancer Research Network (TCRN)

The Text Information Extraction System (TIES) Cancer Research Network is a federated network of clinical reports and biospecimen registry to support and facilitate basic science, clinical, and translational research in cancer. TIES uses a sophisticated concept based search to retrieve pathology and radiology reports containing concepts of interest. Plans include enabling virtual slides and tissue microarray creation. The current participants in the network are University of Pittsburgh, University of Pennsylvania, Augusta University, Roswell Park Cancer Institute, Thomas Jefferson University and Stony Brook University.

This work is funded by grant U24 CA180921 from NCI, NIH.

The Pittsburgh Genome Resource Repository (PGRR)

The Pittsburgh Genome Resource Repository (PGRR) provides data management and computing infrastructure to support investigation using The Cancer Genome Atlas (TCGA). TCGA is a “comprehensive and coordinated effort to accelerate the understanding of the molecular basis of cancer through the application of genome analysis technologies, including large-scale genome sequencing”, and is funded by the National Cancer Institute. PGRR processes data and metadata available from TCGA to provide a Pitt-specific ‘snapshot’ of the data and tools for use of this data in a secured environment.

This work is funded by the Institute for Personalized Medicine (IPM) and the University of Pittsburgh Cancer Institute (UPCI).

Learning Electronic Medical Record (LEMR) system

Electronic medical records (EMRs) are capturing increasing amounts of patient data that can be leveraged by machine-learning methods for computerized decision support. My work focuses on the development of intelligent EMRs that contain adaptive and learning components to provide decision support using the right data, at the right time. In addition, I work with a team of collaborators in developing and implementing machine-learning methods for detecting adverse drug events and for identifying anomalies in clinical management of patients.

This work is funded by a R01 grant from the NLM, NIH.

Personalized modeling for precision medicine

In predictive modeling in medicine, the typical paradigm consists of learning a single model from a database of individuals, which is then applied to predict outcomes for any future individual. Such a model is called a population-wide model because it is intended to be applied to an entire population of future individuals. In contrast, personalized modeling focuses on learning models that are tailored to the characteristics of the individual at hand. Personalized models that are optimized to perform well for a specific individual are likely to have better predictive performance than the typical population-wide models that are optimized to have good predictive performance on average on all future individuals. Moreover, personalized models can identify features such as genomic factors that are specific for an individual thus enabling precision medicine.