Jun 19 2017

It’s Benign!

by at 2:09 pm

My surgeon Dr. Shawna Willey walked into the patient exam room where I waited nervously. I first saw her thumbs up before her beaming face. I could breathe again!

My friends and I who recently turned 40 and starting our baseline mammograms can’t help but wonder about the lack of consensus on optimal cancer screening strategies, target populations, its benefits and harms. My colleague Dr. Jeanne Mandleblatt and her team have studied breast screening strategies for decades and have shown that biennial screening from ages 50-74 achieves a median 25.8% breast cancer mortality reduction whereas annual screening from ages 40-74 reduces mortality an additional 12% but introduces very high false positive rates. Many women and their families are subject to extreme anxiety due to the sheer number of repeat mammograms, false-positives, benign biopsies and in 7% of the cases an over diagnosis.

My experience and of my friends with breast cancer screening are raising many questions. How can we better predict the target risk population who must undergo screening early and often? Would this decision-making process consider risk factors, lifestyle, and patient preferences? How often are patients with a diagnosis of a benign breast condition on a stereotactic core needle biopsy upgraded to a non-benign diagnosis on an excisional biopsy which requires full sedation and surgery? What was the care journey like for other patients like me – Asian female, healthy, no family history? How many in the US and globally have access to the excellent care and follow-up that I was privileged to receive from Dr. Willey and her expert team?

Touted as the fourth industrial revolution, Artificial Intelligence is poised to empower clinicians, patients and researchers in answering these questions. What is AI? The term was coined by Dartmouth professor Dr. John McCarthy in 1956 and defined as “the science and engineering of making intelligent machines, especially intelligent computer programs.” Applications of AI in medicine have been limited by the complexity of highly cognitive processes such as making a medical diagnosis or selecting a treatment which require integration of thousands of datasets with millions of variables and multiple interactions between these variables. It takes years to collect, organize and publish practice changing results such as Jeanne’s screening study. What if we could use data that we routinely collect during the care process and effectively use AI to assist clinicians in real-time to make informed treatment decisions?

Interested in learning more about AI in Biomedicine? Want to engage with expert scientists and product developers in AI? Register for Georgetown’s Big Data in Biomedicine symposium on October 27th!

Companies like Google and Amazon are betting big on this. Jeff Bezos wrote “..it is hard to overstate how big of an impact AI will have on society over the next 20 years”; Google’s Sundar Pichai, when asked recently about the next big thing at Google responded “I can’t quite tell exactly but advances in AI and machine learning, we are making a big bet on that and this will bring a difference in many many fields”.

We cannot have a conversation about AI in medicine without discussing IBM Watson, the supercomputer that sifted through 20 million cancer research papers, and conducted a differential diagnosis on a difficult to treat leukemia patient in 10 minutes by combining genomic data with the power of cognitive computing. One concern that informaticians including my informatics mentor Dr. Bill Hersh have raised is that the publicity around Watson has mostly been from news articles and press releases, primarily from researchers at IBM and call for a more scientific analysis, not n-of-one case reports, of its abilities in clinical decision making. Systems like Watson will benefit from systematic expert knowledge input to guide the cognitive computing processes in navigating the complex medical pathways.

While still early, AI is already starting to make important contributions to Medicine says AI professor at MIT and a recent breast cancer survivor, Dr. Regina Barzilay. She and her team are asking all the right questions of data – “can we apply the sophisticated algorithms we use to predict customer’s shoe-buying habits to adjust treatments for cancer patients?” “Can computers detect signs of breast cancer or even pre-malignancy earlier than humans are currently capable of?” And the Holy Grail – “Can we use the huge quantities of data from smart toothbrushes, wearables, genomic sequencing, medical records to get to the first and right treatment?”

What next?

In the last decade, big data in biomedicine has focused on collecting (e.g. through mobile and other IoT) and organizing (e.g. cloud computing) information but all signs point in one direction for the next decade – real world applications of AI. We will witness the development of expert systems, question-answering systems and deep learning methods that begin to address complex real world problems in medicine. These will augment, not replace, human expertise. Winners will find ways to rapidly and accurately integrate human input with computational output. Usability of these tools by end users and human factors will be key.

While a true tech automation enthusiast at heart and practice, I will never forget Dr. Willey’s kind and soft words as she clearly explained my pathology report. She also carefully noted in my medical record the rare chlorohexidine pre-op antiseptic agent hypersensitivity that I had developed post anesthetic induction.

One more data point!

              Let’s continue the conversation:

6 responses so far | Categories: From the director's office,Newsletter,Subha Madhavan | Tags: , , , , ,

Nov 03 2015

Quantified Self, GenomeFirst and a trip to the White House – A busy week for Biomedical informatics

by at 11:22 pm

“You are over pronating!” bleeps Bluetooth enabled, sensor-infused smart socks just 10 minutes into your daily running routine.

Or, “check your blood pressure, temperature and heart rate using Scanadusm, with no cuffs, in just 15 seconds!” quips Kevin Maloy of MedStar Institute for Innovation during our fourth annual Georgetown Biomedical Informatics Symposium on October 16, organized and hosted by the Innovation Center for Biomedical Informatics. Emerging trends in informatics and health IT were demonstrated and discussed with over 350 attendees from academia, industry and government. The event benefited from strong support of institutional and industry sponsors. Find out more about the symposium’2015 here. I present Cliff Notes version of four major themes here for your quick browsing.

  1. Quantified Self

We are increasingly wearing bands to track how much we move, strapping on watches to listen to our heartbeat, and logging what we eat and drink. The underlying proposal is that describing ourselves with these numbers will put healthcare back in the hands of people. Will the “quantified self” become a major driver in how diseases are prevented or treated? This is one of the intriguing questions that our symposium explored.

Informatics opportunity: Design in healthcare is an opportunity to improve signal and reduce noise in a system that is over stretched, under utilized and very expensive.

  1. EHRs and other emerging health technologies

Digitized health is a dream come true for many. But are electronic health records (EHRs) actually getting in the way of physician productivity? At our symposium, Mike Hogarth of University of California, Davis presented results from a survey of 410 internists that estimated that 42 minutes are lost each day by physicians due to EHRs. About 80% of key clinical data are in the form of unstructured narratives – a mess he referred to “dirta,” instead of data. This information requires enormous quality control, structuring, and integration – a reality that raises the question: can practice-based evidence be generated through retrospective studies of EHR datasets?

Informatics opportunity: Nigam Shah of Stanford University suggested that enterprise wide data governance at hospital systems, or a green button function within EHRs, could help clinicians use aggregate patient data to support decisions at the point of care. Ben Schneiderman of University of Maryland demo’ed EventFlow, a tool for visual analysis of temporal events within patient records to enable advanced healthcare discovery. Zak Kohane of Harvard University, in his keynote lecture, cited clinical research data integration software such as i2b2, tranSMART, and SMART Health IT apps as solutions to the “dirta” problem in healthcare innovation.

  1. Trends in Precision Medicine

A lot of the excitement at the symposium – amplified by the talks on targeted therapies in pancreatic cancers and a panel discussion on Next Generation Sequencing (NGS) in the clinic – was focused on Precision Medicine.

Mike Pishvaian of Georgetown University and Dr. Jon Brody of TJU discussed PANCan’s “Know your tumor” program. This program has found that 43% of patients had actionable findings from molecular profiling, resulting in modified treatment recommendations and better responses.

Regeneron’s Rick Dewey asked a provocative question: what if everybody’s genome was available in his or her medical record? Rick and Marc Williams of Geisinger described a collaboration between Regeneron and Geisinger to use EHRs and exome sequencing data from over 200,000 individuals for faster drug discovery. It was a treat to hearabout Geisinger’s GenomeFirst initiative, which is implementing genome inference engines – clinical decision support and predictive models to enable Precision Medicine in a unique way with teams of clinicians, genetic counselors, nurse practitioners and informaticians.

No scientific symposium is complete without an award! The (iPAD winning) best poster award went to Ao Yuan, graduate student in Biostatistics at GU for his work on a semi parametric model for the analysis of patient sub-groups in precision medicine trials.

The Precision Medicine journey is underway, and is already improving medicine. Informaticians are vital to this journey. More work is needed to collect the right patient cohorts for research, to identify the right markers to test, and to develop the appropriate targeted therapies.

The Symposium explored what’s next for all of us in this important journey?

Informatics opportunity: Curating evidence of biomarker association with drug response, novel data wrangling approaches to extract and analyze useful clinical and genomic data to drive new hypothesis generation and clinical decision support, and data science approaches to connect genotypes to phenotypes are a few of many opportunities for informaticians to meaningfully participate in the precision medicine revolution.

  1. Security, Privacy and Trust principles for patient-centered studies

The symposium was a perfect lead-in to a great roundtable discussion on a much-needed security framework for President Obama’s Precision Medicine Initiative at the White House OSTP. I was humbled by the discussion with experts in cyber security, patient privacy, trust principles, and data breach. Will “white hat hacking” help? How can we use it in the context of protecting healthcare data and participants from willful misuse?

Informatics opportunity: DJ Patil, US Chief Data Science Officer emphasized the need for IT teams to focus on data infrastructure, auditing and monitoring of patient genomic data, data transmission and access infrastructure, including tiered data access.

It is so gratifying to see informaticians providing thought leadership across the full spectrum of clinical research and care. Let’s continue the conversation – find me on e-mail at subha.madhavan@georgetown.edu or on twitter at @subhamadhavan.

No responses yet | Categories: From the director's office,Newsletter,Subha Madhavan,Symposium | Tags: , ,

Nov 14 2014

A Symposium to Remember

by at 5:16 pm

With vibrant talks and over 300 attendees from academia, industry and government, the 3rd Annual Biomedical Informatics Symposium at Georgetown was a great place to be on October 2, 2014. I hope many of you had the opportunity to take part and soak in the advances presented from multiple facets of Big Data in biomedical research. If not, you can access the talks, photos and the program here.  Below is a quick recap of the symposium as I witnessed it.

Stanford professor and biotech entrepreneur Atul Butte (@atulbutte) opened his keynote lecture by reminding us of the data deluge at the epicenter of the next scientific revolution. He described four scientific paradigms spanning the centuries as: 1) “Theory” – where people in ancient Greece and China explained their observations of the world around them through natural laws; 2) “Experimentation” – by the 17th century scientists like Newton had begun to devise hypotheses and test them through experimentation; 3) Computation & simulation – The later half of the 20th century witnessed the advent of supercomputers that allowed scientists to explore areas inaccessible to theory or experimentation such as galaxy formation and climate; leading up to the current new paradigm shift in the scientific process; and 4) “Data mining” –exploring relationships among enormous amounts of data to generate and test hypotheses. He illustrated the tremendous benefit of mining public data, such as mining gene expression data from EBI ArrayXpress and NCBI GEO, to discover and develop molecular diagnostics for transplant rejection and preeclampsia.

Did you know that the price to bring a drug to market in the US would pay for 371 Super Bowl ads? With patent cliffs for blockbuster drugs such as Plavix and Lipitor and $290 B in sales risk, Pharma turn to new innovation models such as academic partnering and drug repurposing. In this context, Atul discussed his lab’s work published in Science Translational Medicine using computational repositioning to discover an anti-seizure drug effective against inflammatory bowel disease. He concluded by encouraging participants to take a creative approach to funding science, and treat it as a continuum supported by federal agencies and private organizations. He provided numerous examples of startups originating through ARRA or NIH pilot funding and who have successfully launched companies with robust VC funding to continue development and marketing.

Professor of Oncology and Deputy Director of Lombardi, Mike Atkins, organized and facilitated a panel titled “Cancer Immunotherapies – what can we learn from emerging data?”  Panelist Jim Mule, EVP at Moffitt Cancer Center described ORIEN, the Oncology Research Information Exchange Network between Moffitt and The James Ohio State cancer centers, enabling big data integration and sharing for cancer research and care. As of May 2014, the network assembled data on 443,000 patients. He described a powerful example of precision medicine projects enabled by the network including a 12 chemokine gene expression signatures that predict overall survival in stage IV melanoma patients.

Yvonne Saenger, Director of Melanoma Immunotherapy at Columbia University, discussed a 53 immune-gene panel that is predictive of non-progression in melanoma with resectable stage I, II disease. She and her colleagues used NanoString technology to study transcriptomics with extensive bioinformatics involving literature mining to select genes for the NanoString assay as well as Bayesian approaches to identify key modulatory pathways.

Kate Nathanson, cancer geneticist from Penn, presented the role of inherited (germline) variations in determining drug response to ipilimumab, a monoclonal antibody recently approved by the FDA for treatment of Melanoma and works to activate the immune system by targeting Cytotoxic T Lymphocyte Associated protein (CTLA4). This work provided a nice complement to the somatic studies presented by others on the panel.

Industry perspective was brought to the panel when Julie Gil from Adaptive Biotechnologies discussed the ImmunoSequencing platform tailored to T-Cell and B-Cell receptors for generating diagnostic applications in Oncology.

The recent approval of novel mechanism-based cancer immunotherapies, ipilimumab (Yervoy) and sipuleucel-T (Provenge) has motivated further investigation into the role of immunity in tumor pathogenesis. Despite the recent successes, the field of immunotherapy has experienced nearly a dozen failures in Phase 3. Three major issues need to be addressed to reduce the high failure rates: 1) Finding specific signatures in the tumor microenvironment associated with, or necessary for, response to therapy; 2) Determining molecular mechanisms employed by malignancies to defeat immune recognition and destruction – are they related to specific mutations, pathways, clonal signatures, or organs of origin?; and 3) Identifying a ‘non-inflamed’ tumor that evades the immune system, and then making it ‘inflamed’ for effective immunotherapy treatment. As noted by Kate Nathanson and Robert Vonderheide in Nature Medicine, despite the existing biological and technical hurdles, a framework to implement personalized cancer vaccines in the clinic may be worth considering. The cancer immunotherapies panel at the ICBI symposium shed some new light in this novel direction.

The afternoon panel was kicked-off by UChicago/Argonne National Labs Professor of Computer Science, Ian Foster (@ianfoster), who described the Globus Genomics cloud-based big data analysis platform to accelerate discovery without requiring every lab generating data to acquire a “haystack–sorting” machine to find that proverbial needle. He described projects ranging from 75 to 200 exomes that were analyzed in less than 6 days using a few hundred thousand core compute hours.

As a complement to the infrastructure discussion by Ian, Ben Langmead from Johns Hopkins (@BenLangmead) highlighted tools he and his colleagues developed for RNASeq analysis (Myrna) and multi-experiment gene counts (ReCount). These tools were applied to HapMap and GEUVADIS (Genetic European Variation in Health and Disease) datasets resulting in high profile Nature publications: Understanding mechanisms underlying human gene expression variation with RNA sequencing and Transcriptome and genome sequencing uncovers functional variation in humans. Corporate presentations included Amazon’s Angel Pizarro working with sensitive genomic data on the Amazon cloud, and Qiagen-Ingenuity Systems’ Kate Wendelsdorf’s presentation on assays and informatics tools to study mechanisms of metastases.

A “reality check” special session entitled “Finding Value in Cancer Care” was delivered by Ruesch Center director, John Marshall, who illustrated how the interests of different stakeholders (patients, Pharma, regulatory agencies, and payers) need to be balanced in applying the best and most cost-efficient cancer care.

The event culminated with a reception and poster session with hors devours and wine but not before best poster awards for G-DOC Plus (3rd place), medical literature based clinical decision support (2nd place) and the iPAD award winning first prize to Lombardi’s Luciane Cavalli and her team for “Targeting triple negative breast cancer in African-American Women.”

The free and open-invitation event was made possible by generous support from Lombardi Cancer Center, Georgetown-Howard Universities CTSA, Center for excellence in regulatory science and Georgetown center for cancer systems biology as well as our corporate sponsors.

As I prepare to take off for the annual cancer center informatics directors’ conference in Sonoma, CA (yes more wine coming my way), I am rejuvenated by the vibrant exchanges at the Symposium that promise exciting days ahead for data scientists and bioinformaticians to make impactful contributions to biomedical research.  Let’s continue the conversation – contact me at subha.madhavan@georgetown.edu or find me on Twitter @subhamadhavan

No responses yet | Categories: From the director's office,Subha Madhavan,Symposium | Tags: , , , , ,

Oct 24 2013

Poster Winners!

by at 4:46 pm


First place

Dr. Robert Clarke, Dean of Research at the Lombardi Cancer Center presented the best poster awards during the reception for the 2nd annual biomedical informatics symposium held October 11, 2013.

The first place prize went to ICBI’s own Difei Wang (see below). The top poster winners were chosen through crowdsourcing by conference attendees, with first place receiving an iPAD mini. Dr. Wang, who was quite grateful to be selected, was also very surprised and humbly said to a small group of us, “I didn’t even vote for myself!”

Second place was a tie between two groups: one group at George Washington University on data mining of gene expression and microarray data, and the other group from Georgetown University Medical Center on the impact of pager delays on trauma teams (see below).  The third place winner went to ICBI’s Michael Harris and team on pharmacogenomics.

First Place:  SNP2Structure: A public database for mapping and modeling nsSNPs on human protein structuresSecond place- a
Difei Wang, Kevin Rosso, Shruti Rao, Lei Song, Varun Singh, Shailendra Singh, Michael Harris and Subha Madhavan Innovation Center for Biomedical Informatics, Georgetown University Medical Center, Washington DC

Second Place (tie): Biologically Inspired Data Mining Framework for Detecting Outliers in Gene Expression Microarray Data
Abdelghani Bellaachia and Anasse Bari Department of Computer Science, School of Engineering and Applied Science,The George Washington University

Second Place (tie):The impact of pager notification delays on trauma team dynamics Second place b
Kayvon I. Izadpanah, MS1,2; Imran T. Siddiqui, MS1,2; Sarah H. Parker, PhD2; 1Georgetown University School of Medicine, Washington, DC; 2National Center for Human Factors in Healthcare, Washington DC

Third Place: Pharmacogenomics to clinical care 
Michael Harris, Krithika Bhuvaneshwar, Varun Singh, Subha Madhavan Innovation Center for Biomedical Informatics, Georgetown University Medical Center (award accepted by Krithika) 3rd place

No responses yet | Categories: Symposium | Tags: ,

Oct 24 2013

Keynote Talks at ICBI symposium: Stephen Friend and Eric Hoffman

by at 4:40 pm

Big Data in Precision Medicine was the focus of the 2nd Annual Biomedical Informatics Symposium at Georgetown, which drew nearly 250 people to hear about topics from direct-to-consumer (DTC) testing to mining data from Twitter.

The morning plenary on Genomics and Translational Medicine was kicked off by Stephen Friend, MD, PhD, President, Co-founder, and Director of Sage Bionetworks who discussed the “discontinuity between the state of our institutions and the state of our technology.”   This disconnect stems from the way results are presented in the literature and compared with one another in different scenarios, and sometimes interpreted into the clinic. “We are going to get different answers at the DNA, RNA, and functional levels,” said Friend, and different groups working on the same data can get different answers because science “context dependent” – dependent on the samples, technologies, and statistical parameters.  Our minds are wired for a “2D narrative” but the fact is we are all just “alchemists.”

Friend is a champion of open data sharing and turning the current system on its head.  We need “millions of eyes looking at biomedical data…not just one group, it’s immoral to do so,” Friend said.  We need to get rid of the paradigm, “I can’t tell you because I haven’t published yet.”   He said that GitHub has over 4M people sharing code with version tracking, and in fact hiring managers for software engineering jobs are more likely to look for a potential candidate’s work on GitHub than to considering credentials on a CV.

Sage created Synapse, a collaborative and open platform for data sharing, which he hopes could be the GitHub for biomedical scientists.   He would like to see large communities of scientists worldwide working together on a particular problem and sharing data in real time. As an example of this sort of effort, check out the Sage Crowdsourcing genetic prediction of clinical utility in the Rheumatoid Arthritis Responder Challenge.  His excitement for this future model for large scale collaboration was palpable in his closing remarks—a prediction for a future Nobel prize for “theoretical medicine.”

The afternoon plenary on Big Data in Biomedicine was led by a keynote talk from Eric Hoffman, PhD, Director of the Research Center for Genetic Medicine at Children’s National Medical Center who discussed “data integration in systems biology”  -which is a topic very close to the heart of ICBI.  He presented a new tool, miRNAVis, to integrate and visualize microRNA and mRNA expression data, which he referred to as “vertical” data integration or the integration of heterogeneous data types.  This tool will soon be released for public use.

Hoffman is considered one of the top world experts in muscular dystrophy research, having cloned the dystrophin gene in Louis Kunkel’s lab in 1987.  He has made an enormous contribution to research in this field along with dedicating countless hours to volunteering with children affected by the horrible disease.  He discussed a very exciting project in his lab on a promising new drug – VBP15, which has anti-inflammatory properties, and shows strong inhibition of NF-κB, and repair of skeletal muscle.  Most importantly, VBP15 does not have the side effects of glucocorticoids, which are currently the standard treatment for Duchenne muscular dystrophy. Hoffman said this new drug may potentially be effective against other chronic inflammatory diseases.  Let’s hope this drug will make it into clinical trial testing very soon!

More information about the keynote and other talks can be found on ICBI’s Twitter feed and at #GUinformatics, which provided snapshots of the day.

No responses yet | Categories: Symposium | Tags: , , , , ,

Oct 12 2012

Inaugural Biomedical Informatics Symposium at Georgetown

by at 7:28 pm

With relief felt by the organizers and much gratitude toward the participants, the first Georgetown Biomedical Informatics symposium held on October 12, 2012 was filled with inspiring talks and provided opportunities for rich networking.  The goal of the symposium was to both showcase cutting edge research and applications in the field of biomedical informatics and to inform the Georgetown University Medical Center (GUMC) community of the related educational opportunities and in-house informatics resources we have available to enhance both basic research and clinical trials.  This free, one-day symposium featured a variety of talks by leaders in the fields of clinical and translational sciences, including keynote talks by John Quackenbush at Harvard, and John Niederhuber at Inova Translational Medicine Institute (and former director of the National Cancer Institute).  There were 130 attendees, which exceeded our goal to reach 100 registrants.

The new GUMC Innovation Center for Biomedical Informatics (ICBI)  hosted the event along with the  Georgetown-Howard Universities Center for Clinical and Translational Science, Georgetown Center for Cancer Systems Biology, and Georgetown Lombardi Comprehensive Cancer Center.   We felt honored by the support provided to us at GUMC, with introductory talks by Dr. Lou Weiner and Dr. Robert Clarke, which set the stage for the day.  Dr. Weiner, Lombardi Cancer Center Director, kicked off the symposium with imagery from a 1951 movie “When Worlds Collide” to demonstrate the challenge in biomedical informatics of integrating clinical and quantitative molecular data.  Among those challenges, he said, is that ‘we obtain clinical data idiosyncratically, and share it idiosyncratically so information in place A can’t get to place B’.   With the plethora of data analysis platforms and databases for storage this will be a huge challenge for the community going forward. And although it may be hard to succinctly identify what the future of biomedical informatics will look like, it may have been aptly characterized by Dr. Clarke who said, “It’s a bit like pornography, you’ll know it when you see it!”

ICBI Director, Dr. Subha Madhavan, presented a short overview of the new bioinformatics center with highlights of four main projects.  ICBI primarily performs peer-reviewed research in the translational sciences, although support services to the Georgetown community comprise an important part of the new center mission.  The Georgetown Database of Cancer (G-DOC) is one of the research projects she highlighted as the biomedical informatics platform that integrates patient molecular data with clinical data and provides several analytical tools for processing the results to obtain new insights.  Ultimately, G-DOC will serve not only researchers but clinicians involved in molecular diagnostics who can use G-DOC to make personalized therapeutic decisions based on a patient’s genomic profile.

ICBI is also engaged in a pharmacogenomics project supported by the FDA, said Madhavan, to determine how different genotypes affect drug efficacy and metabolism in hopes of improving labeling and therapeutic decisions. Why put a patient through potentially toxic side effects of certain drugs if based on their genotype the drug may not work, or work effectively at the given dosage?

Taming and making use of “big data” is another major theme for the ICBI and many biomedical research centers in consideration that the “NIH-funded 1000 Genomes Project deposited 200 terabytes of data into the GenBank archive during the project’s first 6 months of operation, twice as much as had been deposited into all of GenBank for the entire 30 years preceding” said Madhavan. The “Million Genomes Project” is not too far way she continued, and as impossible as it is to comprehend that amount of data we are in desperate need of figuring out how to store, deconvolute the data into useful information that clinicians can use to make decisions.

Keynote Addresses

John Quackenbush, the first keynote speaker, said that “biomedical research is changing from a laboratory science to an information science.”  Considering that the cost of sequencing has dropped by “33% every four months since 2007,” he said that he anticipates that when the cost becomes low enough, “I will give my wife her genome for her birthday.”  A gift surly to melt any woman’s heart.  Related to romance, he said that since he met his wife on Match.com, that his 6 year old son will likely meet his wife on “Genematch.com” when considering how cheap sequencing will soon become.  “I guarantee his genome will be sequenced by the time he is 15, but I don’t want it on Facebook,” he said, “I want it to be available to him for his private use.”  Privacy is another critical issue facing the effective use of biomedical informatics, as genomics data may likely be considered HIPPA protected.  Considering that with “only 250 base pairs of DNA a person is identifiable” Quackenbush thinks the government and patients will insist on ensuring privacy despite a patient’s desire to have their genome be widely analyzed for information that may improve their health outcome.  Many companies selling software for genomic storage and clinical use are proactively becoming HIPPA compliant to be ready for the anticipated widespread availability and growing demand for genomic data in the clinic and for use in Electronic Medical Records. One of the flagship biomedical informatics projects Quackenbush and his team at Harvard are involved with is the development of the data-coordinating center of the NIH funded Lung Genomics Research Consortium.  His team collects and integrates data from the LGRC partners and develops new methods to analyze the data and present it to the scientific community to help understand and treat lung disease.  “We developed a proprietary data mining tool,” he joked, “called high-school students.”  His team has developed this portal not only for the bioinformatics researchers but for other users who want to be “editors of genomic content” rather than informatics analysts who develop algorithms and tools for looking at the data. John Niederhuber, the afternoon keynote speaker discussed the future of healthcare as the pursuit of personalized health.  “We manage patient care on the average; how the average patient responds to medication.”  When we talk about personalized healthcare “we take it out of the average” said Niederhuber, “to see how YOU will respond.”  “Is this the wrong drug?  What dosing is best?”  This approach, he said, will allow the clinician to immediately know if the typical drug used to treat the population that normally responds (the average) to a particular medication will be effective on a particular patient who may respond differently than average based on their genotype. Niederhuber, who directs the Inova Translational Medicine Institute, highlighted two projects the Inova is doing to contribute toward the future of personalized medicine.  One study launched in April 2012 has already recruited 2500 family cohorts to build a “generational” genomics database starting with women in their first trimester of pregnancy and following the baby after birth through adulthood.  The project team will sequence the baby, both parents, and the grandparents to garner a huge dataset for genetic, behavioral and environmental data that can contribute to disease outcome.    He hopes to get 2-3 other hospitals/centers on board with the project to add families to this soon-to-be treasure trove of genetic data.  Another study that started last year was to understand the genetic underpinnings of preterm birth through sequencing trios- mom, dad, and baby.  One commenter from the audience brought up the environment (e.g. allergies) as a possible contributor to pre-term birth; Niederhuber said the longitudinal study will address such confounding factors that cannot be explained by genetics alone.  He also stressed the need for “ethnic specific reference genomes” rather than the admixture of genomics that was used to create the first human genome.  Large scale genomic projects will be met with greater success if families or individuals with defined ethnicities can have their genomes compared to a reference genome specific to their genetic background.  Certain mutations in genes from one ethnic group have been shown to have a different effect in a different ethnic group.  Niederhuber said we will soon be able to generate raw (sequencing) data very quickly – less than 24 hours at low cost, but we are still a long way from processing the data efficiently with analytical tools to make the data medically relevant and affordable.

Session 1 – Informatics Enables Clinical Research

Three excellent talks were given by government representatives who are involved in the challenges of big data and how best to analyze the exponential growth of genomic and other translational research information.  Kenna Shaw, director of The Cancer Genome Atlas (TCGA) project discussed the current TCGA collection stated that the goal is to identify molecular alterations in human cancers, not find clinical markers of disease.  She referred to the TCGA as a “biology project” not a clinical project.  Shaw said they will be accepting patient samples until December 15, 2013 as the funding ends in 2014.  And if there is a cohort of at least 100 cases of a rare tumor, Shaw said they are very interested in learning about it for possible incorporation into the TCGA pipeline.

ShaAvhree Buckman, director of the Office of Translational Sciences, Center for Drug Evaluation and Research (CDER) at FDA,  discussed FDA’s major emphasis on improved regulatory decision making.  The FDA is “rapidly moving toward a modernized, integrated informatics-based review environment,” Buckman stated, and a major part of this effort is to incorporate genomic information and new analytical capabilities where available to support “quantitative decision making.” She stressed that “high quality, standardized data is key” to this effort.  Toward the goal of making information standardized and assessable, CDER has created a new Computational Science Center to enhance the review and regulatory process, as well as to “enhance responsiveness to emerging safety problems through better information,”  said Buckman.  This has been a challenge for the FDA since until recently drug submissions have arrived in paper form, and several still do she noted, so they are not amenable to quick analysis. Buckman said that FDA has the “largest repository in the world of subject-level clinical trial and nonclinical study experience,” but this is largely “unstructured data and poorly accessible.”   Through the new center, the FDA is working to reduce the burden for  reviewers who have to wade through volumes of paper.  A new electronic format she said, will be used to create a “Clinical Trials Repository” that supports the structured “acquisition, validation, integration, and  extraction of data from the increasingly large and complex datasets received by the Agency.”  An increasing number of these clinical datasets include genomic data and this new system, she said, will  “make use of enhanced analytical tools and techniques that enable reviewers to search, model, and analyze data to conduct better safety and efficacy analyses.”

Session 2 – Technology Driven Systems Medicine

Two technology development talks were given on some of the exciting developments in bioinformatics.  Joel Saltz, Director of the Center for Comprehensive Informatics, and Chair of Biomedical Informatics at Emory University, discussed progress in the integrative analysis of heterogeneous, multiscale datatypes, which is where the field is going now.  We are at an ‘”intermediate point” with data integration, and “closer to the beginning than the end” he said regarding the integration of data types (e.g. radiology imaging, pathologic features, omics data, and patient outcome) to improve clinical decision making.  The integration of data types will also help reduce variability among pathology interpretations and help to sub-classify patients for therapeutic intervention. Eliot Siegel, Professor and Vice Chair of the University of Maryland Department of Diagnostic Radiology, and Chief of Radiology and Nuclear Medicine for the Veterans Affairs Maryland Healthcare System, spoke about the analysis of big data using artificial intelligence (AI).  For example, IRB approval was recently received for a major VA initiative to process of collecting records from one million veterans, which will be extremely valuable for clinical researchers.  Saltz said that the challenge will be to determine how to search through vast amounts of this largely “unstructured” data for clinical decision making and not just for research. “2011 will be remembered as the re-emergence of artificial intelligence” he said when describing the Jeopardy competition between IBM’s “Watson” AI system and the top human Jeopardy winners of all time.   Watson won, which was a huge boon to AI and IBM’s “DeepQA” or deep question answer software that uses multiple evidence types and algorithms to find answers, and then weighs the probability that an answer is correct.  Watson draws from numerous information databases to link common words and phrases, find and generate hypotheses, score the evidence and generate confidence levels.  The speed of the processing is amazing as Watson can process 500 gigabytes per second (the equivalent of a ~ 1 million books). Siegel said AI can be applied to the health domain to enable more accurate clinical decision making based on the ability of the system to process information with high confidence based on available data.  This would be especially critical in hospital emergency rooms where there are a significant number of errors due to limitations in knowledge and other cognitive factors such as “premature closure” –  where a physician comes up with an answer and stops there, rather than going further in assessing all the relevant options   – computers don’t stop at one option.  He said many previous AIs didn’t have an easy and rapid interface so are not well adopted.  In an ER situation Siegel said, “You want an answer in 3 seconds.”  Similar to Google, he added, people want to be able to input symptoms into a database and receive output diagnoses at a certain confidence level.  For Electronic Medical Records (EMRs) Siegel said you cannot even search for the term “rash” or any other terms within a patient record or across records.  “Institutes across the country are generating large, rich clinical data but none of this data is searchable, said Siegel. He added that “we need standard (imaging, clinical genome etc) data” to provide inputs into AI databases like Watson.  He was optimistic that we are going to see “an explosion of smart applications” related to AI for EMRs and other part of the medical community.

Georgetown Resources

The afternoon talks of the symposium focused on Georgetown informatics educational programs and resources.  Dr. Sona Vasudevan, Associate Professor and Director of the MD/MS program in Systems Medicine discussed the educational programs.  Of particular interest is the MD/MS dual degree program in Systems Medicine that enables a medical student to spend one year doing bioinformatics research. This program provides critical training to medical students since biomedical informatics will soon become an integral part of clinical practice. Dr. Cathy Wu, Professor, and Director of the Protein Information Resource (PIR) spoke about the program, which houses the world’s largest publicly available protein sequence database called the Universal Protein Resource (UniProt). Dr. Yuriy Guesv, Sr. Bioinformatics Scientist within the ICBI discussed the Georgetown Database of Cancer, which is a platform that integrates multiple types of omics and clinical data for numerous cancer studies for use by the clinical and translational research communities. Rachel Kidwiler, Program Director and AVP, Research Information Systems, discussed REDCap, a tool to enable standardized clinical study data collection. Dr. Nawar Shara, Assistant Professor, and Director, Biostatistics and Epidemiology, MedStar Research Institute, discussed Explorys, an enterprise-level platform that for clinical data – enables the aggregation, analysis, management, and research of big data.


A combined poster session and reception was held after the talks with posters judged by crowdsourcing. Three “best poster” prizes were given and the winners are:

1st place – “Mining Social Media for Healthcare”  
Andrew Yates and Nazli Goharian; Department of Computer Science, Georgetown University

2nd place -“Screening of Novel Anti-Neuroinflammatory Agents to Treat Parkinson’s Disease”
Henry North1, Shalonda Williams1, Jau-Shyong Hong2, Xiang Simon Wang1*; 1Molecular Modeling and Drug Discovery Core for District of Columbia Developmental Center for AIDS Research (DC D-CFAR); Laboratory of Cheminfomatics and Drug Design, Department of Pharmaceutical Sciences, College of Pharmacy, Howard University, Washington, District of Columbia 20059; 2Laboratory of Pharmacology, National Institute of Environmental Health Sciences, Research Triangle Park, NC 27709

3rd place (tie)- “Cheminfomatic Studies of Human Ephs Receptorome”    
Terry-Elinor Reid, Dejene Woldemariam, Tewodros Gashaw, Xiang Simon Wang; Molecular Modeling and Drug Discovery Core for District of Columbia Developmental Center for AIDS Research (DC D-CFAR); Laboratory of Cheminfomatics and Drug Design, Department of Pharmaceutical Sciences, College of Pharmacy, Howard University, Washington, District of Columbia 20059

3rd place (tie)- “Practical Aspects of the Development and Implementation of Post Submission Quality Checks for the Data from the Breast and Colon Cancer Family Registries”
Andrea Gabriela Barbo, Mauricio Oberti,  Sweta Ladwa, Peter B McGarvey, Subha Madhavan, Anca D Dragomir; Innovation Center for Biomedical Informatics, Georgetown University Medical Center – See more at: http://icbi.georgetown.edu/blog/index.php?postID=15#sthash.s3kgxcU8.dpuf

No responses yet | Categories: Symposium | Tags: