1
A NIH – Semantic Medline Data Science Data
Publication CommonsDr. Brand Niemann
Director and Senior Data Scientist/Data JournalistSemantic CommunitySemantic Community
Data Science NLM - Semantic Medline Data Science Data Publication
August 17, 2015
2
Federal Big Data Working Group Meetup Precision Medicine Initiative• Data Scientists and Doctors should first do their own Precision Medicine Initiative:
• E.g. Jeff Hammerbacker (Assistant Professor of Genetics and Genomic Sciences, Mount Sinai Hospital-Bipolar Disorder), Brand Niemann (My Kaiser and Natural Medicine for Disease and Wellness Meetup).
• Background for This Meetup:• Dr. Richard Moser, NIH Clinical Psychologist, Public Use Data Sets: Cancer Genomic
Evidence-based Medicine Knowledge Base (CancerGEM KB): • http://cancercontrol.cancer.gov/brp/research_tools.html• https://www.gem-measures.org/public/Dataset.aspx?cat=3
• Muin Khoury, NIH Associate Director, Epidemiology and Genomics Research Program Cancer, GEM KB (Cancer Genomic Evidence-based Medicine Knowledge Base) (version 1.0): An integrated, searchable knowledge base of cancer human genome epidemiology and genomic applications in cancer care and prevention: • http://www.hugenavigator.net/CancerGEMKB/home.do
3
Federal Big Data Working Group Meetup Precision Medicine Initiative• Background for This Meetup (continued):
• Tram Kim Lam, Ph.D., M.P.H., Program Director, Environmental Epidemiology Branch, NIH/NCI: Cancer Genomic Evidence-based Medicine Knowledge Base (CancerGEM KB) See new initiative: CGEN
• Teri Manolio, M.D., Ph.D., A broader context for ‘individualizing’ medical care to advance human health (PDF), National Human Genome Research Institute, National Institutes of Health, Cross-Cohort Collaboration Meeting, March 7, 2015
• GWAS catalog, Lucia Hindorff, and or Cancer Genome Atlas, Carolyn Hutter• Dr. Taha A. Kass-Hout, M.D., M.S., or David Litwack, Ph.D.,
Advancing precision medicine by enabling a collaborative informatics community• Dr. Vivien Bonazzi, Senior Advisor for Data Science Technologies, ADDs (Associate Director
for Data Science) Office, Office of the Director (OD), National Institutes of Health (NIH)
4
Outline
• My Kaiser and Natural Medicine for Disease and Wellness Meetup• Data Science Data Publications for NIH• My Data Science Data Publications for NIH Wish List• Informatics and The Geonome• Glucan
5
New Message from Kaiser Permanente
• Dear Brand L Niemann,• You have a new message available from your provider on the Kaiser
Permanente website.• Please click on the link below, or copy and paste the link into your
browser. After successfully signing on to the Kaiser Permanente website, you will be able to read this new message.• http://kp.org/newmessage• Thank you for using our website.
6
Important messageYou're signed off, or we've signed you off, to protect your privacy.
Want to find out more? Sign on again, or explore our health calculators, featured health topics, drug encyclopedia, and health encyclopedia.
7
My Note: What More Do I Need?I am Traveling to Mongolia and Need To Take My Medical Record.
8
My Note: Blue Button!1.3 MB Zip File
9
Lots of Services:AllergiesDownload my health summaryHealth care remindersHealth statsHealth summaryImmunizationsLetters (Consent Forms)Ongoing health conditionsPast visit informationPersonal action planQuestionnairesTest resultsWallet card
10
Message From My Doctor
• Hello Mr. Niemann,• The pathology report from the biopsy done 6-23-15 on your right
cheek is a basal cell carcinoma. Additional treatment is needed as the margins are not clear.• Dr. Naftanel has referred you to see Dr. Mesfin for treatment with the
Mohs procedure. The Mohs department will contact you in the next several business days to schedule you an appointment. Please follow up with Dr. Naftanel in 3 months.• Vickie Dugan RN, 2:53 PM, July 7, 2015, Falls Church Dermatology
11
Search the Health Encyclopedia for This Term
12
See Below: What increases your risk for nonmelanoma skin cancer?You may also be more likely to get it if you have been exposed often to strong X-rays, to certain chemicals (such as arsenic, coal tar, and creosote), or to radioactive substances (such as radium).My Note: I was given X-ray for acne as a teenager and now I am paying the price for that!
13
My Note: Mohs surgery is precision medicine.
14
What creams are used for treatment?
• The creams used to treat basal cell skin cancer are imiquimod and 5-FU (fluorouracil). They contain powerful medicines that cause a painful irritation in the treated area. The skin gets inflamed and crusts over as it heals.• You apply the cream every day or two for several weeks.• 5-FU has a cure rate of 90 out of 100 for basal cell cancer that is
superficial (only in the top layer of skin). That means that in 10 out of 100 cases, the cream does not cure the cancer.• Imiquimod has a cure rate of more than 75 out of 100 for superficial
basal cell cancer. That means that in 25 out of 100 cases, the cream does not cure the cancer.
15
Search the Health Encyclopedia for This Term
16
Biologic therapy
• Biologic therapy is a treatment that uses the patient's immune system to fight cancer. Substances made by the body or made in a laboratory are used to boost, direct, or restore the body's natural defenses against cancer. This type of cancer treatment is also called biotherapy or immunotherapy.• My Note: I am getting pre-cancer immunotherapy!
• Immunomodulators are a type of biologic therapy. Thalidomide, lenalidomide, and pomalidomide are immunomodulators used to treat multiple myeloma and other plasma cell neoplasms.• Interferon is a type of biologic therapy. It affects the division of cancer
cells and can slow tumor growth.
17
Data Science Data Publications for NIH
• NIH Data Publication 1, Part of Data Culture at the NIH, done for Dr. Philip Bourne earlier.
• NLM Semantic Medline Data Science Data Publication 1:• Data Science Data Publication: Natural Medicine
for Disease and Wellness-Semantic Medline• Policy Makers: Future of NLM - Report• Public: NLM MedlinePlus - Gluten• Researcher: Press Release, Slides, & PubMed
Search - Glucan• Data Scientist: Publication - Leukemia &
Lymphoma • Semantic Medline: Context - For Each & Add More
Data (Genomic & Nutrition)• Researchers: Have Examples - Data Scientists Help
Them
• We have been working to support Drs. Bourne, Komatsoulis, and Rindflesch as follows:• Sematic Medline takes us to the
important results in the clinical text so we better know why and where to look for the clinical data.
• My data science data publication examples for our July 20th and August 17th Meetups show the combination of both.
• The Clinical Literature and Clinical Data need to be integrated into Data Science Data Publications in a Data Commons.
18
NIH Data Publication 1, Part of Data Culture at the NIH, done for Dr. Philip Bourne earlier.
19
NLM Semantic Medline Data Science Data Publication 1
20
My Data Science Data Publicationsfor NIH Wish List
• Traumatic Brain Injury (TBI): LandWarNet 2011 Conference• Post Traumatic Stress Disorder (PTSD): 2015 Foundry Challenge Cup• Dr. Eric Green, Director of the National Human Genome Research
Institute (NHGRI): Seminar: Big Data, Genomics, and Precision Medicine• NHGRI’s Precision Medicine Cohort: Any designated group followed or
traced over a period, as in an epidemiologic cohort study.• NHGRI’s Genome-Wide Association Studies (GWAS): Catalog• The Cancer Genome Atlas: Service to America Medal Finalists
21
Informatics: The Power of I
• There’s been some debate in the AMIA online communities about what “precision medicine” means. While it is traditionally associated with tailoring therapies based on genomic information, I think it is much more than that.
• Precision medicine is about having all the information you need to precisely tailor interventions for an individual, so that you can achieve a better outcome.
• For some, this might mean understanding their activity record in their FitBit so that you can identify the best time for someone to take their insulin; it might mean analyzing their EHR information to see if the person is eligible for a clinical study; it might mean identifying that an individual lives in a food desert that makes dietary modifications difficult; and it might mean using an individual’s genomic information to predict if they will respond to a particular intervention.
• What is different and exciting about the Precision Medicine Initiative is that it is all about the person — it’s about engaging people in improving health and healthcare and having them be a part of something bigger than themselves.
http://fridsma.amia.org/tag/precision-medicine/
22
23
The Genome
• The genome is the entire set of genetic instructions found in a cell. In humans, the genome consists of 23 pairs of chromosomes, found in the nucleus, as well as a small chromosome found in the cells' mitochondria. Each set of 23 chromosomes contains approximately 3.1 billion bases of DNA sequence.
• Dr. Francis S. Collins, director of the National Institutes of Health, is noted for his landmark discoveries of disease genes and his visionary leadership of the Human Genome Project, a complex multidisciplinary scientific enterprise directed at mapping and sequencing human DNA.
• Dr. Collins was the director of the National Human Genome Research Institute from 1993 to 2008. His research has led to the identification of genetic variants associated with type 2 diabetes and the genes responsible for cystic fibrosis, neurofibromatosis, Huntington's disease and Hutchinson-Gilford progeria syndrome.
• In 2007, Dr. Collins received the Presidential Medal of Freedom, the nation's highest civil award, for his revolutionary contributions to genetic research.http://www.genome.gov/glossary/index.cfm?id=90
24
Semantic CommunityData ScienceData Science for Health Datapalooza 2015NLM - Semantic Medline Data Science Data Publication
25
Data Scientist: Publication - Leukemia & LymphomaA.J. Lanigan (Glucan Producer): Slides
The most extensively studied glucan is derived from Baker’s Yeast (Saccharomyces cerevisiae) , perhaps because it has been proven to produce the highest biological effects.
26
Agenda
• 6:30 p.m. Welcome and Introduction (New Tutorial and Mentoring) Slides NLM - Semantic Medline Data Science Data Publication• 6:45 p.m. Dr. Tom Rindflesh, NIH/NLM, Slides• 7:15 p.m. Brief Member Introductions• 7:30 p.m. Dr. Vivien Bonazzi, Senior Advisor for Data Science
Technologies, ADDs (Associate Director for Data Science) Office, Office of the Director (OD), National Institutes of Health (NIH) Slides • 8:15 p.m. Open Discussion• 8:45 p.m. Networking• 9:00 p.m. Departhttp://www.meetup.com/Federal-Big-Data-Working-Group/events/223222934/
27
http://lhncbc.nlm.nih.gov/personnel/thomas-rindflesch
Zhang R, Adam TJ, Simon G, Cairelli M, Rindflesch TC, Pakhomov S, Melton GB. Mining biomedical literature to explore interactions between cancer drugs and dietary supplements. 2015 Joint Summits on Translational Science Proceedings.
28
Interview with HIMSS Innovator-in-Residence Adam Culbertson
• In September of 2013, HIMSS and the US Department of Health and Human Services announced Adam Culbertson’s appointment as an Innovator-in-Residence. In this interview, Adam shares the details of his work on patient data matching, a problem that, if solved, would revolutionize the use of Big Data.• I spent approximately two years as a biomedical informatics fellow at the National
Institutes of Medicine where I worked on Natural Language processing under the mentorship of Dr. Thomas Rindflesh. We modified and evaluated the system to extract adverse drug events from drug labels from the freely available Daily Med. At the Regenstrief Institute I was exposed to a variety of topics from national experts including Big Data, patient matching, health information exchange, HL7 and LOINC.• A mentor of mine said, “patient matching is a 90% sociopolitical problem and a 10% technical one.”
29
https://datascience.nih.gov/adds/staff