Chair’s Message
We are moving toward our vision with a number of activities. We completed the Clinical Informatics Fellowship match and filled our two open positions with two excellent candidates who started July 2018. We completed the interview process for our research focused MS and research focused PhD programs, and have a new cohort who will start in Fall 2018. Applications are open for our applied on-line MS in Clinical Informatics and Patient Centered Technologies. We are beginning a new overall strategic planning process for all of our Departmental activities in conjunction with preparing for our every 10 year academic program review. We are still actively recruiting new faculty as part of our strategic plan to expand our core faculty by 50%, with 3-4 positions remaining to be filled over the next two years (see link).
Cordially,
Peter Tarczy-Hornoch, MD
Chair and Professor, Department of Biomedical Informatics and Medical Education
Biomedical Informatics and Medical Education Newsletter
October 8-12, 2018
UPCOMING LECTURES AND SEMINARS
BIME 590A – Biomedical & Health Informatics Lecture Series
Thursday, October 11, 4:00pm-5:00pm, UW Medicine South Lake Union, Room C123A&B
(Also broadcast live and archived at tcs.slu.washington.edu; livestream will have a red dot in the top left hand corner)
Title: Ontologies and algorithms for integrating biological pathway data
Speaker: Lucy Lu Wang
Abstract: To improve the outcomes of biological pathway analysis, a better way of integrating pathway data is needed. Ontologies are useful tools for combining and organizing different datasets, and in this case, prove useful for integrating pathway databases. In this talk, I describe motivations for integrating pathway data sets. I explore several ontologies for modeling biological processes, and the increasing automation of ontology curation using machine learning methods. Lastly, I touch on methods for aligning and merging pathways, and how merging redundant pathways will help to improve the results of pathway analysis.
Speaker’s Bio: Lucy Lu Wang is a PhD-candidate in the Department of Biomedical Informatics and Medical Education at the University of Washington. Her research interests include knowledge representation, biomedical ontologies, natural language processing techniques for biomedical text, and ways to improve interoperability and content in biomedical knowledgebases. She has dedicated the better part of her PhD to studying the knowledge representation challenges of modeling biological processes. She recently moved to San Francisco and misses the mountains, trees, fungi, rain (and sun!) of the PNW, and is excited to be back for a brief visit.
BIME 591B– Write the Good Write
Tuesday, October 9, 11:30am- 12:20pm, Health Sciences Building, T530
Facilitators: Wanda Pratt, PhD and Sonali Mishra
See course website for details.
PUBLICATIONS AND PRESENTATIONS
- Tsung-Chien Lu, Yao-Ting Chang, Te-Wei Ho, Yi Chen, Yi-Ting Lee, Yu-Siang Wang, Yen-Pin Chen, Chu-Lin Tsai, Matthew Huei-Ming Ma, Cheng-Chung Fang, Feipei Lai, Anne M. Turner. Using a Smartwatch with Real-Time Feedback Instructions Improves the Delivery of High-Quality Cardiopulmonary Resuscitation. European Resuscitation Council (ERC) congress, Resuscitation 2018, Bologna, Italy, September 22, 2018.
- Tsung-Chien Lu, Yi Chen, Te-Wei Ho, Yao-Ting Chang, Yi-Ting Lee, Yu-Siang Wang, Yen-Pin Chen, Chia-Ming Fu, Wen-Chu Chiang , Matthew Huei-Ming Ma, Cheng-Chung Fang, Feipei Lai, Anne M. Turner. A Novel Depth Estimation Algorithm of Chest Compression for Feedback of High-Quality Cardiopulmonary Resuscitation Based on a Smartwatch. J Biomed Inform. 2018 Sep 27. pii: S1532-0464(18)30188-6. doi: 10.1016/j.jbi.2018.09.014. [Epub ahead of print]
October 1-5, 2018
UPCOMING LECTURES AND SEMINARS
BIME 590A – Biomedical & Health Informatics Lecture Series
Thursday, October 4, 4:00pm-5:00pm, via Zoom and UW Medicine South Lake Union, Building E, Room E130AB
Title: Estimate of disease heritability using 14 million familial relationships inferred from electronic health records
Speaker: Nicholas P. Tatonetti, PhD
Abstract: Heritability is essential for understanding the biological causes of disease, but requires laborious patient recruitment and phenotype ascertainment. Electronic health records (EHR) passively capture a wide range of clinically relevant data and provide a novel resource for studying the heritability of traits that are not typically accessible. EHRs contain next-of-kin information collected via patient emergency contact forms, but until now, these data have gone unused in research. We mined emergency contact data at three academic medical centers and identified millions of familial relationships while maintaining patient privacy. Identified relationships were consistent with genetically-derived relatedness. We used EHR data to compute heritability estimates for 500 disease phenotypes. Overall, estimates were consistent with literature and between sites. Inconsistencies were indicative of limitations and opportunities unique to EHR research. These analyses provide a novel validation of the use of EHRs for genetics and disease research.
Speaker’s Bio: Dr. Nicholas Tatonetti is assistant professor of biomedical informatics in the Departments of Biomedical Informatics, Systems Biology, and Medicine and is Director of Clinical Informatics at the Institute for Genomic Medicine at Columbia University. He received his PhD from Stanford University where he focused on the development of novel statistical and computational methods for observational data mining. He applied these methods to drug safety surveillance and the discovery of dangerous drug-drug interactions. His lab at Columbia is focused on expanding upon his previous work in detecting, explaining, and validating drug effects and drug interactions from large-scale observational data. Widely published in both clinical and bioinformatics, Dr. Tatonetti is passionate about the integration of hospital data (stored in the electronic health records) and high-dimensional biological data (captured using next-generation sequencing, high-throughput screening, and other “omics” technologies). Dr. Tatonetti has been featured by the New York Times, Genome Web, and Science Careers. His work has been picked up by the mainstream and scientific media and generated thousands of news articles.
BIME 591B– Write the Good Write
Tuesday, October 2, 11:30am- 12:20pm, Health Sciences Building, T530
Facilitators: Wanda Pratt, PhD and Sonali Mishra
See course website for details.
FACULTY/STUDENT/ALUMNI/STAFF ACTIVITIES
Successful UW FHIR Workshop
Doctoral students and faculty from Biobehavioral Nursing and Health Informatics (School of Nursing) and Biomedical Informatics and Medical Education (BIME, School of Medicine), in collaboration with the Institute for Translational Health Sciences (ITHS) and the Healthcare Services Platform Consortium (HSPC) hosted a two day workshop on Sept 23 and 24, 2018, held in South Lake Union Bldg C. The conference was well attended with 139 attendees registered for the Monday meeting, over 60 of whom also attended all-day tutorials on Sunday. The sessions covered FHIR, SMART on FHIR, CDS Hooks, and the use and implications of those technologies, including Managing FHIR Innovation, EMR vendors and FHIR, Example applications, Enterprise FHIR, Population Health applications, Patient Engagement, FDA law and mobile apps, Terminology and Standards.
Speakers came from Intermountain Healthcare, University of Utah, Mayo Clinic, Allscripts, Epic, GE Healthcare, Transformative Med, Johns Hopkins University, and the University of Washington. Topics covered included population health, clinical informatics, healthcare governance, and many more. Registrants from 10 unique UW departments and business units were represented including BIME, School of Nursing, Computer Science and Engineering, and UW Medicine ITS. We had registrants from 31 other institutions, including the Washington State Department of Health, Seattle Children’s, Fred Hutch Cancer Research Center, Madigan Army Medical Center, Providence/Swedish, Virginia Mason, OCHIN, Oregon Health & Science University, and industry, including several of the very largest local companies, and several early-stage ventures. Our wide diversity of backgrounds led to interesting conversations, catalyzed future collaborations, and an improved awareness of related work going on around the UW, and in our region.
With great attendance, very positive feedback, and lots of questions about the next event, the organizing committee is focusing first on disseminating the slides and other materials, and on planning for a repeat of the tutorial sessions to accommodate the more than 20 people who remained on the waiting list. Check back at http://uwfhir.org/ in early October to find slides of talks.
BHI PhD Student Jason Thomas will be speaking at the SOM PhD Welcome reception, 10/3 for a “Words of Wisdom” talk.
Jason Thomas is also one of two students to receive the 2018 Healthcare Data and Analytics Association Conference Student Scholarship. Congratulations, Jason!
Congratulations to Nick Robison!
On September 21, Nick successfully defended his dissertation titled, “The Problem of Time: Addressing challenges in spatio-temporal data integration,” with his supervisory committee chaired by Dr. Neil Abernethy. His committee also included Drs. Ian Painter, Abraham Flaxman and James Felak.
Virtual Reality in Academic Health Sciences Libraries: A Primer available for free download
The University of Washington Health Sciences Library is proud to share with you Virtual Reality in Academic Health Sciences Libraries: A Primer. The primer covers the lessons learned, best practices, and requirements for transforming an existing library space for clinical team based care with a librarian role.
The open access PDF version of the primer can be downloaded and shared widely at: https://hsl.uw.edu/vr-studio/
Special thanks to Sandeep Napa, MS BIME for conducting usability testing of current VR hardware and software options.
September 24-28, 2018
UPCOMING LECTURES AND SEMINARS
BIME 590A – Biomedical & Health Informatics Lecture Series
Thursday, September 27, 4:00pm-5:00pm, UW Medicine South Lake Union, Room C123A&B
(Also broadcast live and archived at tcs.slu.washington.edu; livestream will have a red dot in the top left hand corner)
Title: Improving Representations of Biomedical Concepts with Lessons Learned from Neural Word Embeddings
Speaker: Trevor Cohen, MBChB, PhD
Abstract: Recent years have seen a surge in popularity in the application of distributed vector representations of words (word embeddings) across a range of applications, including the representation of biomedical terms and concepts for downstream machine learning. In particular, the neural-probabilistic approaches embodied in the word2vec and FastText software packages have been widely used and extensively evaluated over the past five years. This talk will consider neural-probabilistic methods of producing word vectors in the context of prior methods of distributional semantics, revealing potential enhancements of both sets of methods that we have realized in our recent work. The remainder of the talk will discuss these developments, with a focus on the evolution of our approach to leveraging literature-derived distributed representations to identify plausibly causal drug/side-effect relationships.
Speaker’s Bio: Dr. Trevor Cohen’s research focuses on the development and application methods of distributional semantics – methods that learn to represent the meaning of terms and concepts from the ways in which they are distributed in large volumes of electronic text. The resulting distributed representations (concept or word embeddings) can be applied to a broad range of biomedical problems, such as: (1) using literature-derived models to find plausible drug/side-effect relationships; (2) finding new therapeutic applications for known (drug repurposing); (3) modeling the exchanges between users of health-related online social media platforms; and (4) identifying phrases within psychiatric narrative that are pertinent to particular diagnostic constructs (such as psychosis). An area of current interest involves applying literature-derived distributed representations in conjunction with observational data as a basis for machine learning. More broadly, he is interested in clinical cognition – the thought processes through with physicians interpret clinical findings – and ways to facilitate these processes using automated methods.
Dr. Cohen trained and practiced as a physician in South Africa before obtaining his PhD in 2007 in Medical Informatics at Columbia University. His doctoral work focused on an approach to enhancing clinical comprehension in the domain of psychiatry, leveraging distributed representations of psychiatric clinical text. Upon graduation, he joined the faculty at Arizona State University’s nascent Department of Biomedical Informatics, where he contributed to the development of curriculum for informatics students, as well as for medical students at the University of Arizona’s Phoenix campus. In 2009 he joined the faculty at the University of Texas School of Biomedical Informatics, where (amongst other things) he developed a NLM-funded research program concerned with leveraging knowledge extracted from the biomedical literature for information retrieval and pharmacovigilance, and contributed toward large-scale national projects such as the Office of the National Coordinator’s SHARP-C initiative, which supported a range of research projects that aimed at improving the usability and comprehensibility of electronic health records interfaces.
BIME 591B (SLN 11311) – Write the Good Write
This course will begin the following week, on Tuesday, October 2, 11:30am-12:20pm, Health Sciences Building, T530
Instructors: Dr. Wanda Pratt and Sonali Mishra
FACULTY/STUDENT/ALUMNI/STAFF ACTIVITIES
Janice Sabin was invited by St. Jude Clinical Research Center, Memphis, TN, to deliver the annual St. Jude Sarouf Lecture, March 22, 2019. This is a prestigious lecture which will be followed by lunch, and meetings throughout the day with individual researchers and research groups. The topic is, Implicit Bias in Clinical Care and will feature Sabin research.
UW FHIR Workshop
We are looking forward to hosting all of you here in Seattle in the beautiful South Lake Union area.
All conference details including time, place, and agenda are available at the conference website.
Travel and Parking
Both sessions will be held at the UW Medicine Research Complex, Building C. For Sunday’s tutorial, free parking will be available in the Building C parking garage, and for Monday, the parking will be $3/hr. For those who don’t want to drive or walk, there is ample public transit. The South Lake Union Transit goes from Westlake to South Lake Union and has a stop a block away from the building. Bus Route 40 also has a stop near the complex and goes from Downtown Seattle to Northgate and vice versa.
Application Showcase
We are also looking for folks to talk about their work with FHIR in an application showcase breakout session. If you have a FHIR or SMART on FHIR application that you’d like to share, please fill out this survey.
If you have any questions feel free to reach out to workshop@uwfhir.org. We are looking forward to seeing you all next week! –The UW FHIR Workshop Planning Committee
PUBLICATIONS AND PRESENTATIONS
Backonja U, Hall AK, Painter IS, Kneale L, Lazar A, Cakmak M, Thompson HJ, Demiris G. Comfort and attitudes towards robots among young, middle-aged, and older adults: A cross-sectional study. J of Nursing Scholarship. 2018 [ahead of print]. doi: 10.1111/jnu.12430
Neal ML, Thompson CT, Kim KG, James RC, Cook DL, Carlson BE, and Gennari JH (in press). SemGen: a tool for semantics-based annotation and composition of biosimulation models. Bioinformatics.
Baker-Smith CM, Flinn SK, Flynn JT, Kaelber DC, Blowey D, Carroll AE, Daniels SR, de Ferranti SD, Dionne JM, Falkner B, Gidding SS, Goodwin C, Leu MG, Powers ME, Rea C, Samuels J, Simasek M, Thaker VV, Urbina EM. Diagnosis, Evaluation, and Management of High Blood Pressure in Children and Adolescents. Pediatrics. 2018; 142(3). PMID: 30126937
OTHER NEWS
BHI PhD student Calvin Apodaca would like to everyone in the BHI department that donated to his charity drive during Penny Arcade Expo: Thanks to the generosity of many researchers in the department, we were able to get over $500 dollars in donations for sick kiddos in hospitals!
September 17-21, 2018
AUTUMN QUARTER BHI COLLOQUIA (September 26- December 7)
BIME 590A (SLN 11309) – Biomedical & Health Informatics Lecture Series
Thursdays, 4:00-4:50 p.m., UW Medicine South Lake Union, Building C, Room C123A&B
Facilitator: Adam Wilcox, PhD
Informatics faculty and researchers from the UW and affiliated institutions present their research findings and discuss their views of national developments in their areas of expertise. See the course website for details.
NOTE: There will be no BIME 590 seminar on Thursday, November 22 (Thanksgiving).
BIME 591B (SLN 11311) – Write the Good Write
Tuesdays, 11:30am-12:20pm, Health Sciences Building, T530
Instructors: Dr. Wanda Pratt and Sonali Mishra
Description: Looking for ways to make more time for writing … and get some insight on how to do it better? In this seminar we’ll devote time to both. In each session, we’ll spend 30 minutes writing or editing and 20 minutes discussing topics to make us better writers. We’ll choose topics based on your interests, for example:
- good vs. bad writing
- writing a paper vs. writing a blog post about your work
- strategies for breaking through writer’s block
- writing memos
- giving constructive criticism in editing
- editing someone else’s work: how much is too much
- the pitfalls of prescriptive grammar
Students will be expected to come to class with thoughts to share, stuff to work on, and writing-related puns. Students can either edit someone else’s work or work on their own projects during the 30 minute writing session. See course website for details.
UPCOMING DISSERTATION DEFENSE
Nick Robison
Friday, September 21, 3pm, UW Medicine SLU, Building E, Room E130B
Title: The Problem of Time: Addressing challenges in spatio-temporal data integration
Abstract:
Across scientific disciplines, an ever-growing proportion of data can be effectively described in spatial terms. As researchers have become comfortable with techniques for dealing with spatial data, the next progression is to not only model the data itself, but also the complexities of the dynamic environment it represents. This has led to the rise of spatio-temporal modeling and the development of robust statistical methods for effectively modeling and understanding interactions between complex and dynamic systems. Unfortunately, many of these techniques are an extension to existing spatial analysis methods and struggle to account for the data complexity introduced by the added temporal dimension; this has limited many researchers to developing statistical and visual models that assume either a static state of the world, or one modeled by a set of specific temporal snapshots.
This challenge is especially acute in the world of public health where researchers attempting to visualize historical, spatial data, often find themselves forced to ignore shifting geographic features because both the tooling and the existing data sources are insufficient. Consider, as an example, a model of vaccine coverage for the administrative regions of Sudan over the past 30 years. In wake of civil war, Sudan was partitioned into two countries, with South Sudan emerging as an independent nation in 2011. This has an immediate impact on both the visual accuracy as well as the quantitative usefulness of any data generated from aggregate spatial statistics. Or, consider epidemiological case reports that are issued from local medical facilities, how does one account for the fact that their locations may change, or that new facilities may spring up or close down as time progresses. These are real-world problems that existing GIS platforms struggle to account for.
While there have been prior attempts to develop data models and applications for managing spatio-temporal data, the growing depth and complexity of scientific research has left room for improved systems which can take advantage of the highly interconnected datasets and spatial objects, which are common in this type of research. To that end, we have developed the Trestle data model and application, which leverage graph-based techniques for efficiently storing and querying complex spatio-temporal data. This system simple interface to allow users to perform query operations over time-varying spatial data and return logically valid information based on specific spatial and temporal constraints. This system is applicable to a number of GIS related projects, specifically those attempting to visualize historical public health indicators such as vaccination rates, or develop complex spatio-temporal models, such as malaria risk maps.
FACULTY/STUDENT/ALUMNI/STAFF ACTIVITIES
Announcement for the UW FHIR Workshop on September 23, 24:
The UW FHIR Workshop is coming up in less than two weeks! If you haven’t registered, make sure to do so soon – we have about 85 people registered, and we’ll likely cut off the registration around 100. We had to put in a waitlist for the Sunday tutorial, so make sure to add yourself after registering if you’re interested. Check out www.uwfhir.org for registration and more details!
PUBLICATIONS AND PRESENTATIONS
Mikles, S. P., Suh, H., Kientz, J. A., & Turner, A. M. (2018). The use of model constructs to design collaborative health information technologies: a case study to support child development. Journal of Biomedical Informatics, Epub ahead of print. https://doi.org/10.1016/j.jbi.2018.09.003
Andrea Hartzler and colleagues from UW, FIU, and UNC are leading workshop at AMIA sponsored by the Consumer and Pervasive Health Informatics Working Group):
AMIA Workshop – Sat Nov 3 8:30-12pm https://www.amia.org/amia2018/workshops
How Health Systems Should Be Thinking About Clinical Integration of Electronic Patient Reported Outcomes
Elizabeth Austin, Andrea Hartzler, and Danielle Lavallee, University of Washington
Cynthia LeRouge, Florida International University
Arlene Chung, University of North Carolina
September 10-14, 2018
UPCOMING LECTURES AND SEMINARS
BIME Faculty Candidate – Michael Soh, PhD
Monday, September 10 10:00 a.m., South Lake Union, Brotman Auditorium (from off-site connect through Zoom: https://washington.zoom.us/j/606660973)
Speaker: Michael Soh, PhD
Associate Director, Curriculum and Evaluation, Greater Los Angeles Veterans Affairs, Center of Excellence Interprofessional Academic Homeless PACT
Title: The Push for Interprofessionalism
Abstract: Health professions training continues to move towards a team-based care model and effectively developing the skills and abilities to collaborate interprofessionally is becoming an integral part of medical education. MS will share his experiences with building and evaluating an interprofessional training curriculum, lessons learned from more than two years of interdisciplinary collaboration, and how the push for interprofessionalism can change the landscape of teaching, learning, and clinical practice in healthcare.
FACULTY/STUDENT/ALUMNI/STAFF ACTIVITIES
The National Library of Medicine recently awarded BIME a Biomedical Informatics Research Training Grant Supplement entitled: “Enriching the University of Washington Biomedical and Health Informatics Training Program by engaging the next generation in data science coursework, career seminars, and research internships.” Core faculty include Peter Tarczy-Hornoch (PI), John Gennari, Andrea Hartzler, David Masuda, and Diane Korngiebel.
The supplement will extend our training grant with data science opportunities, particularly targeted at undergraduates, to enhance programmatic capacity and foster the next generation of biomedical informatics researchers through three aims:
Aim 1. To develop an undergraduate course for data science and ethics in biomedical informatics
Aim 2. To offer a professional development seminar on “Careers in Biomedical Data Science”
Aim 3. To seed fund undergraduate research internships in biomedical data science
UW FHIR Workshop on September 23, 24
Registration now open at https://uwfhir.org. A group of faculty and students at the University of Washington (UW FHIR Interest Group), working with the Health Systems Platform Collaboration (https://www.hspconsortium.org/) are hosting a one day workshop, in Seattle on Monday, September 24, 2018 (and a ½ day tutorial the day before, Sunday, September 23). The meetings will explore the uses and capabilities of the FHIR health data standard. We will be exploring the potential and limitations of FHIR, SMART on FHIR, and CDS Hooks, including how health systems manage innovation, and success stories using FHIR. An overview of the agenda and an email sign-up for more info can be found at http://uwfhir.org.