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
January 14-18, 2019
UPCOMING LECTURES AND SEMINARS
BIME 590A – Biomedical & Health Informatics Lecture Series
Thursday, January 17, 11:00am-11:50am, UW Medicine South Lake Union, Building C, 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)
Speaker: Gang Luo, PhD, Associate Professor, University of Washington
Title: Predicting Appropriate Hospital Admission of Emergency Department Patients with Bronchiolitis
Abstract: In children below age two, bronchiolitis is the most common reason for hospitalization. Each year in the United States, bronchiolitis causes 287,000 emergency department visits, 32%-40% of which result in hospitalization. Frequently, emergency department disposition decisions (to discharge or to hospitalize) are made subjectively because of a lack of evidence and objective criteria for bronchiolitis management, leading to significant practice variation, wasted healthcare use, and suboptimal outcomes. At present, no operational definition of appropriate hospital admission for emergency department patients with bronchiolitis exists, although such a definition is essential for assessing care quality. Also, no model for predicting appropriate hospital admission exists, although an accurate model predicting this can guide emergency department disposition decisions for bronchiolitis and improve outcomes.
In this talk, we present our recent work filling these two gaps. First, we provided the first operational definition of appropriate hospital admission for emergency department patients with bronchiolitis. We showed that ~6% of emergency department disposition decisions for bronchiolitis were inappropriate at Intermountain Healthcare. Second, we developed the first machine learning model to predict appropriate hospital admission for emergency department patients with bronchiolitis. Our model achieved an accuracy of 91% and an area under the receiver operating characteristic curve of 0.96. With further improvement, our model could serve as a foundation for building decision support tools to guide disposition decisions for children with bronchiolitis presenting to emergency departments.
Speaker Bio: Gang Luo obtained his Ph.D. degree in Computer Science minor in Mathematics at the University of Wisconsin-Madison in 2004. Between 2004 and 2012, he was a Research Staff Member at the IBM T.J. Watson research center. Between 2012 and 2016, he was a faculty member in the Department of Biomedical Informatics at the University of Utah. Gang is currently a faculty member in the Department of Biomedical Informatics and Medical Education of the School of Medicine at the University of Washington. His research interests include health informatics (software system design/development and data analytics), big data, information retrieval, database systems, and machine learning with a focus on health applications. He invented the first method for automatically providing rule-based explanation for any machine learning model’s prediction results with no accuracy loss, the first method for efficiently automating machine learning model selection, the questionnaire-guided intelligent medical search engine iMed, intelligent personal health record, and SQL, compiler, and machine learning progress indicators.
BIME 591B– BIME 591B– Developing Your Informatics Career Path
Tuesday, January 8, 12:30pm- 1:20pm, Health Sciences Building, E216
Facilitator: David Masuda
UPCOMING DISSERTATION DEFENSE
Ahmad Aljadaan
Wednesday, January 16, 2019, 11:00am, UW Health Sciences Building, BB1602
Title: The Untold Story of Predicting Readmissions for Heart Failure Patients
Abstract: The availability and accessibility of Electronic Health Record (EHR) data create an opportunity for researchers to revolutionize healthcare. The recognition of the importance of secondary use of EHR data has led to the development of research-ready integrated data repositories (IDRs) from EHR data. Analyzing this data can help researchers connect the dots and can lead to critical clinical findings through predictive analytics methods. Unfortunately, poor data quality is a problem that affects the accuracy of such findings. An example of a data quality problem is poor information about the specifics of admission, discharge, and readmission.
Heart Failure (HF) is one of the most common cardiovascular diseases. 5.7 million people in the United States have heart failure with 870,000 new cases annually, and this disease is the leading cause of hospital readmission.
Predicting readmission for heart failure patients has been well-studied. The readmission periods that researchers have studied range between 30 days to one year. However, shorter than 30 days readmission have received less research attention. In my research, I shed light on an overlooked yet important group of readmissions: very early readmissions. Currently, little is known about what causes heart failure patients to come back so quickly. In the long term, my career goal is to predict very early readmission patients before discharge and improve on the discharge decision making. It is a step toward personalized healthcare to improve patient care eventually.
The broad goal of my dissertation is to leverage the availability and accessibility of electronic health data and characterize day 1-30 readmission, more specifically characterizing very early readmissions. My approach to reach my goal went through four major steps: 1) Reviewing the literature to understand the field and how early readmission have been defined, 2) Using retrospective EHR data from UW Medicine to build an accurate visit table for heart failure patients, 3) Using the visit table to build a prediction model to characterize day 1-30 readmissions, 4) Improving on the model by applying different machine learning algorithms and imputation techniques for missing data.
PUBLICATIONS AND PRESENTATIONS
Fathiamini, Safa, Amber M. Johnson, Jia Zeng, Vijaykumar Holla, Nora S. Sanchez, Funda Meric-Bernstam, Elmer V. Bernstam, and Trevor Cohen. “Rapamycin–mTOR+ BRAF=? Using Relational Similarity to Find Therapeutically Relevant Drug-Gene Relationships in Unstructured Text.” Journal of Biomedical Informatics (2019): [epub ahead of print]
INTERNSHIP OPPORTUNITY
2019 Summer Internship in Assessment Science and Psychometrics
OTHER EVENTS
BIME Happy Hour
Thursday, January 17, 5:00 p.m., South Lake Union, Reception Lounge
Please join us for our monthly departmental BYOB Happy Hour, held every third Thursday of the month. As always, please bring your own beverage; snacks will be provided!
January 7-11, 2019
UPCOMING LECTURES AND SEMINARS
BIME 590A – Biomedical & Health Informatics Lecture Series
Thursday, January 10, 11:00am-11:50am, 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)
Speaker: Paul Nagy, PhD, FSIIM, Associate Professor, Johns Hopkins University School of Medicine,
Russell H. Morgan Department of Radiology
Title: The Johns Hopkins Precision Medical Analytics Platform. Accelerating clinical research with a secure big data cloud architecture
Abstract:
In 2016, Johns Hopkins launched the inHealth precision medicine initiative to partner with clinical research groups (Centers of Excellence) to turn clinical data sources into research instruments and constructing the Precision Medicine Analytics Platform (PMAP). PMAP is a platform for data collection and analysis utilizing a cloud based hadoop architecture ingesting electronic medical records, medical imaging, physiological monitoring, and genomic sequencing. PMAP was designed in partnership with the Institutional Review Board (IRB) and the JHM Data Trust to rapidly deliver clinical data to researchers in a secure hosted research environment with a large suite of analytical tools. The twin goals of the initiative are to accelerate biomedical discovery through data science and to leverage those discoveries to improve patient care.
Speaker’s Bio:
Paul Nagy, PhD, FSIIM is an Associate Professor in the Johns Hopkins University School of Medicine Russell H. Morgan Department of Radiology and is faculty in the Division of Health Science Informatics and the Armstrong Institute for Patient Safety and Quality. He serves as the deputy director of the Johns Hopkins Medicine Technology Innovation Center (TIC) with the goal of partnering with clinical inventors to create novel IT solutions that improves patient care. This team of designers, developers, and data scientists work with inventors to build, deploy, and evaluate digital health solutions within the Johns Hopkins Medical System. http://www.jhmtic.org
At Johns Hopkins, Dr. Nagy serves as the program director for year-long multidisciplinary leadership development programs at Johns Hopkins Medicine in precision medicine, clinical informatics, data science and creating commercial ventures. There have been over 360 faculty and staff that have gone through the programs since 2012.
Dr. Nagy is the past-chair of the Society of Imaging Informatics in Medicine and serves on the Board of the American College of Medical Quality and the Board of Health for Howard County Maryland. From 2010-2012 he served as the chair of the American Board of Imaging Informatics (ABII) which created the certification for imaging informatics professionals which has over 1,000 diplomates. In 2012, he was inducted into the college of fellows for the Society of Imaging Informatics in Medicine. The Baltimore Business Journal honored him with the 2015 Healthcare Innovation Educator of the year award.
Dr. Nagy received his PhD in Medical Physics from the Medical College of Wisconsin and is the author of over 125 papers in the fields of informatics and implementation science. https://scholar.google.com/citations?user=tqh1a8sAAAAJ&hl=en
BIME 591B– Developing Your Informatics Career Path
Tuesday, January 8, 12:30pm- 1:20pm, Health Sciences Building, E216
Facilitator: David Masuda
Biomedical Informatics and Medical Education News
December 24-28, 2018
FACULTY/STUDENT/ALUMNI/STAFF ACTIVITIES
Adam Wilcox, PhD, led a committee of thought leaders for AcademyHealth in a response to the “NIH Proposed Provisions for a Future Draft Data Management and Sharing Policy”. Details and the response are here: https://www.academyhealth.org/sites/default/files/academyhealthnihdatasharingresponseweb.pdf
Anne Turner, MD, was voted in as Chair-Elect of the AMIA Academic Forum Executive Committee for 2019 and will serve as Chair of the AMIA Academic Forum Executive Committee in 2020
Peter Tarczy-Hornoch, MD, Professor and Chair of BIME, has been named Chair Elect of the AMIA Academic Leaders Community (ALC) which is the national group of department chairs of Biomedical Informatics programs. He will serve two years as Chair Elect in 2019-20 (and Chair 2021-22, Past-Chair 2023-24).
PUBLICATIONS AND PRESENTATIONS
Lim C, Berry A, Hartzler A, Carrell D, Hirsch T, Bermet Z, Ralston JR. Facilitating Self-reflection about Values and Self-care among Individuals with Chronic Conditions. Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI ’19). Accepted for publication in May 2019.
Berry A, Lim C, Hirsch T, Hartzler A, Kiel L, Bermet Z, Ralston JR. Supporting Communication About Values Between People with Multiple Chronic Conditions and their Providers, Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI ’19). Accepted for publication in May 2019.
December 17-21, 2018
FACULTY/STUDENT/ALUMNI/STAFF ACTIVITIES
Dr. Uba Backonja, BIME Adjunct Assistant Professor, was nominated for the Distinguished Teaching Award for Innovation with Technology
Winners will be announced in spring 2019.
BIME faculty Trevor Cohen received a R01 award from the NLM for a project entitled “Robust Inference from Observational Data with Distributed Representations of Conceptual Relations” (total costs $1,500,000 over three years), with sub awards to collaborators Devika Subramanian at Rice University, and Sahiti Myneni at the University of Texas Health Science Center in Houston. This is a renewal of a previous R01 grant concerning the development and evaluation of methods through which knowledge extracted from the biomedical literature can be leveraged in support of post-marketing drug surveillance using distributed representations of biomedical concepts (concept embeddings). The renewal will focus on the integration of these methods with models of large stores of empirical data, including the Food and Drug Administration’s repository of adverse event reports, and data extracted from the Electronic Health Record.
PUBLICATIONS AND PRESENTATIONS
G. Luo, B.L. Stone, F.L. Nkoy, S. He, and M.D. Johnson. Predicting Appropriate Hospital Admission of Emergency Department Patients with Bronchiolitis: Secondary Analysis. JMIR Medical Informatics.
R. Sadeghian, The Feasibility and Satisfaction of Using Telemedicine to Provide Tertiary Pediatric Obesity Care. Journal of the International Society for Telemedicine and EHealth.
J.A. Thomas‡, A Perez-Alday EA‡ Junell A, Newton K, Hamilton C, Li-Pershing Y, et al. Vectorcardiogram in athletes: The Sun Valley Ski Study. Ann Noninvasive Electrocardiol. 2018 Nov 7;e12614. (‡) equal contribution. https://rdcu.be/baVe3
S. Haldar, SR Mishra, M Khelifi, AH Pollack, W Pratt. Beyond the Patient Portal: Supporting Needs of Hospitalized Patients. Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI ’19). Accepted for publication in May 2019.
OTHER NEWS
T. Payne attended a briefing on Capitol Hill on “Unlocking Patient Data”
HIPAA Modernization Needed, Experts Say | AMIA
AMIA-AHIMA Hill Briefing on Strikingly
December 10-14, 2018
UPCOMING MASTER’S DEFENSES
Wenjun Song
Thursday December 13, 10:00 am, UW SLU C123A
Title: Immune Correlates Analysis of RhCMV/SIV Vaccine Efficacy
Abstract:
In the past 30 years, HIV vaccine studies on traditional CD8+ T cell-targeted HIV vaccines were frustrated by the ineffectiveness of mediating immediate vaccinal interception upon infection acquisition prior to the explosive viral amplification. As the most important lesson of past HIV vaccine researches, the first hours to days immediately after viral infection might be the only vulnerable time period for immunologic interceptions. With this regard, immunologists started a novel research on employing Cytomegelovirus (CMV) as vaccine vector in early 2000s, to exploit CMV vectors’ unique ability on eliciting and maintaining abundant functional T cell responses at all potential HIV infection sites. Recent CMV-based vaccine research, demonstrated by Louis Picker and colleagues, with statistical support by Dr. Edlefsen, manifests a remarkable infection control and clearance on ~50% of HIV-acquired rhesus macaques (RM) vaccinated by Simian immunodeficiency virus (SIV) inserted rhesus cytomegalovirus (CMV) vaccine. This promising protection pattern motivates further immunologic correlates analysis on vaccine efficacy to investigate potential immunological mechanisms of the partial protection. This presentation will show a preliminary immunologic correlates model with strategic informatics interpretations.
December 3-7, 2018
UPCOMING LECTURES AND SEMINARS
BIME 591B– Write the Good Write
Tuesday, December 4, 11:30am- 12:20pm, Health Sciences Building, T530
Facilitators: Wanda Pratt, PhD and Sonali Mishra
See course website for details.
UPCOMING DISSERTATION DEFENSE
Tim Wu
Thursday, December 6; 9:30-10:30 AM; South Lake Union Building C259
Title: Bicluster-Based Identification of Gene Sets Through Multivariate Meta-Analysis (MVMA)
Abstract:
Omics technologies have transformed biology and medicine by generating massive amount of high-resolution data. Much of the data have been made publicly available but have not been fully explored or utilized. The current study aims to mine public gene expression to discover gene sets that may correspond to biological pathways. The challenges with using public data include data heterogeneity, high dimensionality, and small sample sizes. The overall research questions include: (1) what is the data mining method best suited for finding gene sets; and (2) how best to utilize multiple datasets in order to increase statistical strength. Aim 1 is to determine optimal method for constructing bicluster stacks. Aim 2 is to determine suitability of meta-analysis techniques to pool biclusters and assess performance, and Aim 3 is to assess potential utility of gene sets identified in Aim 2 using pathway analyses.
In Aim 1, we demonstrate the technique of biclustering in gene set identification, based on a number of key advantages of biclustering over the traditional clustering methods. In addition, we show that synthesis of summary statistics (biclusters in this case) is a better approach for utilizing multiple datasets compared to simply aggregating the source datasets together. For Aim 2, we adapt the framework of multivariate meta-analysis (MVMA), and a previously published two-step procedure to tackle the issue of high dimensionality with an improvement that involves a sparse estimate for the between-study covariance matrix using the graphical lasso algorithm. The improvement leads to a significant increase in the performance of MVMA in classifying real genes from background genes. In Aim 3, the gene sets found to be significant according to MVMA are further investigated by knowledge-based pathway analyses. The results suggest that the overall effect sizes are a predictor of biological relevance of the gene sets, which is the most significant finding of the study.
NEW FACULTY ANNOUNCEMENT
We are delighted to announce that Dr. Matthew Cunningham will be joining our faculty as an Assistant Professor starting January 2019. Dr. Cunningham received a Ph.D. from the Neurobiology & Behavior graduate program at the University of Washington in 2003. He then transitioned away from biomedical research and into educational evaluation in the UW Biology department, where he completed a certificate program in Program Evaluation. In 2009, he landed in his current role in BIME managing the testing service for the UW School of Medicine, where he has played a large role in moving the Medical School to fully computerized testing, among other things. Starting in January 2019 in addition to joining our faculty, Dr. Cunningham will take on the role of Director of Educational Evaluation (previously held by Dr. Carline).
FACULTY/STUDENT/ALUMNI/STAFF ACTIVITIES
Thomas Payne, MD (GIM), Adjunct Professor in BIME; Fuki Hisama, MD, PhD (Medical Genetics); and Lue-Ping Zhao, PhD (Fred Hutchinson Cancer Research Center) were awarded a 2018 Catalytic Collaborations granting program from the Brotman Baty Institute for their proposal “Using EHR Content to Prevent Breast and Ovarian Cancer.” Dr. Payne will serve as Principal Investigator.
PUBLICATIONS AND PRESENTATIONS
Relational concurrency, stages of infection, and the evolution of HIV set point viral load” Steven M Goodreau, Sarah E Stansfield, James T Murphy, Kathryn C Peebles, Geoffrey S Gottlieb, Neil F Abernethy, Joshua T Herbeck, John E Mittler Virus Evolution, Volume 4, Issue 2, 1 July 2018, vey032, Published: 21 November 2018
Feld LG, Neuspiel DR, Foster BA, Leu MG, Garber MD, Austin K, Basu RK, Conway EE, Fehr JJ, Hawkins C, Kaplan RL, Rowe EV, Waseem M, Moritz ML, Subcommittee on Fluid and Electrolyte Therapy. Clinical Practice Guideline: Maintenance Intravenous Fluids in Children. Pediatrics. 2018 Nov 21. doi: 10.1542/peds.2018-3083.
JOB OPENINGS
Undergraduate Teaching Assistant Position for BIME 498 “Informatics in Healthcare” (Winter 2019)
We are seeking an undergraduate teaching assistant for our new undergraduate course in clinical informatics, BIME 498 “Informatics in Healthcare”. This paid position requires a maximum of 15 hours per week winter quarter. The iSchool administers recruitment and hiring. Contact Andrea Hartzler with any questions andreah@uw.edu. Applications are due 12/3/18: https://jobs.ischool.uw.edu/posting/306
November 26 – November 30, 2018
UPCOMING LECTURES AND SEMINARS
BIME 590A – Biomedical & Health Informatics Lecture Series
Thursday, November 29, 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: Reproducible Research with R
Speaker: Kara Woo, MLIS, Research Scientist, Sage Bionetworks
Abstract:
Reproducibility (or lack thereof) of research findings is a growing concern, but fortunately there are many tools and resources to aid analysts in developing transparent and reproducible projects. Kara will discuss the landscape of some of these tools, and how the rOpenSci community is advancing open, reproducible science through software and community.
Speaker’s Bio:
Kara Woo is a research scientist at Sage Bionetworks where she develops tools to help researchers manage and share their data. She is active in the R community through rOpenSci, R-Ladies, and as a core developer of ggplot2.
BIME 591B– Write the Good Write
Tuesday, November 27, 11:30am- 12:20pm, Health Sciences Building, T530
Facilitators: Wanda Pratt, PhD and Sonali Mishra
See course website for details.
UPCOMING GENERAL EXAM
Jimmy Phuong
Friday November 30, 1:00-3:00 p.m., UW Health Sciences, T498
Title: Enhancing Secondary-use of Electronic Health Records for Population Health Research using Spatiotemporal Analytical Methods
Abstract: For almost three decades, the United States Department of Human and Health Services, Center for Disease Control, and the World Health Organization have recognized social and environmental determinants of health account for the majority of population health. While genetics and personal behavior may predispose an individual to be in a healthy status, community- and population-scale health status are determined in large by factors of socioeconomic status, physical environmental ecology, and access to healthcare services. Hence, the geographic environment and the accessibility to resources are critical components towards understanding and promoting health, by ways such as enacting policy interventions. In disastrous times, spatiotemporally-relevant information escalate in importance as the health system respond to emergent concerns, pre-existing needs, disruption in access to prior resources, and migration among affected populations. Hospital and clinic Electronic Health Record systems (EHRs) contain a richness and diversity of information about where healthy and unhealthy patients are. In disaster preparedness, EHRs could potentially inform where and how to prepare for population-level patient needs in future scenarios with a timely, equitable, and data-driven approach; however, for operational and ethical reasons, the ability to apply EHR-enabled spatiotemporal reasoning and analytics has remained an underrepresented capacity. Moreover, it is unknown how data gaps and changing standards within EHRs may challenge inferential interpretations. This proposal will investigate three areas for building capacities to address population health uses with spatiotemporal analytical methods. The specific aims of this work include: 1) design spatiotemporal use-case workflows to survey trends and anomalies for regional areas using gridded hydrometeorological data products, a surrogate for structured multivariate datasets, 2) assess information needs and high-value use-cases for population health research in hydrologic disaster preparedness, and 3) develop and evaluate spatiotemporal inferential statistics through secondary-use of patient diagnostics within EHRs. These research aims align with recent funding priorities with United States National Institutes of Health, National Science Foundation, World Health Organization, and multi-national Ministries of Health for integrative disaster research and population health initiatives.
UPCOMING DISSERTATION DEFENSE
Sean Mikles
Friday, November 30, 2pm, UW Health Sciences Building, T359
Title: No Wrong Door: Designing Health Information Technology to Support Interprofessional Collaboration Around Child Development Work
Abstract:
Child development refers to children gaining the skills they need to succeed in life, consisting of abilities in different overlapping domains such as speech, motor, social, and cognition. Developmental disabilities are chronic delays in gaining such skills, and if they are not addressed in a timely manner a child can experience negative outcome throughout their life. Responsibilities for identifying and treating developmental delays and disabilities are spread across many stakeholders in the community, including not only parents but an interprofessional collection of service providers such as pediatricians, early educators, childcare providers, providers of home visiting services, and community groups. Regardless of who is involved in a child’s care, there must be ‘no wrong door’ into the ecosystem of development support services. Unfortunately, these stakeholders operate in silos, leading to a fractured system of services that parents struggle to navigate. This often leads to delays in the receipt of necessary services and uncoordinated care. Various researchers and policy leaders such as the American Academy of Pediatrics have suggested that health information technology (HIT) could be an important tool to help stakeholders collaborate in a child’s care management. Current biomedical informatics literature, however, provides little practical guidance on how to design HIT systems to support such interprofessional collaboration.
This dissertation presents four studies that aim to address this design gap by drawing upon the extensive corpus of literature on collaborative practice and the user-centered design framework. These studies demonstrate the use of qualitative methods in conjunction with theoretical concepts to assess the needs of a heterogeneous collection of stakeholders in regards to collaborative work with the goal of deriving design implications for future creators of collaborative HIT systems. The first study demonstrates the utility of using concepts from the collaboration literature to uncover actionable design implications for collaborative systems using previously-collected interview data from an interprofessional collection of stakeholders. The second and third studies utilize the methods of the first study to explore interprofessional work processes and interprofessional trust, respectively, with new original interview data. Building upon the third study, the last study provides practical guidance for designing interprofessional collaborative systems to support the creation of trust between stakeholders of heterogeneous backgrounds. This is achieved through eliciting the information that people use to judge trustworthiness, and then creating and testing prototype information webpages listing the noted information. This research will provide concrete methodological guidance for designers of future systems to support collaborative work as well as concrete design implications for such systems.
PUBLICATIONS AND PRESENTATIONS
Thomas JA‡, Perez-Alday EA‡, Hamilton C, Kabir MM, Park EA, Tereshchenko LG. The utility of routine clinical 12-lead ECG in assessing eligibility for subcutaneous implantable cardioverter defibrillator. Computers in Biology and Medicine. 2018 Nov 1;102:242–50. (‡) equal contribution. https://doi.org/10.1016/j.compbiomed.2018.05.002
Chan EKH, Edwards TC, Haywood K, Mikles SP, Newton L. Implementing patient-reported outcome measures in clinical practice: a companion guide to the ISOQOL user’s guide. Quality of Life Research. 2018. Epub ahead of print. doi: 10.1007/s11136-018-2048-4
Luo G, A Roadmap for Semi-automatically Extracting Predictive and Clinically Meaningful Temporal Features from Medical Data for Predictive Modeling. Global Transitions, 2019.
November 19 – November 21, 2018
UPCOMING LECTURES AND SEMINARS
BIME 591B– Write the Good Write
Tuesday, November 20, 11:30am- 12:20pm, Health Sciences Building, T530
Facilitators: Wanda Pratt, PhD and Sonali Mishra
See course website for details.
BIME 590A – Biomedical & Health Informatics Lecture Series
No session, Thanksgiving Holiday
UPCOMING GENERAL EXAMS
Abhishek Pratap
Wednesday November 21, 2:30 p.m., UW Health Sciences, T360
Title: Using Technology-enabled Services to Improve our Capacity to Assess and Intervene in Depression
Abstract: When it comes to mental health, no country is considered developed. The recent 2018 report from Lancet commission on global mental health highlights the global burden of disease linked to mental disorders has risen in all countries with increasing socioeconomic disparities in timely diagnosis and access to evidence-based treatments. We still don’t fully understand the underlying cause or mechanism behind the mental disorders. To date, there is no objective test to measure the severity of mental health symptoms, and clinical diagnoses are routinely based on subjective expressed symptoms which makes it difficult to manage what we cannot measure. Technology-enabled services offer an incredible opportunity to bridge the gap in mental health care by building objective assessment and symptom tracking tools along with digital psychological interventions that are more accessible and potentially less stigmatizing and can be offered either in conjunction or independently of local mental health services. This digital ecosystem has a realistic potential to address all corners of IOM’s triple aim, i.e. improve mental health at the population level, enhance patient satisfaction and reduce overall costs. In this regard my Aim I is to learn the clinical utility of active and passive digital data collected fully remotely through smartphones for assessing symptoms of the major depressive disorder (MDD) and the feasibility of developing robust digital biomarkers that could potentially identify underlying substructure of depression symptomatology. In Aim II, I propose to investigate the nationwide depression trends using data from > 1.5 million web-based screenings for MDD for the years 2015-2017 and evaluate the impact of environmental factors such as weather, air pollution, and social determinants of health on MDD symptoms. Finally, in Aim III, I will determine the feasibility of using past web-based searches to learn individual-level risk factors and context leading to a suicide attempt; a condition well known to be linked with severe depression. The proposed research aims are also aligned with the NIMH strategic research priorities and are directed toward enabling a digital framework that can help early detection and deployment of tailored interventions at the population level particularly in low resource settings and marginalized populations.
November 12 – November 16, 2018
UPCOMING LECTURES AND SEMINARS
BIME 590A – Biomedical & Health Informatics Lecture Series
Thursday, November 15, 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: The Implementation of Genetic Medicine
Speaker: David Crosslin, PhD, Associate Professor, Biomedical Informatics and Medical Education
Abstract:
Dr. Crosslin will chronicle the National Human Genome Research Institute’s genetic medicine research efforts, mainly through the Electronic Medical Records & Genomics (eMERGE) Network. This will include current opportunities and trends with the implementation of genetic medicine.
Speaker’s Bio:
Dr. Crosslin’s research program focuses on translational bioinformatics with a combination of bioinformatics, statistical association analyses, and computational tools development for applied research. Specifically, his research focuses on integrating genetic data into the electronic health record for clinical decision support. All efforts will advance the national electronic health information infrastructure in support of personalized medicine.
BIME 591B– Write the Good Write
Tuesday, November 13, 11:30am- 12:20pm, Health Sciences Building, T530
Facilitators: Wanda Pratt, PhD and Sonali Mishra
See course website for details.
BIME ACTIVITIES AT AMIA
Mikles, S. P., Haldar, S., Yin, S.-Y., Kientz, J. A., & Turner, A. M. (2018). Trust and Sharing in an Interprofessional Environment: A Thematic Analysis From Child Development Support Work in the Community. Presented at the AMIA 2018 Annual Symposium, San Francisco, CA.
FACULTY/STUDENT/ALUMNI/STAFF ACTIVITIES
Congratulations to Daniel Capurro, Fellow of AMIA!
Daniel Capurro, MD, PhD, Affiliate Assistant Professor of BIME, was included in the inaugural class of 130 Fellows in the newly established FAMIA Applied Informatics Recognition Program, a new program meant to recognize AMIA members who apply informatics skills and knowledge within their professional setting, who have demonstrated professional achievement and leadership, and who have contributed to the betterment of the organization. Mike Leu, MD, Associate Professor of BIME and Director of the Clinical Informatics Fellowship, and Paul Sutton, MD, Adjunct Associate Professor of BIME, were also honored as Fellows of FAMIA (see 11/2/18 BIME News for more information).
New Fellows of AMIA are authorized to use the letters FAMIA in connection with their professional activities. A formal induction ceremony will be held at the AMIA 2019 Clinical Informatics Conference in Atlanta, April 30 – May 2, 2019. Click here for the list of the inaugural class of Fellows.
Congratulations to Reza Sadeghian!
Reza Sadeghian, MD, Clinical Informatics Fellow, has joined Southern Medical Association Faculty team for their online Healthcare Tech Webcast.
https://sma.org/smarter-healthcare-tech-webcasts/
November 5 – November 9, 2018
UPCOMING LECTURES AND SEMINARS
BIME 590A – Biomedical & Health Informatics Lecture Series
Thursday, November 8, 4:00pm-5:00pm, UW Medicine South Lake Union, Building E, Room E130AB
(Also broadcast live and archived at tcs.slu.washington.edu; livestream will have a red dot in the top left hand corner)
Title: Using Predictive Analytics in Healthcare
Speaker: James Perkins, MD, FACS, MSDS, FACMQ, Professor of Transplant and Surgery and Vice Chair of Surgery, University of Washington
Abstract:
The field of predictive analytics has many interrelated terms including artificial intelligence, machine learning, big data, natural language processing, and others. After reviewing these terms, the areas in healthcare where predictive analytics is being used will be explored with some common examples in each area. Finally, a brief overview of a standard method to develop predictive analytic models and pitfalls to avoid will be reviewed.
Speaker’s Bio:
Dr. Perkins obtained his medical degree at the University of Arkansas in 1979. He completed a residency in General Surgery at the University of Kansas in 1984. He became a fellow in renal transplantation at the University of Utah and later in liver transplantation at the Mayo Clinic from 1984 to 1986. He came to the University of Washington as the Division Chief for Abdominal Transplantation from 1989 to 2002. He has been the Vice-Chairman for Quality in the Department of Surgery from 2002 until the present. In 2009, he completed the 10 X 10 Medical Informatics course from Oregon Health and Science University. In 2010, he received certification from the University of Washington in Database Administration. He obtained a Master of Science degree in Data Science in 2016 from Northwestern University. Since 2010, he has been the Director of the Clinical and Bio-Analytics Transplant Laboratory (CBATL) in the Department of Surgery. CBATL is a think tank for improving transplant patient care through: predictive analytics, genomic analysis, microsimulation modeling, and outcomes research.
BIME 591B– Write the Good Write
Tuesday, November 6, 11:30am- 12:20pm, Health Sciences Building, T530
Facilitators: Wanda Pratt, PhD and Sonali Mishra
See course website for details.
BIME ACTIVITIES AT AMIA
Uba Backonja, PhD, RN, BIME Adjunct Assistant Professor, is co-organizer for the Citizen Science workshop (W3, Saturday 11/3/2018 at 8:30 AM–12:00 PM Nov 3, 2018 Franciscan B).
Shefali Haldar, PhD Candidate, will be presenting the following paper on behalf of her co-authors in S40-Patient Engagement and Safety (Monday 11/5 1:45pm-3:15pm, Plaza A): Exploring the Design of an Inpatient Peer Support Tool: Views of Adult Patients.
Lauren Snyder, PhD Candidate, will be presenting the following poster in Poster Session 2 (Tuesday, 11/6 5-6:30pm): Business Process Analysis to Understand Health Policy Information Needs in South Africa. Full author list: Snyder LE, Lane JP, Katz A, Turner AM
Peter Tarczy-Hornoch, MD, Professor and Chair will be presenting a poster on behalf of BIME PhD student Ahmad Aljadaan (Tuesday, 11/6 5-6:30pm): Counting Readmissions: Surprisingly Difficult. Full author list: Aljadaan A, Tarczy-Hornoch P, Wilcox A, Dardas T, Gennari J
Anne Turner, MD, BIME Professor, is presenting S103: Oral Presentation – Patient and Family Participation (Wed. 11/7 8:30-10:00am): A closer look at health information seeking in older adults and involved family and friends.
UPCOMING DISSERTATION DEFENSES
Graham Kim
Friday, November 9, 1pm, UW Medicine SLU, Building E, Room E130A
Title: Secondary Usage of Electronic Health Record Data for Patient-Specific Modeling
Abstract:
Translational research has become an important bridge that moves findings from basic science research to patients’ bedside and to the clinical community. Unfortunately, this notion of translational research seems to be unidirectional in that basic research is translated into clinical research and practice, but basic science research does not seem to benefit as much from clinical medicine.
In my dissertation, I leverage the availability of retrospective EHR data and use them with biosimulation models to translate data from clinical medicine to benefit biosimulation modeling. Biosimulation models are mathematical representations of biological systems, and they can help with mechanistic understanding of physiology and predict the dynamics of a biological system. Using clinical data with biosimulation models has the potential to benefit both the biosimulation modelers, as well as clinicians.
The abundance of retrospective clinical data available for research is a promising alternative to the traditional method of validating models by conducting resource-intensive prospective studies. These models can then be made patient-specific to simulate the physiology of individuals. When used in the clinical setting, these patient-specific models have the potential to be used by clinicians to better understand the underlying pathophysiology of the patient.
In my research, I first conduct a scoping review of model in the literature to quantify model reproducibility and discover the abysmal status of model source code availability in publications. Then using a published hemodynamics model, I demonstrate using retrospective clinical dataset from right heart catheterizations to optimize and validate the model without needing to conduct burdening prospective studies, and explore potential clinical applications of patient-specific modeling. Finally, I describe an ontological approach to extend the data-model connection to be systematic and scalable. I demonstrate this approach by connecting cardiology data and lab results data with a hemodynamics model and several nephrology models, respectively.
FACULTY/STUDENT/ALUMNI/STAFF ACTIVITIES
Congratulations to Mike Leu, MD and Paul Sutton, MD, Fellows of AMIA!
Mike Leu, MD, Associate Professor of BIME and Director of the Clinical Informatics Fellowship, and Paul Sutton, MD, Adjunct Associate Professor of BIME, have been recognized by being included in the inaugural class of 130 Fellows in the newly established FAMIA Applied Informatics Recognition Program, a new program meant to recognize AMIA members who apply informatics skills and knowledge within their professional setting, who have demonstrated professional achievement and leadership, and who have contributed to the betterment of the organization.
FAMIA was established in May 2018, following several months of deliberation by an interdisciplinary Advisory Group of AMIA members to define the FAMIA Eligibility Criteria. These deliberations reaffirmed that the FAMIA Applied Informatics Recognition Program be inclusive – balancing the needs of physicians, nurses, pharmacists, and others within clinical informatics, with the needs of public health, clinical researchers, and others who apply informatics to their practice.
FAMIA recognizes professionals who apply informatics skills and knowledge towards the goals of enhanced personal and population health, improved organizational performance and learning, and individual empowerment in their health, care, and research.
New Fellows of AMIA are authorized to use the letters FAMIA in connection with their professional activities. A formal induction ceremony will be held at the AMIA 2019 Clinical Informatics Conference in Atlanta, April 30 – May 2, 2019. Click here for the list of the inaugural class of Fellows.
PUBLICATIONS AND PRESENTATIONS
Conference paper:
Stephens, K. A., Osterhage, K. P., Fiore-Gartland, B., Lovins, T. L., Keppel, G. A., & Kim, K. K. (in press). Examining the Needs of Patient Stakeholders as Research Partners in Health Data Networks for Translational Research. AMIA Summits Translational Science Proceedings, Mar 27, 2019.
2 Conference abstracts:
Bergquist, T., Estiri, H., Prosser, J., & Stephens, K. A. (2018, December). A Data Quality Testing Tool for Cross-institutional OMOP Electronic Health Record Data Repositories. Abstract and oral presentation presented at International Society for Computational Biology Rocky 2018 Bioinformatics Conference, Aspen, CO.
Stephens, K. A., Wilcox, A., Payne, Ph., Morrison, J. Sprecher, J., Mussa, R., Foraker, R., Biber, S., & Mooney, S. D. (2018, December). Governance Innovations for Promoting Cross-institutional Electronic Health Data Sharing. International Society for Computational Biology Rocky 2018 Bioinformatics Conference, Aspen, CO.