Chair’s Message
We are moving toward our vision with a number of activities across our various programs. We have updated our strategic plan in response to the 10-year academic program review that we recently completed. For our research-oriented MS and PhD programs, we have recently added a specialization in Data Science. We are completing a curriculum revision for our on line applied clinical informatics MS which will be effective Fall 2020. The work of our fellows in the clinical informatics fellowship program has received plaudits from clinical administrators and faculty, and we are currently recruiting a new faculty member in our department to assist with this program (view position description). We are also recruiting a faculty member in medical education to start Summer 2020 (view position description). This is the beginning of a new cycle of admissions to our graduate programs, and we look forward to another productive year, and new growth in our department.
Cordially,
Peter Tarczy-Hornoch, MD
Chair and Professor, Department of Biomedical Informatics and Medical Education
Biomedical Informatics and Medical Education Newsletter
November 15-19, 2021
UPCOMING LECTURES AND SEMINARS
BIME 590A – Biomedical & Health Informatics Lecture Series
Thursday, 11:00am-11:50am, SLU, C123 A/B
Zoom: https://washington.zoom.us/my/peter.th
November 25: No Class, Thanksgiving
BIME 591A – Deep learning and natural language processing within the clinical domain Mondays, 11:30-12:20
Facilitator: Kevin Lybarger
PUBLICATIONS AND PRESENTATIONS
S. Zeng, M. Arjomandi, Y. Tong, Z.C. Liao, and G. Luo. Developing a Machine Learning Model to Predict Severe Chronic Obstructive Pulmonary Disease Exacerbations: Retrospective Cohort Study. Journal of Medical Internet Research (JMIR), 2021.
Brenna N. Renn, Matthew Schurr, Oleg Zaslavsky and Abhishek Pratap – Artificial Intelligence: An Interprofessional Perspective on Implications for Geriatric Mental Health Research and Care | Front. Psychiatry, 15 November 2021 | https://doi.org/10.3389/fpsyt.2021.734909
NEWS
Rethinking Improvement Targets in the Context of Massive Crises
Tuesday, December 14th from 12-1pm PT
Featuring:
Kaveh G. Shojania, MD
Professor and Vice Chair, Quality & Innovation
Department of Medicine, CQuIPS Senior Scholar, University of Toronto
Watch recordings from past webinars and get up to date information about the webinar series on the Center website.
Anna Liss Jacobsen, Medicine and Research Services Librarian at the UW Health Sciences Library is co-author on, “Impact of innovative technology-related interventions on K-12 students’ STEM career-related outcomes: A meta-analysis” to be presented at the 2022 AERA Annual Meeting in San Diego. AERA is the premier conference in the field of education and received more than 10,000 submissions for this meeting. The meta-analysis being presented is part of a NSF grant funded mixed methods review that identifies interventions that increase the likelihood of individuals going into STEM-related careers.
UPCOMING FINAL EXAMS
Chethan Jujjavarapu
Friday, December 3, 2021; 3:00 PM
Zoom: https://washington.zoom.us/j/9205991606
Title: Applying Machine Learning and Application Development to Lower Back Pain and Genetic Medicine
Abstract: Improvement of the healthcare system is a focal point for academic leaders. In recent years, precision medicine initiatives have gained traction as a solution to improve care by leveraging healthcare analytics and informatic tools to assist clinicians in prescribing individualized treatments based on the patient’s health characteristics. This involves data collection, data management and advanced statistical and machine learning methods, and new tools to deliver the promise of data on the outcomes of health and healthcare. To help clinicians, researchers must leverage electronic health record (EHR) data, however these data are complex as they are made up of multiple modalities with an ever increasing volume. While structured EHR data is a popular modality to use for analysis, clinical notes (i.e. unstructured EHR data), for example, provide more granular information about patients that is useful to clinicians. As a result, there is interest in building cohorts of patients based on unstructured data by using natural language processing (NLP). For analysis, there are recent works that discuss the value of using deep learning to integrate multiple data modalities together to better predict clinical outcomes, however rigorous testing is needed to fully understand this value. Once data has been collected and analyzed, the final task is understanding how to further patient involvement with this information. In this dissertation, I focus on creating a framework that can build cohorts based on unstructured data, analyze EHR data using the different modalities, and increase patient involvement. The aims are to: 1) compare NLP methods for the classification of lumbar spine imaging findings related to lower back pain, 2) predict decompression surgery by applying machine learning to patients’ structured and unstructured health data, and 3) demonstrate patient delivery and sharing of data in a smartphone app to facilitate family communication of genetic results.
Wilson Lau
Friday, December 10, 2021; 11:30 AM
Zoom: https://washington.zoom.us/j/99552321462
Title: Text Mining with Deep Learning for Secondary Use In Radiology
Abstract: Radiology reports are the principal means for communicating and documenting diagnostic imaging results. The reports contain a diverse and rich set of information, including radiologic findings, diagnoses, and recommendations for follow-up tests. While there has been some limited exploration of structured radiology reports that capture finding details, radiologists’ findings are predominantly documented in unstructured text. Natural language processing (NLP) can automatically convert this valuable information into a structured semantic representation. Since imaging tests are commonly used for cancer screening and diagnosis, extracting the findings associated with lesions and medical problems could facilitate many secondary use applications, including clinical decision-support systems, diagnostic surveillance of medical problems, and tracking follow-up recommendations. When critical findings are observed in the images, radiologists may recommend further imaging tests to the referring physicians. It is vital that these results, particularly if they are unexpected, are not lost to follow-up. In patients who have an unexpected finding on a chest radiograph, approximately 16% will eventually be diagnosed with a malignant neoplasm. Extracting these follow-up recommendations, clinical findings (lesions and medication problems), provides supporting evidence for clinicians to determine their course of action.
This dissertation adopts the recent advancement in artificial intelligence and unlocks new opportunities to effectively extract information from radiology reports for secondary use. This work makes the following contributions: (1) extracting recommendations and related entities from over 3 millions radiology reports in UW medical institutions (2) a detailed event-based annotated corpus for extracting clinical finding in radiology reports (3) a high performance deep learning extraction framework that can be trained to predict entities and relations from unstructured texts. (4) a new approach to automatically classify protocols for CT examinations and handle data imbalance using knowledge distillation.
UPCOMING GENERAL EXAMS
Kathleen Muenzen
Monday, December 6, 2021; 11:00 AM
South Lake Union Building C; C259
Title: Deriving the technical and sociocultural requirements for clinical genomics discovery in a Genomics-Enabled Learning Healthcare System
Abstract: Recent advances in genetic sequencing technologies and analysis tools have made genomic data widely available for medical research. Despite the widespread expectation that genomic data will revolutionize medicine, there exist major evidence gaps in demonstrating the utility of genomic discovery for improving patient outcomes. One promising avenue for reducing this evidence gap and accelerating the pace of clinical genomics discovery is to foster environments in which genomic research and clinical care exist symbiotically. However, the technical and sociocultural requirements for conducting genomic discovery in clinical spaces are not well-defined. The Learning Healthcare System (LHS) framework is one lens through which the requirements for clinical genomic discovery can be identified and organized. Furthermore, drawing on experiences from clinical genomics research consortia like the Clinical Sequence Evidence-Generating Research (CSER) and Electronic Medical Records and Genomics (eMERGE) networks can help identify requirements that are unique to genomics discovery initiatives that straddle the research-clinical boundary. In the proposed research, we will derive a set of core technical and sociocultural requirements for integrating genomics discovery within a genomics enabled LHS (GLHS). We will first identify themes and recommendations from the clinical genomics research data integration process in the CSER consortium (Aim 1). We will then conduct a needs assessment for clinical genomics discovery among 15-20 practicing, board-certified medical geneticists in CSER, eMERGE and the University of Washington medical system (Aim 2) and perform a logistic regression-based genome-wide risk assessment for Clostridioides difficile infection (CDI) using merged genetic and Electronic Health Record (EHR) data from 12 clinical sites in the eMERGE network (Aim 3). Finally, we will perform a systematic literature review of requirements for clinical genomics discovery and triangulate results from Aims 1, 2 and the literature review into a core set of requirements for genomic discovery in a GLHS (Aim 4). The CDI genetic risk factor analysis from Aim 3 will be used to examine the utility of these requirements in the context of a novel gene-disease association discovery.
Ivan Rahmatullah
Monday, December 6, 2021; 3:00 PM
South Lake Union, Building C; C259
Title: Informing usable prediction model visualizations of flu risk stratifications in communities using human-centered design for biomedical researchers
Abstract: Achieving accurate user understanding and trust remains a challenge of prediction models in the biomedical field. Prediction models are a common statistical tool that uses available data as predictors to predict outcomes often unavailable at the same time as the predictors. The common prediction models used in the biomedical field support individual (e.g., supporting disease diagnosis and prognosis) and population health (i.e., predicting and stratifying diseases in a population). Prediction model studies publish their results in scientific journals, where biomedical researchers often encounter prediction models for the first time. However, report requirements and design recommendations of the usable visualizations for accurate user understanding and trust have been missing from prediction model studies as well as from the study guideline reports such as TRIPOD (Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis). Usable visualizations of prediction model results may improve accurate user understanding and trust. My dissertation overarching objective is to inform the design of usable prediction model visualizations that promote accurate user understanding and trust among biomedical researchers in the context of flu. Across three aims, I will develop prediction models (Aim 1), co-design prediction model visualizations with biomedical researchers (Aim 2), and then test the visualizations with biomedical researchers (Aim 3) using Seattle Flu Study (SFS) data. The completion of this dissertation will contribute design recommendations for visualizations of prediction models for respiratory disease like flu that could translate to other disease contexts and target populations.
November 8-12, 2021
UPCOMING LECTURES AND SEMINARS
BIME 590A – Biomedical & Health Informatics Lecture Series
Thursday, 11:00am-11:50am, SLU, C123 A/B
Zoom: https://washington.zoom.us/my/peter.th
November 18:
BIME 591A – Deep learning and natural language processing within the clinical domain Mondays, 11:30-12:20
Facilitator: Kevin Lybarger
PUBLICATIONS AND PRESENTATIONS
Hyeyoung Ryu, Wanda Pratt, Microaggression clues from social media: revealing and counteracting the suppression of women’s health care, Journal of the American Medical Informatics Association, 2021;, ocab208
NEWS
Dr. Uba Backonja has been selected as a member of AMIA’s Diversity, Equity, and Inclusion Subcommittee on Education, Governance, and Policy.
Ashmitha Rajendran, BHI PhD student, will be presenting a lightning-talk titled Using Predicted Protein 3D Structure Features for Predicting Drug-Target Interactions at virtual Scholars’ Studio on Thursday, November 18, 2021.
Virtual Scholars’ Studio
Thursday, November 18, 4 – 5:30 p.m. (PST)
Register via Zoom:
Advanced AI Applications for Socially Responsible Biomedical Research
November 17, 2021
11:00AM-1:00PM ET, Virtually
This virtual workshop will examine the opportunities and risks of AI applications in health sciences. The purpose is to accelerate research by exploring, explaining and discussing a variety of AI solutions for biomedical research. The workshop will also look into the question of what can go wrong when experimenting with new AI technologies.
Click below to learn more and register:
https://www.fnlm.org/virtual-workshop-series/
UPCOMING FINAL EXAMS
Chethan Jujjavarapu
Friday, December 3, 2021; 3:00 PM
Zoom: https://washington.zoom.us/j/9205991606
Title: Applying Machine Learning and Application Development to Lower Back Pain and Genetic Medicine
Abstract: Improvement of the healthcare system is a focal point for academic leaders. In recent years, precision medicine initiatives have gained traction as a solution to improve care by leveraging healthcare analytics and informatic tools to assist clinicians in prescribing individualized treatments based on the patient’s health characteristics. This involves data collection, data management and advanced statistical and machine learning methods, and new tools to deliver the promise of data on the outcomes of health and healthcare. To help clinicians, researchers must leverage electronic health record (EHR) data, however these data are complex as they are made up of multiple modalities with an ever increasing volume. While structured EHR data is a popular modality to use for analysis, clinical notes (i.e. unstructured EHR data), for example, provide more granular information about patients that is useful to clinicians. As a result, there is interest in building cohorts of patients based on unstructured data by using natural language processing (NLP). For analysis, there are recent works that discuss the value of using deep learning to integrate multiple data modalities together to better predict clinical outcomes, however rigorous testing is needed to fully understand this value. Once data has been collected and analyzed, the final task is understanding how to further patient involvement with this information. In this dissertation, I focus on creating a framework that can build cohorts based on unstructured data, analyze EHR data using the different modalities, and increase patient involvement. The aims are to: 1) compare NLP methods for the classification of lumbar spine imaging findings related to lower back pain, 2) predict decompression surgery by applying machine learning to patients’ structured and unstructured health data, and 3) demonstrate patient delivery and sharing of data in a smartphone app to facilitate family communication of genetic results.
Wilson Lau
Friday, December 10, 2021; 11:00 AM
Zoom: https://washington.zoom.us/j/99552321462
Title: TBD
UPCOMING GENERAL EXAM
Ivan Rahmatullah
Monday, December 6, 2021; 3:00 PM
South Lake Union, Building C; C259
Title: TBD
November 1-5, 2021
UPCOMING LECTURES AND SEMINARS
BIME 590A – Biomedical & Health Informatics Lecture Series
Thursday, 11:00am-11:50am, SLU, C123 A/B
Zoom: https://washington.zoom.us/my/peter.th
November 11: Veteran’s Day, No class
BIME 591A – Deep learning and natural language processing within the clinical domain Mondays, 11:30-12:20
Facilitator: Kevin Lybarger
PUBLICATIONS AND PRESENTATIONS
Narayanan M, Starks H, Tanenbaum E, Robinson E, Sutton PR, and Schleyer AM. Harnessing the electronic health record to actively support providers with guideline-directed telemetry use. Appl Clin Inform 2021. 12 (5):996-1001
NEWS
Annie Chen has been elected Chair-Elect of the Special Interest Group Information Needs, Seeking and Use (SIG-USE) associated with the Association for Information Science and Technology.
Dr. Uba Backonja has accepted a role as a Clinical Informatics Lead at MITRE, which supports work by the Federal Government. She will be working remotely from Seattle on the development and evaluation of national informatics interventions.
October 25-October 29, 2021
UPCOMING LECTURES AND SEMINARS
BIME 590A – Biomedical & Health Informatics Lecture Series
Thursday, 11:00am-11:50am, SLU, C123 A/B
Zoom: https://washington.zoom.us/my/peter.th
November 4: Erik Van Eaton, MD
Title: EHR user interaction – a research field, or just product design? The CORES project (Computerized Rounding and Signout)
Abstract: In healthcare delivery, we expect that all medications, implants, instruments, and devices are subjected to detailed scientific study before their use in patient care. While initial proofs are obtained by the developers of these items, they are later subjected to more generalized testing before being declared fit for use. After that, Phase 4 trials or aftermarket studies are done, where generally available items are monitored in daily use to ensure they are safe and effective in patient care. Numerous examples exist of medications, implants and devices that passed initial scrutiny but were later modified or recalled because of ongoing outcomes surveillance.
The design of Electronic Health Records usability and information management has sometimes been subjected to Phase 4 evaluation, with discovery of problems. Notably, a 2005 publication of an unexpected doubling of Pediatric ICU mortality as a direct consequence of implementation of a commercially available Computerized Provider Order Entry system drew attention to the role EHR design and implementation might play in patient outcomes. In this presentation, we will talk about EHR user interaction design as a product feature managed independently by software companies versus a clinical intervention that can be studied and changed in response to clinical research. The example of CORES, the COmputerized Rounding & Signout system developed at the University of Washington will be discussed as an example
BIME 591A – Deep learning and natural language processing within the clinical domain Mondays, 11:30-12:20 Facilitator: Kevin Lybarger
PUBLICATIONS AND PRESENTATIONS
AMIA 2021 Annual Meeting: Workshop Presentation, Exploring mechanisms to examine racial biases within a LHS framework, Young Ji Li, Kendrick D. Cato, Alaa, Albashayreh, Gregory Alexander, Uba Backonja, Suzanne R. Bakken, Janice A. Sabin, Ruth Marie Masterson Creber, Nicole Weiskopf. October 30, 2021 from 1:00 PM to 4:30 PM. Sabin Presentation: Introduction to Concepts and Issues: Overview and Scope of Racial/other Bias in Healthcare
AAMC 2021 Annual Meeting: Panel Presentation, (virtual) Janice A. Sabin, Brenda Pereda, Ann-Gel Palermo, Dowen Boatright, Tiffani St. Cloud. Panel title: Addressing Institutionalized Racism in Academic Medicine, November 9, 2021. Sabin Presentation: Anti-Racism in Medicine: A Learning-to-Action Approach
UPCOMING GENERAL EXAM
Qifei Dong
Friday, November 5th; 9:00 am; South Campus Center, Room 348
Title: Deep Learning Classification of Spinal Osteoporotic Compression Fractures on Radiographs
Abstract: Although osteoporosis is a debilitating disease that affects 9% of individuals over 50 years of age in the United States and 200 million women globally, osteoporosis screening is underutilized. One surrogate for osteoporosis screening is opportunistic screening using pre-existing images to detect spinal osteoporotic compression fractures (OCFs). However, OCFs are often found incidentally and thus escape manual detection. An accurate automated opportunistic screening tool could improve diagnosis and enable more and earlier treatment of osteoporosis. Since radiography is a ubiquitous imaging modality used in the diagnostic workup of many conditions, an accurate classifier to detect OCFs on radiographs is a crucial component for the automated opportunistic screening tool. To build this OCF classifier, two spine radiograph datasets will be obtained, whose radiographs are in the Digital Imaging and Communications in Medicine (DICOM) format. To annotate these two datasets, we will design a configurable open-source software program for efficient DICOM image annotation. For image classification, deep learning significantly outperforms other machine learning algorithms. In this research, we will train different deep learning models using the two datasets and compare the performance and generalizability of these deep learning models. Training a deep learning model on a large dataset is often time-consuming. During deep learning model training, it is desirable to offer a non-trivial progress indicator that can continuously project the remaining model training time and the fraction of model training work completed. This makes the deep learning model training process more user-friendly.
Committee: Drs. Gang Luo (Chair), Fei Xia, Nathan Cross, Sean Mooney
NEWS
Diane Korngiebel has moved from The Hastings Center (for Ethics) to a new full-time position as of October 4th serving as a bioethicist on the Google Bioethics and Trust Team.
Second, please congratulate Diane on having been elected to the Chair Elect position of the AMIA ELSI Working Group (effective Jan 1, 2022).
October 18-October 22, 2021
UPCOMING LECTURES AND SEMINARS
BIME 590A – Biomedical & Health Informatics Lecture Series
Thursday, 11:00am-11:50am, SLU, C123 A/B
Zoom: https://washington.zoom.us/my/peter.th
October 28: No Speaker/AMIA
BIME 591A – Deep learning and natural language processing within the clinical domain Mondays, 11:30-12:20
Facilitator: Kevin Lybarger
PUBLICATIONS AND PRESENTATIONS
A collaborative COVID study between UW Medicine and Microsoft Research just got published in PLoS One. This study combined data about COVID testing, clinical information from the UW Medicine Enterprise Data Warehouse, and information about geographic and sociodemographic information to understand factors contributing towards COVID positive test model predictions. This study provides a machine learning process to understand the predictive value of individual features and their value as collections of features towards predictions.
Phuong J, Hyland SL, Mooney SJ, Long DR, Takeda K, et al. (2021) Sociodemographic and clinical features predictive of SARS-CoV-2 test positivity across healthcare visit-types. PLOS ONE 16(10): e0258339. https://doi.org/10.1371/journal.pone.0258339
Hendrickson K, Kim S, Stambaugh C, Gronberg M, Kim L, Wang D; MPLA Cases Subcommittee. MPLA Case 3: Don’t criticize me in public! J Appl Clin Med Phys. 2021;22:280–283. https://doi.org/10.1002/ acm2.13334.
Umoren R, Kim S, Gray MM, Best JA, Robins L. Interprofessional model on speaking up behaviour in healthcare professionals: a qualitative study. BMJ Leader. 2021 Apr 26: leader-2020.
Chen, A. T., Cole, C. L. (accepted). Reflexivity in issues of scale and representation in a digital humanities project. Workshop on Visualization for the Digital Humanities, co-located with IEEE VIS 2021.
Valdez, R., Chen, A. T., Hampton, A. J., Madathil, K. C., Papautsky, E. L., Rogers, C. C. (accepted). Leveraging social media for human factors research in health care. Invited to give a panel presentation at Human Factors and Ergonomics Society Annual Meeting (HFESAM) 2021. Baltimore, MD.
Chen, B., Ge, S., Zaslavsky, O., Chen, A. T. (accepted). Investigating information and support interaction patterns in an online health community. Poster to be presented at 84th Annual Meeting of the Association for Information Science & Technology (ASIS&T) SIG-USE Symposium 2021.
Rao, N. D., Coe, S., Huey, J., Fullerton, S. M., Chen, A. T., Shirts, B. H. (accepted). Population genetic screening: What are the psychosocial impacts? American Society of Human Genetics (ASHG) 2021.
Shirts, B., Rao, N., Huey, J., Coe, S., Tsinajinnie, D., Kaganovsky, J., Jarvik, G. J., Fullerton, S. M., Chen, A. T. (2021). A step towards real-world population screening for hereditary cancer and hypercholesterolemia. American Society of Human Genetics (ASHG) 2021.
October 11-October 15, 2021
UPCOMING LECTURES AND SEMINARS
BIME 590A – Biomedical & Health Informatics Lecture Series
Thursday, 11:00am-11:50am, SLU, C123 A/B
Zoom: https://washington.zoom.us/my/peter.th
October 21: Speaker: Patrick Mathias, MD, PhD
Title: Increasing Access to COVID-19 Testing with Open-Source Tools
Abstract: The COVID-19 pandemic has introduced numerous challenges for health care and public health systems throughout the US and the world, from implementing new workflows in support of delivering routine care to improving access to testing to navigating constrained supply chains. Clinical laboratories have been critical to the COVID-19 response, as identification of cases with testing is a key step in containing and managing the SARS-CoV-2 virus. The University of Washington Virology Laboratory has played a key role in expanding access to COVID-19 testing across the Pacific Northwest and grew its capacity from 200 molecular tests per day pre-pandemic to more than 10,000 tests per day. This rapid growth has been enabled by a combination of consumer-centric healthcare applications, traditional clinical information systems, and open source software tools. During this talk, we will discuss the barriers to scaling SARS-CoV-2 testing, the informatics tools that have helped scale testing outside of traditional health care system settings, and how analytics has supported laboratory operations.
BIME 591A – Deep learning and natural language processing within the clinical domain Mondays, 11:30-12:20; Facilitator: Kevin Lybarger
PUBLICATIONS AND PRESENTATIONS
Backonja U, Langford LH, Mook P. How to support the nursing informatics leadership pipeline: Recommendations for nurse leaders and professional organizations. CIN: Computers, Informatics, Nursing. [ePub ahead of print] doi: 10.1097/CIN.0000000000000827
Backonja U, Mook P, Langford LH. Calling Nursing Informatics Leaders: Opportunities for Personal and Professional Growth. Online Journal of Issues in Nursing (OJIN). 2021;26(3):manuscript 6. doi: 10.3912/OJIN.Vol26No03Man06
October 4-October 8, 2021
UPCOMING LECTURES AND SEMINARS
BIME 590A – Biomedical & Health Informatics Lecture Series
Thursday, 11:00am-11:50am, SLU, C123 A/B
Zoom: https://washington.zoom.us/my/peter.th
October 14: Speaker: Sean Mooney, PhD, University of Washington
Title: Using artificial intelligence in healthcare and setting the stage to move from accuracy to improved outcomes
Abstract: Artificial intelligence and machine learning methods are being implemented into all aspects of healthcare business and delivery. In the presentation, I will discuss work within the UW Medicine healthcare system and the University of Washington to create a platform and a community around studying the implementation of advanced data driven methods into care. This includes describing a Medical Data Science Initiative to achieve our goals and the technical platforms to deliver them. Finally, I will describe some pilot projects to demonstrate our opportunity.
BIME 591A – Deep learning and natural language processing within the clinical domain Mondays, 11:30-12:20
Facilitator: Kevin Lybarger
NEWS
Abhishek (Abhi) Pratap, PhD has taken on various new roles:
Group Head, Digital Health & AI | www.aid4mental.health; Independent Scientist | CAMH | Krembil Center for Neuroinformatics; Assistant Professor, Dept of Psychiatry, Univ of Toronto; Faculty Affiliate | Vector Institute Toronto; Affiliate Assistant Professor, BIME, University of Washington, Seattle; Visiting Research Fellow | Institute of Psychiatry, Psychology and Neuroscience, King’s College, London
Abhi is looking for students (interns, long-term visits) who are interested in working in digital mental health. Please reach out to Abhi directly if you are interested: abhishek.vit@gmail.com
70th Anniversary of the NLM Classification
2021 marks the 70th anniversary of the NLM Classification. The first edition of the classification was published in 1951 as the U.S. Army Medical Library Classification. The name changed to the National Library of Medicine Classification with the second edition in 1956 to coincide with the library’s name change. It is still recognized as a standard classification system for the arrangement of library materials in the field of medicine and related sciences used by health and medical libraries all over the world.
President Biden appoints AMD’s Lisa Su to Council of Advisors on Science and Technology.
In addition to Su, Nvidia chief scientist Dr. William Dally, Microsoft chief scientific officer Dr. Eric Horvitz, and Google Cloud chief information security officer Phil Venables are joining PCAST
July 26-30, 2021
NEWS
It is with regret that we announce that Adam Wilcox will be leaving the University of Washington to take on the role of Director of the Applied Clincal Informatics Institute at Washington University St. Louis starting August 27th. During his time at UW as a core BIME faculty member and as UW Medicine Chief Analytics Officer Adam has made many important contributions to UW in all aspects of the BIME mission (research, education, praxis and fiscal/other). Please congratulate Adam on this new opportunity. He wanted us to convey that while he is excited for this upcoming opportunity he will miss the members of the Department
Mike Leu was selected to participate in the development of the American Academy of Pediatrics’ (AAP) next clinical practice guideline, on “Failure to Thrive (Faltering Growth)”.
PUBLICATIONS AND PRESENTATIONS
Mark Phillips is presenting work on a national effort to establish an ontology for the domain of radiation oncology at the annual meeting of the American Association of Physicists in Medicine:
“Radiation Therapy Ontology: A report of the AAPM Working Group”, Mark Phillips, J Bona, A Dekker, P Gabriel, C Mayo.
Weinberg ST, Monsen C, Lehmann CU, Leu MG, Council on Clinical Information Technology. Policy Statement. Integrating Web Services / Applications to Improve Pediatric Functionalities in Electronic Health Records. Pediatrics. 2021 June 28; e2021052047. doi: 10.1542/peds.2021-052047. PMID: 34183360.
Leu MG, Weinberg ST, Monsen C, Lehmann CU. Technical Report: Web Services and Cloud Computing in Pediatric Care. Pediatrics. 2021 June 28; e2021052048. doi: 10.1542/peds.2021-052048. PMID: 34183361.
UPCOMING FINAL EXAMS
Lauren Snyder
Thursday, August 12, 2021; 3:00 PM
Zoom: https://washington.zoom.us/j/5366029713
Title: Improving Design and Usability of Interactive Vulnerability Mapping for Global Health Preparedness
Abstract: Global health preparedness –the ability of organizations and governments to anticipate risks and respond to disease outbreaks– presents both an imperative and a challenging opportunity for public health informatics interventions. Addressing risks of vector-borne and zoonotic disease (VBZD) outbreaks is especially complex as it involves the careful integration of human, animal, entomological, environmental, and infrastructure data. Presentation and understanding of those risks require usable tools and technology. Spatial Systems for Decision Support (SSDS) are a type of visualization tool that enable public health practitioners to make critical decisions informed by timely access to pertinent, analyzed data. In my dissertation research, I introduce a new type of SSDS, interactive vulnerability mapping tools, which can help decision makers in global health preparedness identify spatial areas that are at risk for VBZD outbreaks and have a lower capacity to contain spread. Decision makers include epidemiologists, public health planners, vector control specialists, and directors, who might use this information to allocate vaccine resources or plan intervention activities to high risk regions. Unfortunately, SDSS tools are not routinely developed using a human centered design (HCD) approach, and there is a lack of deliberate consideration of sociotechnical factors. In my doctoral research, I have applied principles of HCD and information visualization to design and evaluate the usability of interactive mapping tools for dengue vulnerability in Peru (Aim 1) and Rift Valley fever vulnerability in Kenya (Aim 2). To situate my Aim 1-2 findings in the literature, I conducted a scoping review of SDSS for VBZD preparedness (Aim 3) that describes data, users, technology, and use cases in published SDSS studies as well as gaps in the existing literature. This work contributes: 1) usable SDSS tools designed for public health decision makers in Peru and Kenya, 2) empirical data on the design, data visualization preferences, usability, and acceptance of SSDS for disease vulnerability in global health settings, and 3) a reproducible search of the literature on SDSS for VBZD that maps the current state of the literature, characterizes health informatics factors, and identifies opportunities for future research.
Committee: Drs. Andrea Hartzler (Chair), Uba Backonja, Nancy Puttkammer, Peter Rabinowitz, Christopher Adolph
Jason Thomas
Friday, August 20, 2021; 10:00 AM
Zoom: https://bit.ly/AdamZoom
Title: Assessing the fitness for use of real and synthetic electronic health record data for observational research
Abstract: Over the past decade, electronic health record (EHR) adoption has led to an explosion in the volume of Electronic health record and log data, then efforts to effectively harness the potential of these data for knowledge discovery (KD) and quality improvement (QI). In parallel, recent gains in artificial intelligence have produced powerful methods to analyze, use, and even create synthetic data. However, limitations in data utility (e.g. bias, data quality, comprehensiveness) and accessibility (e.g. privacy, interoperability, availability), as well as limited means to measure and manage tradeoffs between the two are significant barriers to using these data effectively. Determining whether data are suitable to be used in a specific analysis or context, known as “fitness for use” is not included in current frameworks for general health record data quality characterization nor evaluated by data quality assessment (DQA) tools. EHR log data use is particularly unrefined for QI and KD due to an absence of validated standards and methods. Thus, users of electronic health record and log data remain uninformed as to the fitness for use of their data at baseline and are unable to effectively assess subsequent tradeoffs between utility and privacy when applying preserving technologies.
First, we 1) developed a framework for data utility assessment of electronic health records, then 2) adapted open-source tools to make use of this framework which we then applied to assess the utility of real and synthetic EHR data for observational research related to COVID-19 and/or future influenza pandemics. Second, we evaluated whether synthetic data derived from a national COVID-19 data set could be used for geospatial and temporal epidemic analyses. To do so we conducted replication of studies and computed general summary statistics on original and synthetic data, then compared the similarity of results between the two datasets. Third, we conducted a retrospective, observational analysis – with and without privacy preserving technology – of clinical workstation authentication behaviors from the UW Medicine health system to inform customized solutions that balance usability and security.
Committee: Drs. Adam Wilcox (Chair), Gang Luo, Matthew Thomas Trunnell, Larry Kessler
July 12-16, 2021
NEWS
Dr. Janice Sabin has been asked by Dean Ramsey to serve on a new task force to review existing practices for faculty search processes in the School of Medicine (SoM) that support equity, diversity, and inclusion in recruitment and to propose modifications and improvements to establish best practices in this area.
Dr. Janice Sabin has joined the guest editorial team for a special issue of Frontiers in Psychology, Title: “Implicit Social Cognition: malleability and change.” The team of guest editors also includes: Maddalena Marini, (Italian Institute of Technology, Italy), Brian O’Shea (University of Amsterdam, Netherlands), Michelangelo Vianello (Padua University, Italy), and Sarah Redfield (University of New Hampshire School of Law, USA). The special issue will give a multidisciplinary view of the topic, not only research but also ethical, legal, medical, and practical aspects.
Dr. Anne M. Turner has been asked to serve as a member of the NLM Extramural Program Biomedical Informatics, Library and Data Sciences Review Committee (BILDS) Committee. She will start this June as an ad hoc member and as a standing member (4-year term) starting in November 2021. This is a big honor recognizing Dr. Turner’s sustained research and leadership contributions over the years.
As Associate Direction of the CDC funded UW Health Promotion Research Center (UW HPRC), Dr. Turner will be participating in a CDC funded project focusing on COVID-19 access and hesitance in King County. The UW HPRC has received $500K in supplemental grant funding to support three projects funded under the award which focus on improved communication with limited English proficiency groups, fostering vaccine access to communities of color, and strengthening community partnerships. Additional information about the projects and the award can be found at Collaborating to Increase King County Vaccination Rates | Health Promotion Research Center (washington.edu).
PUBLICATIONS AND PRESENTATIONS
AMIA Paper presentation:
Older adults’ personal health information management: The role and perspective of various healthcare providers Alyssa L. Bosold, MPH, Shih-Yin Lin, PhD, Jean O. Taylor, PhD George Demiris, PhD, Anne M. Turner, MD, MLIS, MPH
AMIA Demonstration:
SHARE-NW: An Innovative Public Health Informatics Tool. Uba Backonja, PhD, RN , Anne M. Turner, MD, MLIS, MPH , Betty Bekemeier, PhD, MPH, RN Northwest Center for Public Health Practice, University of Washington, Seattle, WA
Burkhardt H, Alexopoulos G, Pullmann M, Hull T, Areán P, Cohen T. Behavioral Activation and Depression Symptomatology: Longitudinal Assessment of Linguistic Indicators in Text-Based Therapy Sessions. J Med Internet Res 2021;23(7):e28244. http://dx.doi.org/10.2196/28244
Burkhardt HA, Alexopoulos GS, Pullmann MD, Hull TD, Areán PA, Cohen T. Linguistic indicators of Behavioral Activation in text-based therapy sessions anticipate changes in depression symptomatology. Podium abstract accepted for AMIA 2021.
June 21-June 25, 2021
PUBLICATIONS AND PRESENTATIONS
Sangameswaran S, Segal C, Rosenberg D, Casanova-Perez R, Cronkite D, Gore J, Hartzler AL. Design of digital walking programs that engage prostate cancer survivors: Needs and preferences from focus groups. Paper accepted for AMIA 2021.
Casanova-Perez R, Apodaca C, Bascom E, Mohanraj D, Lane C, Vidyarthi D, Beneteau E, Sabin J, Pratt W, Weibel N, Hartzler AL. Broken down by bias: Healthcare biases experienced by BIPOC and LGBTQ+ patients. Paper accepted for AMIA 2021.
Patel H. Henrikson NB, Ralston JD, Leppig K, Scrol A, Jarvik GP, DeVange S, Larson EB, Hartzler AL. Implementation matters: How patient experiences differ when genetic counseling accompanies the return of genetic variants of uncertain significance. Paper accepted for AMIA 2021.
Snyder L, Phan D, Connor SE, George S, Williams KC, Villatoro J, Saraf A, Kwan L, Reid N, Gore GL, Litwin MS, Hartzler AL. User Evaluation of Interactive Longitudinal PRO Visualizations Designed by Prostate Cancer Survivors with Limited Graph Literacy. Podium abstract accepted for AMIA 2021.
Reed N, Ramos KJ, Hobler MR, Bartlett LE, Kpanadak SG, Hartzler AL. Usability Study of a Decision Support Website to Support People Living with Cystic Fibrosis in Shared Decision Making about Lung Transplant. Poster accepted for AMIA 2021.
Rahmatullah I, Stephens KA, Cole AM, Hartzler AL. Primary Care Providers’ Needs for Usable Clinical Prediction Rule Presentations. Poster accepted for AMIA 2021.
UPCOMING FINAL EXAM
Jared Erwin
Wednesday, June 30, 2021; 3:00 PM
Zoom: https://washington.zoom.us/j/96899262977
Title: Genetic Association to Adverse Drug Events in the eMERGE Pharmacogenomics Cohort
Abstract: Adverse drug events (ADEs) are a serious problem causing over 100,000 hospitalizations in the U.S. annually. One key component in the response to a drug is our genetic variation. Identifying and using genetic information to avoid ADEs is an already proven method that needs further expansion. The eMERGE PGx project collected electronic medical records (EMR) along with targeted DNA variant data in order to create a useful dataset for pharmacogenetic studies. In this research, an automated approach to identify potential adverse drug events (ADE) in the eMERGE PGx cohort is presented. Data from the EMR is examined through the lens of a database of known adverse drug events: the Drug Evidence Base. Diagnosis codes that were known to be adverse events and appeared in a participant’s medical record following a medication order were labeled as a potential ADE. These potential ADEs were used as phenotypes for genetic associations tests at the single variant, gene, and gene-set level. The results were two findings of two single variants, 10 genes and one gene set having a significant association with one more adverse drug events. These results add to the body of knowledge that continues to grow around variation in drug response.
Committee: David Crosslin-Chair, John Gennari, Gail Jarvik, Ali Shojaie
OTHER
Ronald W. Buie has completed his Master of Public Health, Health Systems and Policy . His thesis is titled, “Provider Perspectives on the Coordination of Care for Spinal Cord Injured Veterans”. This work is an analysis of a year of interviews with clinical and administrative leaders revealing gaps between policy, infrastructure, and collaborations with non VHA services within the VHA’s Spinal Cord Injured System of Care. Ron continues to pursue is PhD in Biomedical and Health Informatics under Annie Chen.
June 14-June 18, 2021
PUBLICATIONS AND PRESENTATIONS
UW-BioNLP group AMIA 2021 – Accepted papers and posters
Full papers:
Lybarger K, Mabrey L, Thau M, Bhatraju PK, Wurfel M, Yetisgen M. Identifying ARDS using the Hierarchical Attention Network with Sentence Objectives Framework.
Lau W, Altonen L, Gunn, M, Yetisgen M. Automatic Assignment of Radiology Examination Protocols Using Pre-trained Language Models with Knowledge Distillation.
Posters:
Lau W, Wayne D, Lewis S, Uzuner O, Gunn M, Yetisgen M. A New Corpus for Clinical Findings in Radiology Reports.
Lybarger K, Qiao E, Yetisgen M. An exploration of information extraction models on transcribed patient visits.
Chakraborty A, Lybarger K, Long D, Shah VO, Yetisgen M. Automatic Detection of Surgical Site Infections Using EHR data.
Turner GK, Yetisgen M. Comparison of Different Phrase Chunking Approaches on Medical Concept Coverage in Clinical Text.
Welsh C, Nickerson DP, Rampadarath A, Neal ML, Sauro HM and Gennari JH (2021). LibOmexMeta: Enabling semantic annotation of models to support FAIR principles. Bioinformatics, in press.
Blinov ML, Gennari JH, Karr JR, Moraru II, Nickerson DP, and Sauro HM (2021). Practical Resources for Enhancing the Reproducibility of Mechanistic Modeling in Systems Biology. Current Opinion in Systems Biology, in press.
AMIA 2021:
Dr. Uba Backonja and Dr. Anne Turner will present a system demonstration on November 2nd at 8:30 (S53) showing SHARE-NW: Solutions in Health Analytics for Rural Equity across the Northwest, a user-centered designed website with dashboard and trainings to support rural public health equity (launching August 2021; https://www.nwcphp.org/research/projects/share-nw).
Dr. Uba Backonja and Dr. Janice Sabin are part of a team running a preconference workshop on re: bias in informatics that will be held October 30, 2021 from 1:00 PM to 4:30 PM.
Technology to Support Collaborative Dissemination of Research with Alaska Native Communities by Lisa Dirks and Wanda Pratt
Broken down by bias: Healthcare biases experienced by BIPOC and LGBTQ+ patients by Reggie Casanova-Perez, Calvin Apodaca, Emily Bascom, Deepthi Mohanraj, Cezanne Lane, Drishti Vidyarthi, Erin Beneteau, Janice Sabin, Wanda Pratt, Nadir Weibel, and Andrea Hartzler
Children’s Designs for the Future of Telehealth by Erin Beneteau, Ann Paradiso, and Wanda Pratt
June 7-June 11, 2021
NEWS
Sarah Stansfield, NLM Postdoctoral Fellow has accepted a new position as Postdoctoral Research Fellow in Mathematical Modeling at the Fred Hutch, in their Vaccine and Infectious Disease Division, working with Dr. Dobromir Dimitrov. She will begin her new position Monday, June 14, 2021.
Meliha Yetisgen & Martin Gunn’s NCI funded R01 on large scale clinical and economic impact analysis of incidental findings in radiology reports was on UW Medicine – Newsroom:
https://newsroom.uw.edu/postscript/radiology-study-seeks-fuller-picture-incidentalomas
Meliha Yetisgen received funding for her new project titled “Extraction of Symptom Burden from Clinical Narratives of Cancer Patients using Natural Language Processing” from NCI.
PUBLICATIONS AND PRESENTATIONS
X. Zhang, G. Luo. Ranking Rule-Based Automatic Explanations for Machine Learning Predictions on Asthma Hospital Encounters in Asthma Patients: Secondary Analysis. JMIR Medical Informatics, 2021.
Korngiebel DM, Mooney SD. Considering the possibilities and pitfalls of Generative Pre-trained Transformer 3 (GPT-3) in healthcare delivery. NPJ Digit Med. 2021 Jun 3;4(1):93. doi: 10.1038/s41746-021-00464-x. PMID: 34083689; PMCID: PMC8175735.
https://www.nature.com/articles/s41746-021-00464-x
Dr. Thomas Payne, Professor, UW Department of Medicine; Adjunct Professor, Biomedical Informatics and Medical Education
“We have the means to prevent cancer and to detect it early. But we’re not fully using the resources we have.”
May 31-June 4, 2021
NEWS
Andrea Hartzler was elected to serve a 3-year term on the Council of Academic Affairs for the UW School of Medicine.
The following faculty or staff (PI or collaborator) received a Garvey Institute for Brain Health Solutions Innovation Grant:
Biomedical Informatics and Medical Education
Trevor Cohen, MBChB, PhD, FACMI
Sean Mooney, PhD, FACMI
Andrea Hartzler, PhD
Bill Lober, MD, MS
The following BHI Students contributed to the publications:
Hannah Burkhardt
Jake Portanova
Nic Dobbins
Xiruo Ding
List of projects and descriptions: https://gibhs.psychiatry.uw.edu/current-projects/
UW Medicine News Link: https://newsroom.uw.edu/news/garvey-institute-gives-13-million-advance-brain-health
PUBLICATIONS AND PRESENTATIONS
Augmenting aer2vec: Enriching Distributed Representations of Adverse Event Report Data with Orthographic and Lexical Information, Xiruo Ding, Justin Mower, Devika Subramanian, and Trevor Cohen. Accepted: JBI
Behavioral Activation and Depression Symptomatology: Longitudinal Assessment of Linguistic Indicators in Text-based Therapy Sessions, Hannah A Burkhardt, George S Alexopoulos, Michael D Pullmann; Thomas D Hull; Patricia A Areán, Trevor Cohen. Accepted: JMIR.
UW Undergraduate Research Symposium presentations (5/21/2021):
Fields, S., and Oei, C. Automatically identifying people and exploring social relations in the Svoboda Diaries. (Mentored by Dr. Annie Chen.)
Hallinan, S., Buie, R. W., Conway, M., Chen, A. T., Park, A. Understanding the public response to the coronavirus pandemic through topic modeling.
Papers:
Chen, A. T. (accepted). Affect, cognition, and information behavior in the context of fibromyalgia. Journal of the Association for Information Science and Technology.
Du, J., Yuen, C., Slaughter, M., Chen, A. T. (accepted). The influence of familiarity with digital tools on user experience and perspective in the digital humanities. Annual meeting of the Association for Information Science and Technology (ASIS&T) 2021. October 30 – November 2, 2021.
Panel presentation:
Valdez, R., Chen, A. T., Hampton, A. J., Madathil, K. C., Papautsky, E. L., Rogers, C. C. (accepted). Leveraging Social Media for Human Factors Research in Health Care. Panel presentation at Human Factors and Ergonomics Society Annual Meeting (HFESAM) 2021. October 4-7, 2021. Baltimore, MD.
Tutorial:
Chen, A. T., Cole, C., Fields, S., Perkins, A., Oei, C., Kuru, S. S. (2021). Introduction to network analysis for literary and historical research. Tutorial presented at Canadian Society for Digital Humanities/société canadienne des humanités numériques (CSDH/SCHN) 2021. May 30 – June 3, 2021.
language processing (NLP) methods to create novel measures of expressed emotional experience and mentalizing from transcribed speech responses of two streaming-based tasks. Furthermore, we propose to use these measures to evaluate the effectiveness of oxytocin for the abstraction of an overall pipeline for precision psychiatry. We believe the creation of this methodology will allow for a new approach to the diagnosis, monitoring, and treatment of people with schizophrenia that may be generalizable to other mental health issues.
to elucidate confounders for EHR-based pharmacovigilance, Journal of Biomedical Informatics, Volume 117, 2021