News and Events | Biomedical Informatics and Medical Education

Chair’s Message

pth-use-this-one 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 28 – December 2, 2022

UPCOMING LECTURES AND SEMINARS
BIME 590: Thursday, December 8^th – 11-11:50 am
Title: Putting Principles into Practice: Supporting responsible innovation through the AI review process at Google
https://washington.zoom.us/my/peter.th [washington.zoom.us]

Abstract: As an Ethical, Legal, and Social Implications (ELSI) Scholar and AI Ethicist at Google, Dr. Korngiebel will present on how AI reviews are approached in the context of Google’s AI Principles. Starting with a grounding in the main ethical philosophical underpinnings for the AI Principles, the presentation will include how harms and benefits relate to one another, thoughts on process and product examples, and will also touch upon value trade-offs and features that receive special scrutiny.

Presenter bio: Diane M. Korngiebel has been an ELSI (ethical, legal, and social implications) Scholar on the Responsible Innovation Team at Google since May 2022. Dr. Korngiebel started with Google in Oct. 2021 as a Bioethicist on the Google Bioethics team and was a Research Scholar at The Hastings Center, an independent, non-partisan, non-profit bioethics center in Garrison, New York the previous year. Before joining The Hastings Center in 2020, she was an Associate Professor in the Department of Biomedical Informatics and Medical Education and an adjunct Associate Professor in the Department of Bioethics and Humanities at the University of Washington School of Medicine in Seattle; she maintains affiliate faculty status in both UW departments.

Her interests include the ethics of using AI for health and wellness applications, broadly construed, and the potential and limitations of Big Data science, and appropriate (and inappropriate) design and deployment of digital health applications.

Dr. Korngiebel’s work has appeared in the American Journal of Public Health, Nature: Genetics in Medicine, NPJ Digital Medicine, and PLoS Genetics. She was recently the principal investigator on a grant funded by the National Human Genome Research Institute and the National Institutes of Health’s Office of the Director on developing an ethics framework to guide biomedical data scientists constructing data models and algorithms.

UPCOMING FINAL EXAMS – tomorrow (12/2)!
Title: Needs-driven, utility-oriented, standards-based operationalization of artificial intelligence for clinical decision support: a framework with application to suicide prevention
Student: Hannah Burkhardt
Date/Time: Friday, December 2, 2022, 1-3 pm PST
Location: 750 Republican Street, Building E, 1st Floor [google.com], Room E130B
Zoom: https://washington.zoom.us/my/cohenta [washington.zoom.us]

Abstract: While artificial intelligence (AI) technologies increasingly permeate our daily lives, the adoption and impact of AI have fallen short of expectations in healthcare. The challenges of operationalizing AI in healthcare are complex and include interaction design (e.g., poorly designed user interfaces), model formulation (e.g. algorithmic bias, limited practical utility, trustworthiness or interpretability), and workflow context (e.g. a lack of integration into existing workflows; limited model portability). Critically, AI projects must demonstrate overall utility, balancing their costs with the benefits they confer. To achieve this utility informatics efforts are needed before, during, and after predictive model development, to mediate effective, sustainable, and interoperable AI deployment to support clinical workflows.
In this work, I investigated how human-centered design methods, needs-driven model development, utility-oriented evaluation methods, and standards-based software design can be leveraged collectively to address the unique challenges faced by healthcare AI, and achieve clinically impactful AI implementations. The two key contributions resulting from it are (1) a generalizable framework for the needs-driven operationalization of AI to support healthcare workflows and clinical decision making, and (2) the application of this framework to conceive, implement and evaluate AI support for suicide prevention.
To apply this framework, I used human-centered design methods to assess technological support needs for Caring Contacts, an evidence-based suicide prevention intervention, revealing opportunities for AI-based cognitive support. Using neural transfer learning from publicly available social media data, I developed accurate natural language processing models for risk-based prioritization of patient messages. Through utility-oriented evaluation metrics, I demonstrated that this model has the potential to positively impact clinical practice. Incorporating this model, I devised a standards-based, reusable, interoperable, workflow-integrated information system for cognitive support of Caring Contacts. I developed blueprints for a FHIR data representation model and information system architecture, and implemented and shared an open-source software application.
Together, this work contributes towards bridging the historical implementation gap by furthering methods for design, development, and delivery of AI-supported interventions, and by guiding future attempts to realize the potential of AI in clinical settings.
——————————————————————————————————————
Title: Enhancing Empathy in Text-Based Teletherapy with Emotional State Inference
Student: William Kearns
Date/Time: Friday, December 2, 2022, 9:30-11:30 am PST
Location: Orin Smith Auditorium, South Lake Union, 850 Republican Street, Building C
Zoom: https://washington.zoom.us/my/cohenta [washington.zoom.us]

Abstract: Over half of the U.S. population lives in an area without adequate access to mental health care and the unmet demand for mental health services has shifted to care providers who have not been trained to provide mental health support. This work represents a step toward addressing this supply-demand imbalance by applying recent advances in conversational AI.
The central hypothesis of this work is that both the quality and efficiency of text-based teletherapy can be improved through conversational AI. This was evaluated using mixed-methods approaches with three aims: (1) I explored the ability of computational methods to infer high-fidelity representations of self-reported emotional states, (2) I evaluated these representations as features to predict empathetic responses, (3) I piloted this system as a component of an AI-augmented teletherapy platform for the delivery of problem-solving therapy by nurses and psychologists.
(1) Prior to this work, emotion recognition from conversation (ERC) methods had only been tested on crowdsourced data labels that (a) were inferred by annotators rather than self-described, and (b) did not cover the breadth of emotional states experienced as a result of daily events. This prior work was insufficient to assess the applicability of these methods to characterize self-reported emotional states in the context of check-ins where the emotional states may not be explicitly expressed. To address this gap, I evaluated emotion detection and emotional state inference methods on event-emotional state pairs collected through a daily journaling exercise delivered by SMS. I found that emotional state inference methods improved performance on the task of predicting reported emotions by 71.3% relative to emotion detection methods.
(2) The messages from the daily journaling exercise were labeled by experts based on how they would respond empathetically to them in the context of teletherapy. I found that the addition of emotional state inferences to these messages improved the performance of models on the task of predicting these labels, which in turn indicate appropriate expert-authored empathetic responses to a given utterance.
(3) Quantitative results of the AI-augmented provider platform indicate that the system decreased response times by (+29.34%**; p=0.002), tripled empathetic response accuracy (+200%***; p=0.0001), and increased goal recommendation accuracy (+66.67%**; p=0.001). Structured qualitative interviews indicated that the care providers who used the system felt it would make providing therapy more efficient, lower cognitive load, and be accessible to care providers without mental health training.

UPCOMING GENERAL EXAM
December 5, 2022 – 2-4 pm
Title: Performance and organizational characteristics of analytics teams in healthcare and population health
Student: Ron Buie
Location: Please join us at South Lake Union, 850 Republican St, Building C, Room 123A
Zoom: https://washington.zoom.us/j/96299494457

Abstract: Business analytics (BA) and business analytics systems (BAS) constitute a family of skills, tools, and processes that help an organization study and communicate information about itself. As defined, BASs have most commonly been used for the collection, management, and presentation of data as it relates to current operations (transactional BAS). However, increasingly, organizations are deploying BASs to identify novel information about the business (change recommending BAS).
As an industry, healthcare has only recently, with the passing of the Affordable Care Act, significantly invested in the infrastructure to collect and utilize data at a scale and fineness necessary for large scale BA. Additionally, the use of these systems has not evolved far beyond their capabilities as a transactional BAS.
There are limited resources available to assist organizations in formally understanding BAS activities and the teams that engage them. Formal descriptions are narrow, often focused on the use of information technology, user acceptance of analytics resources, or high-level descriptions of analytics processes. Furthermore, the healthcare industry presents a new environment with unique cultural, regulatory, and economic hurdles.
In order to improve future evaluation and management of these systems, I intend to identify frameworks and models useful for describing the BAS within the context of organizations (A1) and describe the activities, tools, and context of BASs within health care and population health settings (A2). This research can pave the way for a study of how resultant frameworks are used by different organizations across healthcare and population health, and the use of quantitative approaches to evaluating and monitoring BASs.

ANNOUNCEMENTS
UW is #6 in the World!
The University of Washington rose from No. 7 to No. 6 on the U.S. News & World Report’s Best Global Universities rankings, released this week. The UW maintained its No. 2 ranking among U.S. public institutions. U.S. News also ranked several subjects, and the UW placed in the top 10 in 10 subject areas, including immunology (No. 4), molecular biology and genetics (No. 5) and clinical medicine (No. 6).
See the full report here.

Dr. Reza Sadeghian (Class of 2019) currently holds a position as Chief Medical Informatics Officer (CMIO) at Hunterdon Medical Center in Flemington, NJ. He received a CPE ( Certified Physician Executive ) credential from American Association for Physician Leadership ( AAPL) this month which is a crucial requirement for the path to receive their fellow status (FAAPL). He also became board eligible with the American College of Healthcare Executives (ACHE) to sit for their board of governor fellow exam. With these credentials, his CI fellowship training at UW, and extensive work experience, he is aiming to get accepted into Yale GELP program next year. Please feel free to connect with him as he always welcomes UW CI fellows and is willing to assist and share his journey to becoming the Chief Medical Information Officer.
His personal page Link
His Linkedin page Link

November 14 – November 18, 2022

UPCOMING LECTURES AND SEMINARS

BIME 590: Thursday, December 1^st – 11-11:50 am
Presenter: Sean Mooney, PhD, FACMI
https://washington.zoom.us/my/peter.th [washington.zoom.us]

PUBLICATIONS & PRESENTATIONS
Annie T. Chen, Uba Backonja, Kenrick D. Cato. Integrating health disparities content into health informatics courses: a cross-sectional survey study and recommendations. Accepted for publication in JAMIA Open.

UPCOMING FINAL EXAMS
Title: Deriving a sociotechnical model for discovery in a genomics-enabled learning health system
Student: Kathleen Muenzen Ferar
Date/Time: Wednesday, November 30th, 2022, 3-5 pm PST
Location: 750 Republican Street, Building E, 1st Floor [google.com], Room E130B
Zoom: https://washington.zoom.us/j/98238845441 [washington.zoom.us]

Abstract: Recent advances in genetic sequencing technologies and analysis tools have made genomic data widely available for medical research. Despite the expectation that genomic data will revolutionize medicine, there exist major evidence gaps in demonstrating the utility of genomic discovery for improving patient outcomes and increasing healthcare efficiency. 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 barriers and enablers of clinical genomics discovery can be identified and organized. Furthermore, drawing on experiences from clinical genomics research consortia like the Clinical Sequence Evidence-Generating Research (CSER) Consortium and Electronic Medical Records and Genomics (eMERGE) Network can help identify requirements that are unique to genomics discovery initiatives that straddle the research-clinical boundary. In this work, we sought to derive a sociotechnical model for clinical genomics discovery in a genomics enabled LHS (GLHS). We first identified themes and recommendations from the clinical genomics research data integration process in the CSER consortium, and found that the social processes involved in data coordination are tantamount to the informatics tools used to facilitate those processes (Aim 1). We then explored medical geneticist perspectives on clinical genomics discovery by interviewing 20 board-certified medical geneticists in CSER, eMERGE and the University of Washington medical system (Aim 2). Using constructivist grounded theory methods, we developed a preliminary model of GLHS discovery that utilizes the concepts of representation, responsibility, risks & benefits, relationships, and resources (“5R”) to explain negotiations and limits involved in clinical-research integration in genomics. To demonstrate the utility of merging Electronic Health Record (EHR) data with genomic data for discovery, we then conducted a logistic regression-based genome-wide risk assessment for Clostridioides difficile infection (CDI) using merged genetic and EHR data from 12 clinical sites in the eMERGE Network, and found a strong gene-disease association in the HLA-DRB locus (P=8.06 x 10^-14) that predisposes carriers to CDI (Aim 3). Finally, we conducted a systematic literature review of proposed enablers of clinical genomics discovery and synthesized the results from the literature review and Aim 1 with the a priori framework developed in Aim 2 using best-fit framework synthesis (BFFS) (Aim 4). We found that the vast majority of themes identified in the literature were accommodated by the a priori framework, suggesting that the 5R model of GLHS discovery is a reasonable representation of processes involved in learning healthcare. An enhanced 5R sociotechnical model was developed to represent how the negotiation tools identified in the literature could be used to facilitate virtuous cycles of learning in clinical genomics research.

ANNOUNCEMENTS
The paper “‘There’s a problem, now what’s the solution?’: suggestions for technologies to support the menopausal transition from individuals experiencing menopause and healthcare practitioners” by Uba Backonja (Adjunct Faculty), Lisa Taylor-Swanson (NLM Postdoc alum), Andrew Miller (NLM Postdoc alum), Shefali Haldar (PhD alum), and colleagues was a finalist for the Harriet Werley Best Nursing Informatics Paper at the AMIA 2022 Annual Symposium.

Hot Off the Press…
Cohen, TA. Patel, VL. Shortliffe, EH (eds). Intelligent Systems in Medicine and Health: The Role of AI. Springer Verlag 2022.
The book is available through Springer (https://lnkd.in/euiBRbbv [lnkd.in]), and further details are available on our textbook website (https://lnkd.in/eHdEdGVp [lnkd.in]).

Awards!
As part of Google’s growing efforts to advance health equity and mitigate health disparities, Lisa Dirks (iSchool PhD student) and Wanda Pratt received a $50,000 gift from Google to support Lisa’s thesis work on “Co-designing with Alaska Native communities to communicate equitable health research results.”

Wanda Pratt received a $10,000 gift from Google for her work related to “Gender and Health Informatics.”

November 7 – November 11, 2022

UPCOMING LECTURES AND SEMINARS

BIME 590: Thursday, November 17^th – 11-11:50 am
Title: The ‘Real World’ of Language Technology: A Case Study of Machine Translation”
https://washington.zoom.us/my/peter.th [washington.zoom.us]
Abstract: Natural language processing (NLP) technologies have transformed how people access information and communicate with one another. Machine translation, one of the most familiar language technologies, has advanced to a high level of quality for dozens of language pairs and is routinely consulted in an array of situations, from medical appointments to social media interactions. However, the overall impact of machine translation has been mixed. There are hundreds of languages for which there are insufficient digital resources to sustain quality machine translation, and errors abound even in translations for so-called “high resource” language pairs, leading to critical misunderstandings. In this talk, I trace some of these issues to the social and political contexts that have shaped the linguistic data landscape and the situations in which machine translation systems are used. I discuss the role of design in addressing some of these issues.
Presenter Bio: Amandalynne Paullada, MA, PhD, is an NLM postdoctoral fellow in the department of Biomedical Informatics and Medical Education at the University of Washington School of Medicine. She completed her PhD in computational linguistics at UW in 2021. Her doctoral work included an examination of the societal impacts of natural language processing technologies, focusing on data collection practices and the design process, and also presented results of a study on the effect of incorporating linguistic structure in computational representations of biomedical relationships. Her ongoing work is concerned with ethical issues in data practices and applications for language technology in healthcare with a focus on justice.

PUBLICATIONS & PRESENTATIONS
NR Johnson, K Dzara, A Pelletier, and IT Goldfarb. 2022. “Medical Students’ Intention to Change After Receiving Formative Feedback: Employing Social Cognitive Theories of Behavior.” Medical Science Educator. https://link.springer.com/article/10.1007/s40670-022-01668-w [link.springer.com]

UPCOMING GENERAL EXAM
November 14^th, 2022 – 3 – 5 pm
Title: Explainable query generation for cohort discovery and biomedical reasoning using natural language.
Student: Nic Dobbins
Location: Please join us at South Lake Union, 850 Republican St, Building C, Room 123A or on Zoom.
Abstract: Clinical trials serve a critical role in the generation of medical evidence and progress in biomedical research. In order to identify potential participants, investigators publish eligibility criteria, such as certain conditions, treatments, or laboratory test results. Recruitment of participants remains, however, a major barrier to successful trial completion, and manual chart review of hundreds or thousands of patients to determine a candidate pool can be prohibitively labor- and time-intensive. While cohort discovery tools such as Leaf or i2b2 can serve to assist in finding participants meeting eligibility criteria, such tools nonetheless often have significant learning curves. Moreover, certain complex queries may simply be impossible due to structural limitations on the types of possible queries presented in these tools. An alternative approach is the use of natural language processing (NLP) to automatically analyze eligibility criteria and generate queries. Such approaches have the advantage of leveraging existing eligibility criteria composed in a free-text format researchers are already familiar with. The goal of this project is the development of a cohort discovery tool called LeafAI. In Aim 1, we create a gold-standard annotated corpus of eligibility criteria. In Aim 2, we develop methods for generating data model-agnostic SQL queries and multi-hop biomedical reasoning using a natural language interface with near-human performance. In Aim 3, we develop an interactive chatbot-like web application to enable users to dynamically query clinical databases for cohort discovery using natural language.

ANNOUNCEMENTS
AMIA Best Paper Award
Wanda Pratt and iSchool PhD student Hyeyoung Ryu won an AMIA Best Paper Award at the Annual AMIA Symposium. The award is for work that honors “Samantha Adams’s work at the intersection of informatics and ethics.”
Hyeyoung Ryu and Wanda Pratt. Microaggression clues from social media: revealing and counteracting the suppression of women’s health care, Journal of the American Medical Informatics Association, 29 (2), 257-270. https://doi.org/10.1093/jamia/ocab208 [doi.org]

AMIA Distinguished Paper Award
Hannah Burkhardt won the Distinguished Paper Award at AMIA this week for the following paper:
Hannah A. Burkhardt, Megan Laine, Amanda Kerbrat, Katherine A. Comtois, Trevor Cohen, Andrea Hartzler. Identifying opportunities for informatics-supported suicide prevention: the case of Caring Contacts.
Mike Leu Featured
Learn more about Mike Leu and the new Division of Clinical Informatics. He is featured in The Huddle newsletter here. Warning: there is an extremely cute dog picture included!

CLIME Conversation Café
Recognizing Anxiety in Learners
Shannon Uffenbeck, PhD, Assistant Professor, Alaska Academic Support Coordinator
December 1, 2022, 12:00 pm – 1:00 pm (PT)
Zoom (Online) – Register: https://bit.ly/3Vfc8hr [bit.ly]

October 31 – November 4, 2022

UPCOMING LECTURES AND SEMINARS

BIME 590: Thursday, November 10^th – 11-11:50 am
Title: Patient profiles to target engagement and health care delivery strategies
https://washington.zoom.us/my/peter.th [washington.zoom.us]
Presenter: Casey Overby Taylor, Ph.D.
Associate Professor of Medicine and Biomedical Engineering
Division of General Internal Medicine, Biomedical Informatics & Data Science Section
Interim Associate Director, Institute for Computational Medicine
Johns Hopkins University School of Medicine

Alumni Panel November 9th
Please join us for an “Alumni panel” of local BIME PhD Alumni on Wed, Nov 9th at 10:30am (Room 235, in the new Health Sciences Education Bldg). Each alumni will comment on the aspects of the BIME program that helped (or didn’t help!) on their career path to date.
Panel Members:

- Tim Bergquist (2021), Research Scientist at Sage Bionetworks
- Ryan James (2019), CEO Dopl Technologies
- Ross Lordon (2019), UX Researcher at Microsoft
- Lauren Snyder (2021), Senior Program Officer at The Gates Foundation
- Lucy Lu Wang (2019), Assistant Professor at the UW iSchool

(BIME graduation dates indicated in parentheses)
The goal is to showcase the variety of careers one can pursue with a PhD in BHI, and allow current students the chance to ask questions of our recent graduates.

PUBLICATIONS & PRESENTATIONS
Jablonowski K, Hooker B. Delayed Vigilance: A Comment on Myocarditis in Association with the COVID-19 Injections. International Journal of Vaccine Theory, Practice, and Research 2(2), October17, 2022 p651.1. https://ijvtpr.com/index.php/IJVTPR/article/view/61/108 [ijvtpr.com]

October 24 – 28, 2022

UPCOMING LECTURES AND SEMINARS

BIME 590: Thursday, November 3^rd – 11-11:50 am
Title: Reading and writing academic papers: citations are mini-summaries with a view
https://washington.zoom.us/my/peter.th [washington.zoom.us]

Presenter Bio: Lucy Vanderwende, Ph.D., is Affiliate Associate Faculty at University of Washington Department of Biomedical Health Informatics, a member of the UW BioNLP group, who are using NLP technology to extract critical information from patient reports. She holds a Ph.D. in Computational Linguistics from Georgetown University. Lucy worked at Microsoft Research, Redmond, WA, from 1992 – 2018. She first was a member of the 7 person team who created the Microsoft Grammar Checker, a product that has impacted people all over the world. Her work in Natural Language Processing since 1998 includes research in Common Sense Reasoning and Knowledge Acquisition, in addition to Information Retrieval, Summarization, Opinion Mining, Question Generation, and Knowledge Base Population. As a member of BIME, Lucy collaborates with Meliha Yetisgen on the definition of schemas for extracting information from Electronic Health Records. Interests include automated acquisition of semantic knowledge; information extraction from clinical records; robust, broad-coverage language analysis.

Abstract: This talk will take time to reflect on how we read and write research papers. The pace of research and electronic publishing gives us access to large numbers of papers in any field, yet makes it more challenging to assess the quality of a specific paper and more challenging to find the correct works to support or refute findings. This talk will show how we can use the sentences that describe a referenced paper as a retrospective abstract, one that authors may not have anticipated at the moment of writing. I will talk about a dataset we defined as a task for summarization at the Text Analysis Conference, sponsored by NIST, enabling computational systems to identify these citing sentences and abstracts automatically. This talk will highlight the importance of writing good citing sentences as an author and the importance of close-reading citing sentences to discern any opinions the author may have about the referenced paper.

UPCOMING GENERAL EXAM

November 14th, 2022 – 3-5 pm

Title: Explainable query generation for cohort discovery and biomedical reasoning using natural language.
Student: Nic Dobbins

Abstract: Clinical trials serve a critical role in the generation of medical evidence and progress in biomedical research. In order to identify potential participants, investigators publish eligibility criteria, such as certain conditions, treatments, or laboratory test results. Recruitment of participants remains, however, a major barrier to successful trial completion, and manual chart review of hundreds or thousands of patients to determine a candidate pool can be prohibitively labor- and time-intensive. While cohort discovery tools such as Leaf or i2b2 can serve to assist in finding participants meeting eligibility criteria, such tools nonetheless often have significant learning curves. Moreover, certain complex queries may simply be impossible due to structural limitations on the types of possible queries presented in these tools. An alternative approach is the use of natural language processing (NLP) to automatically analyze eligibility criteria and generate queries. Such approaches have the advantage of leveraging existing eligibility criteria composed in a free-text format researchers are already familiar with. The goal of this project is the development of a cohort discovery tool called LeafAI. In Aim 1, we create a gold-standard annotated corpus of eligibility criteria. In Aim 2, we develop methods for generating data model-agnostic SQL queries and multi-hop biomedical reasoning using a natural language interface with near-human performance. In Aim 3, we develop an interactive chatbot-like web application to enable users to dynamically query clinical databases for cohort discovery using natural language.

Location: Please join us at South Lake Union, 850 Republican St, Building C, Room 123A or on Zoom.

ANNOUNCEMENTS

Applications Are Now Being Accepted for the TL1 Translational Research Program 2023 Cohort!

The Institute of Translational Health Sciences TL1 program [iths.org], is a one-year NIH funded program that offers rigorous training in clinical and translational research for pre-doctoral students in an interdisciplinary cohort environment. This program provides funding, mentorship, and training. While in the program, participants will receive a stipend, research funds and tuition support.

We would like to encourage applicants interested in all types of research, including patient-oriented research, translational research, small- and large-scale clinical investigation and trials, epidemiologic and natural history studies, clinical and biomedical informatics, health services research, and health behavior research to apply. The application deadline is December 16, 2022. Learn more and apply on the ITHS website [iths.org].

We’ll be having a few information sessions for anyone interested in attending and learning more about the program.

- - Wednesday, October 26^th, 2022 from 4-4:30PM (PST); Register Here [washington.zoom.us]
  - Thursday, November 3^rd, 2022 from 12-12:30PM (PST);Register Here [washington.zoom.us]

For questions, please contact Milu Worku at mworku@uw.edu.

October 17 – 21, 2022

UPCOMING LECTURES AND SEMINARS

BIME 590: Thursday, October 27 – 11-11:50 am
Title: Inferring Race and Ethnicity from Clinical Notes: Annotation, Model Auditing, and Ethical Implications
https://washington.zoom.us/my/peter.th [washington.zoom.us]

Presenter Bio: Oliver J. Bear Don’t Walk IV is a citizen of the Apsáalooke Nation in present day Montana and is a Postdoctoral Scholar and AIM-AHEAD Research Fellow at the University of Washington in Biomedical Informatics and Medical Education. They completed their PhD in biomedical informatics at Columbia University and received their bachelors in Math and Computational Science from Stanford University. Oliver’s research is at the intersection of clinical natural language processing (NLP), fairness, and ethics. His thesis focused on the technical and ethical aspects of extracting race and ethnicity from clinical notes and identifying biased associations in NLP models trained to extract this information. Oliver is thankful for the community support which has brought him this far, and as such Oliver pays it forward through teaching and mentorship positions such as serving as an organizer and faculty for IndigiData and a co-chair for the American Medical Informatics Association’s Diversity, Equity, and Inclusion Committee.

Abstract: Many areas of clinical informatics research rely on accurate and complete race and ethnicity (RE) patient information. Structured data in the electronic health record (EHR) is an easily accessible source for patient-level information, however RE information is often missing or inaccurate in structured EHR data. Clinical notes provide a rich source of information that can be leveraged to increase granularity and/or recover RE information missing in structured data through state-of-the-art clinical natural language processing (NLP) approaches. However, NLP has also been shown to inherit, exacerbate, and create new biased and harmful associations, especially in modern deep learning approaches. In this talk, I will present results from my dissertation exploring the relationships between explicit mentions of RE and RE inferences in clinical text made by clinicians. I will also present results from? an audit for bias in deep NLP models trained to identify RE in clinical text. This work is underpinned by a (soon to be) publicly available gold-standard corpus with annotations for information related to RE and RE labels. These gold-standard annotations allowed us to explore what kinds of information are used to describe RE categories and what kinds of associations deep NLP models learn when identifying RE in clinical text.

PUBLICATIONS & PRESENTATIONS

Nguemeni Tiako MJ, Rahman F, Sabin J, Black A, Boatright D and Genao I (2022). Piloting web-based structural competency modules among internal medicine residents and graduate students in public health. Front. Public Health10:901523. October 14, 2022.

ANNOUNCEMENTS

Janice Sabin is Co-Investigator on a new NIH grant: “PAINED: Project Addressing INequities in the Emergency Department.” Principal Investigator: Monika Goyal, MD, MSCE, Children’s National Hospital Research Institute, Washington, DC.

October 10 – 14, 2022

UPCOMING LECTURES AND SEMINARS

BIME 590: Thursday, October 20 – 11-11:50 am
Title: The CORES Story: Creating Something New & Needed
https://washington.zoom.us/my/peter.th [washington.zoom.us]

Abstract: Health systems in the United States spent $14.5 billion on Electronic Health Records systems in 2019, and are expected to spend $19.9 billion in 2024. Many clinical users of these systems do not feel that they are getting good usability value for that much spending. What kinds of things could be wrong with software systems that have so much money invested in them yet the users would feel they offer poor usability? In this talk, you’ll learn about the difference between design and user experience. You’ll see an example of an EHR quality improvement project that became academic research. You’ll be able to explain the real goals of record-keeping in medicine, from a clinician’s point of view. You’ll be able to describe one model of taking academic innovation to commercial product.

Speaker Bio: Erik G. Van Eaton, MD, FACS, is an Associate Professor of Surgery and Surgical Critical Care, and an Adjunct Associate Professor of Biomedical Informatics and Medical Education at the University of Washington and Harborview Medical Centers, in Seattle, Washington. Dr. Van Eaton specializes in Trauma Surgery, Surgical Critical Care, Emergency General Surgery, Acute Care Surgery, and General Surgery. As part of his General Surgery practice, Dr. Van Eaton’s clinical focus is complex hernia operations, surgical treatment of fistula, intestinal surgery, gallbladder surgery, and reconstructive abdominal procedures after recovery from major trauma A trained medical informatics scientist, Dr. Van Eaton studies how Electronic Health Record (EHR)-embedded software can support core clinical workflows. Research avenues include observational studies of EHR use in physician handoffs, subjective evaluations of EHR-related burnout and stress, and impact of EHR-embedded software and mobile apps on quality metrics. Dr. Van Eaton builds collaborative relationships among successful clinical informatics projects health systems throughout the world to bring high-performance clinical information management to bedside decisions. As an NIH NLM Fellow at UW, Dr. Van Eaton developed a computerized rounding and sign-out software system that changed the ways in which residents communicate about, and manage “ownership” of, their patients. This work led to a spin-out healthcare information technology company from the University of Washington in 2011 called TransformativeMed Inc.

PUBLICATIONS & PRESENTATIONS

Jim Phuong was invited to participate in the plenary session of the International Academy of Health Sciences Informatics (IAHSI), the Honorific International Society of AMIA, at the 2022 AMIA Annual Meeting. This year’s plenary session focuses on the topic of informatics and climate change. Jim will present an overview of his latest JAMIA publication.

Phuong J, Riches NO, Calzoni L, Datta G, Duran D, Lin AY, Singh RP, Solomonides AE, Whysel NY, Kavuluru R. Toward informatics-enabled preparedness for natural hazards to minimize health impacts of climate change. J Am Med Inform Assoc. 2022 Sep 12:ocac162. doi: 10.1093/jamia/ocac162 [10.1093]. Epub ahead of print. PMID: 36094062.

October 3 – 7, 2022

UPCOMING LECTURES AND SEMINARS

BIME 590
10/13/2022
Integrating longitudinal clinical phenotype and exposome into multiomics at scale
Jennifer Hadlock, MD
Assistant Professor, Director of Medical Data Science
Institute for Systems Biology

Bio: Dr. Jennifer Hadlock is an Assistant Professor and Director of Medical Data Science at the Institute for Systems Biology (ISB). Her interdisciplinary lab investigates ways to accelerate research into transitions between wellness and disease by combining machine learning, biomedical logic and knowledge graphs. Specific areas of focus include explainable decision support for immune-mediated inflammatory diseases, chronic multimorbidity and maternal/fetal health. As a Principal Investigator in the NIH NCATS Biomedical Translator Consortium, Dr. Hadlock works closely with national experts to develop data harmonization and analytic methods for sharing knowledge from real-world data at scale, while preserving patient privacy. She has also led advances in scalable machine learning for research with ISB’s affiliate partner, Providence St Joseph Health, a healthcare system that provides care through 51 hospitals and 1085 clinics across seven states, with records for over 20,000,000 patients. In addition, she supports integration of longitudinal real world data into multiomic studies. Her lab is funded by grants from NIH institutes, nonprofit organizations and industry. Prior to joining ISB, she led engineering teams at Microsoft for 15 years, including work on natural language processing (NLP), geographic information systems (GIS) and digital imaging technology, used by hundreds of millions of people worldwide. She subsequently earned an MD from the University of Washington, with a focus on care for underserved populations.

PUBLICATIONS & PRESENTATIONS
Hartzler AL, Bartlett LE, Hobler MR, Reid N, Pryor JB, Kapnadak SG, Berry DL, Lober WB, Goss CH, Ramos KJ. Take On Transplant: Human-centered design of a patient education tool to facilitate informed discussions about lung transplant among people with cystic fibrosis. J Am Med Inform Assoc. 2022 Sep 29;ocac176. doi: 10.1093/jamia/ocac176. Online ahead of print. PMID: 36173364.

Segal CD, Lober WB, Revere D, Lorigan D, Karras BT, Baseman JG. Trading-off privacy and utility: the Washington State experience assessing the performance of a public health digital exposure notification system for coronavirus disease 2019, Journal of the American Medical Informatics Association, 2022;, ocac178, https://doi.org/10.1093/jamia/ocac178

ANNOUNCEMENTS
Andrea Hartzler and Lauren Snyder were invited to present their recent JAMIA paper at the JAMIA Journal Club Webinar on Thursday Oct 13 12-1pm PST. https://amia.org/education-events/education-catalog/jamia-journal-club-webinar-october-2022 [amia.org]

September 26 – 30, 2022

UPCOMING LECTURES AND SEMINARS

BIME 590

Thursday, October 6^th

PLEASE NOTE: Class is in SLU, Building C, in the Orin Smith Auditorium (NOT in the normal room!)

Title: Comprehension, utility, and preferences of prostate cancer survivors for visual timelines of patient-reported outcomes co-designed for limited graph literacy: meters and emojis over comics

Bio: Andrea Hartzler is an Associate Professor in the Department of Biomedical Informatics and Medical Education at the University of Washington and Co-directs the Clinical Informatics and Patient-Centered Technologies Graduate program. She also serves as a clinical informatics leader in operational efforts at University of Washington Medicine. Dr. Hartzler’s research spans consumer health informatics, clinical informatics, and human-computer interaction with a focus on the human-centered design of technologies that promote health equity. Dr. Hartzler earned her PhD in Biomedical Informatics at the University of Washington in 2009. She was an Investigator at Kaiser Permanente Washington Health Research Institute before joining the faculty at University of Washington School of Medicine in 2017.

Abstract: Visual timelines of patient-reported outcomes (PRO) that help survivors track longitudinal trends in symptoms may be most effective when designed with deliberate consideration of users. Yet, graph literacy is often overlooked as a design constraint, particularly when users with limited graph literacy are not engaged in their development. Building upon our prior work co-designing longitudinal PRO visualizations for survivors with limited literacy, we engaged 18 prostate cancer survivors in a user study to assess comprehension, utility, and preferences among 4 prototypes: Meter, Words, Comic, and Emoji. This talk with cover study findings, design considerations for users with limited graph literacy, and lessons on engaging hard to reach groups in remote user testing.

————————————————————————————————-

CLIME Grand Rounds
Allowing Medicine to Flourish Again: Cultivating Professional Identity in Medical Education
Audrea Burns, PhD, Associate Professor of Pediatrics, Baylor College of Medicine
October 13, 2022
12:00pm – 1:00pm (PT)
Zoom (Online)

Register here: https://uw.cloud-cme.com/course/courseoverview?P=29&EID=8414 [uw.cloud-cme.com]

ANNOUNCEMENTS

Yong Choi, PhD, will be joining the University of Pittsburgh School of Health and Rehabilitation Sciences Department of Health Information Management as an Assistant Professor starting in October. Congratulations Yong!