News and Events
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
September 25 – September 29, 2023
UPCOMING LECTURES AND SEMINARS
BIME 590: speaker will be in-person
Presenter: Peter Tarczy-Hornoch, MD, FACMI
Thursday, October 5th – 11-11:50 am
850 Republican Street, Building C, Room 123 A/B
Zoom Information: https://washington.zoom.us/my/bime590
Title: The Department of Biomedical Informatics Vision, History, Strategic Plan and Praxis
Abstract: The presentation will provide an overview of the Department of Biomedical Informatics and Medical Education through the lens of the current strategic plan. The overview will include vision, history and evolution looking at the synergy between research, education and practice (praxis) as well as the synergy between practice, applied research and foundational research. Within each area (research, praxis, education) current activities and future plans will be reviewed.
Presenter Bio: Peter Tarczy-Hornoch has over 40 years of experience in computer science, over 35 years in biomedical informatics and 20 years in clinical medicine (pediatrics and neonatology). He has been at the University of Washington since 1992, serving as Head of the Division of Biomedical and Health Informatics since 2001 and serving as Chair of the Department of Biomedical Informatics and Medical Education since 2011. He has served in a variety of operational leadership roles in UW Medicine IT Services since 1992 in the analytics, research, and clinical computing domains, currently (since January 2022) serving as UW Medicine Chief Data Officer. He has played a leadership role in the creation and evolution of the BIME educational programs (undergraduate (joint with iSchool), MS/PhD, postdoctoral, applied clinical informatics MS (CIPCT) joint with Nursing, Clinical Informatics Fellowship joint with Family Medicine). He has led a number of key initiatives in informatics practice (praxis) including the areas of telemedicine, digital library, electronic medical records, data warehousing, analytics, clinical research informatics). His unifying theme of research over the last two decades has been data integration of electronic biomedical data (clinical, genomic and other including data) both for a) knowledge discovery and b) in order to integrate this knowledge with clinical data at the point of care for decision support. His current research focuses on a) secondary use of electronic medical record (EMR) for translational research including outcomes research, learning healthcare systems, patient accrual and biospecimen acquisition based on complex phenotypic eligibility criteria, b) the use of EMR systems for cross institutional comparative effectiveness research, and c) integration of genomic data into the EMR for clinical decision support.
UPCOMING GENERAL EXAM
Title: How to support people living with cystic fibrosis to incorporate innovative practices and treatments into their lives.
Student: Nick Reid
Date/Time: Thursday, October 12th 2023, at 8am PT
Location: SLU (Room C123A) and https://washington.zoom.us/my/andreahartzler
Abstract: Care innovations — meaning new practices and treatments — are changing how people living with cystic fibrosis (CF) live their lives. Over the last decade, the predicted life expectancy of a person living with CF has almost doubled from 36 to 65 years old, and is expected to continue rising. CF is a rare genetic disease, traditionally associated with childhood death due to progressive lung failure, requiring burdensome care routines from people living with CF and their caregivers. Many care innovations have contributed to the improvements in CF care — particularly the medication Trikafta, that can dramatically improve CF lung function, and for some reducing daily CF care routines to taking a pill twice daily. Yet, medical guidelines and knowledge about Trikafta’s efficacy are still emerging and more care innovations promise to continue changing the lives of people living with CF — and people living with CF already struggle to incorporate current CF care practices and treatments into their lives. Inductive qualitative research is needed to understand how to support people living with CF to incorporate care innovations into their lives.
Aim 1: To describe how people living with CF have incorporated care innovations, I will interview people living with CF about critical incidents related to learning about and adopting care innovations to construct a grounded theory of CF care innovation incorporation.
Aim 2: To identify preferred methods of CF care innovation incorporation, I’ll survey a sample of people living with CF about how they would prefer to learn about or adopt different care innovations.
Aim 3: To design recommendations for how to support people living with CF incorporate care innovations, I will conduct design workshops in an asynchronous remote community of people living with CF using reflective and scenario-based design activities and nominal group technique. By conducting this research, I’ll understand how to support people living with CF to incorporate care innovations, which may be transferable to other communities living with rare diseases.
ANNOUNCEMENTS
Melissa Clarkson has received funding from NIGMS to develop a derivative of the Foundational Model of Anatomy (FMA) ontology. The FMA was developed under the leadership of Cornelius Rosse and Jim Brinkley over a 20-year period. The new ontology will be called the Foundational Model of Human Anatomy (FMHA) and will provide anatomical information in a form designed to be used by the next generation of intelligent systems. As part of this project her team will also create libraries of anatomical graphics that will serve as both visual standards and components of user interfaces. Dr. Clarkson is an Assistant Professor at the University of Kentucky and alumni of the UW BHI PhD program, with dissertation work completed in the Structural Informatics Group led by Jim Brinkley.
NEWS FROM ALUMNI
Two updates from Hyunggu Jung (BHI Ph.D., 2017):
-
- He was promoted to associate professor of Computer Science & Engineering in September 2022. He is now an associate professor in the Department of Computer Science & Engineering and the Department of Artificial Intelligence at the University of Seoul. Personal website: http://hyunggujung.com/
- He directs a research group, Human-Centered Artificial Intelligence Lab (HCAIL). HCAIL pursues research in the combinations of the following directions: artificial intelligence, health informatics, and human-computer interaction. HCAIL aims to advance AI research through design and engineering to support individuals with special needs (e.g., older adults with chronic diseases, content creators with visual impairments, and model developers) across multiple domains: health, social media, and education. HCAIL website: https://hcail.uos.ac.kr/
He is interested in potential collaborations with BIME faculty, students and alumni – if interested email him at hjung@uos.ac.kr.
September 18 – September 22, 2023
UPCOMING LECTURES AND SEMINARS
BIME 590: Please join us – speaker will be in-person
Presenter: Eric Horvitz, MD PhD
Thursday, September 28th – 11-11:50 am
850 Republican Street, Building C, Room 123 A/B
Zoom Information: https://washington.zoom.us/my/bime590
Title: Large Language Models in Healthcare: Explorations, Challenges, and Directions
Abstract:
Language models with powers of generation are newcomers to the computing toolkit of bioinformatics research. Excitement about possibilities has been tempered with questions about capabilities and limitations, including concerns with accuracy and reliability. I will share reflections and examples drawn from early explorations of the power of generative language models for applications in healthcare including uses of the technology in administrative tasks, education, clinical support, and research.
Presenter Bio:
Eric Horvitz serves as Microsoft’s Chief Scientific Officer. He spearheads company-wide initiatives, navigating opportunities and challenges at the confluence of scientific frontiers, technology, and society, including strategic efforts in AI. His efforts and contributions in bioinformatics include leveraging probability and decision theory for diagnosis and decision support and uses of supervised machine learning to address key challenges in clinical care. He has been elected fellow of the American College of Medical Informatics (ACMI), National Academy of Engineering, Association of Computing Machinery, Association for the Advancement of AI (AAAI), and the American Academy of Arts and Sciences. He serves on the President’s Council of Advisors on Science and Technology (PCAST). He has served on the Board of Regents of the National Library of Medicine, and on advisory committees for the U.S. National Academies of Sciences, Engineering, and Medicine, and National Science Foundation. He earned MD and PhD degrees at Stanford University. More information and publications can be found at https://erichorvitz.com.
PUBLICATIONS & PRESENTATIONS
E. Alipour, M. Chalian, A. Pooyan, A. Azhideh, F. Shomal Zadeh, and H. Jahanian, “Automatic MRI–based rotator cuff muscle segmentation using U-Nets,” Skeletal Radiology, pp. 1–9, 2023.
Weipeng Zhou, Meliha Yetisgen, Majid Afshar, Yanjun Gao, Guergana Savova, Timothy A Miller, Improving model transferability for clinical note section classification models using continued pretraining, Journal of the American Medical Informatics Association, 2023, Online Preview.
UPCOMING GENERAL EXAM
Title: How to support people living with cystic fibrosis to incorporate innovative practices and treatments into their lives.
Student: Nick Reid
Date/Time: Thursday, October 12th 2023, at 8am PT
Location: SLU (Room C123A) and https://washington.zoom.us/my/andreahartzler
Abstract: Care innovations — meaning new practices and treatments — are changing how people living with cystic fibrosis (CF) live their lives. Over the last decade, the predicted life expectancy of a person living with CF has almost doubled from 36 to 65 years old, and is expected to continue rising. CF is a rare genetic disease, traditionally associated with childhood death due to progressive lung failure, requiring burdensome care routines from people living with CF and their caregivers. Many care innovations have contributed to the improvements in CF care — particularly the medication Trikafta, that can dramatically improve CF lung function, and for some reducing daily CF care routines to taking a pill twice daily. Yet, medical guidelines and knowledge about Trikafta’s efficacy are still emerging and more care innovations promise to continue changing the lives of people living with CF — and people living with CF already struggle to incorporate current CF care practices and treatments into their lives. Inductive qualitative research is needed to understand how to support people living with CF to incorporate care innovations into their lives.
Aim 1: To describe how people living with CF have incorporated care innovations, I will interview people living with CF about critical incidents related to learning about and adopting care innovations to construct a grounded theory of CF care innovation incorporation.
Aim 2: To identify preferred methods of CF care innovation incorporation, I’ll survey a sample of people living with CF about how they would prefer to learn about or adopt different care innovations.
Aim 3: To design recommendations for how to support people living with CF incorporate care innovations, I will conduct design workshops in an asynchronous remote community of people living with CF using reflective and scenario-based design activities and nominal group technique. By conducting this research, I’ll understand how to support people living with CF to incorporate care innovations, which may be transferable to other communities living with rare diseases.
September 11 – September 14, 2023
UPCOMING LECTURES AND SEMINARS
BIME 590: See you soon!
PUBLICATIONS & PRESENTATIONS
Nikita Pozdeyev, Manjiri Dighe, Martin Barrio, Christopher Raeburn, Harry Smith, Matthew Fisher, Sameer Chavan, Nicholas Rafaels, Jonathan A Shortt, Meng Lin, Michael G Leu, Toshimasa Clark, Carrie Marshall, Bryan R Haugen, Devika Subramanian, Kristy Crooks, Christopher Gignoux, Trevor Cohen, Thyroid cancer polygenic risk score improves classification of thyroid nodules as benign or malignant., The Journal of Clinical Endocrinology & Metabolism, 2023; dgad530, https://doi.org/10.1210/clinem/dgad530.
Molly C. Reid, John E. Mittler, James T. Murphy, Sarah E. Stansfield, Steven M. Goodreau, Neil Abernethy, Joshua T. Herbeck. Evolution of HIV virulence in response to disease-modifying vaccines: A modeling study, Vaccine, 2023. https://www.sciencedirect.com/science/article/abs/pii/S0264410X23010277
UPCOMING GENERAL EXAM
Title: Deciphering neurodevelopmental origins of pediatric brain cancer using single cell genomics and NLP approaches
Student: Ashmitha Rajendran
Date/Time: Thursday, September 21, 2023, 8:30-9:30 am PST (public presentation)
Location: Only zoom
Zoom: https://washington.zoom.us/j/2066162813
Abstract: A growing body of evidence has shown that many pediatric brain tumors have embryonic origins with driving aberrations arising in precursor or stem cells associated with neurodevelopment. Several pediatric brain cancers show spatio-temporal and spatio-molecular patterns that map to developmental dynamics. These linked patterns, however, are not fully understood yet. Here, we integrate and expand upon several of the largest single cell atlases of the human prenatal brain and across several pediatric brain cancers to identify developmental transcriptional programs and cellular origins of tumor initiation. We focus on three poorly characterized pediatric brain cancer types with the worst patient outcomes: Diffuse intrinsic pontine gliomas (DIPG), atypical teratoid rhabdoid tumor (ATRT), and medulloblastoma (MB). We hypothesize that expanding on existing neurodevelopmental and pediatric atlases using single cell rna sequencing integrative approaches will allow us to identify the developmental genetic programs involved in pediatric brain cancer progression. In this work, we use both conventional and novel approaches for single cell RNA sequencing analysis—proposing new methods for cell identification and gene module creation rooted in probabilistic topic models and information theory. This work will identify gene sets and cellular lineages putatively linked to the developmental origins of these tumors. It will also investigate tumor-specific transcriptomic dynamics. These analyses are anticipated to ultimately inform targeted therapeutic interventions.
August 28 – Sept 1, 2023
UPCOMING GENERAL EXAM
Title: NeuroPathPredict (NPP), a novel data-driven approach to map AD brain pathology distribution
Student: Raghav Madan
Date/Time: Friday, September 8, 2023, 12:30-1:30 pm PST (public presentation)
Location: 750 Republican Street, Building E, Room E103
Zoom: https://washington.zoom.us/my/jhgennari?pwd=TUx0clkwKzdnS1ZQV1dXRnZqMWMzZz09
Abstract: Alzheimer’s disease (AD) currently afflicts over 6 million Americans and millions more globally. Several neuropathological protein aggregates like amyloid-beta plaques (Aβ), neuro-fibrillary tau tangles (NFT), and transactive response DNA-binding protein of 43 kDa (TDP-43) have been linked with AD. Existing methods to measure neuropathology (NP) distribution, including targeted in-vivo PET imaging and post-mortem histopathology have drawbacks. PET imaging can only measure one pathology at a time, and is limited by off-target tracer binding. Histopathology provides precise measurements for multiple pathologies but for only a handful of regions. A whole-brain histopathological analysis is theoretically possible, but prohibitively resource-intensive. Precise brain-wide spatial NP distribution can bolster AD research and may help develop specific interventions. For my dissertation, I propose NeuroPathPredict (NPP), a novel data-driven computational approach to precisely map brain-wide NP distribution. NPP will use existing post-mortem quantitative neuropathology data from a few regions. It will adapt techniques from air pollution spatial modeling research. Further, NPP will be built atop an Integrated-Brain Information System (I-BIS), a human brain connectome information- schema. Specific aims to develop NPP are as follows:
Aim 1: To establish a foundational framework for the prediction of the spatial distribution of neuro-fibrillary tau tangles (NFTs) at a regional level.
Aim 2: To extend the framework for the prediction of the spatial distribution of neuro-fibrillary tau tangles (NFTs) at a voxel level.
Aim 3: To implement the framework for the prediction of the spatial distribution of Aβ, and TDP-43 at a voxel level.
August 21 – August 25, 2023
PUBLICATIONS & PRESENTATIONS
Association of fibroglandular breast tissue characteristics from multiparametric MRI with cancer risk factors in women undergoing breast cancer screening. Wesley Surento, Debosmita Biswas, Anum S. Kazerouni, Jin You Kim, Isabella Li, Habib Rahbar, Savannah C. Partridge. Abstract accepted for Biomedical Engineering Society poster, October, 2023, Seattle, WA.
Lor M, Yang NB, Backonja U, Bakken S. Evaluating and Refining a Pain Quality Information Visualization Tool with Patients and Interpreters to Facilitate Pain Assessment in Primary Care Settings. Informatics for Health and Social Care. doi:10.1080/17538157.2023.2240411
August 7 – August 11, 2023
UPCOMING LECTURES AND SEMINARS
BIME 590: See you all next Fall!
PUBLICATIONS & PRESENTATIONS
Yim W, Fu Y, Abacha AB, Snider N, Lin T, Yetisgen M. ACI-BENCH: a Novel Ambient Clinical Intelligence Dataset for Benchmarking Automatic Visit Note Generation. Accepted to Nature – Scientific Data.
Dobbins N, Han B, Zhou W, Lan K, Kim N, Harrington R, Uzuner O, Yetisgen M. LeafAI: query generator for clinical cohort discovery rivaling a human programmer. Accepted to JAMIA.
Fu V, Ramachandran GK, Dorvall N, Stiles E, Raub S, Lybarger K, McInnes B, Yetisgen M, Uzuner O. Domain Adaptation for Clinical Relation Extraction. Accepted to AMIA Annual Symposium. (podium abstract)
ANNOUNCEMENTS
Check out the Seattle Magazine article “Dr. AI? Not So Fast .“ Our own Sean Mooney, PhD, Chief Research Information Officer, was interviewed and said, “At the very highest level, AI can help providers make better decisions at the right time.”
CLIMECast: “Instructions for Scholarly Writing: Write an Effective Introduction!”
CLIME has a podcast which offers a conversational approach to improving teaching and educational scholarship. Our prior podcast on “Instructions for Scholarly Writing: Write an Effective Introduction” featuring Bridget O’Brien is available for listen.
July 31 – August 4, 2023
FINAL EXAM
MS Final Defense:
Title: Design and Development of an Intelligent Moderator Dashboard for an Online Support Community for Aging-Related Experiences
Student: Sharon H. Wong
Date/Time: Friday, August 04, 2023, Public presentation: 10:00am~10:45 am PST
Location (remote only): https://washington.zoom.us/j/95486182068
Abstract: Medical conditions and other experiences related to aging can be challenging to manage for older adults and their caregivers. Virtual Online Communities for Aging Life Experiences (VOCALE) is an online community-based digital health intervention that aims to encourage problem-solving skills amongst older adults and caregivers through participation in weekly discussions. The VOCALE intervention is overseen by trained members of the VOCALE research team, known as “moderators”, whose responsibilities include monitoring the discussion platform and responding to the needs of participants. However, there are still unmet needs amongst VOCALE moderators, such as a desire to facilitate the intervention more effectively while also gaining a deeper understanding of how well participants are engaging with the study.
This thesis project proposes a design for an intelligent moderator dashboard, which is a tool that can assist VOCALE moderators with their study-related duties and provide insights about participant engagement with the VOCALE intervention. To inform the design of this tool, a series of user-centered design activities were conducted with current and former VOCALE moderators. The final output of this project was a prototype for a proposed moderator dashboard design, recommendations for further stages of development, and an overall assessment of how differing user needs inform the experience of those who moderate online digital health interventions.
**General Exam for Nick Reid has been postponed. Details will be provided at a later date**
ANNOUNCEMENTS
IAMSE Fall 2023 Web Series: Brains, Bots, & Beyond
*This webinar series is provided by CLIME to all UW affiliated faculty, staff, and students
The Fall 2023 IAMSE Webinar Series will explore how Artificial Intelligence (AI) is transforming medical education, especially its impact on faculty teaching and student learning? Join the upcoming IAMSE Fall webinar series entitled “Brains, Bots, and Beyond: Exploring AI’s Impact on Medical Education” to learn about the intersection of AI and medical education. Over five sessions, we will cover topics ranging from the basics of AI to its use in teaching and learning essential biomedical science content. Don’t miss this exciting opportunity to join the conversation on the future of AI in medical education.
September 7: An Introduction to Artificial Intelligence and Machine Learning with Applications in Healthcare
September 14: Artificial Intelligence: Preparing for the Next Paradigm Shift in Medical Education
September 21: Transforming Healthcare Together: Empowering Health Professionals to Address Bias in the Rapidly Evolving AI-Driven Landscape
September 28: AI Tools for Medical Educators
October 5: ChatGPT and Other AI Tools for Medicine and Medical Education
Register here: https://clime.washington.edu/clime-events/iamse-fall-2023-web-series-brains-bots-beyond/
July 24 – July 28, 2023
PUBLICATIONS & PRESENTATIONS
Posters:
Wesley Surento, Anum S. Kazerouni, Daniel S. Hippe, Debosmita Biswas, Michael Hirano, John H. Gennari, Habib Rahbar, Savannah C. Partridge. Association of Screening MRI Features with Development of Future Breast Cancer. To be presented at the annual meeting of the American Medical Informatics Association (AMIA), Nov.11-15th, 2023, New Orleans, LA.
Chaliparambil, R. K., Johnny, S., Wong, S. H., Glass, J. E., Wang, L., Conway, M., Chen, A. T. (accepted). A theory-informed approach to studying social media about substance use. To be presented at the annual meeting of the American Medical Informatics Association (AMIA), Nov.11-15th, 2023, New Orleans, LA.
Chen, A. T., Johnny, S., Chaliparambil, R., Wong, S., Glass, J. (accepted). Considering the role of information and context in promoting health-related behavioral change. To be presented at the annual meeting of the Association for Information Science & Technology (ASIS&T), Oct. 27-31, London, UK.
Buie, R., Zachry, M., Chen, A. T. (accepted). Performance and organizational characteristics of analytics teams in healthcare and population health: Methods and preliminary observations. To be presented at the annual meeting of the Association for Information Science & Technology (ASIS&T), Oct. 27-31, London, UK.
Papers:
Chen, A. T., Komi, M., Bessler, S., Mikles, S. P., Zhang, Y. (accepted). Integrating statistical and visual analytic methods for bot identification of health-related survey data. Journal of Biomedical Informatics. https://doi.org/10.1016/j.jbi.2023.104439
Rao, N. D., Kaganovsky, J., Fullerton, S. M., Chen, A. T., Shirts, B. (accepted). Factors influencing genetic screening enrollment among a diverse, community-ascertained cohort. Public Health Genomics.
Janice Sabin gave a presentation to the Washington State Bar Association, Health Equity CLE July 19, 2023, titled: Implicit Bias in Health Care. The educational session also included a presentation by Will O’Connor, an Assistant Attorney General at the Washington Attorney General’s Office who detailed the Consumer Protection Division’s enforcement of the Charity Care Act, an Act that enables vulnerable populations to receive necessary medical care and relatedly, better health outcomes.
Janice Sabin gave a presentation titled Implicit Bias in Healthcare on July 26, 2023 to the UW General Internal Medicine MedStAR program. The MedStar program, directed by Dr. Judith Tsui, trains medical students in Addiction Medicine Research (R25).
ANNOUNCEMENTS
CLIME Grand Rounds
Practices to Improve Basic Science and Clinical Integration in Medical Education
Nicole Woods, PhD, Associate Professor of Family and Community Medicine, University of Toronto
October 27th, 2023
12:00pm – 1:00pm (PT)
Zoom (Online)
Register here: https://uw.cloud-cme.com/course/courseoverview?P=0&EID=8725
July 17 – July 21, 2023
PUBLICATIONS & PRESENTATIONS
AMIA Papers:
Bridging the Skills Gap: Evaluating an AI-Assisted Provider Platform to Support Care Providers with Empathetic Delivery of Protocolized Therapy. William Kearns, PhD, Jessica Bertram, Myra Divina, MS, BS, Lauren Kemp MN, RN, Yinzhou Wang, BA, Alex Marin, PhD, Trevor Cohen, MBChB, PhD, Weichao Yuwen, PhD, RN.
Deep Representations of First-person Pronouns for Prediction of Depression Symptom Severity. Xinyang Ren, Hannah A Burkhardt, PhD, Patricia A. Areán, PhD, Thomas D Hull, Ph.D., Trevor Cohen, MBChB, PhD.
Backdoor Adjustment of Confounding by Provenance for Robust Text Classification of Multi-institutional Clinical Notes. Xiruo Ding, MS, Zhecheng Sheng, MS, Meliha Yetisgen, PhD, Serguei Pakhomov, PhD, Trevor Cohen, MBChB, PhD.
Improving physical activity among prostate cancer survivors through a peer-based digital walking program. Sangameswaran S, Casanova-Perez R, Patel H, Cronkite DJ, Idris A, Rosenberg DE, Wright JL, Gore JL, Hartzler AL.
“Meditation for me is just an app in my phone”– co-designing mind-body technologies for sleep with adolescents. Sangameswaran S, Laine M, Reid N, Xie SJ, Zampino L, Garrison MM, Rosenberg DE, Yip JC, Hartzler AL.
Imagining Improved Interactions: Patients’ Designs to Address Implicit Bias. Yang C, Coney L, Mohanraj D, Casanova-Perez R, Bascom E, Effrem N, Garcia JT, Sabin J, Pratt W, Weibel N, Hartzler AL.
AMIA Podium:
Can Natural Language Processing Support Cultural Adaptation of Digital Health Interventions? A Scoping Review. Paullada A, Xie SJ, Wang Y, Louden D, Cohen T, Yuwen W. Can Natural Language Processing Support Cultural Adaptation of Digital Health Interventions? A Scoping Review.
AMIA Poster:
Retrieval-Augmented Generation of Lay Language Background Explanations. Yue Guo, MHS, MBBS, Wei Qiu, Gondy Leroy, Ph.D., Sheng Wang, Ph.D., and Trevor Cohen, MBChB, Ph.D.
AMIA Panel:
Using AI to Improve Mental Health Care: Challenges and Opportunities. Jyotishman Pathak, PhD, Trevor Cohen, MBChB, PhD, Julia Edgcomb, MD, PhD. Vasa Curcin, PhD, Yiye Zhang, PhD.
Fostering Inclusive and Equitable Health Care and Public Health: Addressing Stigma and Discrimination with Informatics. Antonio M, Lowens B, Beals A, Hartzler AL, Zhou Li, Veinot T.
Additional Acceptances:
Lauren E. Bartlett, Nick Reid, Siddhartha G. Kapnadak, Donna Berry, Andrea L. Hartzler, Melissa Basile, Kathleen J. Ramos. Qualitative analysis of a pilot RCT of a CF-specific educational website that aims to prepare people with CF for lung transplant discussions and decisions. North American Cystic Fibrosis Conference (NACFC), 2023.
G. Sawicki, J. Greenberg, N. Reid, A. Berlinski, M. Rosenfeld, A.L. Hartzler. Research Coordination Perceptions of a Coached Home Spirometry Protocol: Ongoing Experiences with the OUTREACH Study. North American Cystic Fibrosis Conference (NACFC), 2023.
Condon C, Hartzler AL, Yuen W. Internal Testing of COCO Prototype: Preparation for Pilot Testing with Family Caregivers. 18th Annual Seattle Nursing Research Conference. June 2023.
Margaret Rosenfeld, Barb Fogarty, Ariel Berlinski, Greg Sawicki, Andrea Hartzler. Home Spirometry as a Clinical Trial Endpoint: Qualitative Needs Assessment and Co-Production of Training Materials. European CF Society (ECFS), Vienna, Austria June 7-11, 2023.
ANNOUNCEMENTS
CLIME Conversation Café on “Metacognition for Teaching and Learning in Health Professions Education Conversation Cafe” Recording Now Available!
Check out the recording of CLIME’s Conversation Café on “Metacognition for Teaching and Learning in Health Professions Education” featuring Jonika Hash, PhD, RN.
July 3 – July 7, 2023
ANNOUNCEMENTS
CLIMECast on “Humanizing the Classroom” Available!
CLIME has a podcast which offers a conversational approach to improving teaching and educational scholarship. Our recent podcast on Humanizing the Classroom with David Masuda, MD, MS is available.
June 26 – June 30, 2023
PUBLICATIONS & PRESENTATIONS
Champieux R, Solomonides A, Conte M, Rojevsky S, Phuong J, Dorr DA, Zampino E, Wilcox A, Carson MB, Holmes K. (2023) Ten simple rules for organizations to support research data sharing. PLOS Computational Biology 19(6): e1011136. https://doi.org/10.1371/journal.pcbi.1011136
Cullen R, Heitkemper E, Backonja U, Bekemeier B, Kong HK. Designing an infographic webtool for public health [published online ahead of print, 2023 Jun 24]. J Am Med Inform Assoc. 2023;ocad105. doi:10.1093/jamia/ocad105
ANNOUNCEMENTS
Oliver Li received the gold medal for the rapid/tech talk at the National Library of Medicine (NLM) T15 Training Conference for the project “Quantifying Controversy: Characterizing Resistance to COVID-19 Misinformation in Social Networks.” Congratulations!
Thomas Payne, MD, has been elected to Fellowship in the International Academy of Health Sciences Informatics (the Academy of International Medical Informatics Association), joining the 2023 Class.
CLIME has developed a series of “CLIME Clips!” to offer succinct actionable teaching tips for medical and health professions educators. Check out the rest of our “CLIME Clips!”
June 19 – June 23, 2023
PUBLICATIONS & PRESENTATIONS
Zeng, G. Luo, D.A. Lynch, R.P. Bowler, and M. Arjomandi. Lung Volumes Differentiate the Predominance of Emphysema versus Airway Disease Phenotype in Early COPD: An Observation Study of COPDGene Cohort. ERJ Open Research, 2023.
ANNOUNCEMENTS
CLIMECast on “Well-Being in Higher Education” Available!
CLIME has a podcast which offers a conversational approach to improving teaching and educational scholarship. Our recent podcast on Well-Being in Higher Education with Anne Browning, PhD and Megan Kennedy, MA, LMHC is available.
June 12 – June 16, 2023
UPCOMING FINAL EXAM
Title: Explainable query generation for cohort discovery and biomedical reasoning using natural language
Student: Nic Dobbins
Date/Time: Tuesday, June 20, 2023, Public presentation 2-3 pm PST
Location: 850 Republican St., Building C, Room 123B
Zoom: https://washington.zoom.us/my/melihay
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 created a gold-standard annotated corpus of eligibility criteria. In Aim 2: we developed methods for generating data model-agnostic SQL queries and multi-hop biomedical reasoning using a natural language interface rivaling human performance. In Aim 3: we developed an interactive chatbot-like web application to enable users to dynamically query clinical databases for cohort discovery using natural language.
ANNOUNCEMENTS
CLIME has developed a series of “CLIME Conclusions!” to summarize complex medical and health professions education topics in one page! Check out “Social Media and Digital Scholarship for Promotion and Tenure!”
June 5 – June 9, 2023
UPCOMING GENERAL EXAM
Title: Deconfounding Deep Neural Networks under Distribution Shift
Student: Xiruo Ding
Date/Time: Tuesday, June 13th, Public presentation: 10-11 am PST
Location: 850 Republican Street, Building C, Room 123 A/B
Zoom: https://washington.zoom.us/j/93739973390?pwd=MngydytONmkxT0NUTG8zQXBLdXVxdz09
Meeting ID: 937 3997 3390
Passcode: 608289
Abstract: Data collection and integration across different institutions is increasingly pursued to evaluate and improve the model generalizability. This can introduce a form of bias called confounding by provenance, where data distributions differ by location. When source-specific data distributions differ at deployment, this may harm model performance, which is especially important for high-stakes applications in healthcare. In this work, I will address the issue of confounding by provenance with natural language data in clinical settings with three specific aims. SA1: Defining an evaluation framework of confounding by provenance. SA2: Mitigation of confounding through distribution adjustments. SA3: Mitigation of confounding through model architecture.
ANNOUNCEMENTS
Dr. Bryant Karras receives the 2023 Washington state employee Extra Mile Award!
Congratulations to Dr. Bryant T. Karras, Chief Medical Informatics Officer in the Executive Office of Innovation and Technology, who is one of 15 state employees (and the only one from DOH!) receiving the Washington state Extra Mile Award.
CLIME has developed a series of “CLIME Clips!” to offer succinct actionable teaching tips for medical and health professions educators. Check out the rest of our “CLIME Clips!”
May 29 – June 2, 2023
PRESENTATIONS AND PUBLICATIONS
Asma Ben Abacha, Wen-wai Yim, Griffin Thomas Adams, Neal Snider, Meliha Yetisgen. Overview of the MEDIQA-Chat 2023 Shared Tasks on the Summarization & Generation of Doctor-Patient Conversations. Accepted to 2023 ACL Clinical NLP workshop.
Gridhar Ramanchandran, Velvin Fu, Bin Han, Kevin Lybarger, Ozlem Uzuner, Meliha Yetisgen. Prompt-based Extraction of Social Determinants of Health Using Few-shot Learning. Accepted to 2023 ACL Clinical NLP workshop.
Sitong Zhou, Meliha Yetisgen, Mari Ostendorf. Building blocks for complex tasks: Robust generative event extraction for radiology reports under domain shifts. Accepted to 2023 ACL Clinical NLP workshop.
Weipeng Zhou, Majid Afshar, Dmitriy Dligach, Yanjun Gao, Timothy A Miller. Improving the Transferability of Clinical Note Section Classification Models with BERT and Large Language Model Ensembles. Accepted to 2023 ACL Clinical NLP workshop.
UPCOMING GENERAL AND FINAL EXAMS
Final Exam
Title: A Novel Translational Bioinformatics Pipeline to Improve Precision Medicine Research
Student: Rich Green
Date/Time: Friday, June 2, 2023, Public presentation 2-3 pm PST
Location: Brotman Auditorium
Zoom: https://washington.zoom.us/j/9072437665
Abstract: Diverse Mouse models can serve as precursors to precision medicine in clinical practice (Li and Auwerx 2020) but requires the integration, analysis, and cross-species interpretation across multi-omics data sets. We present here a multi-omics pipeline designed to identify biomarkers with translational applicability using the Collaborative Cross (CC) mouse model. The CC project is a mouse genetic reference panel (GRP) that seeks to determine genetic markers driving outcomes. The CC was designed to introduce genetic diversity (like in a human population) into mouse models.
Our approach comprises three overarching aims (Aim 1) Construct Networks and Linear Models. (Aim 2) Detect Genetic Drivers and Candidate Genes. (Aim 3) Verify Clinical Correlations and Biomarker Detection, which we applied our pipeline to our driving biological project (DBP) to identify markers of neuroinvasion during West Nile virus (WNV) infection.
Aim 1 produced three novel immune networks (A-C) in the CC mouse model of West Nile virus infection. Network A was enriched in pattern recognition, innate immunity, and cell differentiation. Network B contained interferon and inflammation, and C was enriched for interferon signaling and neutrophil degranulation. Regression modeling and pathway analysis are also performed and identify unique immune regulators of disease outcomes across different CC strains. Using public data sets, we correlated novel gene-to-gene connections using an innovative approach, Integrated Transcriptomics Analysis (ITA).
In Aim 2, using the CC mouse model of WNV infection, genetic regions were correlated to the DBP through Quantitative Trait Loci analysis (QTL) which is a statistical approach that uses genotype data (genetic markers) and phenotype (viral detection, IFITM1 expression). The purpose of a QTL is to explain if there is any basis for genetic variation in the complex traits of our phenotype. QTL analysis identified three regions 59-80Mb in chromosome 4, 107-110.5Mb in chromosome 12, and 57.1-94.5 Mb in the X chromosome. Using viral load as a phenotype, identified areas in chromosomes 4 and 12. IFITM1 as a phenotypic marker identified a QTL in chromosome X. Transcriptional analysis from Aim 1 paired with Aim 2’s QTLs identified Toll-Like Receptor 4 (TLR4) in chromosome 4, Tryptophanyl-tRNA synthetase WARS in chromosome 12, and Membrane palmitoylated protein (MPP1) in chromosome X.
In Aim Three, translating findings from the CC model of WNV infection into human correlates, genetic regions from Aim 2 were converted to human genomic coordinates, and a Phenome Wide Association Study (PheWAS) using the Electronic Medical Records and Genomics (eMERGE) network (25k and 109k human genotyped participants) was performed. A PheWAS is a statistical test that uses genetic loci (or variants) and queries across a curated dataset of phenotypes defined by clinical codes. The result is genetic regions that are enriched by clinical phenotypes.
PheWAS identified various clinical associations with the genetic regions identified in the CC mouse model and mapped to human genomic coordinates, including essential tremor, Type 2 diabetes with neurological manifestations, chronic kidney disease, intestinal infection due to Clostridium difficile, end-stage renal failure, and other similar clinical phenotypes. Other clinical associations were identified in genes TLR4 and TRIM32, including codes for the circulatory system, dermatologic, endocrine, hematopoietic, infectious diseases, and neoplasms.
To augment the PheWAS, Bulk RNAseq was also performed on four human brains (two WNV infected, two mocks). Several target genes (Tnfsf8, PTBP3, Akna, and TLR4) identified as chromosome 4 were also significant in WNV-infected human brains. WARS gene in chromosome 12 and MMP1 In chromosome X were also identified.
The transcriptional analysis also revealed which sections of the brain contained the activated QTL-derived genes. TLR4 was significant in the Basal Ganglia. Akna was significant in the Cortex. PTBP3 was significant in the Basal Ganglia, Cortex, and Thalamus. In chromosome 12, the Wars gene was significant in the Basal Ganglia, Cortex, and Thalamus. MPP1 and MCFS appeared statistically significant in chromosome X in the Basal Ganglia.
Our pipeline leveraged a diverse mouse model to calculate genetic and transcriptional markers associated with disease phenotypes. Connecting the results and our findings across our aims revealed distinct connections and biomarkers to be used in precision medicine applications.
_____________________________________________________________________________________
General Exams
Title: Multi-modal and Federated Predictive Models for Disease Outcome Prediction: Examples in Diabetic Kidney Disease and Soft Tissue Sarcoma
Student: Ehsan Alipour
Date/Time: Wednesday, June 7th, Public presentation: 11-12 pm PST
Location: Zoom Only – https://washington.zoom.us/my/peter.th
Abstract: Disease outcome prediction is a crucial field of research in biomedical informatics, offering numerous benefits such as identifying high-risk patients, discovering modifiable risk factors, and understanding disease mechanisms. However, effectively utilizing different types of patient data and extracting interactions between modalities present significant challenges, including data incompatibility, differences in data processing, and data siloing. We are going to explore different data fusion techniques and use state of the art deep learning models to create robust outcome prediction algorithms using data across multiple institutes while preserving the privacy of each center.
This research project focuses on two diseases as examples, namely soft tissue sarcoma and type 2 diabetes leading to chronic kidney disease (CKD). For type 2 diabetes patients progressing to CKD, multimodal machine learning techniques will be employed to combine clinical, genomics, and survey data. Soft tissue sarcoma, a rare and aggressive cancer, will be used as an example for combining clinical and imaging data.
We will compare early, intermediate, and late fusion techniques and assess the incremental value of adding each data modality. Finally, a federated multi-modal learning pipeline will be developed to predict the risk of CKD and other adverse outcomes in patients with type 2 diabetes, utilizing clinical, genetics, and exposure data from the All of Us and UK Biobank repositories. By exploring different data fusion approaches and leveraging diverse datasets, this research aims to improve disease outcome prediction models, enhance clinical care, and advance our understanding of underlying disease mechanisms. Study aims include:
Aim 1: Evaluation and comparison of early, intermediate, and late fusion techniques for combining exposures, clinical and genomics data using All of Us to predict the risk of CKD in patients with type 2 diabetes.
Aim 2: Development and assessment of the incremental value of combining a deep convolutional neural network feature extractor on imaging data and clinical data to predict outcomes in soft tissue sarcomas.
Aim 3: Development and evaluation of a federated multi-modal learning pipeline to use clinical, genetics, and exposure data from All of Us and UK biobank to predict the risk of CKD and other adverse outcomes in patients with type 2 diabetes.
_____________________________________________________________________________________
ANNOUNCEMENTS
Weipeng Zhou is one of the recipients of the 2023 IMDS Pilot Award for his project titled “Towards Automatic Identification of Patients in Need of Long COVID Care with Natural Language Processing Methods”. Weipeng will be advised by Meliha Yetisgen and Kari Stephens.
CLIME has developed a series of “CLIME Clips!” to offer succinct actionable teaching tips for medical and health professions educators. Check out the rest of our “CLIME Clips!”
May 22 – May 26, 2023
UPCOMING LECTURES AND SEMINARS
BIME 590
Title: Causal Discovery from Data
Presenter: David Heckerman, MD, PhD
Thursday, June 1, 11-11:50 am
Speaker will only present remotely
Zoom information: https://washington.zoom.us/my/bime590
Abstract: Some basics on causality—its definition, how it differs from correlation, and why the distinction is important, will be covered. Then, the discussion will focus on diverse approaches to inferring cause and effect from data, with and without interventions, with examples from healthcare.
Presenter Bio:David Heckerman worked at Microsoft Research for 25 years from 1992 to 2017. At MSR, he founded the first AI group in 1992, the first machine-learning group in 1994, the first bioinformatics group in 2004, and the first genomics group in 2015. Notable products he invented include the world’s first machine-learning spam filter, the Answer Wizard (which became the backend for Clippy), and the Windows Troubleshooters. He also led the MSR team in building Microsoft’s first machine-learning platform, which was hosted in SQL Server. On the research side, David is known for developing the first practical platform for constructing probabilistic expert systems, the topic of his PhD dissertation, which won the ACM best dissertation award in 1990. He is also known for (1) developing an approach for learning Bayesian networks from a combination of expert knowledge and data, which has proven useful in causal discovery, (2) developing an HIV vaccine design through machine learning, and (3) developing state-of-the-art methods for genome associations studies that can process millions of subjects. David received his Ph.D. (1990) and M.D. (1992) from Stanford University, and is an ACM, AAAI, and ACMI Fellow.
PUBLICATIONS AND PRESENTATIONS
Lybarger K, Dobbins NJ, Long R, Singh A, Wedgeworth P, Uzuner Ö, Yetisgen M. (2023). Leveraging natural language processing to augment structured social determinants of health data in the electronic health record. J Am Med Inform Assoc. 2:ocad073. doi: 10.1093/jamia/ocad073
UPCOMING GENERAL AND FINAL EXAMS
Final Exams
Title: A Novel Translational Bioinformatics Pipeline to Improve Precision Medicine Research
Student: Rich Green
Date/Time: Friday, June 2, 2023, Public presentation 2-3 pm PST
Location: Brotman Auditorium
Zoom: https://washington.zoom.us/j/9072437665
Abstract: Diverse Mouse models can serve as precursors to precision medicine in clinical practice (Li and Auwerx 2020) but requires the integration, analysis, and cross-species interpretation across multi-omics data sets. We present here a multi-omics pipeline designed to identify biomarkers with translational applicability using the Collaborative Cross (CC) mouse model. The CC project is a mouse genetic reference panel (GRP) that seeks to determine genetic markers driving outcomes. The CC was designed to introduce genetic diversity (like in a human population) into mouse models.
Our approach comprises three overarching aims (Aim 1) Construct Networks and Linear Models. (Aim 2) Detect Genetic Drivers and Candidate Genes. (Aim 3) Verify Clinical Correlations and Biomarker Detection, which we applied our pipeline to our driving biological project (DBP) to identify markers of neuroinvasion during West Nile virus (WNV) infection.
Aim 1 produced three novel immune networks (A-C) in the CC mouse model of West Nile virus infection. Network A was enriched in pattern recognition, innate immunity, and cell differentiation. Network B contained interferon and inflammation, and C was enriched for interferon signaling and neutrophil degranulation. Regression modeling and pathway analysis are also performed and identify unique immune regulators of disease outcomes across different CC strains. Using public data sets, we correlated novel gene-to-gene connections using an innovative approach, Integrated Transcriptomics Analysis (ITA).
In Aim 2, using the CC mouse model of WNV infection, genetic regions were correlated to the DBP through Quantitative Trait Loci analysis (QTL) which is a statistical approach that uses genotype data (genetic markers) and phenotype (viral detection, IFITM1 expression). The purpose of a QTL is to explain if there is any basis for genetic variation in the complex traits of our phenotype. QTL analysis identified three regions 59-80Mb in chromosome 4, 107-110.5Mb in chromosome 12, and 57.1-94.5 Mb in the X chromosome. Using viral load as a phenotype, identified areas in chromosomes 4 and 12. IFITM1 as a phenotypic marker identified a QTL in chromosome X. Transcriptional analysis from Aim 1 paired with Aim 2’s QTLs identified Toll-Like Receptor 4 (TLR4) in chromosome 4, Tryptophanyl-tRNA synthetase WARS in chromosome 12, and Membrane palmitoylated protein (MPP1) in chromosome X.
In Aim Three, translating findings from the CC model of WNV infection into human correlates, genetic regions from Aim 2 were converted to human genomic coordinates, and a Phenome Wide Association Study (PheWAS) using the Electronic Medical Records and Genomics (eMERGE) network (25k and 109k human genotyped participants) was performed. A PheWAS is a statistical test that uses genetic loci (or variants) and queries across a curated dataset of phenotypes defined by clinical codes. The result is genetic regions that are enriched by clinical phenotypes.
PheWAS identified various clinical associations with the genetic regions identified in the CC mouse model and mapped to human genomic coordinates, including essential tremor, Type 2 diabetes with neurological manifestations, chronic kidney disease, intestinal infection due to Clostridium difficile, end-stage renal failure, and other similar clinical phenotypes. Other clinical associations were identified in genes TLR4 and TRIM32, including codes for the circulatory system, dermatologic, endocrine, hematopoietic, infectious diseases, and neoplasms.
To augment the PheWAS, Bulk RNAseq was also performed on four human brains (two WNV infected, two mocks). Several target genes (Tnfsf8, PTBP3, Akna, and TLR4) identified as chromosome 4 were also significant in WNV-infected human brains. WARS gene in chromosome 12 and MMP1 In chromosome X were also identified.
The transcriptional analysis also revealed which sections of the brain contained the activated QTL-derived genes. TLR4 was significant in the Basal Ganglia. Akna was significant in the Cortex. PTBP3 was significant in the Basal Ganglia, Cortex, and Thalamus. In chromosome 12, the Wars gene was significant in the Basal Ganglia, Cortex, and Thalamus. MPP1 and MCFS appeared statistically significant in chromosome X in the Basal Ganglia.
Our pipeline leveraged a diverse mouse model to calculate genetic and transcriptional markers associated with disease phenotypes. Connecting the results and our findings across our aims revealed distinct connections and biomarkers to be used in precision medicine applications.
_____________________________________________________________________________________
General Exams
Title: Multi-modal and Federated Predictive Models for Disease Outcome Prediction: Examples in Diabetic Kidney Disease and Soft Tissue Sarcoma
Student: Ehsan Alipour
Date/Time: Wednesday, June 7th, Public presentation: 11-12 pm PST
Location: Zoom Only – https://washington.zoom.us/my/peter.th
Abstract: Disease outcome prediction is a crucial field of research in biomedical informatics, offering numerous benefits such as identifying high-risk patients, discovering modifiable risk factors, and understanding disease mechanisms. However, effectively utilizing different types of patient data and extracting interactions between modalities present significant challenges, including data incompatibility, differences in data processing, and data siloing. We are going to explore different data fusion techniques and use state of the art deep learning models to create robust outcome prediction algorithms using data across multiple institutes while preserving the privacy of each center.
This research project focuses on two diseases as examples, namely soft tissue sarcoma and type 2 diabetes leading to chronic kidney disease (CKD). For type 2 diabetes patients progressing to CKD, multimodal machine learning techniques will be employed to combine clinical, genomics, and survey data. Soft tissue sarcoma, a rare and aggressive cancer, will be used as an example for combining clinical and imaging data.
We will compare early, intermediate, and late fusion techniques and assess the incremental value of adding each data modality. Finally, a federated multi-modal learning pipeline will be developed to predict the risk of CKD and other adverse outcomes in patients with type 2 diabetes, utilizing clinical, genetics, and exposure data from the All of Us and UK Biobank repositories. By exploring different data fusion approaches and leveraging diverse datasets, this research aims to improve disease outcome prediction models, enhance clinical care, and advance our understanding of underlying disease mechanisms. Study aims include:
Aim 1: Evaluation and comparison of early, intermediate, and late fusion techniques for combining exposures, clinical and genomics data using All of Us to predict the risk of CKD in patients with type 2 diabetes.
Aim 2: Development and assessment of the incremental value of combining a deep convolutional neural network feature extractor on imaging data and clinical data to predict outcomes in soft tissue sarcomas.
Aim 3: Development and evaluation of a federated multi-modal learning pipeline to use clinical, genetics, and exposure data from All of Us and UK biobank to predict the risk of CKD and other adverse outcomes in patients with type 2 diabetes.
ANNOUNCEMENTS
Kristina Dzara, PhD, MMSc will be leaving UW, BIME, and CLIME this summer. She has accepted a role as Assistant Dean for Scholarly Teaching and Learning, Director of the Center for Scholarly Teaching and Learning, and Associate Professor of Family and Community Medicine at the Saint Louis University School of Medicine. We thank her for her leadership and wish her well in her future endeavors.
Last call for applications for the CLIME Teaching Scholars Program! Prepares clinicians and educators to become leaders in all aspects of health professions education. Program fee $4500. Deadline May 30, 2023. Email CLIME@UW.EDU with questions.