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
July 8 – July 12, 2024
UPCOMING LECTURES AND SEMINARS
BIME 590 – See you in autumn quarter – 9/26/2024!
PAPERS & PUBLICATIONS
Feng Chen, Manas Satish Bedmutha, Ray-Yuan Chung, Janice Sabin, Wanda Pratt, Brian R. Wood, Nadir Weibel, Andrea L. Hartzler, Trevor Cohen. Toward Automated Detection of Biased Social Signals from the Content of Clinical Conversations. Accepted for the AMIA 2024 Symposium.
Faisal Yaseen, Daniel S. Hippe, Parth Vijaykumar Soni, Shouyi Wang, Chunyan Duan, Stephen R. Bowen. Variogram Modeling of Spatially Variant Early Response to Concurrent Chemo- and Immunotherapy for Metastatic Non-Small Cell Lung Cancer has been accepted as a podium abstract for oral presentation for the AMIA 2024 Annual Symposium.
Faisal Yaseen, Luna Li, Raina H. Langevin. Enhancing Public Health Surveillance in King County: Applying Data Modernization to Social Determinants of Health has been accepted for poster presentation for the AMIA 2024 Annual Symposium.
Bhargav Vemuri, Peter Tarczy-Hornoch P, Jen Hadlock. Multivariate Longitudinal Trajectories of Response to GLP-1 RA Therapy has been accepted for a poster presentation for the AMIA 2024 Annual Symposium.
Faisal Yaseen, Murtaza Taj, Resmi Ravindran, Fareed Zaffar, Paul A. Luciw, Aamer Ikram, Saerah Iffat Zafar, Tariq Gill, Michael Hogarth, Imran H. Khan. An exploratory deep learning approach to investigate tuberculosis pathogenesis in nonhuman primate model: Combining automated radiological analysis with clinical and biomarkers data. Journal of Medical Primatology, https://doi.org/10.1111/jmp.12722
UPCOMING FINAL EXAMS
Title: Deep Learning Classification of Spinal Osteoporotic Compression Fractures on Radiographs
Student: Qifei Dong
Date/Time: Friday, July 12 @ 11 am
Location: Zoom Only
Zoom Info: https://washington.zoom.us/j/4666998448?pwd=dXo1NjFCQkNJclFYc2Y0SHN3c0JPZz09
Abstract: Although osteoporosis is a debilitating disease that affects 9% of individuals over 50 years of age in the US and 200 million women globally, osteoporosis screening is underutilized. A complementary approach to osteoporosis screening is opportunistic screening using pre-existing images to detect spinal osteoporotic compression fractures (OCFs). Spinal OCFs are often incidental findings and under-reported. An automated opportunistic screening tool can ensure earlier diagnosis and treatment of spinal OCFs and osteoporosis. A crucial component for the automated opportunistic screening tool is an OCF classifier that detects OCF on each vertebral body. In this research, we focus on building this OCF classifier. To do this, two spine radiograph datasets were obtained, whose radiographs are in the Digital Imaging and Communications in Medicine (DICOM) format. To annotate the data, we designed DicomAnnotator, a configurable open-source software program for efficient DICOM image annotation. With the annotated radiographs, we used five deep learning algorithms to build the OCF classifier. Training a deep learning model on a large dataset is often time-consuming. During deep learning model training, it is desirable to offer a non-trivial progress indicator that can continuously project the remaining model training time and the fraction of model training work completed. This makes the deep learning model training process more user-friendly. We designed the first set of techniques to support progress indication for deep learning model training that allows early stopping. In summary, we realized the following three aims in this research:
1) Aim 1: Design DicomAnnotator. Usability evaluation shows that DicomAnnotator is easy to learn, is efficient to use, and allows annotators to quickly make several types of annotations on a large set of DICOM images.
2) Aim 2: Build the OCF classifier. Model evaluation results show that our OCF classifier has some generalizability to clinical data and a suitable performance for our future opportunistic osteoporosis screening.
3) Aim 3: Design progress indication methods for deep learning model training. Our experiments show that our progress indicator can offer useful information even if the run-time system load varies over time and can self-correct its initial estimation errors, if any, over time.
Title: A Longitudinal Study Based on Secondary Usage of Electronic Health Record for Identification of Erectile Dysfunction (ED) Risk Factors and Identification of Patients
Student: Tianran Li
Date/Time: 7/19 8:30-9:30am
Location: Zoom only
Zoom: https://washington.zoom.us/j/4655089720
Abstract: Erectile Dysfunction (ED) affects one in five men in the United States and rises in prevalence with increasing age. Recognizing the chronic nature of ED and the lacking in comprehensive longitudinal healthcare documentation and multifactor analysis, this study utilized integrated and enriched electronic health records (EHR) from the electronic MEdical Records and GEnomics (eMERGE) cohort 3 at Kaiser Permanente/University of Washington (KPWA) site. We developed a novel method to systematically identify ED cases and employed statistical methods for survival analysis of risk factors and the longitudinal patterns associated with ED. This approach enhances our comprehension of disease progression, supports improved clinical management, and ultimately aims to elevate the quality of life and healthcare outcomes for affected individuals. Our study demonstrates the significant potential of integrated EHR-based informatics in advancing the understanding and management of complex chronic conditions like ED.
ANNOUNCEMENT
Hasan Ahmad, DO, MBA, MSc, FACP, has accepted a position as Associate Chief Medical Information Officer at Parkview Health in Fort Wayne, Indiana.
June 17 – June 21, 2024
UPCOMING LECTURES AND SEMINARS
BIME 590 – See you in autumn quarter – 9/26/2024!
PAPERS & PRESENTATIONS
Andrea Hartzler was invited to represent work from the UnBIASED project at the “Human-centered AI Mini Conference at the Microsoft reactor on June 12th. The community event celebrated Pride month and attracted technologists, researchers, students, and enthusiasts from around the area.
UPCOMING EXAM
Final Exam
Title: Robust Methods for Clinical Text Classification and Disease Understanding with NLP Extracted Symptoms from Clinical Notes
Student: Weipeng Zhou
Date/Time: Tuesday, June 25 @ 10 am
Location: 750 Republican Street, Building F, Room 107
Zoom: https://washington.zoom.us/my/melihay
Abstract: Electronic Health Records (EHR) contain comprehensive medical and treatment histories of patients and have the potential to be used to provide better healthcare. A significant portion of the EHR is in the form of clinical notes and Natural Language Processing (NLP) methods can help extract hidden information from them. However, applying NLP in healthcare has challenges. Many of the clinical note datasets are scarce and imbalanced, making it difficult to develop generalizable and robust NLP methods. Additionally, effective use of NLP in healthcare requires close collaboration with medical experts to identify and understand meaningful clinical problems. This dissertation addresses these challenges and explores the application of NLP in healthcare. In Chapter 1 and 2, we develop generalizable and robust NLP methods for clinical note classification and female suicide report coding. In aims 3 and 4, we apply NLP to extract symptoms from clinical notes and study risk factors associated with out-of-hospital cardiac arrest (OHCA) and Long COVID.
ANNOUNCEMENTS
WSAS 2024 Symposium on AI for Washington State: Using Artificial Intelligence to Explore, Discover and Understand
Find more information here. Event is *free* for students. Keynote speaker is the President of NASEM.
June 10 – June 14, 2024
PAPERS & PRESENTATIONS
Trevor Cohen was a presenter at “Publishing NLP in JAMIA: Past, Present, and Future” on June 11, 2024, where trends in publishing NLP work, including insights from the forthcoming focus issue on Large Language Models were discussed.
Sunan Cui, Jing Zeng, Daniel Hippe, Jie Fu, Faisal Yaseen, Yulun He, John Kang, Clemens Grassberger, Ramesh Rengan, Stephen Bowen. “Phase II Trial of Risk-Adaptive Chemoradiation for Unresectable Non-Small Cell Lung Cancer: FLARE-RT Mature Outcomes and Patterns of Failure” has been accepted for presentation in ORAL scientific session for the 66th annual meeting of American Society for Radiation Oncology (ASTRO).
UPCOMING EXAMS
Final Exams
Title: Reporting understandable, useful, and trustworthy results of clinical prediction model studies: insights from biomedical researchers
Student: Ivan Rahmatullah
Date/Time: Monday, June 17th, 1 pm
Location: Zoom only – https://washington.zoom.us/my/andreahartzler
Abstract:
Despite the increasing number of clinical prediction model (CPM) studies, the quality of reporting, especially for preimpact analysis studies focusing on developing and validating CPMs in research papers, remains subpar. This poor reporting quality hinders the progression of CPM studies by impeding follow-up studies, such as external validation, impact analysis studies, and systematic reviews. While the reporting guideline for these studies, TRIPOD (Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis), emphasizes transparency, biomedical researchers advocate for CPM study results to additionally embody three quality attributes: understandable, useful, and trustworthy. Yet, the extent to which biomedical researchers perceive and ensure that CPM study results meet these quality attributes, has not been explored
This dissertation aims to bridge these gaps by identifying challenges, needs, and visualization preferences among biomedical researchers to ensure CPM study results meet these three quality attributes. Each main chapter in this dissertation addresses a specific aim. Aim 1, presented in Chapter 4, uses a mixed-method survey to explore biomedical researchers’ challenges in ensuring that CPM study results meet the three quality attributes as authors and reviewers. Aim 2, detailed in Chapter 5, involves interviews with biomedical researchers to characterize their needs to ensure the three quality attributes in CPM study results. Aim 3, outlined in Chapter 6, based on interviews with biomedical researchers, identifies visualization preferences that could enhance the quality of CPM study results. The concluding Chapter 7 summarizes these findings and their contributions to biomedical informatics, which highlight a novel approach to improve the quality of CPM study results by focusing on the three quality attributes and engaging biomedical researchers beyond traditional expert panels.
Furthermore, the dissertation includes foundational chapters setting the research stage. Chapter 1 reviews relevant prior work and outlines my motivations for this study, rooted in my experiences as a primary care clinician and biomedical researcher. Chapter 2 reports on my preliminary work through a primary care provider survey about their use of clinical prediction rules. Chapter 3 describes recruitment strategies that enhanced biomedical researchers’ participation in the Chapter 4 survey, utilizing PubMed records for expanded outreach.
ANNOUNCEMENTS
Congratulations to IMDS Pilot Awardees!
Zoljargal (Zoey) Lkhagvajav was selected as an awardee for the 24-25 Institute of Medical Data Science pilot award program for her proposal “Data pipeline development for curation of Geriatric Trauma Outcome prognostication.” She will be working with Jim Phuong and Hamilton Tsang.
Yifan Wu, Trevor Cohen and Ian DeBoer were selected as awardees for their proposal entitled “Using temporality, dose effect, and co-medication to improve drug safety surveillance,” for a 2024-25 Medical Data Science Pilot Award. The proposal concerns the use of Transformer architectures, including variants that represent dose and lab information as continuous variables, to model electronic health record data for the purpose of post-marketing surveillance of pharmaceutical products.
CRBM Receives NIBIB Grant
National Institute of Biomedical Imaging and Bioengineering has committed a multi-million-dollar grant to support the Center for Reproducible Biomedical Modeling (CRBM) at the University of Washington. Under the leadership of UW Bioengineering Professor, Herbert Sauro, the grant will allow CRBM to continue its innovative work for an additional five years. This significant investment underscores the importance of the Center’s mission to enhance the reliability and reproducibility of biomedical models. John Gennari, along with PhD student Luna Li, will be a key contributor to the project.
Leveraging Data Standards for Improving Interoperability
July 9, 2024 | 1:00–2:00 p.m. ET
Join Austin Fitts, Pharm.D., Nikki Wood, D.O., David Noyd, M.D., M.P.H., and Wayne H. Liang, M.D., M.S., FAMIA, for a discussion on how to enhance interoperability with data standards, with an emphasis on the National Childhood Cancer Registry (NCCR), Childhood Cancer–Data Integration for Research, Education, Care, and Clinical Trials (CC-DIRECT), development of pediatric content within the HemOnc.org ontology standard, and creation of the minimal Common Oncology Data Elements (mCODE) pediatrics extension. Click here to register.
June 3 – June 7, 2024
PAPERS & PRESENTATIONS
Yujuan Fu*, Giridhar Kaushik Ramachandran*, Nicholas J Dobbins, Namu Park, Michael Leu, Abby R. Rosenberg, Kevin Lybarger, Fei Xia, ̈Özlem Uzuner, and Meliha Yetisgen. Extracting social determinants of health from pediatric patient notes using large language models: Novel corpus and methods. LREC-COLING, 2024. – Outstanding Paper Award
ANNOUNCEMENTS
Angad Singh was selected as the 2024 recipient of David Thorud Leadership Award as part of UW’s Awards of Excellence series. This award is the highest leadership honor at the University of Washington and is given to one faculty member across the University each year. Please see more information here.
May 27 – May 31, 2024
UPCOMING LECTURES AND SEMINARS
BIME 590 – See you in autumn quarter – 9/26/2024!
PAPERS & PRESENTATIONS
Ojas A. Ramwala, Kathryn P. Lowry, Nathan M. Cross, William Hsu, Christopher C. Austin, Sean D. Mooney, Christoph I. Lee, Establishing a Validation Infrastructure for Imaging-Based AI Algorithms Prior to Clinical Implementation, Journal of the American College of Radiology, 2024, ISSN 1546-1440 https://doi.org/10.1016/j.jacr.2024.04.027.
UPCOMING EXAMS
Final Exams
Title: Relationship between Metabolic Measurements and Brain Injury in Post-Cardiac Arrest Comatose Patients
Student: Kevin Chen
Date/Time: Wednesday, June 5, 9 AM
Location-Zoom only: https://washington.zoom.us/my/jhgennari?pwd=TUx0clkwKzdnS1ZQV1dXRnZqMWMzZz09
Abstract:
Cardiac arrest is a leading cause of death in the United States contributing to 5.6% of annual deaths. More than 80% of survivors are in permanent coma and 50-80% of those will die. Despite advancements in cardiac care, the mechanisms underlying brain injury are complex and not well understood, which has limited advancement in brain targeted therapies. Specifically, the relationship between regional brain metabolism and risk of brain injury is not known. This thesis investigated the relationship between brain injury in post-cardiac arrest comatose patients and metabolic characteristics: cerebral blood flow (CBF), cerebral blood volume (CBV), cerebral metabolic rate of oxygen (CMRO2), and cerebral metabolic rate of glucose (CMRglu). The study analyzed whole brains, brains clustered by injury percentages, and brain regions clustered by injury percentage. Resulting correlations showed that CMRO2 and CMRglu had stronger correlations with brain injury than CBF and CBV, indicating a closer link between oxygen and glucose utilization and brain damage. Patients with minimal injury exhibited weak correlations, while patients with moderate to severe injuries displayed stronger correlations, emphasizing the critical role of oxygen and glucose metabolism in brain damage progression.
General Exam
Title: Enhancing Generalizability and Explainability in Medical Language and Vision Models
Student: Yujuan Velvin Fu
Date/Time: Thursday, June 6, 2 PM (Pacific)
Location: C123 A&B
Zoom: https://washington.zoom.us/my/melihay
Abstract:
Recent advances in large language models (LLMs) and vision-language models (VLMs) have achieved human-comparable performance across a variety of specialized medical tasks involving text and multimodal data, without requiring annotated datasets for model development. Despite these achievements, our observations identify two primary gaps: firstly, the generalization of current medical LLMs to some natural language understanding (NLU) tasks is suboptimal under zero-shot settings, compared to traditional fine-tuning-based approaches; secondly, the current generalizable and explainable VLMs in dermatology in under-explored for fine-grained diagnostic concept explanation. Addressing these challenges is critical, as enhancing model generalizability ensures quality and facilitates broader adoption of clinical LLMs and VLMs under potential patient distribution shifts, while improving explainability is essential for debugging AI-driven decision-making systems and fostering trust between humans and AI. Therefore, our work aims to tackle these issues through three major aims: (1) developing benchmark datasets for clinical information extraction (IE), as a subset of NLU, to more accurately identify the shortcomings of zero-shot LLMs; (2) developing a more generalizable medical NLU model through instruction fine-tuning and knowledge distillation, and evaluating it on the dataset developed in aim (1); and (3) developing more generalizable and explainable dermatology VLM through open-vocabulary concept-based image segmentation and object detection. Together, we hope to enhance the generalizability and explainability of medical language and vision models.
ANNOUNCEMENTS
New $12.6M grant to help unravel hallucinations
UW Medicine researchers, Dr. Dror Ben-Zeev and Dr. Trevor Cohen have received a five-year, $12.6 million grant to create a predictive AI tool for people who experience hallucinations. Hallucinations are the most common psychotic experience, they occur in about 13% of the U.S. population. The new project, an app that will be given to 2,000 participants, is meant to help clinicians identify the severity of hallucinations and the need for a deeper level of care.
May 20 – May 24, 2024
UPCOMING LECTURES AND SEMINARS
BIME 590
Walter H. Curioso, M.D., Ph.D., M.P.H.
Thursday, May 30th – 11-11:50 am
850 Republican Street, Building C, Room 123 A/B
Zoom Information: https://washington.zoom.us/my/bime590
Speaker will be in-person
Title: Telehealth for Strengthening Health Systems in Low- and Middle-income Countries: A Perspective from Peru
Abstract: The COVID-19 pandemic underscored the critical need for robust infrastructure and strengthened health information systems in low- and middle-income countries. Telehealth has the potential to significantly improve access to care, especially in rural and hard-to-reach areas. However, barriers such as the digital divide, privacy concerns, and resistance from healthcare professionals need to be addressed.
The pandemic prompted Peru to rapidly adjust its legal framework to adopt telemedicine and promote telehealth services, addressing urgent healthcare needs. This talk will review the regulatory changes and highlight key telehealth initiatives that emerged in Peru during the pandemic. The evolution of the Peruvian telehealth framework began in 2005, with subsequent laws aimed at establishing a national telehealth network. Despite these efforts, challenges remain, such as inadequate infrastructure in healthcare centers, limited high-speed Internet connectivity, and the need for better interoperability of health information systems. Telehealth represents a transformative approach to enhancing health systems in Peru and other low- and middle-income countries, with the potential to improve public health services beyond the pandemic.
Speaker Bio: Dr. Curioso holds a Ph.D. in Biomedical Informatics from the University of Washington (UW), Seattle, United States, as well as an M.P.H. from UW, and received his M.D. from Universidad Peruana Cayetano Heredia in Peru. Over the past 20 years, Dr. Curioso has held numerous leadership positions at both national and international levels, spanning the public and private sectors. He was elected a member of the World Health Organization Digital Health Roster of Experts. In academia, he is an Affiliate Associate Professor in the Department of Biomedical Informatics and Medical Education in the School of Medicine at the University of Washington, Seattle, Washington, USA. Dr. Curioso is currently the Vice Provost for Research at Universidad Continental in Peru. He is a founding associate editor of Oxford Open Digital Health and a member of the editorial board of the journals International Journal of Medical Informatics, Informatics for Health and Social Care, and Population Health Metrics. Dr. Curioso has recently been elected to the 2024 class of Academy Fellows of the International Academy of Health Sciences Informatics. His full bio and publications can be found here.
PAPERS & PRESENTATIONS
Wei Q, Mease PJ, Chiorean M, Iles-Shih L, Matos WF, Baumgartner A, Molani S, Hwang YM, Belhu B, Ralevski A, Hadlock J. Machine learning to understand risks for severe COVID-19 outcomes: a retrospective cohort study of immune-mediated inflammatory diseases, immunomodulatory medications, and comorbidities in a large US health-care system. Lancet Digit Health. 2024 May, 10.1016/S2589-7500(24)00021-9.
UPCOMING EXAMS
Final Exams
Title: Making Health Knowledge Accessible Through Personalized Language Processing
Student: Yue Guo
Date/Time: Thursday, May 30, 2 pm
Location: C123 A/B
Zoom: https://washington.zoom.us/my/cohenta
Abstract: The pandemic exposed the difficulties the general public faces when attempting to use scientific information to guide their health-related decisions. Though widely available in scientific papers, the information required to guide these decisions is often not accessible: medical jargon, scientific writing styles, and insufficient background explanations make this information opaque to non-experts. Consequently, there is a pressing need to deliver scientific knowledge in lay language, which has motivated researches on automated plain language summary generation to make the health information more accessible.
In this talk, I will discuss my efforts in this direction, including building a novel dataset, identifying unique challenges within this task, and developing new methods to address those challenges. A key part of this process has been evaluating existing metrics to see if they effectively measure performance for this task, and considering if there might be better options. Finally, I will broaden the discussion beyond just health information – exploring how we can personalize and improve communication across different domains.
Title: Relationship between Metabolic Measurements and Brain Injury in Post-Cardiac Arrest Comatose Patients
Student: Kevin Chen
Date/Time: Wednesday, June 5, 9 AM
Location-Zoom only: https://washington.zoom.us/my/jhgennari?pwd=TUx0clkwKzdnS1ZQV1dXRnZqMWMzZz09
Abstract:
Cardiac arrest is a leading cause of death in the United States contributing to 5.6% of annual deaths. More than 80% of survivors are in permanent coma and 50-80% of those will die. Despite advancements in cardiac care, the mechanisms underlying brain injury are complex and not well understood, which has limited advancement in brain targeted therapies. Specifically, the relationship between regional brain metabolism and risk of brain injury is not known. This thesis investigated the relationship between brain injury in post-cardiac arrest comatose patients and metabolic characteristics: cerebral blood flow (CBF), cerebral blood volume (CBV), cerebral metabolic rate of oxygen (CMRO2), and cerebral metabolic rate of glucose (CMRglu). The study analyzed whole brains, brains clustered by injury percentages, and brain regions clustered by injury percentage. Resulting correlations showed that CMRO2 and CMRglu had stronger correlations with brain injury than CBF and CBV, indicating a closer link between oxygen and glucose utilization and brain damage. Patients with minimal injury exhibited weak correlations, while patients with moderate to severe injuries displayed stronger correlations, emphasizing the critical role of oxygen and glucose metabolism in brain damage progression.
ANNOUNCEMENTS
Dr. Janice Sabin will lead a workshop, as a member of the Women’s National Health Forum Working Group, National Academies of Sciences, Engineering, and Medicine, Health & Medicine Division, title: Understanding micro-aggression and implicit bias awareness among providers and educators in maternal health. The workshop is #4 of a 5-part series, June 14, 2024. Panelists: Janice A. Sabin, PhD, MSW, Mary Owen, MD, Lauren Ramos, MPH. https://www.nationalacademies.org/our-work/maternal-health-disparities-the-women-behind-the-data-a-webinar-series
May 6 – May 10, 2024
UPCOMING LECTURES AND SEMINARS
BIME 590
Yue Guo, M.B.B.S., MHS
Thursday, May 16th – 11-11:50 am
850 Republican Street, Building C, Room 123 A/B
Zoom Information: https://washington.zoom.us/my/bime590
Title: Making Health Knowledge Accessible Through Personalized Language Processing
Abstract: The pandemic exposed the difficulties the general public faces when attempting to use scientific information to guide their health-related decisions. Though widely available in scientific papers, the information required to guide these decisions is often not accessible: medical jargon, scientific writing styles, and insufficient background explanations make this information opaque to non-experts. Consequently, there is a pressing need to deliver scientific knowledge in lay language, which has motivated researches on automated plain language summary generation to make the health information more accessible.
In this talk, I will discuss my efforts in this direction, including building a novel dataset, identifying unique challenges within this task, and developing new methods to address those challenges. A key part of this process has been evaluating existing metrics to see if they effectively measure performance for this task, and considering if there might be better options. Finally, I will broaden the discussion beyond just health information – exploring how we can personalize and improve communication across different domains.
Speaker Bio: Yue Guo is a physician-scientist and doctoral candidate at the University of Washington, Seattle, where she is pursuing a Ph.D. in Biomedical and Health Informatics. Her unique background, which includes an M.B.B.S (equivalent to an M.D.) from Capital Medical University in China, a master’s in epidemiology from Johns Hopkins University, and postdoctoral research experience in Radiation Oncology and Molecular Radiation Sciences at the Johns Hopkins University School of Medicine, allows her to bridge the gap between clinical medicine and informatics research.
Dr. Guo’s research is driven by a passion for improving healthcare delivery through the innovative application of artificial intelligence techniques. By leveraging her expertise in natural language processing and her deep understanding of clinical medicine, her doctoral work focuses on harnessing the power of cutting-edge AI technologies, such as large language models, to make health information more accessible, understandable, and actionable for patients and the general public.
PAPERS & PRESENTATIONS
Thomas Payne gave an invited plenary presentation titled “Artificial intelligence/machine learning in clinical care” at the Medicaid Medical Directors Network Spring Workshop in Seattle on May 2nd.
Presentations at EPIC XGM, Verona, WI:
- Hasan Ahmad and Angad Singh presented “Two Thumbs Up: Streamlining User Feedback on Order Sets and SmartSets.”
- Terri Kim and Angad Singh presented “Expanding Digital Access for Pregnancy Management Options.”
- Angad Singh presented “The Ins and Outs of Advance Beneficiary Notices (ABNs)” and “Honoring Patient Identities Across the Care Continuum.”
UPCOMING EXAMS
General Exam
Title: Imaging-based breast cancer risk prediction
Student: Wesley Surento
Date/Time: Monday, May 13, 2024, 2 pm
Location: 1144 Eastlake Ave E, LG502
Zoom: https://washington.zoom.us/my/jhgennari?pwd=TUx0clkwKzdnS1ZQV1dXRnZqMWMzZz09
Abstract: Many current breast cancer risk assessment tools applied in clinical settings utilize risk factors such as age, menopausal status, personal biopsy history, and family history of breast cancer, which reflect risk characteristics well at an aggregate level. While imaging markers could potentially better provide risk estimates at the individual level, they are not built into most breast cancer risk prediction models. There remains much unexplored potential in leveraging imaging markers as part of risk assessment models for prevention and early prediction.
In this work, we aim to develop and assess a new risk prediction model that incorporates MRI-derived features along with clinical risk factors. For Aim 1, we will build a collection of breast imaging and clinical risk factors for a population of women who underwent breast cancer screening. In addition to our repository of MR image data for the study cohort, a REDcap database will be used to store their clinical risk factors obtained from electronic health records, such as select demographic information, menopausal status, BRCA mutation, and family history of breast cancer. In Aim 2, we will develop image processing pipelines to extract quantitative breast imaging markers such as background parenchymal enhancement and apparent diffusion coefficient. We are interested in assessing their ability to predict breast cancer diagnosis in women at high risk. In Aim 3, we will develop a new breast cancer risk model that incorporates both imaging markers as well as clinical risk factors in a multimodal approach, and compare its performance against a conventional risk prediction tool.
ANNOUNCEMENTS
New $12.6M NIH grant awarded to UW Medicine researchers
Researchers from UW Psychiatry and Biomedical Informatics have received a 5-year grant to create a digital evaluation tool for people who experience hallucinations. Project staff include BIME constituents Meliha Yetisgen, Patrick Wedgeworth and Oliver Bear Don’t Walk, as well as two BIME PhD students (Weizhe Xu and Feng Chen) as RAs. Please see more information here.
Renewal of NIH Center for Reproducible Biomedical Modeling Grant
The Department of Bioengineering and Herbert M Sauro, PI, are pleased to announce that nearly $6 million will be provided by the National Institute of Biomedical Imaging and Bioengineering to continue the work of the Center. This is a unique collaborative, multi-institutional project, with leading investigators at the University of Connecticut (Ion Moraru, Eran Agmon), University of Wisconsin-Madison (Elebeoba May), the University of Auckland (David Nickerson) and the UW Department of Biomedical Informatics and Medical Education (John Gennari), as well as the UW eScience Institute (Joseph Hellerstein). The goal of the center is to improve multi-scale and integrative modeling of biomedical systems that can support precision medicine and credible predictive models for biomedicine. The center aims to CURE these models by making them credible, understandable, reproducible, and extensible.
Yue Guo will be joining UIUC iSchool as a tenure-track Assistant Professor this Fall.
April 29 – May 3, 2024
UPCOMING LECTURES AND SEMINARS
BIME 590
Zhiyong Lu, PhD FACMI, FIAHSI
Thursday, May 9th – 11-11:50 am
850 Republican Street, Building C, Room 123 A/B
Zoom Information: https://washington.zoom.us/my/bime590
Speaker will be in-person
Title: Transforming Medicine with AI: from PubMed Search to TrialGPT
Abstract: The explosion of biomedical big data and information in the past decade or so has created new opportunities for discoveries to improve the treatment and prevention of human diseases. As such, the field of medicine is undergoing a paradigm shift driven by AI-powered analytical solutions. This talk explores the benefits (and risks) of AI and ChatGPT, highlighting their pivotal roles in revolutionizing biomedical discovery, patient care, diagnosis, treatment, and medical research. By demonstrating their uses in some real-world applications such as improving PubMed searches (Fiorini et al., Nature Biotechnology 2018), supporting precision medicine (LitVar, Allot et al., Nature Genetics 2023), and accelerating patient trial matching (TrialGPT), we underscore the potential of AI and ChatGPT in enhancing clinical decision-making, personalizing patient experiences, and accelerating knowledge discovery.
Speaker Bio: Dr. Zhiyong Lu is a tenured Senior Investigator at the NIH/NLM IPR, leading research in biomedical text and image processing, information retrieval, and AI/machine learning. In his role as Deputy Director for Literature Search at NCBI, Dr. Lu oversees the overall R&D efforts to improve literature search and information access in resources like PubMed and LitCovid, which are used by millions worldwide each day. Additionally, Dr. Lu is Adjunct Professor of Computer Science at the University of Illinois Urbana-Champaign (UIUC). Dr. Lu serves as an Associate Editor of Bioinformatics, Organizer of the BioCreative NLP challenge, and Chair of the ISCB Text Mining COSI. With over 350 peer-reviewed publications, Dr. Lu is a highly cited author, and a Fellow of the American College of Medical Informatics (ACMI) and the International Academy of Health Sciences Informatics (IAHSI).
PAPERS & PRESENTATIONS
Bradley ER*, Portanova J*, Woolley JD, Buck B, Painter IS, Hankin M, Xu W, Cohen T. Quantifying abnormal emotion processing: a novel computational assessment method and application in schizophrenia. Psychiatry Research. 2024 Apr 4:115893. * denotes co-first authorship. (link)
UPCOMING EXAMS
Final Exam
Title: Transformative Diagnostics: Applying Transformer Networks and Semantic Guidance to Whole Slide Images
Student: Meredith (Wenjun) Wu
Date/Time: Monday, May 6 at 11 am
Location: Allen Center 303 Conference Room
Zoom: https://washington.zoom.us/j/97904765629
Abstract: This dissertation advances digital pathology by developing deep learning techniques for more accurate and efficient analysis of skin and breast cancer from whole slide images. It introduces innovative approaches like VSGD-Net and a two-stage segmentation method, along with transformer-based models such as HatNet and ScatNet, which leverage self-attention to understand contextual relationships within the images. A key innovation is the Semantics-Aware Attention Guidance framework that enhances diagnostic precision and interpretability by focusing on critical areas, significantly outperforming existing models. These advancements provide pathologists with powerful tools, bridging the gap between computational models and clinical applications, thereby improving early detection, diagnosis, and treatment of cancer.
General Exam
Title: Imaging-based breast cancer risk prediction
Student: Wesley Surento
Date/Time: Monday, May 13, 2024, 2 pm
Location: 1144 Eastlake Ave E, LG502
Zoom: https://washington.zoom.us/my/jhgennari?pwd=TUx0clkwKzdnS1ZQV1dXRnZqMWMzZz09
Abstract: Many current breast cancer risk assessment tools applied in clinical settings utilize risk factors such as age, menopausal status, personal biopsy history, and family history of breast cancer, which reflect risk characteristics well at an aggregate level. While imaging markers could potentially better provide risk estimates at the individual level, they are not built into most breast cancer risk prediction models. There remains much unexplored potential in leveraging imaging markers as part of risk assessment models for prevention and early prediction.
In this work, we aim to develop and assess a new risk prediction model that incorporates MRI-derived features along with clinical risk factors. For Aim 1, we will build a collection of breast imaging and clinical risk factors for a population of women who underwent breast cancer screening. In addition to our repository of MR image data for the study cohort, a REDcap database will be used to store their clinical risk factors obtained from electronic health records, such as select demographic information, menopausal status, BRCA mutation, and family history of breast cancer. In Aim 2, we will develop image processing pipelines to extract quantitative breast imaging markers such as background parenchymal enhancement and apparent diffusion coefficient. We are interested in assessing their ability to predict breast cancer diagnosis in women at high risk. In Aim 3, we will develop a new breast cancer risk model that incorporates both imaging markers as well as clinical risk factors in a multimodal approach, and compare its performance against a conventional risk prediction tool.
ANNOUNCEMENTS
Zoljargal Lkhagvajav (Zoey) was an organizer of the workshop presented by the Mongolian Ministry of Health and the Ministry of Digital Development – “State Productivity Recovery – Digital Health Convergence Workshop” in April with the support of the Mongolian Prime Minister, UNICEF, and the Asia eHealth Information Network. Almost 300 participants from various sectors gathered to attend the discussion about Mongolia’s current digital health landscape and the development of the National Digital Health Strategy. More details are available here.
Janice Sabin was invited by the National Institutes of Health and the National Institute on Minority Health and Health Disparities (NIH/NIMHD) to participate as a discussant in an upcoming workshop titled, Addressing the Influence of Interpersonal Biases on Health Outcomes and Disparities, June 18, 2024. Knowledge from the workshop will help NIH assess the need for future funding opportunities in this understudied area. Participants will include federal program staff, and research scientists and clinicians with expertise in the science of interpersonal biases (implicit and explicit stereotyping and prejudice) and health.