Chair’s Message
We are moving toward our vision with a number of activities. We completed the Clinical Informatics Fellowship match and filled our two open positions with two excellent candidates who started July 2018. We completed the interview process for our research focused MS and research focused PhD programs, and have a new cohort who will start in Fall 2018. Applications are open for our applied on-line MS in Clinical Informatics and Patient Centered Technologies. We are beginning a new overall strategic planning process for all of our Departmental activities in conjunction with preparing for our every 10 year academic program review. We are still actively recruiting new faculty as part of our strategic plan to expand our core faculty by 50%, with 3-4 positions remaining to be filled over the next two years (see link).
Cordially,
Peter Tarczy-Hornoch, MD
Chair and Professor, Department of Biomedical Informatics and Medical Education
Biomedical Informatics and Medical Education Newsletter
May 27-May 31, 2019
UPCOMING LECTURES AND SEMINARS
BIME 590A – Biomedical & Health Informatics Lecture Series
Thursday, May 30, 4:00pm-4:50pm, UW Medicine South Lake Union, Building C, Room C259 (livestream at tcs.slu.washington.edu)
Speaker: Milen Nokolov
Title: TBD
BIME 591C– Hands on with FHIR and other Healthcare Data Standards
Monday, May 27: No Class, Memorial Day Holiday
UPCOMING DISSERTATION DEFENSE
Karl Jablonowski
Monday, June 3; 3:00 pm; Room: CSE 403
Title: Data Mining the Electronic Medical Record with Intelligent Agents to Inform Decision Support Systems
Abstract: An intelligent agent framework is used on an ICU EMR to create prediction models for disease onset. Eleven models are created to inspect 5 diseases: acute respiratory distress syndrome (ARDS); severe acute hypoxemic respiratory failure (SAHRF); acute kidney injury (AKI); sepsis; and disseminated intravascular coagulation (DIC).
Four of the models (ARDS, AKI Stage 1, AKI Stage 2, and sepsis) are competitive or superior to the best comparable peer-reviewed models. The other seven are novel, including: SAHRF (AUC=0.952); DIC from ARDS positive patients (AUC=0.722); ARDS from DIC positive patients (AUC=0.675); AKI Stage 3 (AUC=0.983); the progression from AKI Stage 1 to Stage 2 (AUC=0.930); the progression from AKI Stage 2 to Stage 3 (AUC=0.951); and DIC (AUC=0.838).
In derivative work: a correlation between pre-DIC patients and metabolic acidosis is shown, a meta-analysis on misclassified patients is given, a disease pathway that demonstrates how ARDS and DIC can interact in a positive feedback loop is presented. DIC is shown to be implicated in 78% of all in-hospital mortality of ARDS patients.
Ryan James
Tuesday, June 4; 9:00 am, 4545 Roosevelt Way NE, #300
Title: A New Perspective On Minimally Invasive Procedures: Exploring the Utility of a Novel Virtual Reality Endovascular Navigation System
Abstract: TBD
UPCOMING MASTER’S DEFENSE
Sandeep Napa
Monday, June 3; 11:00 am, Room: Trail Room, Health Sciences Library
Title: An evaluation of the insidious consequences of clinical computing infrastructure failures at a large academic medical center
Abstract: Electronic Health Records (EHRs) are intended to make healthcare delivery safer, more effective and accountable. EHRs are complex socio-technical systems that are dependent on the proper functioning of many individual components that comprise the clinical computing infrastructure (CCI), such as networking equipment, message routing systems, and departmental clinical computing systems and many others. However, on occasion these CCI components fail or need maintenance, causing clinical workflow and data flow disruptions. Considering the inherently disruptive nature of EHR downtimes, organizations typically have mitigating procedures in place. However, many other small hardware or software CCI components also fail, causing loss of EHR functionality, insidiously. A systematic analysis of CCI failures has not been undertaken so far. A dataset of CCI system failure logs gathered at one health care system was classified and categorized to shed light on the nature, frequency and user impact of such CCI failures. By number of records, the top 3 components that had the highest frequency of failure are: Network (393 incidents, 59.5% of which were unscheduled) the inpatient EHR (ORCA) (372 incidents, 49.5% unscheduled) the outpatient EHR (Epic) (228 incidents, 12.3% unscheduled). In terms of user impact, components that accumulated the most failures are: the inpatient EHR (ORCA) (284.8 hours among under 5 users), Cloverleaf (interface engine) (263.5 hours among under 200 users), imaging (205.8 hours among under 50 users), and network (193.9 hours among under 50 users, and 193.4 hours among under 10 users). It is interesting to note that 4 of the 5 aforementioned components affected under 50 users. So, it is possible that cumulatively these small-impact but more frequent CCI component failures may approach or exceed the clinical impact of EHR downtimes. Although the data used in this work have important limitations in in their accuracy and completeness, this exploratory analysis is the first step towards a better understanding how to build a safe, resilient CCI that more reliably serves the needs of patients and providers.
UPCOMING GENERAL EXAM
Pascal Brandt
Tuesday, June 11; 12:00 pm, Room T473, Health Sciences Building
Title: EHR-Driven Phenotyping: Improving Standards & Methods for Secondary Use of EHR Data
Abstract: The meteoric rise of electronic health record (EHR) use over the past decade has led to the creation of large clinical databases. These databases present an un- precedented opportunity for biomedical knowledge discovery. Data may be used for any number of research purposes, such as epidemiological, operational or quality improvements studies, pragmatic trials or clinical trial recruitment, comparative effectiveness research, predictive modeling, clinical decision support, pharmacovigilance, and genome-wide association studies, to name a few. In every case, one of the first steps involved is identifying the appropriate cohort of patients matching inclusion and exclusion criteria, using only data available in the EHR. This is currently done by developing executable queries using local data models and terminologies, which is a slow, error prone process that must be repeated for each database included in a study. This process, known as EHR-driven phenotyping, is a critical rate limiting factor that prevents massive scaling of knowledge discovery, and ultimately inhibits our ability to achieve the promise of national imperatives such as the Learning Healthcare System and All of Us. This research will attempt to improve the state of the art of EHR-driven phenotyping in three specific ways. First, we will propose a framework to reason about the complexity of existing inclusion and exclusion criteria (called phenotype algorithms). Second, we will assess the potential of popular and emerging standards for their suitability as a formal phenotype algorithm representation. Finally, we will develop and evaluate a standards-based tool that can be used to author phenotype algorithms and execute them on existing EHR databases.
PUBLICATIONS AND PRESENTATIONS
Lucy Lu Wang; G. Thomas Hayman; Jennifer R. Smith; Monika Tutaj; Mary E. Shimoyama; John H. Gennari; Predicting instances of Pathway Ontology classes for pathway integration
Journal of Biomedical Semantics JBSM-D-18-00054R2
FACULTY/STUDENT/ALUMNI/STAFF ACTIVITIES
Jason Thomas, BS, University of Washington; Congratulations to the 2019-2020 JAMIA Student Editorial Board! The AMIA student members will contribute to the peer-review process for JAMIA by attending Editorial Board meetings and reviewing manuscripts.
Fred Wolf Mentorship Award:
As most of you know, our former department Chair, Fred Wolf passed away in 2018 after a long and courageous battle. At his memorial service a recurring theme from most everyone who spoke of him was what a wonderful and inspiring mentor he was. As a way to honor Fred and keep his spirit in our midst, the department announced the establishment of the Fred Wolf Mentorship Award. We are soliciting nominations for this award again this year.
The award is open to all BIME faculty, staff, postdocs and students to both nominate and receive the award.
The process is simple, please send an email to Heidi, heidi5@uw.edu with a paragraph or two nominating a faculty member, staff member, postdoc or student to receive the award. Please briefly describe how your nominee has mentored you. A review committee will be formed to review the nominations and make the final selection.
Nomination deadline is Friday, June 7th. The award recipient will be announced at our annual end of year celebration on June 14th.
Please let Heidi know if you have any questions (heidi5@uw.edu).
May 20-May 24, 2019
UPCOMING LECTURES AND SEMINARS
BIME 591C– Hands on with FHIR and other Healthcare Data Standards
Monday, May 13: 12:30pm- 1:20pm, Health Sciences Building, T530
Facilitators: Hannah Burkhardt, Jared Erwin, Piotr Mankowski, David Crosslin, Bill Lober
UPCOMING DISSERTATION DEFENSE
Karl Jablonowski
Monday, June 3; 3:00 pm; Room: CSE 403
Title: Data Mining the Electronic Medical Record with Intelligent Agents to Inform Decision Support Systems
Abstract: An intelligent agent framework is used on an ICU EMR to create prediction models for disease onset. Eleven models are created to inspect 5 diseases: acute respiratory distress syndrome (ARDS); severe acute hypoxemic respiratory failure (SAHRF); acute kidney injury (AKI); sepsis; and disseminated intravascular coagulation (DIC).
Four of the models (ARDS, AKI Stage 1, AKI Stage 2, and sepsis) are competitive or superior to the best comparable peer-reviewed models. The other seven are novel, including: SAHRF (AUC=0.952); DIC from ARDS positive patients (AUC=0.722); ARDS from DIC positive patients (AUC=0.675); AKI Stage 3 (AUC=0.983); the progression from AKI Stage 1 to Stage 2 (AUC=0.930); the progression from AKI Stage 2 to Stage 3 (AUC=0.951); and DIC (AUC=0.838).
In derivative work: a correlation between pre-DIC patients and metabolic acidosis is shown, a meta-analysis on misclassified patients is given, a disease pathway that demonstrates how ARDS and DIC can interact in a positive feedback loop is presented. DIC is shown to be implicated in 78% of all in-hospital mortality of ARDS patients.
UPCOMING MASTER’S DEFENSE
Sandeep Napa
Monday, June 3; 11:00 am, Room: Trail Room, Health Sciences Library
Title: An evaluation of the insidious consequences of clinical computing infrastructure failures at a large academic medical center
Abstract: Electronic Health Records (EHRs) are intended to make healthcare delivery safer, more effective and accountable. EHRs are complex socio-technical systems that are dependent on the proper functioning of many individual components that comprise the clinical computing infrastructure (CCI), such as networking equipment, message routing systems, and departmental clinical computing systems and many others. However, on occasion these CCI components fail or need maintenance, causing clinical workflow and data flow disruptions. Considering the inherently disruptive nature of EHR downtimes, organizations typically have mitigating procedures in place. However, many other small hardware or software CCI components also fail, causing loss of EHR functionality, insidiously. A systematic analysis of CCI failures has not been undertaken so far. A dataset of CCI system failure logs gathered at one health care system was classified and categorized to shed light on the nature, frequency and user impact of such CCI failures. By number of records, the top 3 components that had the highest frequency of failure are: Network (393 incidents, 59.5% of which were unscheduled) the inpatient EHR (ORCA) (372 incidents, 49.5% unscheduled) the outpatient EHR (Epic) (228 incidents, 12.3% unscheduled). In terms of user impact, components that accumulated the most failures are: the inpatient EHR (ORCA) (284.8 hours among under 5 users), Cloverleaf (interface engine) (263.5 hours among under 200 users), imaging (205.8 hours among under 50 users), and network (193.9 hours among under 50 users, and 193.4 hours among under 10 users). It is interesting to note that 4 of the 5 aforementioned components affected under 50 users. So, it is possible that cumulatively these small-impact but more frequent CCI component failures may approach or exceed the clinical impact of EHR downtimes. Although the data used in this work have important limitations in in their accuracy and completeness, this exploratory analysis is the first step towards a better understanding how to build a safe, resilient CCI that more reliably serves the needs of patients and providers.
PUBLICATIONS AND PRESENTATIONS
Hartzler AL, Ralston JD, Hannan T, Kelleher K, Penfold RB. Designing safer use of antipsychotics in youth: A human-centered approach. Psychiatric Services, in Press.
Chen, A. T., Wu, S., Tomasino, K. N., Lattie, E. G., & Mohr, D. C. (2019). A multi-faceted approach to characterizing user behavior and experience in a digital mental health intervention. Journal of Biomedical Informatics, 94, 103187. https://doi.org/10.1016/j.jbi.2019.103187
Swaminathan, A., Shirts, B. H., & Chen, A. T. (2019). Incorporating user feedback in the design of a genetics analysis tool: A two-part approach. Journal of Biomedical Informatics, 103204. https://doi.org/10.1016/j.jbi.2019.103204
Luo, B.L. Stone, C. Koebnick, S. He, D.H. Au, X. Sheng, M.A. Murtaugh, K.A. Sward, M. Schatz, R.S. Zeiger, G.H. Davidson, and F.L. Nkoy. Using Temporal Features to Provide Data-Driven Clinical Early Warnings for Chronic Obstructive Pulmonary Disease and Asthma Care Management: Protocol for Secondary Analysis. JMIR Research Protocols, 2019
FACULTY/STUDENT/ALUMNI/STAFF ACTIVITIES
Mike Leu, MD, MS, MHS, FAAP, has been recognized as part of the inaugural class of Fellows of the American Medical Informatics Association at the AMIA Clinical Informatics Conference in Atlanta in April. https://www.amia.org/fellows-amia
Abdul Alshammari, PhD Candidate, and his wife Sana are proud parents to a new baby girl. Alia was born on April 17th at 2:08 AM, weighing about 7 pounds and measuring about 20 inches. All are doing well!
May 13-May 17, 2019
UPCOMING LECTURES AND SEMINARS
BIME 590A – Biomedical & Health Informatics Lecture Series
Thursday, May 16, 4:00pm-4:50pm, UW Medicine South Lake Union, Building C, Room C123AB
(livestream at tcs.slu.washington.edu)
Speaker: Joey Mukherjee
Title: TBD
BIME 591C– Hands on with FHIR and other Healthcare Data Standards
Monday, May 13: 12:30pm- 1:20pm, Health Sciences Building, T530
Facilitators: Hannah Burkhardt, Jared Erwin, Piotr Mankowski, David Crosslin, Bill Lober
UPCOMING MASTER’S DEFENSE
Sandeep Napa
Monday, June 3; 11:00 am, Room: TBD
Title: An evaluation of the insidious consequences of clinical computing infrastructure failures at a large academic medical center
Abstract: Electronic Health Records (EHRs) are intended to make healthcare delivery safer, more effective and accountable. EHRs are complex socio-technical systems that are dependent on the proper functioning of many individual components that comprise the clinical computing infrastructure (CCI), such as networking equipment, message routing systems, and departmental clinical computing systems and many others. However, on occasion these CCI components fail or need maintenance, causing clinical workflow and data flow disruptions. Considering the inherently disruptive nature of EHR downtimes, organizations typically have mitigating procedures in place. However, many other small hardware or software CCI components also fail, causing loss of EHR functionality, insidiously. A systematic analysis of CCI failures has not been undertaken so far. A dataset of CCI system failure logs gathered at one health care system was classified and categorized to shed light on the nature, frequency and user impact of such CCI failures. By number of records, the top 3 components that had the highest frequency of failure are: Network (393 incidents, 59.5% of which were unscheduled) the inpatient EHR (ORCA) (372 incidents, 49.5% unscheduled) the outpatient EHR (Epic) (228 incidents, 12.3% unscheduled). In terms of user impact, components that accumulated the most failures are: the inpatient EHR (ORCA) (284.8 hours among under 5 users), Cloverleaf (interface engine) (263.5 hours among under 200 users), imaging (205.8 hours among under 50 users), and network (193.9 hours among under 50 users, and 193.4 hours among under 10 users). It is interesting to note that 4 of the 5 aforementioned components affected under 50 users. So, it is possible that cumulatively these small-impact but more frequent CCI component failures may approach or exceed the clinical impact of EHR downtimes. Although the data used in this work have important limitations in in their accuracy and completeness, this exploratory analysis is the first step towards a better understanding how to build a safe, resilient CCI that more reliably serves the needs of patients and providers.
PUBLICATIONS AND PRESENTATIONS
Accepted for MedInfo 2019: Backonja U, Velez O, Cato K, Hardiker NR. Addressing Health Disparities Through Informatics (panel).
Misirli, Goksel; Taylor, Renee; Goñi-Moreno, Angel; Mclaughlin, James; Myers, Chris; Gennari, John; Lord, Phillip; Wipat, Anil. SBOL-OWL: An ontological approach for formal and semantic representation of synthetic biology information. sb-2018-00532g.R1 ACS Synthetic Biology
FACULTY/STUDENT/ALUMNI/STAFF ACTIVITIES
BIME Happy Hour
Thursday, May 16, 5:00 p.m., South Lake Union, Reception Lounge (immediately following the BIME 590 Seminar)
Please join us for our monthly departmental BYOB Happy Hour. As always, please bring your own beverage; snacks will be provided!
May 6-May 10, 2019
UPCOMING LECTURES AND SEMINARS
BIME 590A – Biomedical & Health Informatics Lecture Series
Thursday, May 9, 4:00pm-4:50pm, UW Medicine South Lake Union, Building C, Room C123AB
(livestream at tcs.slu.washington.edu)
Speaker: Arpit Patel
Title: TBD
BIME 591C– Hands on with FHIR and other Healthcare Data Standards
Monday, May 6: 12:30pm- 1:20pm, Health Sciences Building, T530
Facilitators: Hannah Burkhardt, Jared Erwin, Piotr Mankowski, David Crosslin
BIME Special Guest – Ajay Dharod, MD
Monday, May 6, 10:00 a.m., South Lake Union, Brotman Auditorium (from off-site connect through Zoom: https://washington.zoom.us/j/569844395)
Speaker: Ajay Dharod, MD
Assistant Professor, Wake Forest School of Medicine, Winston-Salem, NC
Title: An Epic Truth
Abstract: Developing informatics programs can be challenging in the era of ubiquitous commercial electronic health records (EHRs). Commercial EHR policies, adherence to change management, regulatory-, security- and privacy-issues are important considerations in the development and implementation of clinical informatics agendas to improve human health, improve provider satisfaction and decrease health-related costs. Dr. Ajay Dharod shares examples of applied clinical informatics innovations and collaborations developed at Wake Forest School of Medicine in the operations, research and education domains.
PUBLICATIONS AND PRESENTATIONS
Demiris, G, Lin, S-L, Turner, AM. The role of Patient Safety in Personal Health Information Management in promoting patient safety in the home: A qualitative study. MED INFO 2019
FACULTY/STUDENT/ALUMNI/STAFF ACTIVITIES
Accepted to MEDINFO 2019
Workshop: The Wave of Patient Generated Health Data: Implications for Health Systems (D Capurro, A Turner, G Demiris)
Poster: Personal Health Information Management Practices of Older Adults: One Size Does Not Fit All (A Turner, K Osterhage, A Hartzler, J Taylor, G Demiris)
clinical data analytics, and healthcare process mining.OTHER NEWS
VAHC 2019 (10th workshop on Visual Analytics in Healthcare)
http://www.visualanalyticshealthcare.org/
The primary objective of the annual workshop is to bring together medical experts, leading scientists, and visionaries to discuss visualization techniques that can be applied to healthcare data and discuss the areas of healthcare that need more attention from the visualization and visual data mining communities. The workshop will allow participants to showcase their ongoing work on visual analytics of healthcare-related data through podium, posters, or demo presentations. This year we are accepting posters for both original work, and for work previously accepted elsewhere or concurrently at VIS.
IMPORTANT DATES:
Deadline for submission:
June 17th, 2019
Notification of acceptance:
August 5th, 2019
Camera-ready papers due:
August 22th, 2019
VAHC 2019 workshop: October 20th, 2019
CONTACT: vahc.sig@gmail.com