Are You Unsure what to work on over Christmas break? Why not write a paper for one of these special issues?


Special Focus Issue on Health Informatics and Health Equity: Improving Our Reach and Impact

Deadline: January 9, 2019

Special Focus Issue on 2018 n2c2 Shared-Task and Workshop on Adverse Drug Event Extraction

Deadline: January 30, 2019

Special Focus Issue on Cohort Selection for Clinical Trials

Deadline: January 16, 2019


Special Issue: Precision Medicine in the Patient-Centered Era

Deadline: January 15, 2019 

Journal of Biomedical and Health Informatics

Pervasive Sensing and Machine Learning for Mental Health

Deadline: December 31, 2018

Information Fusion for Medical Data: early, late and deep fusion methods for multimodal data

Deadline: December 31, 2018

Predictive Intelligence in Biomedical and Health Informatics

Deadline: January 31, 2019

Deep Learning in Ultrasound Imaging

Deadline: April 30, 2019

Journal of Artificial Intelligence

Special Issue on Ethics for Autonomous Systems

Deadline: September 5, 2018

Special Issue on Epistemic Planning

Deadline: March 1, 2019

Special Issue on Autonomous Agents Modelling Other Agents

Deadline: December 31, 2018

Journal of Artificial Intelligence in Medicine

Precision Digital Medicine and Health

Deadline: March 31, 2019

—tweet reply to comment—

My AMIA Annual Symposium 2018

AMIA2018 banner.png

Today’s post shows the sessions I am most interested in.

Sunday November 4th

8:00 AM — 12:00 PM

Student Paper Competition

8:30 AM — 12:00 PM

W23: Analysis of Human Interactive Behavior for Improving Health IT Usability and Clinical Workflow

3:30 PM — 5:00 PM

S01: Panel - Innovative Informatics Research and Practice in the Era of Commercial Electronic Health Records: Our Experience Using Epic

S04: Panel - The Healthcare Services Platform Consortium: building a marketplace for healthcare applications

Monday November 5th

8:30 AM–10:00 AM

S13: Panel - Making Electronic Health Records Safer: Practical Strategies for Evaluation and Improvement

S14: Panel - Preemptive Clinical Decision Support: Delivering Precise Information Clinicians Will Actually Use to Prevent Harm

S22: Featured Presentation - Year in Review

10:30 AM–12:00 PM

S24: Panel - The Road to Broader Adoption of CDS in a Learning Health System

S29: Doctoral Dissertation Award Presentations

1:45 PM–3:15 PM

S42: Oral Presentation - Predictive Models in Health Care

3:30 PM–5:00 PM

S48: Panel - Family Planning, FHIR, and the Office of Population Affairs: Creating Interoperability Standards for Large-scale Public Health Programs

S50: Oral Presentations - User-centered Design

S51: Featured Presentation - High School Scholars Program

5:00 PM–6:30 PM

Poster Session 1

Tuesday November 6th

8:30 AM–10:00 AM

S65: Featured Presentation - Informatics Inside the Beltway: Watching What Matters

S71: Oral Presentation - Phenotype and Event Prediction

S74: Oral Presentation - Health Information Systems and Assessment

10:30 AM–12:00 PM

S67: Panel - EHR Log Data: An Untapped Health Data Goldmine for Clinical Informatics Research?

S76: AMIA/HL7 FHIR© App Showcase

1:45 PM–3:15 PM

S78: Panel - Sensor Based Assessment for Learning and Care Quality: The New Frontier

S80: Panel - Collaborative Science Within Academic Medical Centers: Opportunities and Challenges for Informatics

3:30 PM–5:00 PM

S90: Panel - Natural Language Processing at Scale – Perspectives from Five Healthcare Organizations

S95: Oral Presentation - EHR and Workflow

5:00 PM–6:30 PM

Poster Session 2

Wednesday November 7th

8:30 AM–10:00 AM

S104: Oral Presentation - CDS and Quality

S105: Oral Presentation - Clinical Prediction and Documentation

S107: Oral Presentation - Transforming the EHR: Overcoming Barriers to Pragmatic Optimization [My Talk]

10:30 AM–12:00 PM

S116: Oral Presentation - Deep Learning

12:30 PM–1:45 PM

Closing Session and Keynote Presentation

Share the sessions you are excited about with a tweet reply!

Weekend Reads - Modeling Information Flows in Clinical Decision Support: Key insights for enhancing system effectiveness

We all want our clinical decision support systems (CDSS) to be effective. Metlock et al. (2016) seek to improve the categorization of CDSS effectiveness with a two-stream model of CDSS information flow: the clinical stream (reasoning about the patient) and the cognitive-behavioral stream (reasoning about the user).

Comment through a tweet reply below


Less COWs, better conversation

A JAMA research letter found "a reduction in simultaneous conversations and difficulty hearing" when rounding with fewer computers on wheels. They speculate that without individual access to the patient record, team members turned to the rounding conversation for information, increasing engagement. 

 Tweet reply to comment

Tweet reply to comment

A Model of Situational Awareness


Today's figure is from Understanding diagnostic errors in medicine: a lesson from aviation. Improving a clinician's situational awareness of a patient is one way for clinical decision support to lead to improved patient care. A clinician with high situational awareness perceives the details in a patient case, comprehends them, and uses them to project the future status of the patient. Projections are augmented by the different treatment options under consideration. Tweet reply to comment. 

Context Taxonomy

Context is the problem and the solution to improving AI systems. I will specify what I mean in future posts, but for now, I offer an introduction to how context is used in context-aware systems. 

 From Perera, Charith, et al. " Context aware computing for the internet of things: A survey ."  IEEE communications surveys & tutorials  16.1 (2014): 414-454.

From Perera, Charith, et al. "Context aware computing for the internet of things: A survey." IEEE communications surveys & tutorials 16.1 (2014): 414-454.

Weekend Reads: Designing better clinical decision support interfaces


You end of April weekend read will teach you how to design better interfaces. Miller et. al.provides recommendations on three fronts: interface (presentation), Information (content), and interaction (function). 

Which recommendation surprised you?  As always, Tweet reply below to comment.

Self-driving fatalities to become more frequent in the years ahead


Sad news out of Tempe, Arizona: a self-driving care has struck and killed a pedestrian.

Self-driving fatalities will become more frequent in the years ahead. This is not a critique of the technology, but a hard truth. There are over 30,000 traffic related deaths in the United States every year. So, even if self-driving cars were 1,000 times safer than human drivers, they would still be involved in 30 deaths a year.

The current automotive death toll is important to keep in mind as we look at the safety record of self-driving cars. Would it be better to have self-driving cars kill 10,000 people a year or human-driven cars kill 30,000?

[Tweet-reply to comment]