Paper presentation at the Workshop on Visual Analytics in Healthcare in conjunction with the IEEE VisWeek 2011, Providence, RI, 2011.
Abstract:
Electronic Medical Record (EMR) databases contain a large amount of temporal events
such as diagnosis dates for various symptoms.
Analyzing disease progression pathways in terms of these observed events
can provide important insights into how diseases evolve over time.
Moreover, connecting these pathways to the eventual outcomes of the corresponding patients
can help clinicians understand how certain progression paths may lead to better or worse outcomes.
In this paper, we describe the Outflow visualization technique,
designed to summarize temporal event data that has been extracted from the EMRs of a cohort of patients.
We include sample analyses to show examples of the insights that can be learned from this visualization.
3. Time
Patient #1
Aug 1998 Oct 1998 Jan 1999
Ankle Edema Cardiomegaly Weight Loss
m
4. Many patient records
Time
Patient #1
Ankle Cardio. Weight
Patient #2
Ankle Cardio. Rales
Patient #3
Ankle Rales Cardio.
Patient #n
Ankle Weight Rales Cardio.
m
5. with outcome
Time
Patient #1 Live (1)
Ankle Cardio. Weight
Patient #2 Live (1)
Ankle Cardio. Rales
Patient #3 Die (0)
Ankle Rales Cardio.
Patient #n Live (1)
Ankle Weight Rales Cardio.
m
19. Select alignment point
Target patient’s current state
What are the paths What are the paths
that led to ? after ?
Ankle
Cardio.
Weight
[A,C,W]
m
20. Outflow Graph
Alignment Point
[A] [A,C]
[]
[A,C,W]
[A,C,D,W]
m
21. Outflow Graph
Alignment Point
[A] [A,C]
[] [A,W]
[A,C,W]
[A,C,D,W]
m
22. Outflow Graph
Alignment Point
[A] [A,C]
[A,C,R,W]
[] [A,W]
[A,C,W]
[A,C,D,W]
m
23. Outflow Graph
Alignment Point
[A] [A,C]
[A,C,R,W]
[] [C] [A,W]
[A,C,W]
[A,C,D,W]
[W] [C,W]
Average outcome = 0.4
Average time = 10 days
Number of patients = 10
m
25. Past Future
NOW
Node’s horizontal position
shows sequence of states.
A!
C!
W! End of path
A!
A!
C!
time link A!
Node’s height is
edge edge C! number of patients.
D!
C!
Color is outcome Time edge’s width is
measure. duration of transition. m
32. Future Work
• Evaluation & Design Improvement
• Use outcome from predictive modeling
• Similarity measure to select similar patients
m
33. Conclusions
• Electronic Medical Records
– Rich information
– Large
• Visualization: Outflow
– Visual summary: overview
– Interactive exploration: zoom, filter and details
• Not specific to CHF, or medical domain
Contact me
krist.wongz@gmail.com
@kristwongz
m
34. Soccer Results
Alignment Point
1-0 2-0
2-2
0-0 1-1
2-1
3-1
0-1 0-2
Average outcome = win/lose
Average time = 10 minutes
Number of games = 10
m
36. Conclusions
• Electronic Medical Records
– Rich information
– Large
• Visualization: Outflow
– Visual summary: overview
– Interactive exploration: zoom, filter and details
• Not specific to CHF, or medical domain
Contact me
krist.wongz@gmail.com
@kristwongz
m