idmvis
play

IDMVis: Temporal Event Sequence Visualization for Type 1 Diabetes - PowerPoint PPT Presentation

Oct 28, 2022 •490 likes •1.16k views

IDMVis: Temporal Event Sequence Visualization for Type 1 Diabetes Treatment Decision Support Yixuan (Janice) Zhang Kartik Chanana Cody Dunne Contributions Contributions IDMVis a temporal event sequence visualization tool to support

  1. IDMVis: Temporal Event Sequence Visualization for Type 1 Diabetes Treatment Decision Support Yixuan (Janice) Zhang Kartik Chanana Cody Dunne

  2. Contributions

  3. Contributions • IDMVis – a temporal event sequence visualization tool to support diabetes treatment decision • Hierarchical Task Abstraction

  4. Contributions • IDMVis – a temporal event sequence visualization tool to support diabetes treatment decision • Hierarchical Task Abstraction Hierarchical Task Analysis

  5. Contributions • IDMVis – a temporal event sequence visualization tool to support diabetes treatment decision • Hierarchical Task Abstraction Hierarchical Task Analysis Task Abstraction

  6. Contributions • IDMVis – a temporal event sequence visualization tool to support diabetes treatment decision • Hierarchical Task Abstraction Hierarchical Task Analysis Task Abstraction Design

  7. Imagine a 10-year-old kid, who has been diagnosed with type 1 diabetes…

  8. Imagine a 10-year-old kid, who has been diagnosed with type 1 diabetes… Continuous Glucose Monitor (CGM)

  9. Imagine a 10-year-old kid, who has been diagnosed with type 1 diabetes… Continuous Glucose Monitor (CGM) Glucose Meter

  10. Imagine a 10-year-old kid, who has been diagnosed with type 1 diabetes… Continuous Glucose Monitor (CGM) Glucose Meter Insulin Injection

  11. Imagine a 10-year-old kid, who has been diagnosed with type 1 diabetes… Continuous Glucose Monitor (CGM) Glucose Meter Diabetes Logbook Insulin Sickness Food Exercise Injection

  12. During a clinical visit …

  13. During a clinical visit …

  14. During a clinical visit …

  15. During a clinical visit …

  16. How to help diabetes clinicians make treatment decisions? What are the tasks ?

  17. Hierarchical Task Analysis

  18. Hierarchical Task Analysis Task Abstraction Design Task analysis : Task 1 Task 2 Task 3 Task 4

  19. Hierarchical Task Analysis Task Abstraction Design Task analysis : Ultimate Goal ^ Hierarchical Task 1 Task 2 Task 1.1 Task 1.2

  20. Hierarchical Task Analysis Task Abstraction Design Develop a treatment plan and educate patients

  21. Hierarchical Task Analysis Task Abstraction Design 0. Develop a treatment plan and educate patients

  22. Hierarchical Task Analysis Task Abstraction Design Increasing Task Specificity 0. Develop a treatment plan and educate patients 1. Collect and display the patient’s data

  23. Hierarchical Task Analysis Task Abstraction Design Increasing Task Specificity 0. Develop a treatment plan and educate patients 1. 2. Collect and display Overview the the patient’s data patient’s data

  24. Hierarchical Task Analysis Task Abstraction Design Increasing Task Specificity 0. Develop a treatment plan and educate patients 1. 2. 3. Collect and display Overview the Reason about patient the patient’s data patient’s data blood glucose levels

  25. Hierarchical Task Analysis Task Abstraction Design Increasing Task Specificity 0. Develop a treatment plan and educate patients 1. 2. 3. 4. Collect and display Overview the Reason about patient Educate patients the patient’s data patient’s data blood glucose levels and caregivers

  26. Hierarchical Task Analysis Task Abstraction Design Increasing Task Specificity 0. Develop a treatment plan and educate patients 1. 2. 3. 4. 5. Collect and display Overview the Reason about patient Educate patients Make a the patient’s data patient’s data blood glucose levels and caregivers treatment plan

  27. Hierarchical Task Analysis Task Abstraction Design Increasing Task Specificity 0. Develop a treatment plan and educate patients 1. 2. 3. 4. 5. Collect and display Overview the Reason about patient Educate patients Make a the patient’s data patient’s data blood glucose levels and caregivers treatment plan 3.1 Examine post-event glucose level

  28. Hierarchical Task Analysis Task Abstraction Design Increasing Task Specificity 0. Develop a treatment plan and educate patients 1. 2. 3. 4. 5. Collect and display Overview the Reason about patient Educate patients Make a the patient’s data patient’s data blood glucose levels and caregivers treatment plan 3.1 3.2 Examine post-event Examine the interplay glucose level between events

  29. Hierarchical Task Analysis Task Abstraction Design Increasing Task Specificity 0. Develop a treatment plan and educate patients 1. 2. 3. 4. 5. Collect and display Overview the Reason about patient Educate patients Make a the patient’s data patient’s data blood glucose levels and caregivers treatment plan 3.1 3.2 Examine post-event Examine the interplay glucose level between events

  30. Hierarchical Task Analysis Task Abstraction Design 3.1 Examine post-event glucose level

  31. Hierarchical Task Analysis Task Abstraction Design Examine related 3.1 data to understand Examine post-event observation glucose level

  32. Hierarchical Task Analysis Task Abstraction Design Design Requirements

  33. Hierarchical Task Analysis Task Abstraction Design Design Requirements • DR1. Composite Visualization of Integrated Data

  34. Hierarchical Task Analysis Task Abstraction Design Design Requirements • DR1. Composite Visualization of Integrated Data • DR2. Visualization of Folded Temporal Data

  35. Hierarchical Task Analysis Task Abstraction Design Design Requirements • DR1. Composite Visualization of Integrated Data • DR2. Visualization of Folded Temporal Data • DR3. Align and Scale Temporal Data

  36. Hierarchical Task Analysis Task Abstraction Design Design Requirements • DR1. Composite Visualization of Integrated Data • DR2. Visualization of Folded Temporal Data • DR3. Align and Scale Temporal Data • DR4. Summary Statistics

  37. Hierarchical Task Analysis Task Abstraction Design Design of IDMVis

  38. Hierarchical Task Analysis Task Abstraction Design 14-Day Overview Summary Statistics Panel Detail View

  39. Hierarchical Task Analysis Task Abstraction Design 14-Day Overview Use small multiples to partition data folded by days

  40. Hierarchical Task Analysis Task Abstraction Design 14-Day Overview

  41. Hierarchical Task Analysis Task Abstraction Design Glucose Events from logbooks with blood glucose readings Meter

  42. Hierarchical Task Analysis Task Abstraction Design Glucose Events from logbooks with blood glucose readings Meter Continuous Glucose Monitor ( CGM )

  43. Hierarchical Task Analysis Task Abstraction Design Glucose Events from logbooks with blood glucose readings Meter Continuous below range Glucose (<70 mg/dL) Monitor normal range ( CGM ) (70-180 mg/dL) above range (>180 mg/dL)

  44. Hierarchical Task Analysis Task Abstraction Design Events from logbooks with blood glucose readings CGM normal range (70-180 mg/dL) CGM above range (>180 mg/dL) CGM below range (<70 mg/dL)

  45. Hierarchical Task Analysis Task Abstraction Design A pattern of high blood glucose after Single-event alignment lunch shown by purple circles

  46. Hierarchical Task Analysis Task Abstraction Design A pattern of high blood glucose after Single-event alignment lunch shown by purple circles 3.1 Examine post-event glucose level

  47. Hierarchical Task Analysis Task Abstraction Design Zoom-in window to show event details 3.1 Examine post-event glucose level

  48. Hierarchical Task Analysis Task Abstraction Design 3. Reason about patient blood glucose levels Zoom-in window to show event details 3.1 … Examine post-event glucose level

  49. Hierarchical Task Analysis Task Abstraction Design Dual-event alignment Stretch time scaling Events from logbooks with blood glucose readings CGM normal range (70-180 mg/dL) CGM above range (>180 mg/dL) CGM below range (<70 mg/dL)

  50. Hierarchical Task Analysis Task Abstraction Design Dual-event alignment Left-justified time scaling Events from logbooks with blood glucose readings CGM normal range (70-180 mg/dL) CGM above range (>180 mg/dL) CGM below range (<70 mg/dL)

  51. Hierarchical Task Analysis Task Abstraction Design Dual-event alignment Right-justified time scaling Events from logbooks with blood glucose readings CGM normal range (70-180 mg/dL) CGM above range (>180 mg/dL) CGM below range (<70 mg/dL)

  52. Hierarchical Task Analysis Task Abstraction Design Detail View

  53. Qualitative Study

  54. Participants Dietitians Certified diabetes educators (CDEs)

  55. Participants Average years of work experience: 17.2 years Dietitians Certified diabetes educators (CDEs)

  56. Methodology Semi-structured interviews C A B Day-by-meal table Exploration using IDMVis

  57. Results

  58. Results Superimposed detail view helps identify issues of data quality (e.g., missing or conflicting data) “ So sugar-to-treat [blood glucose] should have gone up from here, not down. It went down. Kept going down. Sugar to treat should be here , before this curve comes back up. That’s my concern . It’s missing something here . ” Missing something?

  59. Results Sentinel event alignment allows exploration of event sequence relationships

Recommend

More recommend