composer visual cohort analysis of patient outcomes
play

Composer: Visual Cohort Analysis of Patient Outcomes Jennifer - PowerPoint PPT Presentation

Composer: Visual Cohort Analysis of Patient Outcomes Jennifer Rogers, Nicholas Spina, Ashley Neese, Rachel Hess, Darrel Brodke, Alexander Lex 1 Lower Back Pain is a Significant Health Burden 2.6 Million Emergency Room visits Treatment exceeding


  1. Composer: Visual Cohort Analysis of Patient Outcomes Jennifer Rogers, Nicholas Spina, Ashley Neese, Rachel Hess, Darrel Brodke, Alexander Lex 1

  2. Lower Back Pain is a Significant Health Burden 2.6 Million Emergency Room visits Treatment exceeding $100 Billion 2

  3. This is Frank. He has a herniated disc. 3

  4. Intervertebral herniated disc Dakota Harr lower back pain weakness in legs bladder and bowel problems 4

  5. Three treatment options to consider with his doctor. 5

  6. Surgery mostly effective for persistent symptoms Risk involved, takes time to recover 12% will need another one within 4 years. 43% of these will need fusion 6

  7. Frank has some pre-existing conditions. Age 55 Diabetic BMI: 29 Tried physical therapy 7

  8. Takes these into account along with past experience and clinical guidelines. 8

  9. general population may not provide an accurate reflection of potential outcomes for patients with pre-existing conditions . diabetic BMI: 30 9

  10. EHR for evidence based comparisons Identify factors that can influence recovery and more accurately predict outcomes 10

  11. Dataset of Prior Cases Outcome Accurate Cohort Measures at Many Definition Timepoints Prognosis Under Different Treatment Options 11

  12. Cohorts : subset of the general population shares defining characteristics 12

  13. Effective for identifying influential factors. 13

  14. Investigating Patient Reported Outcomes as measure of well-being 14

  15. PROMIS P atient R eported O utcome M easurement I nformation S ystem. Evaluate and monitor physical, mental, social health . 15

  16. Focus on PROMIS physical function scores. 16

  17. 55: 72: Can go on a 32: Can run 10 short hike. Can stand for miles. short time. Way to quantify the physical ability 17

  18. 65: 2 months after surgery. 55: 1 month after 72: surgery. Can run 10 34: miles. 2 weeks after surgery 32: Can stand for Collected over time short time. Track patient progression 18

  19. use PROMIS PF to more accurately evaluate progression To compare outcomes Smokes Age: 45 CCI: 1 Diabetic Age: 70 BMI: 28 Age: 35 Age: 55 19

  20. Lack tools that use PROMIS PF trajectories Smokes Age: 45 CCI: 1 Diabetic Age: 70 BMI: 28 Age: 35 Age: 55 20

  21. Dataset PROMIS PF scores for 6071 patients beginning in 2013 Range of 1 to more than 20 scores ICD/CPT codes, demographic data, comorbidities 21

  22. 3 requirements for functionality 1. Define meaningful cohorts of patients 2. Compare outcomes of different cohorts 3. Compare outcomes of different treatments 22

  23. Domain Requirements 1. Define meaningful cohorts of patients. 23

  24. Domain Requirements 1. Define meaningful cohorts of patients. 24

  25. Domain Requirements 2. Compare outcomes of different cohorts . Cohort 1 Cohort 1 Cohort 2 25

  26. Domain Requirements 3. Compare outcomes of different treatments . Injection Surgery 26

  27. Related Work 27

  28. Patient score trajectories in the context of a similar group of patients. Mane, K.K., Bizon, C., Schmitt, C., Owen, P., Burchett, B., Pietrobon, R. and Gersing, K., 2012. VisualDecisionLinc: A visual analytics approach for comparative effectiveness-based clinical decision support in psychiatry. Journal of Biomedical Informatics, 45(1), pp.101-106. 28

  29. Iterative cohort refinement. Bernard, Jürgen, et al. "A visual-interactive system for prostate cancer cohort analysis." IEEE computer graphics and applications 35.3 (2015): 44-55. 29

  30. Contributions Comparison of treatment options measured by patient score trajectories Ability to normalize and adjust representation of trajectories Flexible definition of multiple patient cohorts for comparison 30

  31. 31

  32. 32

  33. 33

  34. Define a cohort for Frank by filtering based on attributes. Age 55 Diabetic BMI: 29 Tried physical therapy 34

  35. Filter History. Patient count of cohort at each filter stage 35

  36. Filter History. Remove and recalculate 36

  37. Demographic Filters. 37

  38. Score & CPT Filters. 38

  39. Filtering by attributes to define a cohort like Frank 39

  40. Added Cohort control panel. 40

  41. Cohort control panel. Branched 41

  42. Remove Cohort control panel. 42

  43. How did patients like Frank progress after surgery ? 43

  44. Realign scores to see trend after surgery Aligned by surgery Aligned by first recorded PROMIS score 44

  45. Aligning by event 45

  46. Patient score trajectories have different baselines Small change (2-8) clinically meaningful 46

  47. Hard to see measured change in scores 47

  48. Changing scales to relative score change 48

  49. This is messy. 49

  50. We want to see the general trend in score fluctuation 50

  51. Aggregation of scores 51

  52. How did the patients with the most positive change in score progress? What about the bottom quantile for score change? 52

  53. Adjust the day range to calculate average score change. Separation of Scores by Quantiles. 53

  54. How did patients like Frank progress after surgery vs injection ? 54

  55. Compare cohorts in layer view 55

  56. We find a patient line of interest What other events are present in their medical histories? 56

  57. Drill down into individual patient histories 57

  58. Moving Forward Generalize to a broader clinical base Development of a shared decision-making interface 58

  59. Thank You Learn more about our lab: http://vdl.sci.utah.edu/ Learn more on the project website: http://bit.ly/composer_paper 59

  60. Comparison of multiple treatment outcomes. Franklin, L., Plaisant, C., Minhazur Rahman, K. and Shneiderman, B., 2014. TreatmentExplorer: An interactive decision aid for medical risk communication and treatment exploration. Interacting with Computers, 28(3), pp.238-252. 60

  61. Separating By quantiles 61

  62. Utah Health Using PROMIS scores longer than any other institution in the country. PROMIS physical function scores. 62

  63. Cohort control panel. Cohorts can be added, branched and deleted. 63

  64. Adding, Branching, Removing Cohorts 64

Recommend


More recommend