Successfully reported this slideshow.

Information Visualization for Health Care

1

Share

INFORMATION VISUALIZATION
for healthcare
Krist wongsuphasawat
@kristwongz
Department of Computer Science & Human-Computer ...
INFORMATION VISUALIZATION
INFO. VIS.
A picture is worth a thousand words.

YouTube videos are no longer supported on SlideShare

View original on YouTube

YouTube videos are no longer supported on SlideShare

View original on YouTube

1 of 45
1 of 45

Information Visualization for Health Care

1

Share

Download to read offline

Transcript

  1. 1. INFORMATION VISUALIZATION for healthcare Krist wongsuphasawat @kristwongz Department of Computer Science & Human-Computer Interaction Lab University of Maryland
  2. 2. INFORMATION VISUALIZATION INFO. VIS.
  3. 3. A picture is worth a thousand words.
  4. 4. INFORMATION VISUALIZATION INFO. VIS. “ Using visual representations and interaction techniques, which take advantage of the human eye’s broad bandwidth pathway into the mind, to allow users to see, explore, and understand large amounts of information at once.” [Wikipedia]!  
  5. 5. Anscombe’s quartet #1 #2 #3 #4 X Y X Y X Y X Y 10.0 8.04 10.0 9.14 10.0 7.46 8.0 6.58 8.0 6.95 8.0 8.14 8.0 6.77 8.0 5.76 13.0 7.58 13.0 8.74 13.0 12.74 8.0 7.71 9.0 8.81 9.0 8.77 9.0 7.11 8.0 8.84 11.0 8.33 11.0 9.26 11.0 7.81 8.0 8.47 14.0 9.96 14.0 8.10 14.0 8.84 8.0 7.04 6.0 7.24 6.0 6.13 6.0 6.08 8.0 5.25 4.0 4.26 4.0 3.10 4.0 5.39 19.0 12.50 12.0 10.84 12.0 9.13 12.0 8.15 8.0 5.56 7.0 4.82 7.0 7.26 7.0 6.42 8.0 7.91 5.0 5.68 5.0 4.74 5.0 5.73 8.0 6.89
  6. 6. Anscombe’s quartet #1 #2 #3 #4 Property Value Mean of X 11.0 Variance of X 10.0 Mean of Y 7.5 Variance of Y 3.75 Correlation between X and Y 0.816 Linear regression y = 3.0 +0.5x Identical statistics
  7. 7. Anscombe’s quartet #1 #2 #3 #4 12! 10! 14! 14! 9! 10! 12! 12! 8! 7! 10! 10! 8! 6! 8! 8! 6! 5! 4! 6! 6! 4! 3! 4! 4! 2! 2! 2! 2! 1! 0! 0! 0! 0! 0! 5! 10! 15! 0! 5! 10! 15! 0! 5! 10! 15! 0! 10! 20! But very different
  8. 8. INFORMATION VISUALIZATION Visual representation + User interactions click, drag, zoom, select, etc.!  
  9. 9. Healthcare Electronic medical records (EMRs) “ To improve the quality of our health care while lowering its cost, we will make the immediate investments necessary to ensure that, within five years, all of America's medical records are computerized. This will cut waste, eliminate red tape and reduce the need to repeat expensive medical tests. But it just won't save billions of dollars and thousands of jobs; it will save lives by reducing the deadly but preventable medical errors that pervade our health-care system.” [President Barack Obama – Jan 2009]!  
  10. 10. EMRs + INFO. VIS. A lot of data! Help understand data!    
  11. 11. One patient x
  12. 12. Example of EMRs System
  13. 13. Lifelines One patient x [Plaisant et al. 1998]! http://www.cs.umd.edu/hcil/lifelines!
  14. 14. LifeLines
  15. 15. LifeLines
  16. 16. LifeLines
  17. 17. LifeLines
  18. 18. LifeLines
  19. 19. Lifelines user study Faster decision Better recall
  20. 20. Lifelines One patient Demographic -  Gender -  Age -  … x [Plaisant et al. 1998]! Medical Events* -  Emergency room on Jan 15 -  Surgery on Oct 1 -  … http://www.cs.umd.edu/hcil/lifelines!
  21. 21. Lifelines 2 Multiple patients xxxxx [Wang et al. 2008, 2009]! http://www.cs.umd.edu/hcil/lifelines2!
  22. 22. Case study Contrast-induced nephropathy Radiographic Examination (Medical Imaging) e.g. X-ray using a contrast agent e.g. Iodine, Barium x Creatinine -  Amino Acid Damage to the kidney -  Levels in blood reflect kidney function
  23. 23. Data : contrast & creatinine CREAT- Normal level of Creatinine RADIOLOGY Radiographic exam (with contrast) CREAT-H High level of Creatinine (bad) x Time Jan Feb Mar Apr
  24. 24. LifeLines2
  25. 25. Video demo Data Analysis with Lifelines2
  26. 26. Lifelines 2 Multiple patients xxxxx [Wang et al. 2008, 2009]! http://www.cs.umd.edu/hcil/lifelines2!
  27. 27. Lifelines 2 search from medical events xxxxx [Wang et al. 2008, 2009]! http://www.cs.umd.edu/hcil/lifelines2!
  28. 28. Data : patients transfer ARRIVAL Arrive the hospital EMERGENCY Emergency room ICU Intensive Care Unit FLOOR Normal room EXIT-ALIVE Leave the hospital alive EXIT-DEAD Leave the hospital dead
  29. 29. Improve the Quality of Care Pa$ent  ID:  45851733     Pa$ent  ID:  45851732     12/02/2008  14:26  Arrival   12/02/2008  14:26I  D:  45851731 Pa$ent   Emergency       Emergency Department 12/02/2008  14:26  Arrival   6,000+ 12/02/2008  22:44  ICU  mergency   12/02/2008  14:26  E   12/05/2008  05:071Floor  Arrival   12/02/2008     4:26 12/02/2008  22:44  ICU  mergency   12/02/2008  14:26  E 12/08/2008  10:02  Floor   12/05/2008  05:07  Floor   12/02/2008  22:44  ICU   12/14/2008  06:19  Discharge   12/08/2008  10:02  Floor   12/05/2008  05:07  Floor     12/14/2008  06:19  Discharge   12/08/2008  10:02  Floor     12/14/2008  06:19  Discharge   patients per month  
  30. 30. task Find “Bounce backs” ICU Floor ICU within 2 days Limitations High-level questions Arrival ? ICU ? ?
  31. 31. patients x x x xx x x x xx x xx x x x x x x x x x x
  32. 32. LifeFlow overview xx x x xx x x x xx [Wongsuphasawat et al. 2011]! http://www.cs.umd.edu/hcil/lifeflow!
  33. 33. Video demo Creating LifeFlow
  34. 34. LifeFlow
  35. 35. Video demo Data Analysis with LifeFlow
  36. 36. collected visual representation large eye interactions rich EMRs + INFO. VIS. A lot of data! Help understand data!     and more… Lifelines LifeFlow Save more lives Lifelines 2 Patientslikeme / i2b2 / BTRIS Many case studies / etc. Krist wongsuphasawat @kristwongz kristw@cs.umd.edu! http://www.cs.umd.edu/hcil/temporalviz!  
  37. 37. Other examples Visualizations in the Medical Domain
  38. 38. MIDGAARD hFp://www.infovis-­‐wiki.net/index.php?$tle=MIDGAARD  
  39. 39. HemoVis hFp://people.seas.harvard.edu/~borkin/HemoVis/  

Transcript

  1. 1. INFORMATION VISUALIZATION for healthcare Krist wongsuphasawat @kristwongz Department of Computer Science & Human-Computer Interaction Lab University of Maryland
  2. 2. INFORMATION VISUALIZATION INFO. VIS.
  3. 3. A picture is worth a thousand words.
  4. 4. INFORMATION VISUALIZATION INFO. VIS. “ Using visual representations and interaction techniques, which take advantage of the human eye’s broad bandwidth pathway into the mind, to allow users to see, explore, and understand large amounts of information at once.” [Wikipedia]!  
  5. 5. Anscombe’s quartet #1 #2 #3 #4 X Y X Y X Y X Y 10.0 8.04 10.0 9.14 10.0 7.46 8.0 6.58 8.0 6.95 8.0 8.14 8.0 6.77 8.0 5.76 13.0 7.58 13.0 8.74 13.0 12.74 8.0 7.71 9.0 8.81 9.0 8.77 9.0 7.11 8.0 8.84 11.0 8.33 11.0 9.26 11.0 7.81 8.0 8.47 14.0 9.96 14.0 8.10 14.0 8.84 8.0 7.04 6.0 7.24 6.0 6.13 6.0 6.08 8.0 5.25 4.0 4.26 4.0 3.10 4.0 5.39 19.0 12.50 12.0 10.84 12.0 9.13 12.0 8.15 8.0 5.56 7.0 4.82 7.0 7.26 7.0 6.42 8.0 7.91 5.0 5.68 5.0 4.74 5.0 5.73 8.0 6.89
  6. 6. Anscombe’s quartet #1 #2 #3 #4 Property Value Mean of X 11.0 Variance of X 10.0 Mean of Y 7.5 Variance of Y 3.75 Correlation between X and Y 0.816 Linear regression y = 3.0 +0.5x Identical statistics
  7. 7. Anscombe’s quartet #1 #2 #3 #4 12! 10! 14! 14! 9! 10! 12! 12! 8! 7! 10! 10! 8! 6! 8! 8! 6! 5! 4! 6! 6! 4! 3! 4! 4! 2! 2! 2! 2! 1! 0! 0! 0! 0! 0! 5! 10! 15! 0! 5! 10! 15! 0! 5! 10! 15! 0! 10! 20! But very different
  8. 8. INFORMATION VISUALIZATION Visual representation + User interactions click, drag, zoom, select, etc.!  
  9. 9. Healthcare Electronic medical records (EMRs) “ To improve the quality of our health care while lowering its cost, we will make the immediate investments necessary to ensure that, within five years, all of America's medical records are computerized. This will cut waste, eliminate red tape and reduce the need to repeat expensive medical tests. But it just won't save billions of dollars and thousands of jobs; it will save lives by reducing the deadly but preventable medical errors that pervade our health-care system.” [President Barack Obama – Jan 2009]!  
  10. 10. EMRs + INFO. VIS. A lot of data! Help understand data!    
  11. 11. One patient x
  12. 12. Example of EMRs System
  13. 13. Lifelines One patient x [Plaisant et al. 1998]! http://www.cs.umd.edu/hcil/lifelines!
  14. 14. LifeLines
  15. 15. LifeLines
  16. 16. LifeLines
  17. 17. LifeLines
  18. 18. LifeLines
  19. 19. Lifelines user study Faster decision Better recall
  20. 20. Lifelines One patient Demographic -  Gender -  Age -  … x [Plaisant et al. 1998]! Medical Events* -  Emergency room on Jan 15 -  Surgery on Oct 1 -  … http://www.cs.umd.edu/hcil/lifelines!
  21. 21. Lifelines 2 Multiple patients xxxxx [Wang et al. 2008, 2009]! http://www.cs.umd.edu/hcil/lifelines2!
  22. 22. Case study Contrast-induced nephropathy Radiographic Examination (Medical Imaging) e.g. X-ray using a contrast agent e.g. Iodine, Barium x Creatinine -  Amino Acid Damage to the kidney -  Levels in blood reflect kidney function
  23. 23. Data : contrast & creatinine CREAT- Normal level of Creatinine RADIOLOGY Radiographic exam (with contrast) CREAT-H High level of Creatinine (bad) x Time Jan Feb Mar Apr
  24. 24. LifeLines2
  25. 25. Video demo Data Analysis with Lifelines2
  26. 26. Lifelines 2 Multiple patients xxxxx [Wang et al. 2008, 2009]! http://www.cs.umd.edu/hcil/lifelines2!
  27. 27. Lifelines 2 search from medical events xxxxx [Wang et al. 2008, 2009]! http://www.cs.umd.edu/hcil/lifelines2!
  28. 28. Data : patients transfer ARRIVAL Arrive the hospital EMERGENCY Emergency room ICU Intensive Care Unit FLOOR Normal room EXIT-ALIVE Leave the hospital alive EXIT-DEAD Leave the hospital dead
  29. 29. Improve the Quality of Care Pa$ent  ID:  45851733     Pa$ent  ID:  45851732     12/02/2008  14:26  Arrival   12/02/2008  14:26I  D:  45851731 Pa$ent   Emergency       Emergency Department 12/02/2008  14:26  Arrival   6,000+ 12/02/2008  22:44  ICU  mergency   12/02/2008  14:26  E   12/05/2008  05:071Floor  Arrival   12/02/2008     4:26 12/02/2008  22:44  ICU  mergency   12/02/2008  14:26  E 12/08/2008  10:02  Floor   12/05/2008  05:07  Floor   12/02/2008  22:44  ICU   12/14/2008  06:19  Discharge   12/08/2008  10:02  Floor   12/05/2008  05:07  Floor     12/14/2008  06:19  Discharge   12/08/2008  10:02  Floor     12/14/2008  06:19  Discharge   patients per month  
  30. 30. task Find “Bounce backs” ICU Floor ICU within 2 days Limitations High-level questions Arrival ? ICU ? ?
  31. 31. patients x x x xx x x x xx x xx x x x x x x x x x x
  32. 32. LifeFlow overview xx x x xx x x x xx [Wongsuphasawat et al. 2011]! http://www.cs.umd.edu/hcil/lifeflow!
  33. 33. Video demo Creating LifeFlow
  34. 34. LifeFlow
  35. 35. Video demo Data Analysis with LifeFlow
  36. 36. collected visual representation large eye interactions rich EMRs + INFO. VIS. A lot of data! Help understand data!     and more… Lifelines LifeFlow Save more lives Lifelines 2 Patientslikeme / i2b2 / BTRIS Many case studies / etc. Krist wongsuphasawat @kristwongz kristw@cs.umd.edu! http://www.cs.umd.edu/hcil/temporalviz!  
  37. 37. Other examples Visualizations in the Medical Domain
  38. 38. MIDGAARD hFp://www.infovis-­‐wiki.net/index.php?$tle=MIDGAARD  
  39. 39. HemoVis hFp://people.seas.harvard.edu/~borkin/HemoVis/  

More Related Content

More from Krist Wongsuphasawat

Related Books

Free with a 30 day trial from Scribd

See all

Related Audiobooks

Free with a 30 day trial from Scribd

See all

×