preha
play

preha Establishing Precision Rehabilitation with Visual Analytics - PowerPoint PPT Presentation

Nov 10, 2022 •1.76k likes •2.15k views

preha Establishing Precision Rehabilitation with Visual Analytics Georg Bernold, Kresimir Matkovic, M.Eduard Grller, Renata G. Raidou Renata Raidou 2 Conventional Rehabilitation Renata Raidou 3 Precision Rehabilitation Challenges: Data

  1. preha Establishing Precision Rehabilitation with Visual Analytics Georg Bernold, Kresimir Matkovic, M.Eduard Gröller, Renata G. Raidou

  2. Renata Raidou 2

  3. Conventional Rehabilitation Renata Raidou 3

  4. Precision Rehabilitation Challenges: Data Resources Users Tasks Renata Raidou 4

  5. Contribution preha : a new approach to tackle the analysis of p recision reha bilitation data. Two main components: A detailed data–users–tasks analysis 1. A visual analytics dashboard approach within preha 2. Renata Raidou 5

  6. Data–Users–Tasks Analysis Renata Raidou 6

  7. Data–Users–Tasks Analysis 46,000 cases 2012 – 2019 large – heterogeneous – high-dimensional 1 – inconsistent 2 – missing 3 Renata Raidou 7

  8. Data–Users–Tasks Analysis Data Analysts Engineers Domain Experts Renata Raidou 8

  9. Data–Users–Tasks Analysis Interviews Abstract Tasks 30-50 minutes typologies for each task semi-structured Renata Raidou 9

  10. Data–Users–Tasks Analysis Eng1 : Provide meaningful data partitions Eng2 : Prepare templates for patient assessment Eng3 : Prepare templates for clinical benchmarking Eng4 : Predict rehabilitation outcome Exp1 : Show rehabilitation outcome to patients Exp2 : Perform clinical benchmarking Exp3 : Explore clinical datasets Exp4 : Analyze data for clinical studies Exp5 : Intervention planning Renata Raidou 10

  11. Data–Users–Tasks Analysis Eng1 : Provide meaningful data partitions Eng2 : Prepare templates for patient assessment Eng3 : Prepare templates for clinical benchmarking Eng4 : Predict rehabilitation outcome Exp1 : Show rehabilitation outcome to patients Exp2 : Perform clinical benchmarking Exp3 : Explore clinical datasets Exp4 : Analyze data for clinical studies Exp5 : Intervention planning Renata Raidou 11

  12. Eng4 : Predict Rehabilitation Outcome What? Why? How? [inspired by Brehmer et al. 2013] Renata Raidou 12

  13. Typologies for All Tasks Renata Raidou 13

  14. preha * if required by task Renata Raidou 14

  15. preha Renata Raidou 15

  16. Preprocessing Rule-based approach, done once: easy to introduce new rules Profiling: identification and communication of quality problems Set of regular expressions/rules defined by the users Whatever doesn’t match these � “dirty” Wrangling: modifying structure to make it suitable for processing Standardization of tables and scores Each patient is assigned one (non-redundant) row in a data table Cleansing: correcting dirty data We know how correct data should look like Cleansing programs/rules to match this appearance Renata Raidou 16

  17. preha Renata Raidou 17

  18. preha Visualization Renata Raidou 18

  19. Visualization Flexible, reusable, adaptable, expressive Kibana framework: All basic visualizations Extensible through d3.js Supports multiple linked views Interaction functionality Predictive analysis support Renata Raidou 19

  20. Eng4 : Predict Rehabilitation Outcome What? Why? How? [inspired by Brehmer et al. 2013] Renata Raidou 20

  21. Visualize interesting Filter characteristics of cohort Predict assessment scores Visualize interesting characteristics of cohort Visualize interesting characteristics of cohort

  22. Visualize interesting Filter characteristics of cohort Predict assessment scores Visualize interesting characteristics of cohort Visualize interesting characteristics of cohort

  23. Visualize interesting Filter characteristics of cohort Visualize interesting characteristics of cohort Visualize interesting characteristics of cohort

  24. Visualize interesting Filter characteristics of cohort Visualize interesting characteristics of cohort Visualize interesting characteristics of cohort

  25. Filter

  26. Filter

  28. Eng4: Use machine learning to predict rehabilitation outcome

  29. Dashboards for All Tasks Renata Raidou 29

  30. Pilot Study Introduce preha to four potential users Provide a set of small assignments to complete Findings: (+) Flexibility, adaptability to own working style (-) Documentation/language, more digestible for domain experts Renata Raidou 30

  31. Conclusion and Future Work Design study for the workflow of precision rehabilitation Development of a dashboard-based strategy Extend evaluation to domain experts Predictive analytics extension Guided analytics incorporation Renata Raidou 31

  32. Thank You! Questions? preha Georg Bernold, Kresimir Matkovic, M.Eduard Gröller, Renata G. Raidou rraidou@cg.tuwien.ac.at 32

Recommend

More recommend