1 / 41

Coding of Selection Criteria for Cancer Treatment Plans

Coding of Selection Criteria for Cancer Treatment Plans. Savvas Nikiforou. Automated Matching of Patients to Clinical Trials. Part of the project:. Research Group. Faculty Lawrence Hall Dmitry Goldgof Eugene Fink Students Lynn Fletcher Princeton Kokku Savvas Nikiforou Rochelle Harris.

galcala
Download Presentation

Coding of Selection Criteria for Cancer Treatment Plans

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Coding of Selection Criteria for Cancer Treatment Plans Savvas Nikiforou

  2. Automated Matching of Patients to Clinical Trials Part of the project:

  3. Research Group • Faculty • Lawrence Hall • Dmitry Goldgof • Eugene Fink • Students • Lynn Fletcher • Princeton Kokku • Savvas Nikiforou • Rochelle Harris

  4. Motivation • Selecting among treatment plans • Minimizing pain and cost of the selection process • Reducing the physician’s effort

  5. Expert System • Guides the nurse through related questions • Identifies the appropriate medical tests

  6. Outline of the Talk • Eligibility decisions • Knowledge base • Input of the knowledge • Demonstration

  7. Related Work • Initial expert systemFletcher, Hall and Goldgof, 1999 • Minimizing pain and costKokku, Hall and Goldgof, 2001

  8. Example: Selection Criteria • Female, not older than 50 • Breast cancer, stage II • No prior surgery

  9. Example: Questions Female Male Sex: Age: 35

  10. Example: Conclusion Patient is not eligible

  11. Example: Questions Female Male Sex: Age: 35

  12. Example: Questions I II III IV Cancer stage: Prior surgery? Yes No Unknown

  13. Example: Conclusion Patient is eligible

  14. Full Functionality • Orders and groups the questions • Considers multiple treatment plans

  15. Old System • A programmer has to code the questions

  16. New System • A programmer has to code the questions A nurse enters the questions through a friendly interface Problem: Build the interface

  17. Outline of the Talk • Eligibility decisions • Knowledge base • Input of the knowledge • Demonstration

  18. Main Objects • Questions Tests Eligibility criteria

  19. Types of Questions • Yes / No / Unknown • Multiple choice • Numeric

  20. Examples of Questions Prior surgery? Yes No Unknown

  21. Examples of Questions Prior surgery? Yes No Unknown Cancer stage: I II III IV

  22. Examples of Questions Prior surgery? Yes No Unknown Cancer stage: I II III IV Age:

  23. Tests A medical test answers several questions. It involves certain pain and cost.

  24. Example Test: Name and Cost Test Name: Blood test Cost: 42.23 Pain: 1

  25. Example Test: Questions • Yes / No Question: Histologically proven breast cancer?

  26. Example Test: Questions • Multiple choice Question: Options: Patient’s clinical state T-1 T-2 T-3

  27. Example Test: Questions • Numeric Question: Min Max Prec White cell blood count 0 0 500000

  28. Eligibility Criteria • A logical expression that determines eligibility for a specific treatment

  29. Example: Criteria AND White Blood Count >100,000 No Heart Related Problems OR Cancer Stage I Cancer Stage II

  30. Outline of the Talk • Eligibility decisions • Knowledge base • Input of the knowledge • Demonstration

  31. Input • Questions Tests Eligibility criteria

  32. Input: Test • Name: Type test name here Cost: $$$$.$$ Pain: 0-5

  33. Input: Question Format Type Yes / No Multiple Choice Numeric Text

  34. Input: Yes / No Question Type Yes / No Text Is patient’s age less than 64?

  35. Input: Multiple Choice Question Type Multiple Choice Text Options Patient’s age < 20 20 to 40 41 to 60 > 60

  36. Input: Numeric Question Type Numeric Text Min Max Prec. Patient’s age 0 120 0

  37. AND OR Yes No Yes No Input: Eligibility Logical structure Female Sex Male Age Questions 40 65 From To Eligibility answers Tumors? Lesions?

  38. Outline of the Talk • Eligibility decisions • Knowledge base • Input of the knowledge • Demonstration

  39. Current System Online Demo

  40. Main results • Formal model of selection criteria and related optimization problems Visual representation of these criteria Friendly input interface

  41. Coming soon • Completion of the interface Converting the input knowledge into internal logical structures

More Related