1 / 13

Chih-Hung Wu, Wei-Ting Lin, Chi-Hua Li, I-Ching Fang, Chia-Hsiang Wu

Ant Colony Optimization on building an online Delayed Diagnosis Detection Support System for Emergency Department. Chih-Hung Wu, Wei-Ting Lin, Chi-Hua Li, I-Ching Fang, Chia-Hsiang Wu. OUTLINE. Introduction ACO classification Delayed diagnosis data Data analysis Conclusion References.

Télécharger la présentation

Chih-Hung Wu, Wei-Ting Lin, Chi-Hua Li, I-Ching Fang, Chia-Hsiang Wu

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. Ant Colony Optimization on building an onlineDelayed DiagnosisDetection Support Systemfor Emergency Department Chih-Hung Wu, Wei-Ting Lin, Chi-Hua Li, I-Ching Fang, Chia-Hsiang Wu

  2. OUTLINE • Introduction • ACO classification • Delayed diagnosis data • Data analysis • Conclusion • References

  3. INTRODUCTION • Medical error • Delayed diagnosis • AI on medical diagnosis • Ant colony optimization (ACO)

  4. ACO CLASSIFICATION • Classification rulesIF conditions THEN class

  5. ACO CLASSIFICATION • Six steps:1. An ant selects a path (a rule).2. Prune the rule for higher quality. 3. Update the pheromone intensity.4. Optimal rule is chosen after all ants. 5. Remove cases with this rule.6. Update the dataset.

  6. ACO CLASSIFICATION • Step 1: • Step 2: • Step 3: • Step 6:

  7. DELAYED DIAGNOSIS DATA • Data source: Emergency Department • 7 attributes 1 Class Age Injury TriageConsciousnessBreathBlood pressure PulseBody temperature Doctor’s diagnosis

  8. DELAYED DIAGNOSIS DATA • Coding:X1: Age (1)~30 (2)30~60 (3)60~X2: Injury Triage (1)1st class (2)2nd class (3)3rd classX3: Consciousness (1)Clear (2)To Call (3)To Pain (4)ComaX4: Breath (1)10-24/min.(normal) (2)OtherX5: Blood pressure (1)90-140mmHG (2)OtherX6: Pulse (1)60-100/min (2)OtherX7: Body temperature (1)35.5-37.5℃ (2)OtherY: Doctor’s Diagnosis (1)Delayed (2)Did not delay

  9. DATA ANALYSIS • Accuracy – ACO V.S. BPN:

  10. Rule8: 1 DATA ANALYSIS • Classification Rules: Rule1: consciousness = 2 & breathe = 1 & pulse = 2 2 Rule2: temp = 1 1 Rule3: consciousness = 1 1 Rule4: triage = 1 & breathe = 2 1 Rule5: triage = 1 & age = 2 1 Rule6: age = 3 1 Rule7: consciousness = 3 1 triage = 1 & pulse = 2

  11. CONCLUSION • An online detection support system * construct with php

  12. CONCLUSION • Future study:-> More attributes?-> Routine clinic diagnosis?-> More convenient equipement?-> Different rule sets?-> Meaning behind rules?

  13. THANK YOUFOR YOUR ATTENTION!

More Related