1 / 15

Intern 曾順承

Intern 曾順承. Introduction 1. Computerized medical decision support systems Discriminant analysis Logistic regression Recursive partitioning Neural networks. Introduction 2.

hedia
Download Presentation

Intern 曾順承

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. Intern 曾順承

  2. Introduction1 • Computerized medical decision support systems • Discriminant analysis • Logistic regression • Recursive partitioning • Neural networks

  3. Introduction2 • This report compares three different mathematical models for building a traumatic brain injury (TBI) medical decision support system (MDSS) • A logistic regression model • A multi-layer perceptron (MLP) neural network • A radial-basis-function (RBF) neural network

  4. Introduction3

  5. Introduction4

  6. Introduction5 • These models were developed based on a large TBI patient database. • This MDSS accepts a set of patient data • The types of skull fracture • Glasgow Coma Scale (GCS) • Episode of convulsion • Return the chance that a neurosurgeon would recommend an open-skull surgery for this patient.

  7. Method1 • From the 12640 patients selected from the database • A randomly drawn 9480 cases were used as the training group to develop/train our models • The other 3160 cases were in the validation group which we used to evaluate the performance of these models

  8. Method2 • The indicator of how accurate these models are in predicting a neurosurgeon’s decision on open-skull surgery • Sensitivity • Specificity • Areas under receiver-operating characteristics (ROC) curve and calibration curves

  9. Result1 • Assuming equal importance of sensitivity and specificity • The logistic regression model (sensitivity, specificity) of(73%, 68%) • The RBF model (80%, 80%) • The MLP model (88%, 80%)

  10. Result2

  11. Result3 • The resultant areas under ROC curve • Logistic regression: 0.761 • RBF: 0.880 • MLP: 0.897 • P < 0.05 • Among these models, the logistic regression has noticeably poorer calibration.

  12. Result4

  13. Conclusion1 • This study demonstrated the feasibility of applying neural networks as the mechanism for TBI decision support systems based on clinical databases.

  14. Conclusion2 • The results also suggest that neural networks may be a better solution for complex, non-linear medical decision support systems than conventional statistical techniques such as logistic regression.

  15. Thank you for attention!

More Related