Webbläsaren som du använder stöds inte av denna webbplats. Alla versioner av Internet Explorer stöds inte längre, av oss eller Microsoft (läs mer här: * https://www.microsoft.com/en-us/microsoft-365/windows/end-of-ie-support).

Var god och använd en modern webbläsare för att ta del av denna webbplats, som t.ex. nyaste versioner av Edge, Chrome, Firefox eller Safari osv.

Foto på Mattias Ohlsson

Mattias Ohlsson

Professor

Foto på Mattias Ohlsson

Exploring new possibilities for case based explanation of artificial neural network ensembles

Författare

  • Michael Green
  • Ulf Ekelund
  • Lars Edenbrandt
  • Jonas Björk
  • Jakob Lundager Hansen
  • Mattias Ohlsson

Summary, in English

Artificial neural network (ANN) ensembles have long suffered from a lack of interpretability. This has severely limited the practical usability of ANNs in settings where an erroneous decision can be disastrous. Several attempts have been made to alleviate this problem. Many of them are based on decomposing the decision boundary of the ANN into a set of rules. We explore and compare a set of new methods for this explanation process on two artificial data sets (Monks 1 and 3), and one acute coronary syndrome data set consisting of 861 electrocardiograms (ECG) collected retrospectively at the emergency department at Lund University Hospital. The algorithms managed to extract good explanations in more than 84% of the cases. More to the point, the best method provided 99% and 91% good explanations in Monks data 1 and 3 respectively. Also there was a significant overlap between the algorithms. Furthermore, when explaining a given ECG, the overlap between this method and one of the physicians was the same as the one between the two physicians in this study. Still the physicians were significantly, p-value <0.001, more similar to each other than to any of the methods. The algorithms have the potential to be used as an explanatory aid when using ANN ensembles in clinical decision support systems.

Avdelning/ar

  • Beräkningsbiologi och biologisk fysik - Genomgår omorganisation
  • Medicin/akutsjukvård, Lund
  • Nuklearmedicin, Malmö
  • Centrum för ekonomisk demografi
  • Avdelningen för arbets- och miljömedicin

Publiceringsår

2009

Språk

Engelska

Sidor

75-81

Publikation/Tidskrift/Serie

Neural Networks

Volym

22

Issue

1

Dokumenttyp

Artikel i tidskrift

Förlag

Elsevier

Ämne

  • Radiology, Nuclear Medicine and Medical Imaging
  • Anesthesiology and Intensive Care

Nyckelord

  • Neural Network Ensembles
  • Acute Coronary Syndrome
  • Case-Based Explanation
  • Sensitivity Analysis

Status

Published

Projekt

  • AIR Lund Chest pain - More efficient and equal emergency care with advanced medical decision support tools

Forskningsgrupp

  • Nuclear medicine, Malmö

ISBN/ISSN/Övrigt

  • ISSN: 1879-2782