Paper Search Console

Home Search Page About Contact

Journal Title

Title of Journal: Data Min Knowl Disc

Search In Journal Title:

Abbravation: Data Mining and Knowledge Discovery

Search In Journal Abbravation:

Publisher

Springer US

Search In Publisher:

DOI

10.1007/978-3-642-03906-5_72

Search In DOI:

ISSN

1573-756X

Search In ISSN:
Search In Title Of Papers:

Medical data mining insights from winning two com

Authors: Saharon Rosset Claudia Perlich Grzergorz Świrszcz Prem Melville Yan Liu
Publish Date: 2009/12/23
Volume: 20, Issue: 3, Pages: 439-468
PDF Link

Abstract

Two major data mining competitions in 2008 presented challenges in medical domains KDD Cup 2008 which concerned cancer detection from mammography data and Informs Data Mining Challenge 2008 dealing with diagnosis of pneumonia based on patient information from hospital files Our team won both of these competitions and in this paper we share our lessons learned and insights We emphasize the aspects that pertain to the general practice and methodology of medical data mining rather than to the specifics of each modeling competition We concentrate on three topics information leakage its effect on competitions and proofofconcept projects consideration of reallife model performance measures in model construction and evaluation and relational learning approaches to medical data mining tasks

Keywords:

References

.
Search In Abstract Of Papers:
Other Papers In This Journal:
  1. CrossClus: user-guided multi-relational clustering
  2. Binary matrix factorization for analyzing gene expression data
  3. Parameter-less co-clustering for star-structured heterogeneous data
  4. RTG: a recursive realistic graph generator using random typing
  5. Clustering daily patterns of human activities in the city
  6. Ranking episodes using a partition model
  7. Efficient algorithms for segmentation of item-set time series
  8. Guest Editorial: Global modeling using local patterns
  9. Learning Semi-Structured Document Categorization Using Bounded-Length Spectrum Sub-Sequence Kernels
  10. Ontology of core data mining entities
  11. i SAX: disk-aware mining and indexing of massive time series datasets
  12. Size matters: choosing the most informative set of window lengths for mining patterns in event sequences
  13. All normalized anti-monotonic overlap graph measures are bounded
Search Result: