Conformal predictors in early diagnostics of ovarian and breast cancers

Autor: Stephane Camuzeaux, Rainer Cramer, John Sinclair, Dmitry Devetyarov, Ilia Nouretdinov, Brian Burford, Volodya Vovk, John F. Timms, Ali Tiss, Ian Jacobs, Celia Smith, Mike Waterfield, Alexander Gammerman, Alexey Ya. Chervonenkis, Aleksandra Gentry-Maharaj, Zhiyuan Luo, Rachel Hallett, Usha Menon
Rok vydání: 2012
Předmět:
Zdroj: Progress in Artificial Intelligence. 1:245-257
ISSN: 2192-6360
2192-6352
DOI: 10.1007/s13748-012-0021-y
Popis: The work describes an application of a recently developed machine-learning technique called Mondrian pre- dictors to risk assessment of ovarian and breast cancers. The analysis is based on mass spectrometry profiling of human serum samples that were collected in the United Kingdom Collaborative Trial of Ovarian Cancer Screening. The work describes the technique and presents the results of clas- sification (diagnosis) and the corresponding measures of confidence of the diagnostics. The main advantage of this approach is a proven validity of prediction. The work also describes an approach to improve early diagnosis of ovar- ian and breast cancers since the data in the United Kingdom Collaborative Trial of Ovarian Cancer Screening were col- lected over a period of 7 years and do allow to make obser- vations of changes in human serum over that period of time. Significance of improvement is confirmed statistically (for up to 11 months for ovarian cancer and 9 months for breast cancer). In addition, the methodology allowed us to pinpoint
Databáze: OpenAIRE
Externí odkaz: