| 1. |
|
|
| 2. |
- Gustafsson, Mats G., et al.
(författare)
-
Improving Bayesian credibility intervals for classifier error rates using maximum entropy empirical priors
- 2010
-
Ingår i: Artificial Intelligence in Medicine. - : Elsevier BV. - 0933-3657 .- 1873-2860. ; 49:2, s. 93-104
-
Tidskriftsartikel (refereegranskat)abstract
- Objective:Successful use of classifiers that learn to make decisions from a set of patient examples require robust methods for performance estimation. Recently many promising approaches for determination of an upper bound for the error rate of a single classifier have been reported but the Bayesian credibility interval (Cl) obtained from a conventional holdout test still delivers one of the tightest bounds. The conventional Bayesian CI becomes unacceptably large in real world applications where the test set sizes are less than a few hundred. The source of this problem is that fact that the Cl is determined exclusively by the result on the test examples. In other words, there is no information at all provided by the uniform prior density distribution employed which reflects complete lack of prior knowledge about the unknown error rate. Therefore, the aim of the study reported here was to study a maximum entropy (ME) based approach to improved prior knowledge and Bayesian CIs, demonstrating its relevance for biomedical research and clinical practice.Method and material:It is demonstrated how a refined non-uniform prior density distribution can be obtained by means of the ME principle using empirical results from a few designs and tests using non-overlapping sets of examples.Results:Experimental results show that ME based priors improve the CIs when employed to four quite different simulated and two real world data sets.Conclusions:An empirically derived ME prior seems promising for improving the Bayesian Cl for the unknown error rate of a designed classifier.
|
|
| 3. |
- Hagberg, Anette, et al.
(författare)
-
Gene expression analysis identifies a genetic signature potentially associated with response to alpha-IFN in chronic phase CML patients
- 2007
-
Ingår i: Leukemia research. - : Elsevier BV. - 0145-2126 .- 1873-5835. ; 31:7, s. 931-938
-
Tidskriftsartikel (refereegranskat)abstract
- Microarray-based gene expression analysis was performed on diagnostic chronic phase CML patient samples prior to interferon treatment. Fifteen patient samples corresponding to six cytogenetic responders and nine non-responders were included. Genes differentially expressed between responder and non-responder patients were listed and a subsequent leave-one-out cross validation (LOOV) procedure showed that the top 20 genes allowed the highest prediction accuracy. The relevant genes were quantified by real-time PCR that supported the microarray results. We conclude that it might be possible to use gene expression analysis to predict future response to interferon in CML diagnostic samples.
|
|
| 4. |
- Hägerstrand, Daniel, et al.
(författare)
-
Characterization of an imatinib-sensitive subset of high-grade human glioma cultures
- 2006
-
Ingår i: Oncogene. - : Springer Science and Business Media LLC. - 0950-9232 .- 1476-5594. ; 25:35, s. 4913-4922
-
Tidskriftsartikel (refereegranskat)abstract
- High-grade gliomas, including glioblastomas, are malignant brain tumors for which improved treatment is urgently needed. Genetic studies have demonstrated the existence of biologically distinct subsets. Preliminary studies have indicated that platelet-derived growth factor (PDGF) receptor signaling contributes to the growth of some of these tumors. In this study, human high-grade glioma primary cultures were analysed for sensitivity to treatment with the PDGF receptor inhibitor imatinib/Glivec/Gleevec/STI571. Six out of 15 cultures displayed more than 40% growth inhibition after imatinib treatment, whereas seven cultures showed less than 20% growth inhibition. In the sensitive cultures, apoptosis contributed to growth inhibition. Platelet-derived growth factor receptor status correlated with imatinib sensitivity. Supervised analyses of gene expression profiles and real-time PCR analyses identified expression of the chemokine CXCL12/SDF-1 (stromal cell-derived factor 1) as a predictor of imatinib sensitivity. Exogenous addition of CXCL12 to imatinib-insensitive cultures conferred some imatinib sensitivity. Finally, coregulation of CXCL12 and PDGF alpha-receptor was observed in glioblastoma biopsies. We have thus defined the characteristics of a novel imatinib-sensitive subset of glioma cultures, and provided evidence for a functional relationship between imatinib sensitivity and chemokine signaling. These findings will assist in the design and evaluation of clinical trials exploring therapeutic effects of imatinib on malignant brain tumors.
|
|
| 5. |
|
|
