Validation of Toxicogenomic Technologies A Workshop Summary (2007) / Chapter Skim
Currently Skimming:
Attachment 4. Diagnostic Classifier – Gaining Confidence Through Validation
Attachment 4. Diagnostic Classifier – Gaining Confidence Through Validation
Pages 66-74
The Chapter Skim interface presents what we've algorithmically identified as the most significant single chunk of text within every page in the chapter.
Select key terms on the right to highlight them within pages of the chapter.
From page 66... ...
Food and Drug Administration Jefferson, Arizona INTRODUCTION In clinical settings, accurate diagnosis and prognosis relies mainly on histopathology, cytomorphology, or immunophenotyping. Unfortunately, some diseases are hard to classify by current clinical techniques.
|
From page 67... ...
Diagnostic Classifier -- Gaining Confidence Through Validation 67 expression patterns, SELDI-TOF MS data, and SNPs (single nucleotide polymorphisms) profiles in a case-control study.
|
From page 68... ...
68 Validation of Toxicogenomic Technologies from combining classifiers is valuable in assessing prediction confidence, which is usually difficult to obtain from a single classifier. DECISION FOREST -- A ROBUST CONSENSUS METHOD FOR DIAGNOSTIC CLASSIFICATION Most consensus modeling relies on resampling approaches that use only a portion of the subjects for constructing the individual classifiers.
|
From page 69... ...
Diagnostic Classifier -- Gaining Confidence Through Validation 69 A data set with N independent variables (e.g., genes in microarray data) Repeating the process until no qualified tree Develop a tree classifier using can be developed only m (m |
From page 70... ...
70 Validation of Toxicogenomic Technologies 12 10 Misclassifications ion 8 6 4 2 0 1st tree 1st 2 trees 1st 3 trees 1st 4 trees Tree Combining FIGURE 4-2 Plot of misclassifications versus the number of tree classifiers to be combined in DF. Source: Tong et al.
|
From page 71... ...
Diagnostic Classifier -- Gaining Confidence Through Validation 71 It is worthwhile to mention that classifier development and variable selection are integral in DF. Thus, DF avoids the selection bias during cross-validation that thereby provides a realistic assessment of the predictivity of a DF classifier.
|
From page 72... ...
72 Validation of Toxicogenomic Technologies 100% 90% 80% Accuracy 70% 60% Forest 50% Tree 40% 30% 1 2 3 4 5 6 7 8 9 0 0.
|
From page 73... ...
Diagnostic Classifier -- Gaining Confidence Through Validation 73 validation on each of pseudo data sets to generate a null distribution, i.e., the distribution of prediction accuracy from all classifiers developed on all pseudo data sets. The null distribution can then be compared with the distribution of multiple 10-fold cross-validation results derived from the real data set.
|
From page 74... ...
74 Validation of Toxicogenomic Technologies CONCLUSIONS Diagnostic classification based on omics data presents challenges for most conventional supervised learning methods. Validation is a vital step towards the practical use of diagnostic classifiers.
|
Key Terms
This material may be derived from roughly machine-read images, and so is provided only to facilitate research.
More
information on Chapter Skim is available.