Sentence examples for algorithm decisions from inspiring English sources

In our algorithm decisions are primarily based on the value of blood glucose, but not on the actual glucose trend [ 21].

The 2 weeks >50% granulation, being an earlier surrogate, may also have practical value for treatment algorithm decisions and/or pharmacoeconomic considerations.

So, Weka workbench is used for implementing 3-data-mining techniques e.g. association rule (PredictiveApriori algorithm), decision tree (ID3 algorithm), attribute selection (FilteredAttributeEvaluator with Ranker algorithm) etc.

These data collectively suggest that, at least for this quantitative trait, algorithm decision logic and phenotyping details do not appreciably impact genetic association study test statistics.

Genetic algorithm, decision tree, and neural network based approaches had also been attempted to distinguish the drug-like compounds from the non drug-like compounds [ 17- 19].

The present study focuses on examining the impact algorithm decision logic has on genetic associations related to a single quantitative trait, HDL-C.

These data collectively suggest that, at least for HDL-C, algorithm decision logic and phenotyping details do not appreciably impact genetics association study tests statistics.

Larger sample sizes are needed to make comprehensive comparisons of genetic effect sizes and significance rankings for EMR-derived phenotypes susceptible to algorithm decision logic and phenotyping details.

Given the number of possible algorithms that could be developed for any one EMR-derived phenotype, we explored here the impact algorithm decision logic has on genetic association study results for a single quantitative trait, high density lipoprotein cholesterol (HDL-C).

Further study is needed to more fully explore the limitations and impact algorithm decision logic may have on genetic association studies for binary clinical outcomes such as myocardial infarction or pharmacogenomic studies for traits such as warfarin dosing.

While our data suggest that EMR-derived phenotypes may be robust to certain aspects of the algorithm decision logic and phenotyping details, these data do not imply that genetic association studies are not impacted by poor phenotyping.