Summary of predictive performance per dataset when using gene-expression and clinical predictors.

<p>We predicted patient states using gene-expression and clinical predictors (Analysis 3). For each combination of dataset, class variable, and classification algorithm, we calculated the arithmetic mean of area under the receiver operating characteristic curve (AUROC) values across 50 iterati...

وصف كامل

محفوظ في:

التفاصيل البيبلوغرافية
المؤلف الرئيسي:	Stephen R. Piccolo (8367780) (author)
مؤلفون آخرون:	Avery Mecham (12231713) (author), Nathan P. Golightly (12231716) (author), Jérémie L. Johnson (12231719) (author), Dustin B. Miller (7064549) (author)
منشور في:	2022
الموضوعات:	Genetics Cancer Space Science Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified transcriptomic measurements reflect measurements per patient combined clinical predictors particular disease subtype represent diverse machine performing hyperparameter optimization classify patients based expression data varies learning classification algorithms hyperparameter optimization classification algorithms expression data particular therapy learning methodologies learning libraries expression datasets expression biomarkers xlink "> univariate feature uniform approach sophisticated methods held constant findings illustrate epigenomic variations effective care critical step classifying patients benchmark comparison
الوسوم:	إضافة وسم لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!

Summary of predictive performance per dataset when using gene-expression and clinical predictors.

مواد مشابهة