Speech/Talk (Diverse speeches and writings)
Omics signature detection for improved diagnostics
Debit, Ahmed
2019
 

Files


Full Text
SAB_Medical_Genomics_2019.pdf
Author preprint (1.63 MB)
Download

All documents in ORBi are protected by a user license.

Send to



Details



Keywords :
biomarker signature; random forest; Omics data
Abstract :
[en] Machine learning approaches are heavily used to produce models that will one day support clinical decisions. To be reliably used asa medical decision, such diagnosis and prognosis tools have to harbor a high-level of precision. Random Forests have been already used in cancer diagnosis, prognosis, and screening. Numerous Random Forests methods have been derived from the original random forest algorithm. Nevertheless, the precision of their generated models remains unknown when facing biological data. The precision of such models can be therefore too variable to produce models with the same accuracy of classification, making them useless in daily clinics. Here, we perform an empirical comparison of Random Forest based strategies, looking for their precision in model accuracy and overall computational time. An assessment of 15 methods is carried out for the classification of paired normal-tumor patients, from 3 TCGA RNA-Seq datasets: BRCA (Breast Invasive Carcinoma), LUSC (Lung Squamous Cell Carcinoma), and THCA (Thyroid Carcinoma). Results demonstrate noteworthy differences in the precision of the model accuracy and the overall time processing, between the strategies for one dataset, as well as between datasets for one strategy. Therefore, we highly recommend to test several random forest strategies prior to modeling. This will certainly improve the precision in model accuracy while revealing the method of choice for the candidate data.
Research center :
BIO3 Unit, Human Genetics GIGA-R
Disciplines :
Engineering, computing & technology: Multidisciplinary, general & others
Author, co-author :
Debit, Ahmed ;  Université de Liège - ULiège > GIGA
Language :
English
Title :
Omics signature detection for improved diagnostics
Publication date :
19 February 2019
Number of pages :
38
Event name :
Scientific Advisory Board SAB Evaluation, Thematic Unit of Medical Genomics
Event organizer :
ULiège - Université de Liège
Event place :
Liege, Belgium
Event date :
19-02-2019 to 20-02-2019
Audience :
International
Name of the research project :
WALInnov-NACATS 1610125
Funders :
Région wallonne [BE]
Available on ORBi :
since 26 August 2020

Statistics


Number of views
42 (3 by ULiège)
Number of downloads
8 (3 by ULiège)

Bibliography


Similar publications



Contact ORBi