Home
Resource
An interpretable random survival forest modeling pipeline to identify novel biomarkers of event-free survival in high-risk pediatric acute lymphoblastic leukemia
PDF
PDF format is widely accepted and good for printing.
Plug-in required
PDF-1(2.64 MB)
Citation & Export
View Usage Statistics
Staff View

Citation & Export
Hide

Simple citation

Bohannan, Zachary. An interpretable random survival forest modeling pipeline to identify novel biomarkers of event-free survival in high-risk pediatric acute lymphoblastic leukemia. Retrieved from https://doi.org/doi:10.7282/t3-r9rz-cc16

Export

Click here for information about Citation Management Tools at Rutgers.

Statistics
Hide

Description

TitleAn interpretable random survival forest modeling pipeline to identify novel biomarkers of event-free survival in high-risk pediatric acute lymphoblastic leukemia
NameBohannan, Zachary (author); Mitrofanova, Antonina (chair); Coffman, Frederick (member); Gohel, Suril (member); Rutgers University; School of Health Professions
Date Created2022
Other Date2022-01 (degree)
SubjectOncology, Bioinformatics, Biostatistics, Lymphoblastic leukemia -- Computer simulation, Lymphoblastic leukemia in children
Extent99 pages : illustrations
DescriptionHigh-risk pediatric B-ALL patients experience 5-year negative event rates up to 25%. Although some biomarkers of relapse are utilized in the clinic, their prevalence is limited. Here, we propose a random survival forest (RSF) machine learning model utilizing interpretable genomic inputs to predict relapse/death in high-risk pediatric B-ALL patients. We utilized whole exome sequencing profiles from 156 patients in the TARGET-ALL study (with samples collected at presentation) further stratified into training and test cohorts (109 and 47 patients, respectively). To avoid overfitting and facilitate the interpretation of machine learning results, input genomic variables were engineered using a stepwise approach involving univariable Cox models to select variables directly associated with outcomes, genomic coordinate-based analysis to select mutational hotspots, and correlation analysis to eliminate feature co-linearity. Model training identified 7 genomic regions most predictive of relapse/death-free survival. The test cohort error rate was 12.47%, and a polygenic score based on the sum of the top 7 variables effectively stratified patients into two groups, with significant differences in time to relapse/death (log-rank P=0.001, hazard ratio=5.41). Our model compared favorably to other commonly utilized methods and outperformed RSF that used gold-standard prognostic variables (error rate=24.35%). Validation in 174 standard-risk patients and 3 patients who failed to respond to induction therapy confirmed that our RSF model and polygenic score were specific to high-risk disease. We propose that our feature selection/engineering approach can increase the clinical utility of RSF, and our polygenic score could be utilized for enhance clinical decision-making in high-risk B-ALL.
NotePh.D.
NoteIncludes bibliographical references
Genretheses
Persistent URLhttps://doi.org/doi:10.7282/t3-r9rz-cc16
LanguageEnglish
CollectionSchool of Health Professions ETD Collection
Organization NameRutgers, The State University of New Jersey
RightsThe author owns the copyright to this work.
Version 8.5.5
Rutgers University Libraries - Copyright ©2024