Article

Machine learning detects hidden treatment response patterns only in the presence of comprehensive clinical phenotyping

2024-10-09

Abstract excerpt

<h4>ABSTRACT</h4> Inferential statistics traditionally used in clinical trials can miss relationships between clinical phenotypes and treatment responses. We simulated a randomised clinical trial to explore how gradient boosting (XGBoost) machine learning (ML) compares with traditional analysis when ‘ground truth’ treatment responsiveness depends on the interaction of multiple phenotypic variables. As expected, tr...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 746335ef-65e7-5e83-bf18-0f094843f602
DOI: 10.1101/2024.10.09.24315155

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Machine learning detects hidden treatment response patterns only in the presence of comprehensive clinical phenotypingDOI 10.1101/2024.10.09.24315155Read

Inclusion of genetic variants in an ensemble of gradient boosting decision trees does not improve the prediction of citalopram treatment response.Semantic proximity Read

Retrospective evaluation of human genetic evidence for clinical trial success using Mendelian randomization and machine learningSemantic proximity Read

RAINFOREST: a random forest approach to predict treatment benefit in data from (failed) clinical drug trials.Semantic proximity Read

Empirical Sample Size Determination for Popular Classification Algorithms in Clinical ResearchSemantic proximity Read

Can we use machine learning to discover risk factors? Testing the proof of principle using data on >11,000 predictors and mortality in the UK BiobankSemantic proximity Read

A Meta-Learner Framework to Estimate Individualized Treatment Effects for Survival OutcomesSemantic proximity Read

Modeling the Pretest Probability of Identifying Druggable Mutations in Lung Cancer Using Nationwide Comprehensive Genomic Profiling Data.Semantic proximity Read

A Sequential Multiple Assignment Randomized Trial Design with Response-Adaptive Tailoring FunctionSemantic proximity Read

Probabilistic classification of gene-by-treatment interactions on molecular count phenotypesSemantic proximity Read

Performance metrics for models designed to predict treatment effectSemantic proximity Read

Efficient gradient boosting for prognostic biomarker discoverySemantic proximity Read

Predicting Drug Response with Multi-Task Gradient-Boosted Trees in EpilepsySemantic proximity Read