Case-only analysis in small studies of predictive biomarkers

Abstract Characteristics of tumors and patients can be used as predictive biomarkers to guide treatment choice. Although many potential biomarkers are evaluated each year, only few will eventually be used since evidence is usually based on small studies leading to inconclusive results. Such data are...

Full description

Saved in:
Bibliographic Details
Main Authors: M. Hauptmann, V. H. Nguyen, L. Sollfrank, S. C. Linn, K. Jóźwiak
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-96904-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849699573871673344
author M. Hauptmann
V. H. Nguyen
L. Sollfrank
S. C. Linn
K. Jóźwiak
author_facet M. Hauptmann
V. H. Nguyen
L. Sollfrank
S. C. Linn
K. Jóźwiak
author_sort M. Hauptmann
collection DOAJ
description Abstract Characteristics of tumors and patients can be used as predictive biomarkers to guide treatment choice. Although many potential biomarkers are evaluated each year, only few will eventually be used since evidence is usually based on small studies leading to inconclusive results. Such data are often analyzed with Cox proportional hazards regression using a multiplicative interaction term between biomarker and treatment, with insufficient power and possibly biased results. Instead of analyzing patients who do (cases) and do not experience (non-cases) the survival event of interest, case-only analysis with logistic regression has been proposed, however with unknown small sample properties. We evaluated the performance of case-only analysis with bias-eliminating Firth correction and confidence intervals obtained with a profile likelihood method in a simulation study tailored to breast cancer. Our results show that this approach is generally inferior to the full cohort analysis but has acceptable properties when the marker is protective or null among patients treated with the standard treatment, the event rate is low (e.g., a rare event and a protective marker) and treatment assignment is independent of the marker level (e.g., in randomized studies). In such situations, the case-only design offers substantial cost savings. However, the model is sensitive to these assumptions.
format Article
id doaj-art-5d97bd5af12944f285502e57840cf9d7
institution DOAJ
issn 2045-2322
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-5d97bd5af12944f285502e57840cf9d72025-08-20T03:18:32ZengNature PortfolioScientific Reports2045-23222025-04-011511810.1038/s41598-025-96904-9Case-only analysis in small studies of predictive biomarkersM. Hauptmann 0V. H. Nguyen1L. Sollfrank 2S. C. Linn 3K. Jóźwiak4Brandenburg Medical School Theodor Fontane, Institute of Biostatistics and Registry ResearchBrandenburg Medical School Theodor Fontane, Institute of Biostatistics and Registry ResearchBrandenburg Medical School Theodor Fontane, Institute of Biostatistics and Registry ResearchDivision of Molecular Pathology, The Netherlands Cancer InstituteBrandenburg Medical School Theodor Fontane, Institute of Biostatistics and Registry ResearchAbstract Characteristics of tumors and patients can be used as predictive biomarkers to guide treatment choice. Although many potential biomarkers are evaluated each year, only few will eventually be used since evidence is usually based on small studies leading to inconclusive results. Such data are often analyzed with Cox proportional hazards regression using a multiplicative interaction term between biomarker and treatment, with insufficient power and possibly biased results. Instead of analyzing patients who do (cases) and do not experience (non-cases) the survival event of interest, case-only analysis with logistic regression has been proposed, however with unknown small sample properties. We evaluated the performance of case-only analysis with bias-eliminating Firth correction and confidence intervals obtained with a profile likelihood method in a simulation study tailored to breast cancer. Our results show that this approach is generally inferior to the full cohort analysis but has acceptable properties when the marker is protective or null among patients treated with the standard treatment, the event rate is low (e.g., a rare event and a protective marker) and treatment assignment is independent of the marker level (e.g., in randomized studies). In such situations, the case-only design offers substantial cost savings. However, the model is sensitive to these assumptions.https://doi.org/10.1038/s41598-025-96904-9Biomarker-treatment interactionCase-only analysisFirth’s penalized maximum likelihoodTreatment heterogeneity
spellingShingle M. Hauptmann
V. H. Nguyen
L. Sollfrank
S. C. Linn
K. Jóźwiak
Case-only analysis in small studies of predictive biomarkers
Scientific Reports
Biomarker-treatment interaction
Case-only analysis
Firth’s penalized maximum likelihood
Treatment heterogeneity
title Case-only analysis in small studies of predictive biomarkers
title_full Case-only analysis in small studies of predictive biomarkers
title_fullStr Case-only analysis in small studies of predictive biomarkers
title_full_unstemmed Case-only analysis in small studies of predictive biomarkers
title_short Case-only analysis in small studies of predictive biomarkers
title_sort case only analysis in small studies of predictive biomarkers
topic Biomarker-treatment interaction
Case-only analysis
Firth’s penalized maximum likelihood
Treatment heterogeneity
url https://doi.org/10.1038/s41598-025-96904-9
work_keys_str_mv AT mhauptmann caseonlyanalysisinsmallstudiesofpredictivebiomarkers
AT vhnguyen caseonlyanalysisinsmallstudiesofpredictivebiomarkers
AT lsollfrank caseonlyanalysisinsmallstudiesofpredictivebiomarkers
AT sclinn caseonlyanalysisinsmallstudiesofpredictivebiomarkers
AT kjozwiak caseonlyanalysisinsmallstudiesofpredictivebiomarkers