EUVIMEDEUVIMED entdecken
Crossref

Overview and Practical Recommendations on Using Shapley Values for Identifying Predictive Biomarkers via CATE Modeling

David Svensson, Erik Hermansson, Nikolaos Nikolaou, Konstantinos Sechidis iD, Ilya Lipkovich

Statistics in Medicine · 2026-01 · 45 (1-2)

DOI: 10.1002/sim.70375 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Statistics in Medicine, online erschienen am 22.01.2026. Verfasst von David Svensson und 4 weiteren Autor:innen. Beteiligte Einrichtung: AstraZeneca, Gothenburg, Sweden. Hauptthemen laut MEDLINE: Biomarkers, Models, Statistical, Machine Learning. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 81 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, two parallel research trends have emerged in machine learning, yet their intersections remain largely unexplored. On one hand, there has been a significant increase in literature focused on Individual Treatment Effect (ITE) modeling, particularly targeting the Conditional Average Treatment Effect (CATE) using meta‐learner techniques. These approaches often aim to identify causal effects from observational data. On the other hand, the field of Explainable Machine Learning (XML) has gained traction, with various approaches developed to explain complex models and make their predictions more interpretable. A prominent technique in this area is Shapley Additive Explanations (SHAP), which has become mainstream in data science for analyzing supervised learning models. However, there has been limited exploration of SHAP's application in identifying predictive biomarkers through CATE models, a crucial aspect in pharmaceutical precision medicine. We address inherent challenges associated with the SHAP concept in multi‐stage CATE strategies and introduce a surrogate estimation approach that is agnostic to the choice of CATE strategy, effectively reducing computational burdens in high‐dimensional data. Using this approach, we conduct simulation benchmarking to evaluate the ability to accurately identify biomarkers using SHAP values derived from various CATE meta‐learners and Causal Forest.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

BiomarkersModels, StatisticalMachine LearningHumansComputer SimulationPrecision MedicineTreatment OutcomeTreatment Effect Heterogeneity

Stichwörter der Autor:innen

SHAPShapley valuescausal inferenceconditional average treatment effectdiscovery ratesindividual treatment effectsmachine learningprecision medicineprognostic and predictive biomarkerstreatment effect heterogeneity

Substanzen

Biomarkers

Autor:innen und Institutionen

  • AstraZeneca, Gothenburg, Sweden.
  • Faculty of Informatics and Data Science, University of Regensburg, Regensburg, Germany.
  • UCL, London, UK.
  • Novartis, Basel, Switzerland.
  • Eli Lilly and Company, Indianapolis, Indiana, USA.

ORCID-Profile: Konstantinos Sechidis

Zitieren

APA

Svensson, D., Hermansson, E., Nikolaou, N., Sechidis, K., & Lipkovich, I. (2026). Overview and Practical Recommendations on Using Shapley Values for Identifying Predictive Biomarkers via CATE Modeling. Statistics in Medicine, 45(1-2). https://doi.org/10.1002/sim.70375

Vancouver

Svensson D, Hermansson E, Nikolaou N, Sechidis K, Lipkovich I. Overview and Practical Recommendations on Using Shapley Values for Identifying Predictive Biomarkers via CATE Modeling. Statistics in Medicine. 2026;45(1-2). doi:10.1002/sim.70375

BibTeX
@article{Svensson2026,
  author = {Svensson, David and Hermansson, Erik and Nikolaou, Nikolaos and Sechidis, Konstantinos and Lipkovich, Ilya},
  title = {Overview and Practical Recommendations on Using Shapley Values for Identifying Predictive Biomarkers via CATE Modeling},
  journal = {Statistics in Medicine},
  year = {2026},
  volume = {45},
  number = {1-2},
  doi = {10.1002/sim.70375}
}
Kostenlos starten →