Automated causal inference in application to randomized controlled clinical trials

Ji Q. Wu*, Nanda Horeweg, Marco de Bruyn, Remi A. Nout, Ina M. Jürgenliemk-Schulz, Ludy C.H.W. Lutgens, Jan J. Jobsen, Elzbieta M. van der Steen-Banasik, Hans W. Nijman, Vincent T.H.B.M. Smit, Tjalling Bosse, Carien L. Creutzberg, Viktor H. Koelzer*

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

2 Citations (Scopus)
2 Downloads (Pure)

Abstract

Randomized controlled trials (RCTs) are considered the gold standard for testing causal hypotheses in the clinical domain; however, the investigation of prognostic variables of patient outcome in a hypothesized cause–effect route is not feasible using standard statistical methods. Here we propose a new automated causal inference method (AutoCI) built on the invariant causal prediction (ICP) framework for the causal reinterpretation of clinical trial data. Compared with existing methods, we show that the proposed AutoCI allows one to clearly determine the causal variables of two real-world RCTs of patients with endometrial cancer with mature outcome and extensive clinicopathological and molecular data. This is achieved via suppressing the causal probability of non-causal variables by a wide margin. In ablation studies, we further demonstrate that the assignment of causal probabilities by AutoCI remains consistent in the presence of confounders. In conclusion, these results confirm the robustness and feasibility of AutoCI for future applications in real-world clinical analysis.

Original languageEnglish
Pages (from-to)436-444
Number of pages9
JournalNature Machine Intelligence
Volume4
Issue number5
Early online date25 Apr 2022
DOIs
Publication statusPublished - May 2022

Bibliographical note

Funding Information: We convey our gratitude to all clinicians and technicians that participated in the PORTEC 1 and 2 trials (registration no. ISRCTN16228756), and all scientists, pathologists and patients involved in the data processing and analysis. The PORTEC 1 and 2 trials were supported by the grants from the Dutch Cancer Society (grant nos. CKTO 90–01 and CKTO 2001–04, respectively). Molecular profiling was supported by the grants from the Dutch Cancer Society (grant nos. KWF UL2012-5447 and KWF/YIG 10418, respectively). V.H.K. reports a grant from the Promedica Foundation (grant no. F-87701-41-01) during the conduct of the study. N.H. reports grants from the Dutch Cancer Society (grant nos. KWF-2021-13400, KWF-2021-13404) during the conduct of the study.

Publisher Copyright: © 2022, The Author(s).

Fingerprint

Dive into the research topics of 'Automated causal inference in application to randomized controlled clinical trials'. Together they form a unique fingerprint.

Cite this