Automated causal inference in application to randomized controlled clinical trials

Nature Machine Intelligence, vol. 4, pp. 436–444

Abstract

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.

Authors 13

1. Ji Q. Wu corresponding

   University of Zurich · University Hospital Zurich

   Affiliation as printed

   Department of Pathology and Molecular Pathology, University Hospital, University of Zurich, Zurich, Switzerland

2. Nanda Horeweg Aachen Department of Radiation Oncology

   Leiden University Medical Center

   Affiliation as printed

   Department of Radiation Oncology, Leiden University Medical Center, Leiden, the Netherlands

3. Marco de Bruyn

   University Medical Center Groningen · University of Groningen

   Affiliation as printed

   Department of Obstetrics and Gynecology, University of Groningen, University Medical Center, Groningen, Groningen, the Netherlands

4. Remi A. Nout Aachen Department of Radiation Oncology

   Leiden University Medical Center

   Affiliation as printed

   Department of Radiation Oncology, Leiden University Medical Center, Leiden, the Netherlands

5. Ina Maria Jurgenliemk-Schulz

   University Medical Center Utrecht

   Affiliation as printed

   Department of Radiation Oncology, University Medical Center Utrecht, Utrecht, the Netherlands

6. Ludy C.H.W. Lutgens
   Affiliation as printed

   Maastricht Radiation Oncology Clinic, Maastricht, the Netherlands

7. Jan J. Jobsen

   Medisch Spectrum Twente

   Affiliation as printed

   Department of Radiotherapy, Medisch Spectrum Twente, Enschede, the Netherlands

8. Elzbieta M. van der Steen‐Banasik

   Radiotherapiegroep

   Affiliation as printed

   Radiotherapiegroep, Arnhem, the Netherlands

9. Hans W. Nijman

   University Medical Center Groningen · University of Groningen

   Affiliation as printed

   Department of Obstetrics and Gynecology, University of Groningen, University Medical Center, Groningen, Groningen, the Netherlands

10. Vincent T.H.B.M. Smit Aachen Department of Pathology, Leiden University Medical Center

    Leiden University Medical Center

    Affiliation as printed

    Department of Pathology, Leiden University Medical Center, Leiden, the Netherlands

11. Tjalling Bosse Aachen Department of Pathology, Leiden University Medical Center

    Leiden University Medical Center

    Affiliation as printed

    Department of Pathology, Leiden University Medical Center, Leiden, the Netherlands

12. Carien L. Creutzberg Aachen Department of Radiation Oncology

    Leiden University Medical Center

    Affiliation as printed

    Department of Radiation Oncology, Leiden University Medical Center, Leiden, the Netherlands

13. Viktor Hendrik Koelzer corresponding

    University of Zurich · University Hospital Zurich

    Affiliation as printed

    Department of Pathology and Molecular Pathology, University Hospital, University of Zurich, Zurich, Switzerland