Application of artificial intelligence to analyze data from randomized controlled trials: An example from DECAAF II
Heart Rhythm, vol. 22, pp. 3035–3041
Abstract
BACKGROUND: Causal machine learning (ML) provides an efficient way of identifying heterogeneous treatment effect groups from hundreds of possible combinations, especially for randomized trial data. OBJECTIVE: The aim of this paper is to illustrate the potential of applying causal ML on the DECAAF II trial data. We proposed a causal ML model to predict the treatment response heterogeneity. METHODS: We applied causal tree learning to the DECAAF II trial data as an example of real applications, identifying subgroups that may be superior when subject to one of the treatments over the other through an easily interpretable process. For each subgroup identified, the characteristics were summarized, and the relationship between treatment arms and risk for recurrence of atrial tachyarrhythmia (aTA) among subjects was assessed. RESULTS: Causal tree learning demonstrated that, among all the preablation predictors, dividing subgroups according to age, with a cutoff of 58 years, provides the most heterogeneous subgroups in response to fibrosis-guided ablation in addition to pulmonary vein isolation (PVI) compared with PVI alone. The difference in the risk of recurrence of aTA between 2 treatments was nonsignificant in older patients (hazard ratio [HR] 1.06; 95% confidence interval [CI] 0.77-1.47; P = .72). However, among the younger patients, the risk of aTA recurrence was significantly lower in the fibrosis-guided ablation group compared with PVI-only (HR 0.50; 95% CI 0.28-0.90); P = .02). CONCLUSION: Applying causal ML on random controlled trial datasets helped us identify groups of patients that profited from the treatment of interest in an efficient and unbiased manner.
Authors 23
-
Affiliation as printed
Cardiology Department, Tulane University School of Medicine, New Orleans, Louisiana
Cardiology Department, Tulane University School of Medicine, New Orleans, Louisiana, United States
-
University of Washington · University of Washington Medical Center
Affiliation as printed
Cardiology Department, University of Washington Medical Center, Seattle, Washington
Cardiology Department, University of Washington Medical Center, Seattle, Washington, United States
-
Heart and Diabetes Center North Rhine-Westphalia
Affiliation as printed
Heart and Diabetes Center NRW, Bad Oeynhausen, Germany
-
Heart and Diabetes Center North Rhine-Westphalia
Affiliation as printed
Heart and Diabetes Center NRW, Bad Oeynhausen, Germany
-
Affiliation as printed
Klinikum Coburg, Coburg, Germany
-
Johns Hopkins University · Johns Hopkins Medicine · Johns Hopkins Hospital
Affiliation as printed
Cardiology Department, Johns Hopkins Medicine, Baltimore, Maryland
Cardiology Department, Johns Hopkins Medicine, Baltimore, Maryland, United States
-
Leiden University Medical Center
Affiliation as printed
Cardiology Department, Leiden University Medical Center, Leiden, The Netherlands
-
Affiliation as printed
Cardiology Department, Adelaide Medical School, Adelaide, Australia
-
Affiliation as printed
Swedish Center, Seattle, Washington
Swedish Center, Seattle, Washington, United States
-
Hospital of the University of Pennsylvania
Affiliation as printed
Hospital of the University of Pennsylvania, Philadelphia, Pennsylvania
Hospital of the University of Pennsylvania, Philadelphia, United States
-
Massachusetts General Hospital
Affiliation as printed
Cardiology Department, Massachusetts General Hospital, Boston, Massachusetts
Cardiology Department, Massachusetts General Hospital, Boston, Massachusetts, United States
-
Affiliation as printed
Cardiology Department, Leipzig University, Leipzig, Germany
-
Affiliation as printed
Cardiology Department, Loyola University Chicago, Chicago, Illinois
Cardiology Department, Loyola University Chicago, Chicago, Illinois, United States
-
Johns Hopkins University · Johns Hopkins Medicine · Johns Hopkins Hospital
Affiliation as printed
Cardiology Department, Johns Hopkins Medicine, Baltimore, Maryland
Cardiology Department, Johns Hopkins Medicine, Baltimore, Maryland, United States
-
Affiliation as printed
Cardiology Department, Segalen University, Bordeaux, France
-
Affiliation as printed
Cardiology Department, Tulane University School of Medicine, New Orleans, Louisiana
Cardiology Department, Tulane University School of Medicine, New Orleans, Louisiana, United States
-
Affiliation as printed
Cardiology Department, Tulane University School of Medicine, New Orleans, Louisiana
Cardiology Department, Tulane University School of Medicine, New Orleans, Louisiana, United States
-
Affiliation as printed
Cleveland Clinic, Cleveland, Ohio
Cleveland clinic, Cleveland, Ohio, United States
-
Affiliation as printed
Cardiology Department, Tulane University School of Medicine, New Orleans, Louisiana
Cardiology Department, Tulane University School of Medicine, New Orleans, Louisiana, United States
-
Affiliation as printed
Cardiology Department, Tulane University School of Medicine, New Orleans, Louisiana
Cardiology Department, Tulane University School of Medicine, New Orleans, Louisiana, United States
-
Affiliation as printed
Cardiology Department, Tulane University School of Medicine, New Orleans, Louisiana
Cardiology Department, Tulane University School of Medicine, New Orleans, Louisiana, United States
-
Affiliation as printed
Cleveland Clinic, Cleveland, Ohio
Cleveland clinic, Cleveland, Ohio, United States
-
Nassir F. Marrouche corresponding
Affiliation as printed
Cardiology Department, Tulane University School of Medicine, New Orleans, Louisiana. Electronic address: nmarrouche@tulane.edu
Cardiology Department, Tulane University School of Medicine, New Orleans, Louisiana, United States. Electronic address: nmarrouche@tulane.edu
Cited by 1 stored of 1
1 result
No patents citing this paper on Lens.org (checked 2026-10-11).