Key result
Machine learning model outperforms Mayo and NAC staging for predicting major events in ATTR-CM.
Why the study?
Existing staging systems have limited ability to accurately predict outcomes in contemporary patients with ATTR-CM, a condition associated with poor prognosis and significant morbidity and mortality.
Does a machine learning-based prediction model improve prognostic discrimination for all-cause mortality and heart failure hospitalization in patients with ATTR-CM compared to established staging systems?
Cohort (n=850)
Yes
Does a machine learning-based prediction model improve prognostic discrimination for all-cause mortality and heart failure hospitalization in patients with ATTR-CM compared to established staging systems?
Effect estimate: Harrell C indices of 0.74, 0.77, and 0.72 across cohorts
An ML-based prediction model provides superior individualized prognostication in ATTR-CM compared to traditional staging systems.
Captured external expert commentary on this paper, strongest first. Original sources are linked where available.
“The accompanying editorial praises the authors for performing cross-validation. But cross-validation with the same flawed predictor definitions cannot address this problem. True external validation could have empirically evaluated the magnitude of the issue, but it was not performed.”
ML model may refine ATTR-CM risk stratification; hypothesis-generating and requires prospective validation before clinical adoption.
Importance: Transthyretin cardiac amyloidosis (ATTR-CM) is associated with poor prognosis and significant morbidity and mortality, yet existing staging systems have limited ability to accurately predict outcomes in contemporary patient populations. Objective: To develop and validate a machine learning (ML)-based prognostic model for patients with ATTR-CM. Design, Setting, and Participants: This multicenter cohort study, including specialized referral centers for cardiac amyloidosis, used data from patients with confirmed ATTR-CM in the Swiss Cardiac Amyloidosis Registry (February 2018 to November 2025) and the Cardiac Amyloidosis Registry of the Medical University of Vienna (July 2014 to February 2025). A random survival forest model was developed and evaluated through internal-external cross-validation, with each center iteratively held out for validation. The model was compared with the National Amyloidosis Centre and Mayo Clinic staging systems. Data analysis was conducted from December 2025 to February 2026. Exposure: Clinical, demographic, medication, laboratory, and echocardiographic variables were used to train an ML-based time-to-event prediction model. Main Outcomes and Measures: The primary outcome was defined as a composite event of all-cause mortality and hospitalization for heart failure. Results: A total of 850 patients (median [IQR] age, 79 [74-83] years; 750 [88.2%] male) were included across 3 cohorts (from Bern, Switzerland [Bern-Swiss cohort], n = 352; the other centers from Switzerland combined [Other-Swiss cohort], n = 260; and Vienna, Austria [Vienna cohort], n = 238). The random survival forest model demonstrated good discrimination across all held-out cohorts, with Harrell concordance indices of 0.74 (95% CI, 0.69-0.78), 0.77 (95% CI, 0.69-0.83), and 0.72 (95% CI, 0.67-0.77) for the Bern-Swiss, Other-Swiss, and Vienna cohorts, respectively, and 3-year area under the curve (AUC) of 0.73 (95% CI, 0.66-0.80), 0.80 (95% CI, 0.70-0.88), and 0.75 (95% CI, 0.67-0.83), respectively. The model showed improved discrimination compared with the National Amyloidosis Centre and Mayo Clinic staging systems, with Harrell concordance indices 2% to 10% higher and 3-year AUC improvements ranging from 3% to 19% across cohorts and scoring systems. Calibration was generally acceptable across cohorts and time points. Model performance remained satisfactory in the subgroup of patients receiving disease-modifying therapy. Explainability analyses identified clinically plausible drivers of risk. Conclusions and Relevance: An ML-based time-to-event prediction model demonstrated promising predictive performance and showed improved discrimination compared with established staging systems in patients with ATTR-CM, supporting its potential for individualized prognostication.
No takes yet. Share an insight, caveat, or question.
Baj et al. (2026) conducted a cohort in Transthyretin cardiac amyloidosis (ATTR-CM) (n=850). Machine learning-based time-to-event prediction model (Random Survival Forest) vs. National Amyloidosis Centre (NAC) and Mayo Clinic staging systems was evaluated on Composite of all-cause mortality and hospitalization for heart failure (Harrell C indices of 0.74, 0.77, and 0.72 across cohorts). A machine learning-based prediction model demonstrated improved discrimination for all-cause mortality and heart failure hospitalization compared with established NAC and Mayo Clinic staging systems in patients with ATTR-CM.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: