Key result
Federated machine learning matches centralized models for predicting coronary calcification with ~67% sensitivity.
Why the study?
Implementation of artificial intelligence in healthcare faces significant hurdles, primarily access to data, which federated machine learning could support by enabling privacy-preserving data access.
Does a federated machine learning approach predict coronary artery calcification scores as accurately as a centralized model?
Does a federated machine learning approach predict coronary artery calcification scores as accurately as a centralized model?
Federated machine learning provides a privacy-preserving alternative to centralized models for predicting coronary artery calcification scores with comparable accuracy.
Answers are grounded in this paper and cite their sources.
May support privacy-preserving CAC prediction across sites; hypothesis-generating and requires prospective validation before adoption.
The implementation of Artificial Intelligence (AI) still faces significant hurdles and one key factor is the access to data. One approach that could support that is federated machine learning (FL) since it allows for privacy preserving data access. For this proof of concept, a prediction model for coronary artery calcification scores (CACS) has been applied. The FL was trained based on the data in the different institutions, while the centralized machine learning model was trained on one allocation of data. Both algorithms predict patients with risk scores ≥5 based on age, biological sex, waist circumference, dyslipidemia and HbA1c. The centralized model yields a sensitivity of c. 66% and a specificity of c. 70%. The FL slightly outperforms that with a sensitivity of 67% while slightly underperforming it with a specificity of 69%. It could be demonstrated that CACS prediction is feasible via both, a centralized and an FL approach, and that both show very comparable accuracy. In order to increase accuracy, additional and a higher volume of patient data is required and for that FL is utterly necessary. The developed "CACulator" serves as proof of concept, is available as research tool and shall support future research to facilitate AI implementation.
No takes yet. Share an insight, caveat, or question.
Wolff et al. (2022) studied Coronary artery calcification (n=680). Federated machine learning (FL) model vs. Centralized machine learning model was evaluated on Sensitivity for predicting CACS ≥5. Federated machine learning demonstrated comparable performance to centralized machine learning for predicting coronary artery calcification scores ≥5, yielding a sensitivity of 66.7% and specificity of 68.6%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: