Article Text
Statistics from Altmetric.com
To the Editor We read with great interest the manuscript of Pinto-Filho et al.1 It is a multicentre study about the prognostic values of electrocardiographic findings, where such a gap was provided by the US Preventive Services Task Force that the current evidence was insufficient to relate such findings to predict and thus prevent cardiovascular disease (CVD) events.2
Clinical findings must have proper statistical analysis to ensure reliability.3 It is especially important for clinical prediction, where the experimental design, validation framework and source of biases must be precisely taken into account.4–6 Various standards, including TRIPOD,7 have been proposed in the literature and have become part of the author guidelines of journals such as Heart. The multiple logistic regression model (MLR) was used by Pinto-Filho et al 1 as …
Footnotes
Contributors All the authors have significantly contributed to the manuscript.
Funding This work was supported by the Beatriu de Pinós post-doctoral programme from the Office of the Secretary of Universities and Research from the Ministry of Business and Knowledge of the Government of Catalonia (Grant number: #2020 BP 00261).
Competing interests None declared.
Provenance and peer review Commissioned; internally peer reviewed.
Linked Articles
- Correspondence
- Arrhythmias and sudden death