Delgado, Rosario https://orcid.org/0000-0003-1208-9236
Fernández-Peláez, Francisco
Pallarés, Natàlia
Diaz-Brito, Vicens
Izquierdo, Elisenda
Oriol, Isabel
Simonetti, Antonella
Tebé, Cristian
Videla, Sebastià
Carratalà, Jordi
Funding for this research was provided by:
Ministerio de Ciencia e Innovación (PID2021-123733NB-I00)
Article History
Received: 14 February 2024
Accepted: 22 October 2024
First Online: 18 November 2024
Declarations
:
: The authors declare no potential conflict of interests nor competing interests.
: The computer programming code (R function) that has been developed and utilized in this study, to implement Algorithm 1 (the Multi-Thresholding meta-algorithm, MTh) is accessible under an open-access (MIT) license. You can find it at .
: The use of predictive models in clinical settings raises several important ethical considerations. First and foremost, privacy and data security are critical: patient data used for training and validating models must be protected, and all practices must comply with data protection regulations. Second, it is essential to address potential biases within the model to ensure that predictions are equitable across different patient groups and to prevent discrimination in care. Third, predictive models should be used to complement, rather than replace, clinical judgment. It is important to be transparent about the limitations and uncertainties inherent in the model’s predictions. Lastly, patients should be adequately informed about the use of predictive models in their care. Clear communication is necessary to help patients to understand how these models influence clinical decisions.