Interpretable deep neural networks for advancing early neonatal birth weight prediction using multimodal maternal factors
Our results demonstrate the substantial benefits of integrating multimodal maternal factors into predictive models for neonatal BW, markedly enhancing the precision over traditional AI methods. The developed decision-support system not only has a possible application in prenatal care but also provides actionable insights that can be leveraged to mitigate the risks associated with LBW, thereby improving clinical decision-making processes and outcomes.
Authors
- Domènec Puig (ORCID: https://orcid.org/0000-0002-0562-4205)
- Luis Adolfo Santos-Calderón (ORCID: https://orcid.org/0000-0002-6871-1103)
- Pere Cavallé (ORCID: https://orcid.org/0000-0002-5683-7219)
- Hatem A. Rashwan (ORCID: https://orcid.org/0000-0001-5421-1637)
- Muhammad Mursil (ORCID: https://orcid.org/0000-0002-6986-8188)
- Michelle M. Murphy (ORCID: https://orcid.org/0000-0002-6304-6204)
- Adnan Khalid (ORCID: https://orcid.org/0000-0001-9467-8055)
Institutions
- Institut de Recerca Biomèdica Catalunya Sud (ES)
- Hospital Universitari Sant Joan de Reus (ES)
- Universitat Rovira i Virgili (ES)
Publication Details
- Journal
- Journal of Biomedical Informatics
- Published
- 2025-05-06
- DOI
- https://doi.org/10.1016/j.jbi.2025.104838
- Citations
- 4
- Primary Topic
- Neonatal and fetal brain pathology
- Type
- article
- Field-Weighted Citation Impact
- 13.98