Impact of analytical bias on machine learning models for sepsis prediction using laboratory data
Bias can influence model performance depending on the parameters and their combinations. Developing new validation strategies to assess the impact of analytical bias on laboratory data in ML models could improve their reliability.
Authors
- Yasemin Üstündağ (ORCID: https://orcid.org/0000-0003-2415-0372)
- Mario Plebani (ORCID: https://orcid.org/0000-0002-0270-1711)
- Chiara Cosma (ORCID: https://orcid.org/0000-0002-0678-0277)
- Meryem Rümeysa Yeşil (ORCID: https://orcid.org/0000-0002-6492-6094)
- Ilaria Talli (ORCID: https://orcid.org/0000-0002-9425-6140)
- Michela Pelloso (ORCID: https://orcid.org/0000-0002-2853-4499)
- Andrea Padoan (ORCID: https://orcid.org/0000-0003-1284-7885)
- Elisa Pangrazzi (ORCID: https://orcid.org/0009-0002-6043-5471)
Institutions
- University of Padua (IT)
- University of Health Science (KH)
- Bursa Technical University (TR)
- Sağlık Bilimleri Üniversitesi (TR)
- S.B.Ü. Bursa Yüksek İhtisas Eğitim ve Araştırma Hastanesi (TR)
Publication Details
- Journal
- Clinical Chemistry and Laboratory Medicine (CCLM)
- Published
- 2025-05-27
- DOI
- https://doi.org/10.1515/cclm-2025-0491
- Citations
- 5
- Primary Topic
- Sepsis Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 6.77