Optimizing machine learning models for predicting anemia among under-five children in Ethiopia: insights from Ethiopian demographic and health survey data
In general, the random forest algorithm emerged as the preferred model for predicting anemia in children under five. The model exhibited a specificity of 79.26%, sensitivity of 83.07%, positive predictive value of 80.02%, negative predictive value of 82.40%, and an area under the curve of 81.80%.
Authors
- Abdulaziz Kebede Kassaw
- Nurye Sirage (ORCID: https://orcid.org/0000-0003-4561-1289)
- Ali Yimer (ORCID: https://orcid.org/0000-0002-4805-0133)
- Sabah Ahmed (ORCID: https://orcid.org/0000-0001-6042-0558)
- Alemu Birara Zemariam (ORCID: https://orcid.org/0000-0001-8195-3011)
- Endris Mussa
- Adem Yesuf
- Hassen Ahmed Yesuf
Institutions
- Wollo University (ET)
- Woldia University (ET)
Publication Details
- Journal
- BMC Pediatrics
- Published
- 2025-04-22
- DOI
- https://doi.org/10.1186/s12887-025-05659-9
- Citations
- 9
- Primary Topic
- Iron Metabolism and Disorders
- Type
- article
- Field-Weighted Citation Impact
- 15.93