Development of a screening model for APL using cell population data and deep learning-extracted WBC scattergram features
The RFC-S model represents an innovative approach to APL screening by combining deep learning-derived scattergram features with routine blood parameters. This two-stage methodology achieves high diagnostic accuracy (AUC > 0.98) while maintaining computational efficiency. Importantly, the model's ability to utilize existing laboratory data without requiring additional tests makes it particularly valuable for resource-constrained settings where access to genetic testing or hematological expertise may be limited. Our findings suggest this approach could serve as a practical tool for early APL identification, potentially reducing diagnostic delays in diverse clinical environments.
Authors
- Jianbiao Wang (ORCID: https://orcid.org/0000-0002-5004-3047)
- Yimin Shen (ORCID: https://orcid.org/0000-0002-9449-734X)
- Yushuai Ma
- Wenbo Zheng (ORCID: https://orcid.org/0000-0001-9732-3217)
- Dengbing Yao (ORCID: https://orcid.org/0000-0002-5177-0318)
- Bo Ye (ORCID: https://orcid.org/0000-0001-6967-4220)
- Huihui Zhang (ORCID: https://orcid.org/0000-0002-9781-6086)
- Shihong Zhang (ORCID: https://orcid.org/0000-0002-9661-1089)
- Qi Cai (ORCID: https://orcid.org/0000-0003-3766-8074)
- Jianhua Hu (ORCID: https://orcid.org/0000-0003-1293-6829)
- Jingxian Zhang (ORCID: https://orcid.org/0009-0008-0368-2365)
- Yong Wang (ORCID: https://orcid.org/0000-0001-6363-3452)
- Zhixi Huang
Institutions
- Sun Yat-sen University (CN)
- Ruijin Hospital (CN)
- Soochow University (CN)
- The First Affiliated Hospital, Sun Yat-sen University (CN)
- First Affiliated Hospital of Soochow University (CN)
- First Affiliated Hospital of Zhengzhou University (CN)
- Mindray (China) (CN)
Publication Details
- Journal
- BMC Cancer
- Published
- 2025-11-07
- DOI
- https://doi.org/10.1186/s12885-025-15034-7
- Primary Topic
- Inflammatory Biomarkers in Disease Prognosis
- Type
- article
- Field-Weighted Citation Impact
- 0.00