Prediction of hemoglobin levels and red blood cell parameters using deep learning on blood smear images

Chao Yang, Dongling Li, Chouxia Zhao, Xiaohe Zhang, Nengliang Ouyang, Yonghui Guo, Limei Feng, Yongjian He, Bo Situ, Dehua Sun, Lei Zheng,
Prediction of hemoglobin levels and red blood cell parameters using deep learning on blood smear images,
Intelligent Medicine,
2025,
,
ISSN 2667-1026,
https://doi.org/10.1016/j.imed.2025.05.011.
(https://www.sciencedirect.com/science/article/pii/S2667102625001056)
Abstract: Objective
Hemoglobin (HGB), hematocrit (HCT), and red blood cell (RBC) concentration are critical parameters for diagnosing anemia, traditionally measured using automated hematology analyzers. Recent advancements in deep learning in blood cell analysis have primarily focused on the classification of white blood cells, yet there is limited research on the quantitative prediction of HGB and RBC parameters from peripheral blood smear images. This study aims to develop and validate deep learning models to predict HGB, HCT, and RBC levels directly from blood smear images, offering a potential low-cost alternative to traditional methods.
Methods
A multicenter dataset of over 13,000 stained blood smear images paired with corresponding hematology analysis results was collected from three medical centers between March 2021 and March 2022. Deep learning models, based on the ResNet18 architecture, were trained to quantitatively predict HGB, HCT, and RBC levels. The models were evaluated using Pearson’s correlation coefficient (PCC), R² values, and mean absolute error (MAE). Ten-fold cross-validation was employed to ensure robustness, and external validation was performed on two independent datasets.
Results
The deep learning models achieved strong performance in predicting HGB (PCC = 0.977, R² = 0.954, MAE = 4.269 g/L), HCT (PCC = 0.982, R² = 0.965, MAE = 0.013 L/L), and RBC concentration (PCC = 0.982, R² = 0.964, MAE = 0.155 × 10¹²/L). The models also demonstrated the ability to predict RBC concentration from single images with varying cell densities, leveraging the global cell distribution patterns. External validation showed consistent performance, with PCCs exceeding 0.9 for HGB, HCT, and RBC predictions.
Conclusion
This study demonstrates the feasibility of using deep learning models to predict HGB, HCT, and RBC levels directly from blood smear images, offering a novel, cost-effective, and efficient method for hematology analysis.
Keywords: Hemoglobin; Hematocrit; Red blood cell count; Deep learning