Machine learning prediction of human blood optical properties: a comparative study of optimized algorithms with SHAP-based interpretability analysis
Прогнозирование оптических свойств человеческой крови с помощью машинного обучения: сравнительное исследование оптимизированных алгоритмов с анализом интерпретируемости на основе SHAP
2026-08-27
SCID: 54.1/x4fy8few
Discuss with AI
Optuna-optimized random forestSHAP interpretabilitybiomedical opticsblood optical propertiesmachine learning
Figures from the paper
Abstract (AI)
Accurate characterization of the optical properties of blood is essential for biomedical optics, diagnostic imaging, and therapeutic applications. conventional measurement techniques are frequently constrained by complex setups and idealized assumptions, highlighting the need for robust predictive models. This study presents a comparative machine learning framework to predict three blood optical properties: the absorption coefficient (µa), the scattering coefficient (µs), and the refractive index (RI). We developed and systematically optimized support vector regression (SVR), random forest (RF), and extreme gradient boosting (XGBoost) models using the Optuna framework, training them on a comprehensive dataset utilizing wavelength, hematocrit (Hct%), and oxygen saturation (SO2%) as input features. On the test dataset, the Optuna-optimized RF model achieved the highest predictive accuracy, with an R2 of 0.9981 and a root mean squared error (RMSE) of 1.3680. It significantly outperformed both SVR (R2 = 0.9736) and XGBoost (R2 = 0.9865), demonstrating superior generalization capability. SHAP analysis provided model interpretability, confirming that the predictions were based on a physically meaningful relationship. Wavelength was the dominant predictor, while hematocrit and oxygen saturation contributed with light–tissue interaction principles, reinforcing model validity. Additionally, the analysis demonstrated that tree-based models exhibit superior feature utilization with clearer decision boundaries compared to SVR, more effectively capturing the nonlinear, hierarchical relationships inherent in biological systems. Finally, the optimized models were deployed via a user-friendly web interface, providing the biomedical optics community with accessible, interpretable tools for rapid optical property prediction to advance fundamental research and clinical applications.
Key Findings
1
Optuna-optimized random forest achieved the best test performance, with R² = 0.9981 and RMSE = 1.3680.
2
SHAP analysis identified wavelength as the dominant predictor, while hematocrit and oxygen saturation contributed through physically meaningful light–tissue interactions.
3
The optimized random forest significantly outperformed SVR (R² = 0.9736) and XGBoost (R² = 0.9865), indicating superior generalization.
4
The study predicts blood absorption coefficient, scattering coefficient, and refractive index from wavelength, hematocrit, and oxygen saturation using optimized machine-learning models.
5
Tree-based models captured nonlinear, hierarchical biological relationships more effectively than SVR, and the optimized models were deployed in an accessible web interface.
Research Object
Human blood optical properties as functions of wavelength, hematocrit, and oxygen saturation
Research Subject
Machine-learning prediction accuracy, feature contributions, interpretability, and nonlinear relationships for blood absorption coefficient, scattering coefficient, and refractive index
Publication Details
Publication Date
2026-08-27
Journal
Publisher
ISSN
Cited by
0
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai5
XGBoost2016
Greedy function approximation: A gradient boosting machine.2001
Optical properties of circulating human blood in the wavelength range 400-2500 nm1999
A literature review and novel theoretical approach on the optical properties of whole blood2013
Determination of optical properties of human blood in the spectral range 250 to 1100 nm using Monte Carlo simulations with hematocrit-dependent effective scattering phase functions2006