Non-Invasive Anemia Detection: A Multichannel PPG-Based Hemoglobin Estimation with Explainable Artificial Intelligence

2026-02-19

AI Summary

This study addresses the limitations of conventional hemoglobin testing—namely its reliance on invasive blood sampling and infeasibility for large-scale or continuous anemia screening—by proposing a non-invasive approach based on multi-channel photoplethysmography (PPG) signals at four wavelengths (660, 730, 850, and 940 nm). The method extracts cross-wavelength optical features and employs a gradient boosting regression model to estimate hemoglobin concentration, enabling initial anemia screening according to WHO criteria. Individualized interpretability is achieved through SHAP (SHapley Additive exPlanations) analysis. Evaluated on a public dataset with unseen subjects, the approach achieves a mean absolute error of 8.50 ± 1.27 g/L and a root mean square error of 8.21 g/L. This work represents the first integration of multi-wavelength PPG with interpretable AI, demonstrating both clinical validity and practical utility while rigorously avoiding data leakage.

Technology Category

• Humans and AI: AI for Accessibility
• Machine Learning: Hardware-aware ML
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Large pretrained models with web data
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Anemia is a prevalent hematological disorder that requires frequent hemoglobin monitoring for early diagnosis and effective management. Conventional hemoglobin assessment relies on invasive blood sampling, limiting its suitability for large-scale or continuous screening. This paper presents a non-invasive framework for hemoglobin estimation and anemia screening using multichannel photoplethysmography (PPG) signals and explainable artificial intelligence. Four-wavelength PPG signals (660, 730, 850, and 940~nm) are processed to extract optical and cross-wavelength features, which are aggregated at the subject level to avoid data leakage. A gradient boosting regression model is employed to estimate hemoglobin concentration, followed by post-regression anemia screening using World Health Organization (WHO) thresholds. Model interpretability is achieved using SHapley Additive explanations (SHAP), enabling both global and subject-specific analysis of feature contributions. Experimental evaluation on a publicly available dataset demonstrates a mean absolute error of 8.50 plus minus 1.27 and a root mean squared error of 8.21~g/L on unseen test subjects, indicating the potential of the proposed approach for interpretable, non-invasive hemoglobin monitoring and preliminary anemia screening.

Problem

• anemia detection
• non-invasive hemoglobin estimation
• photoplethysmography
• explainable AI
• anemia screening

Innovation

• multichannel PPG
• explainable AI
• non-invasive hemoglobin estimation
• SHAP
• anemia screening