Wavelength Configuration and Signal Duration for Low-Complexity PPG-Based Anemia Detection: A Preliminary Validation Study
Abstract
Anemia remains a major global health problem, while standard diagnosis still depends on invasive hemoglobin testing, which may be less practical for repeated and resource-limited screening. Photoplethysmography (PPG) offers a potential non-invasive alternative, but the contribution of different wavelength configurations to anemia classification remains unclear. This preliminary subject-based validation study evaluated the effect of PPG wavelength configuration and recording duration on low-complexity anemia classification. A public dataset containing green, red, and infrared PPG recordings from 52 subjects was used, consisting of 42 normal and 10 anemia subjects. Eight morphological and temporal features were extracted from each wavelength. Seven signal configurations, namely Green, Red, IR, Green+Red, Green+IR, Red+IR, and all channels, were evaluated across 30, 45, 60, and 90 s recording durations. Support Vector Machine, Logistic Regression, Random Forest, and Extra Trees classifiers were trained using class-weighted learning and assessed with 5-fold subject-based cross-validation to reduce subject-level data leakage. The Red+IR configuration with a class-weighted SVM at 90 s achieved the best pooled performance, with a macro F1-score of 0.754, F1-Anemia of 0.588, anemia recall of 0.500, anemia precision of 0.714, accuracy of 0.769, and an error rate of 0.231. Fold-wise analysis showed substantial variability, with a macro F1-score of 0.617 ± 0.251, sensitivity of 0.467 ± 0.506, specificity of 0.846 ± 0.144, ROC-AUC of 0.864 ± 0.150, and PR-AUC of 0.694 ± 0.344. These findings suggest that adding more PPG wavelengths does not necessarily improve classification performance. However, the model still missed 5 of 10 anemia cases, and the limited anemia recall, small minority class, and demographic imbalance indicate that the results should be interpreted as preliminary and require validation on larger, more balanced datasets.
Downloads
References
G. A. Stevens et al., “National, regional, and global estimates of anaemia by severity in women and children for 2000-19: a pooled analysis of population-representative data,” Lancet Glob. Health, vol. 10, no. 5, pp. e627-e639, 2022, doi: 10.1016/S2214-109X(22)00084-5.
S. Safiri et al., “Burden of anemia and its underlying causes in 204 countries and territories, 1990-2019: results from the Global Burden of Disease Study 2019,” J. Hematol. Oncol., vol. 14, no. 1, p. 185, Nov. 2021, doi: 10.1186/s13045-021-01202-2.
S. Y. Hess, A. Owais, M. E. D. Jefferds, M. F. Young, A. Cahill, and L. M. Rogers, “Accelerating action to reduce anemia: Review of causes and risk factors and related data needs,” Ann. N. Y. Acad. Sci., vol. 1523, no. 1, pp. 11-23, May 2023, doi: 10.1111/nyas.14985.
M. N. Garcia‐Casal, O. Dary, M. E. Jefferds, and S. Pasricha, “Diagnosing anemia: Challenges selecting methods, addressing underlying causes, and implementing actions at the public health level,” Ann. N. Y. Acad. Sci., vol. 1524, no. 1, pp. 37-50, Jun. 2023, doi: 10.1111/nyas.14996.
V. S. Reddy et al., “Comparison of hemoglobin measurements from venous and capillary blood from the same individual using HemoCue 301 and automated hematology analyzer in a cross-sectional community-based study in India,” Am. J. Clin. Nutr., vol. 123, no. 1, p. 101119, Jan. 2026, doi: 10.1016/j.ajcnut.2025.11.009.
J. Park, H. S. Seok, S.-S. Kim, and H. Shin, “Photoplethysmogram Analysis and Applications: An Integrative Review,” Front. Physiol., vol. 12, p. 808451, Mar. 2022, doi: 10.3389/fphys.2021.808451.
K. B. Kim and H. J. Baek, “Photoplethysmography in Wearable Devices: A Comprehensive Review of Technological Advances, Current Challenges, and Future Directions,” Electronics (Basel)., vol. 12, no. 13, p. 2923, Jul. 2023, doi: 10.3390/electronics12132923.
S. Suner et al., “Prediction of anemia and estimation of hemoglobin concentration using a smartphone camera,” PLoS One, vol. 16, no. 7, p. e0253495, Jul. 2021, doi: 10.1371/journal.pone.0253495.
M. K. Hasan et al., “Noninvasive Hemoglobin Level Prediction in a Mobile Phone Environment: State of the Art Review and Recommendations,” JMIR Mhealth Uhealth, vol. 9, no. 4, p. e16806, Apr. 2021, doi: 10.2196/16806.
G. Zuccotti et al., “Feasibility of a Noncontact Photoplethysmography-Based Mobile App for Noninvasive Hemoglobin Monitoring: Exploratory Observational Study,” JMIR Form. Res., vol. 10, p. e78820, Feb. 2026, doi: 10.2196/78820.
C. Pinto, J. Parab, and G. Naik, “Non-invasive hemoglobin measurement using embedded platform,” Sens. Biosensing Res., vol. 29, p. 100370, Aug. 2020, doi: 10.1016/j.sbsr.2020.100370.
B. Yakimov, K. Buiankin, G. Denisenko, Y. Shitova, A. Shkoda, and E. Shirshin, “Diffuse reflectance spectroscopy and RGB-imaging: a comparative study of non-invasive haemoglobin assessment,” Sci. Rep., vol. 14, no. 1, p. 22874, Oct. 2024, doi: 10.1038/s41598-024-73084-6.
Z. Chen, H. Qin, W. Ge, S. Li, and Y. Liang, “Research on a Non-Invasive Hemoglobin Measurement System Based on Four-Wavelength Photoplethysmography,” Electronics (Basel)., vol. 12, no. 6, p. 1346, Mar. 2023, doi: 10.3390/electronics12061346.
L. Chen et al., “A Four-Wavelength Photoplethysmography dataset for non-invasive hemoglobin assessment,” Sci. Data, vol. 13, no. 1, p. 564, Mar. 2026, doi: 10.1038/s41597-026-06945-6.
R. Ranjith, S. Priya, A. S. Kaviya Dharshini, and J. B. Jeeva, “Non-invasive hemoglobin measurement using optical method,” Heliyon, vol. 10, no. 15, p. e35777, Aug. 2024, doi: 10.1016/j.heliyon.2024.e35777.
H. Gruwez et al., “Real-world validation of smartphone-based photoplethysmography for rate and rhythm monitoring in atrial fibrillation,” Europace, vol. 26, no. 4, p. euae065, Apr. 2024, doi: 10.1093/europace/euae065.
Y. Hu, A. Hu, and S. Song, “Photoplethysmography for Assessing Microcirculation in Hypertensive Patients After Taking Antihypertensive Drugs: A Review,” J. Multidiscip. Healthc., vol. 17, pp. 263-274, Jan. 2024, doi: 10.2147/JMDH.S441440.
M. Elgendi et al., “Recommendations for evaluating photoplethysmography-based algorithms for blood pressure assessment,” Communications Medicine, vol. 4, no. 1, p. 140, Jul. 2024, doi: 10.1038/s43856-024-00555-2.
G. Dimauro, M. E. Griseta, M. G. Camporeale, F. Clemente, A. Guarini, and R. Maglietta, “An intelligent non-invasive system for automated diagnosis of anemia exploiting a novel dataset,” Artif. Intell. Med., vol. 136, p. 102477, Feb. 2023, doi: 10.1016/j.artmed.2022.102477.
M. H. Chowdhury et al., “Estimating Blood Pressure from the Photoplethysmogram Signal and Demographic Features Using Machine Learning Techniques,” Sensors, vol. 20, no. 11, p. 3127, Jun. 2020, doi: 10.3390/s20113127.
J. Zhu et al., “A Non-Invasive Hemoglobin Detection Device Based on Multispectral Photoplethysmography,” Biosensors (Basel)., vol. 14, no. 1, p. 22, Dec. 2023, doi: 10.3390/bios14010022.
F. Peng, N. Zhang, C. Chen, F. Wu, and W. Wang, “Ensemble Extreme Learning Machine Method for Hemoglobin Estimation Based on PhotoPlethysmoGraphic Signals,” Sensors, vol. 24, no. 6, p. 1736, Mar. 2024, doi: 10.3390/s24061736.
V. V. Lychagov, V. M. Semenov, E. K. Volkova, D. I. Chernakov, J. Ahn, and J. Y. Kim, “Noninvasive Hemoglobin Measurements With Photoplethysmography in Wrist,” IEEE Access, vol. 11, pp. 79636-79647, 2023, doi: 10.1109/ACCESS.2023.3300293.
M. A. Almarshad, M. S. Islam, S. Al-Ahmadi, and A. S. BaHammam, “Diagnostic Features and Potential Applications of PPG Signal in Healthcare: A Systematic Review,” Healthcare, vol. 10, no. 3, p. 547, Mar. 2022, doi: 10.3390/healthcare10030547.
P. H. Charlton et al., “The 2023 wearable photoplethysmography roadmap,” Physiol. Meas., vol. 44, no. 11, p. 111001, Nov. 2023, doi: 10.1088/1361-6579/acead2.
S. Hossain, C. A. Haque, and K.-D. Kim, “Quantitative Analysis of Different Multi-Wavelength PPG Devices and Methods for Noninvasive In-Vivo Estimation of Glycated Hemoglobin,” Applied Sciences, vol. 11, no. 15, p. 6867, Jul. 2021, doi: 10.3390/app11156867.
C.-T. Hsiao, C. Tong, and G. L. Coté, “Machine Learning-Based VO2 Estimation Using a Wearable Multiwavelength Photoplethysmography Device,” Biosensors (Basel)., vol. 15, no. 4, p. 208, Mar. 2025, doi: 10.3390/bios15040208.
T. Abuzairi, E. Vinia, M. A. Yudhistira, M. Rizkinia, and W. Eriska, “A dataset of hemoglobin blood value and photoplethysmography signal for machine learning-based non-invasive hemoglobin measurement,” Data Brief, vol. 52, p. 109823, Feb. 2024, https://doi.org/10.1016/j.dib.2023.109823.
B. Ni et al., “An approach to machine learning-based non-invasive hemoglobin estimation using multi-wavelength PPG signal features,” Front. Physiol., vol. 17, p. 1637455, Apr. 2026, doi: 10.3389/fphys.2026.1637455.
N. Saleh, A. M. Salaheldin, Y. Ismail, and H. M. Afify, “Classification of anemic condition based on photoplethysmography signals and clinical dataset,” Biomedical Engineering / Biomedizinische Technik, vol. 70, no. 4, pp. 359-370, Aug. 2025, doi: 10.1515/bmt-2024-0433.
L. Liu, Z. Wang, X. Zhang, Y. Zhuang, and Y. Liang, “A Novel Model for Noninvasive Haemoglobin Detection Based on Visibility Network and Clustering Network for Multi-Wavelength PPG Signals,” Algorithms, vol. 18, no. 2, p. 75, Feb. 2025, doi: 10.3390/a18020075.
R. G. Mannino et al., “Smartphone app for non-invasive detection of anemia using only patient-sourced photos,” Nat. Commun., vol. 9, no. 1, p. 4924, Dec. 2018, doi: 10.1038/s41467-018-07262-2.
C. El-Hajj and P. A. Kyriacou, “A review of machine learning techniques in photoplethysmography for the non-invasive cuff-less measurement of blood pressure,” Biomed. Signal Process. Control, vol. 58, p. 101870, Apr. 2020, doi: 10.1016/j.bspc.2020.101870.
G. Brookshire et al., “Data leakage in deep learning studies of translational EEG,” Front. Neurosci., vol. 18, p. 1373515, May 2024, doi: 10.3389/fnins.2024.1373515.
S. Kapoor and A. Narayanan, “Leakage and the reproducibility crisis in machine-learning-based science,” Patterns, vol. 4, no. 9, p. 100804, Sep. 2023, doi: 10.1016/j.patter.2023.100804.
F. Del Pup, A. Zanola, L. F. Tshimanga, A. Bertoldo, L. Finos, and M. Atzori, “The role of data partitioning on the performance of EEG-based deep learning models in supervised cross-subject analysis: A preliminary study,” Comput. Biol. Med., vol. 196, p. 110608, Sep. 2025, doi: 10.1016/j.compbiomed.2025.110608.
T. Abuzairi and D. B. Maharani, “A hemoglobin concentration dataset derived from triple-wavelength photoplethysmography for machine learning applications,” Data Brief, vol. 63, p. 112241, Dec. 2025, doi: 10.1016/j.dib.2025.112241.
A. J. W. Mathieu et al., “Advanced waveform analysis of the photoplethysmogram signal using complementary signal processing techniques for the extraction of biomarkers of cardiovascular function,” JRSM Cardiovasc. Dis., vol. 13, Feb. 2024, doi: 10.1177/20480040231225384.
E. Mejía-Mejía and P. A. Kyriacou, “Duration of photoplethysmographic signals for the extraction of Pulse Rate Variability Indices,” Biomed. Signal Process. Control, vol. 80, p. 104214, Feb. 2023, doi: 10.1016/j.bspc.2022.104214.
N. Sviridova, T. Zhao, A. Nakano, and T. Ikeguchi, “Photoplethysmogram Recording Length: Defining Minimal Length Requirement from Dynamical Characteristics,” Sensors, vol. 22, no. 14, p. 5154, Jul. 2022, doi: 10.3390/s22145154.
S. Y. L. Tan et al., “Remote Photoplethysmography Technology for Blood Pressure and Hemoglobin Level Assessment in the Preoperative Assessment Setting: Algorithm Development Study,” JMIR Form. Res., vol. 9, p. e60455, Jun. 2025, doi: 10.2196/60455.
Copyright (c) 2026 Mulia Rahmah, Fatma Indriani, Rudy Herteno, Radityo Adi Nugroho, Irwan Budiman
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlikel 4.0 International (CC BY-SA 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
.png)
.png)
.png)
.png)
.png)
