Hemoglobin value prediction with bayesian optimization assisted machine learning models

Year 2024, Volume: 66 Issue: 2, 176 - 200

Koray Açıcı

https://doi.org/10.33769/aupse.1462331

Abstract

This study presents a framework for predicting hemoglobin (Hb) levels utilizing Bayesian optimization-assisted machine learning models, incorporating both time-domain and frequency-domain features derived from photoplethysmography (PPG) signals. Hemoglobin, a crucial protein for oxygen and carbon dioxide transport in the blood, has levels that indicate various health conditions, including anemia and diseases affecting red blood cell production. Traditional methods for measuring Hb levels are invasive, posing potential risks and discomfort. To address this, a dataset comprising PPG signals, along with demographic data (gender and age), was analyzed to predict Hb levels accurately. Our models employ support vector regression (SVR), artificial neural networks (ANNs), classification and regression trees (CART), and ensembles of trees (EoT) optimized through Bayesian optimization algorithm. The results demonstrated that incorporating age and gender as features significantly improved model performance, highlighting their importance in Hb level prediction. Among the tested models, ANN provided the best results, involving normalized raw signals, feature selection, and reduction methods. The model achieved a mean squared error (MSE) of 1.508, root mean squared error (RMSE) of 1.228, and R-squared (R²) of 0.226. This study's findings contribute to the growing body of research on non-invasive hemoglobin prediction, offering a potential tool for healthcare professionals and patients for convenient and risk-free Hb level monitoring.

Keywords

hemoglobin, machine learning, regression

References

• Cho, H., Lee, S.-R., Baek, Y., Anemia diagnostic system based on impedance measurement of red blood cells, Sensors, 21 (23) (2021), 1-12, https://doi.org/10.3390/s21238043.
• Yap, B. K., Soair, S. N. M., Talik, N. A., Lim, W. F., Mei, I. L., Potential point-of-care microfluidic devices to diagnose iron deficiency anemia, Sensors, 18 (8) (2018), 1-17, https://doi.org/10.3390/s18082625.
• Mandal, A. K., Mitra, A., Das, R., Sickle cell hemoglobin, In: Hoeger, U., Harris, J. (eds), Vertebrate and invertebrate respiratory proteins, lipoproteins and other body fluid proteins, Subcellular Biochemistry, vol 94, Springer, Cham, (2020), https://doi.org/10.1007/978-3-030-41769-7_12.
• Telfer, P., Carvalho, S. J., Ruzangi, J., Arici, M., Binns, M., Beaubrun, A., Montealegre Golcher, F., Rice, C. T., Were, J. J., Association between hemoglobin levels and end organ damage in sickle cell disease: A retrospective linked primary and secondary care database analysis in England, Hematol. Transfus. Cell Ther., 44 (Supplement 2) (2022), S10-S11.
• Helmi, N., Bashir, M., Shireen, A., Ahmed, I. M., Thalassemia review: features, dental considerations and management, Electron. Physician, 9 (3) (2017), 4003-4008, https://doi.org/10.19082/4003.
• Gaspar, B. L., Sharma, P., Das, R., Anemia in malignancies: Pathogenetic and diagnostic considerations, Hematology, 20 (1) (2015), 18-25, https://doi.org/10.1179/1607845414Y.0000000161.
• Panjeta, M., Tahirović, I., Sofić, E., Ćorić, J., Dervišević, A., Interpretation of erythropoietin and haemoglobin levels in patients with various stages of chronic kidney disease, J. Med. Biochem., 36 (2) (2017), 145-152, https://doi.org/10.1515/jomb-20170014.
• World Health Organization, Haemoglobin concentrations for the diagnosis of anaemia and of severity, (2011). Available https://www.who.int/publications/i/item/WHO-NMH-NHD-MNM-11.1. at: [Accessed March 2024].
• Hasan, M. K., Aziz, M. H., Zarif, M. I. I., Hasan, M., Hashem, M., Guha, S., Love, R. R., Ahamed, S., Noninvasive hemoglobin level prediction in a mobile phone environment: State of the art review and recommendations, JMIR mHealth and uHealth, 9 (4) (2021), 1-24, https://doi.org/10.2196/16806.
• Peng, F., Zhang, N., Chen, C., Wu, F., Wang, W., Ensemble extreme learning machine method for hemoglobin estimation based on photoplethysmographic signals, Sensors, 24 (6) (2024), 1-14, https://doi.org/10.3390/s24061736.
• Zhu, J., Sun, R., Liu, H., Wang, T., Cai, L., Chen, Z., Heng, B., A non-invasive hemoglobin detection device based on multispectral photoplethysmography, Biosensors, 14 (1) (2024), 1-19, https://doi.org/10.3390/bios14010022.
• Abuzairi, T., Vinia, E., Yudhistira, M. A., Rizkinia, M., Eriska, W., A dataset of hemoglobin blood value and photoplethysmography signal for machine learning-based non-invasive hemoglobin measurement, Data in Brief, 52 (2024), 1-7, https://doi.org/10.1016/j.dib.2023.109823.
• Dimauro, G., Caivano, D., Girardi, F., A new method and a non-invasive device to estimate anemia based on digital images of the conjunctiva, IEEE Access, 6 (2018), 1-8, https://doi.org/10.1109/ACCESS.2018.2867110.
• Ding, H., Lu, Q., Gao, H., Peng, Z., Non-invasive prediction of hemoglobin levels by principal component and back propagation artificial neural network, Biomed. Opt. Express, 5 (2014), 1145-1152, https://doi.org/10.1364/BOE.5.001145.
• Wang, E. J., Li, W., Zhu, J., Rana, R., Patel, S. N., Noninvasive hemoglobin measurement using unmodified smartphone camera and white flash, 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Jeju, Korea (South), (2017), 2333-2336, https://doi.org/10.1109/EMBC.2017.8037323.
• Kavsaoğlu, A., Polat, K., Hariharan, M., Non-invasive prediction of hemoglobin level using machine learning techniques with the PPG signal's characteristic features, Appl. Soft Comput., 28 (2015), 433-441, https://doi.org/10.1016/j.asoc.2015.04.008.
• Hasan, M. K., Haque, M. M., Adib, R., Tumpa, J. F., Begum, A., Love, R. R., Kim, Y. L., Sheikh, I. A., SmartHeLP: Smartphone-based hemoglobin level prediction using an artificial neural network, AMIA Annu. Symp. Proc., 2018, 535-544.
• El-kenawy, E. S. M. T., A machine learning model for hemoglobin estimation and anemia classification, IJCSIS, 17 (2) (2019), 100-108.
• Chen, Z., Qin, H., Ge, W., Li, S., Liang, Y., Research on a non-invasive hemoglobin measurement system based on four-wavelength photoplethysmography, Electronics, 12 (6) (2023), 1-12, https://doi.org/10.3390/electronics12061346.
• Chen, Y., Zhong, K., Zhu, Y., Sun, Q., Two-stage hemoglobin prediction based on prior causality, Front. Public Health, 10, (2022), 1-12, https://doi.org/10.3389/fpubh.2022.1079389.
• Kwon, T.-H., Kim, K.-D., Machine-learning-based noninvasive in vivo estimation of HbA1c using photoplethysmography signals, Sensors, 22 (8) (2022), 1-19, https://doi.org/10.3390/s22082963.
• Robnik-Sikonja, M., Kononenko, I., Theoretical and empirical analysis of ReliefF and RReliefF, Mach. Learn., 53 (2003), 23-69.
• Greenacre, M., Groenen, P.J.F., Hastie, T. et al., Principal component analysis, Nat. Rev. Methods Primers, 2 (2022), 100, https://doi.org/10.1038/s43586-022-00184-w.
• Wang, Y. G., Wu, J., Hu, Z. H., McLachlan, G. J., A new algorithm for support vector regression with automatic selection of hyperparameters, Pattern Recognit., 133 (2023), 1-9, https://doi.org/10.1016/j.patcog.2022.108989.
• Kufel, J,, Bargieł-Łączek, K., Kocot, S., Koźlik, M., Bartnikowska, W., Janik, M., Czogalik, Ł., Dudek, P., Magiera, M., Lis, A., et al., What is machine learning, artificial neural networks and deep learning? Examples of practical applications in medicine, Diagnostics, 13 (15) (2023), 1-22, https://doi.org/10.3390/diagnostics13152582.
• Breiman, L., Friedman, J. H., Olshen, R. A., Stone, C. J., Classification and Regression Trees, Boca Raton, FL: Chapman and Hall, 1984.
• Breiman, L., Bagging predictors, Mach. Learn., 26 (1996), 123-140.
• Friedman, J., Hastie, T., Tibshirani, R., Additive logistic regression: A statistical view of boosting, Ann. Stat., 28 (2) (2000), 337-407.
• Wang, X., Jin, Y., Schmitt, S., Olhofer, M., Recent advances in Bayesian optimization, ACM Comput. Surv., 55 (13s) (2023), 1-36, https://doi.org/10.1145/3582078.
• Jones, D. R., Schonlau, M., Welch, W. J., Efficient global optimization of expensive black-box functions, J. Glob. Optim., 13 (1998), 455-492.