Machine Learning Approach for Prediction of Hematic Parameters in Hemodialysis Patients

Cristoforo Decaro; Giovanni Battista Montanari; Riccardo Molinari; Alessio Gilberti; Davide Bagnoli; Marco Bianconi; Gaetano Bellanca

doi:10.1109/JTEHM.2019.2938951

Machine Learning Approach for Prediction of Hematic Parameters in Hemodialysis Patients

IEEE J Transl Eng Health Med. 2019 Oct 4:7:4100308. doi: 10.1109/JTEHM.2019.2938951. eCollection 2019.

Authors

Cristoforo Decaro¹, Giovanni Battista Montanari², Riccardo Molinari³, Alessio Gilberti², Davide Bagnoli⁴, Marco Bianconi^{2

5}, Gaetano Bellanca¹

Affiliations

¹ 1Department of EngineeringFerrara University44122FerraraItaly.
² 2MIST E-R40129BolognaItaly.
³ 3Tecnoideal s.r.l.41037MirandolaItaly.
⁴ 4Medica s.p.a41036MedollaItaly.
⁵ 5CNR-IMM-UOS di Bologna40129BolognaItaly.

Abstract

Objective: This paper shows the application of machine learning techniques to predict hematic parameters using blood visible spectra during ex-vivo treatments. Methods: A spectroscopic setup was prepared for acquisition of blood absorbance spectrum and tested in an operational environment. This setup is non invasive and can be applied during dialysis sessions. A support vector machine and an artificial neural network, trained with a dataset of spectra, have been implemented for the prediction of hematocrit and oxygen saturation. Results & Conclusion: Results of different machine learning algorithms are compared, showing that support vector machine is the best technique for the prediction of hematocrit and oxygen saturation.

Keywords: Artificial neural network; SVM; hematocrit; hemodialisys; machine learning; non-invasive; oxygen saturation; visible spectroscopy.

Grants and funding

The work of C. Decaro was supported in part by the Emilia Romagna Region in the framework of the PO Fse 2014/2020 Alte competenze per la ricerca, il trasferimento tecnologico e l’imprenditorialita’.