Machine Learning Microfluidic based platform - Integration of Lab-on-Chip devices and data analysis algorithms for Red Blood Cell plasticity evaluation in Pyruvate Kinase Disease monitoring - Submitted to Sensors and Actuators A: Physical

Aug 5, 2026

Microfluidics enables massive biological experiments, yet managing the large information load limits its broader impact. This work applies machine learning to microfluidic lab-on-chip diagnostics, integrating data-analysis methodologies into deep learning to capture cell morphology beyond standard appearance. The proposed MLM platform is evaluated using murine RBC samples in a dedicated in-flow microfluidics device, where RBC shape deformation in a pillar network quantifies Pyruvate Kinase Disease plasticity loss. Results exceed 85% accuracy for PKD recognition in both simulated and real experiments, supporting platform effectiveness.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages33

Reading Time1 h 23 min

AccessFree to download

Introduction

Machine learning microfluidics (MLM) overview

Rationale for data-driven lab-on-chip diagnostics

Validation scenario: Pyruvate Kinase Disease in murine RBCs

Submitted to Sensors and Actuators A: Physical Machine Learning Microfluidic based platform: Integration of Lab-on-Chip devices and data analysis algorithms for Red Blood Cell plasticity evaluation in Pyruvate Kinase Disease monitoring A. Mencattini 1,2, V. Rizzuto 3,4, G. Antonelli 1,2, D. Di Giuseppe 1,2 , M. D’Orazio 1,2, J. Filippi 1,2, M.C. Comes 1,2 , P. Casti 1,2, J.L. Vives Corrons 3, M. Garcia-Bravo 5,6, J.C. Segovia 5,6, Maria del Mar Mañú-Pereira 7, M.J. Lopez-Martinez 3,8,9, J. Samitier 3,8,9, and E. Martinelli 1,2 * 1. Department of Electronic Engineering, University of Rome Tor Vergata, Via del Politecnico 1, 00133 Rome, Italy 2. Interdisciplinary Center for Advanced Studies on Lab-on-Chip and Organ-on-Chip Applications (ICLOC), Via del Politecnico 1, 00133 Rome, Italy 3. Institute for Bioengineering of Catalonia (IBEC) Barcelona Institute of Science and Technology BIST, Barcelona, 08028, Spain. 4. Josep Carreras Leukaemia Research Institute (IJC), Badalona, 08916, Spain and with University of Barcelona, Department of Medicine, Barcelona, 08036, Spain 5. Biomedical Innovation Unit, Centro de Investigaciones Energéticas, Medioambientales y Tecnológicas (CIEMAT) and Centrode Investigación Biomédica en Red de Enfermedades Raras (CIBERER), Madrid, Spain, 6. Unidad Mixta de Terapias Avanzadas. Instituto de Investigación Sanitaria Fundación Jiménez. (IIS-FJD, UAM) . Madrid, Spain. 7. Vall d’Hebron Research Institute, Erithropatology Unit, Translational Research in Child and Adolescent Cancer – Rare anemia disorders research laboratory, Vall d’Hebron Research Institute, ERN-EuroBloodNet member, Barcelona, 08035, Spain 8. Centro de Investigacion Biomedica en Red en Bioingeniería, Biomateriales y Nanomedicina (CIBER-BBN), Madrid, 28029, Spain, University of Barcelona, Department of Electronic and Biomedical Engineering, Barcelona, 08028, Spain. 9. University of Barcelona, Department of Electronic and Biomedical Engineering, Barcelona, 08028, Spain Correspondence to: Prof. Eugenio Martinelli Department of Electronic Engineering University of Rome Tor Vergata Via del Politecnico 1, 00133 Roma, Italy [Email: martinelli@ing.uniroma2.it](Email: martinelli@ing.uniroma2.it) Tel: +39 06 72597259 Fax: +39 06 2020 519 Abstract Microfluidics represents a very promising technological solution for conducting massive biological experiments. However, the difficulty of managing the amount of information available often precludes the wide potential offered. Using machine learning, we aim to accelerate microfluidics uptake and lead to quantitative and reliable findings. In this work, we propose complementing microfluidics with machine learning (MLM) approaches to enhance the diagnostic capability of lab-on-chip devices. The introduction of data analysis methodologies within the deep learning framework corroborates the possibility of encoding cell morphology beyond the standard cell appearance. The proposed MLM platform is used in a diagnostic test for blood diseases in murine RBC samples in a dedicated microfluidics device in flow. The lack of plasticity of RBCs in Pyruvate Kinase Disease (PKD) is measured massively by recognizing the shape deformation in RBCs walking in a forest of pillars within the chip. Very high accuracy results, far over 85%, in recognizing PKD from control RBCs either in simulated and in real experiments demonstrate the effectiveness of the platform. Keywords: machine learning microfluidics, deep transfer learning, video analysis, blood disease 1. Introduction Today, one of the most challenging frontiers in system engineering is the possibility of recapitulating limited parts and activities of the human body in ex-vivo environments [1] . This is made possible by microfluidic devices. Microfluidic and Lab-on-a-chip (LOC) technologies [2-4] have attracted increasing interest in recent years. They deal with the fabrication of silicon/plastic microdevices with channels a

FAQs

What problem does machine learning microfluidics aim to solve?

It targets the challenge that microfluidics generates large amounts of data, where information management often restricts microfluidics’ full potential. Machine learning is used to accelerate analysis and improve quantitative, reliable outcomes.

How is the proposed platform used to evaluate Pyruvate Kinase Disease?

The platform runs a diagnostic test on murine RBC samples in a dedicated in-flow microfluidics device. RBC plasticity loss is measured by recognizing deformation in RBC shapes while they move through a pillar network.

What accuracy level was achieved for disease recognition?

Very high accuracy results were reported, exceeding 85%, for recognizing PKD from control RBCs in both simulated and real experiments.

Aug 5, 2026

Upload by Theodore