A machine learning approach to microwave sensing for non-invasive Alzheimer’s disease early detection - Conference paper

Aug 5, 2026

Early Alzheimer’s disease detection benefits patients, caregivers, and clinicians, yet common diagnostic routes remain invasive, costly, and difficult to deploy in portable settings. Microwave sensing offers a non-invasive alternative by exploiting permittivity variations in cerebrospinal fluid associated with Alzheimer’s pathology. The work applies machine learning to microwave sensing data using a multilayer perceptron classifier. Multiple network architectures are evaluated on experimental measurements from controlled multi-tissue head phantom tests representing different disease stages, with initial results supporting early-stage diagnostic potential.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages7

Reading Time18 min

AccessFree to download

Abstract

Introduction

Alzheimer’s Disease

POLITECNICO DI TORINO Repository ISTITUZIONALE A machine learning approach to microwave sensing for non-invasive alzheimer’s disease early detection Original A machine learning approach to microwave sensing for non-invasive alzheimer’s disease early detection / Cardinali, Leonardo; Spano, Mattia; Gugliermino, Martina; Rodriguez-Duarte, David Orlando; Ricci, Marco; Tobon Vasquez, Jorge Alberto; Palmeri, Roberta; Scapaticci, Rosa; Crocco, Lorenzo; Vipiana, Francesca. -ELETTRONICO. - (2023) .(Intervento presentato al convegno Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering tenutosi a Milano, Italy nel 25-27 ottobre 2023) [10 . 1109/MetroXRAINE58569 .2023. 10405555] . Availability: This version is available at: 11583/2982792 since: 2023-10-06T11:02:19Z Publisher: IEEE Published DOI:10.1109/MetroXRAINE58569.2023.10405555 Terms of use: This article is made available under terms and conditions as specified in the corresponding bibliographic description in the repository Publisher copyright IEEE postprint/Author's Accepted Manuscript ©2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collecting works, for resale or lists, or reuse of any copyrighted component of this work in other works. (Article begins on next page) 18 September 2024 A Machine Learning Approach to Microwave Sensing for Non-invasive Alzheimer’s Disease Early Detection Leonardo Cardinali Dept. of electronics and telecommunications Politecnico di Torino Torino, Italy leonardo.cardinali@polito.it Marco Ricci Dept. of electronics and telecommunications Politecnico di Torino Torino, Italy marco.ricci@polito.it Lorenzo Crocco National Research Council of Italy Institute for the Electromagnetic Sensing of the Environment Napoli, Italy [crocco.l@irea.cnr.it](crocco.l@irea.cnr.it) Mattia Spano Dept. of electronics and telecommunications Politecnico di Torino Torino, Italy s292254@studenti.polito.it Jorge A. Tobon Vasquez Dept. of electronics and telecommunications Politecnico di Torino Torino, Italy jorge.tobonvasquez@polito.it Francesca Vipiana Dept. of electronics and telecommunications Politecnico di Torino Torino, Italy francesca.vipiana@polito.it Martina Gugliermino Dept. of electronics and telecommunications Politecnico di Torino Torino, Italy martina.gugliermino@polito.it Roberta Palmeri National Research Council of Italy Institute for the Electromagnetic Sensing of the Environment Napoli, Italy [palmeri.r@irea.cnr.it](palmeri.r@irea.cnr.it) David O. Rodriguez-Duarte Dept. of electronics and telecommunications Politecnico di Torino Torino, Italy david.rodriguez@polito.it Rosa Scapaticci National Research Council of Italy Institute for the Electromagnetic Sensing of the Environment Napoli, Italy [scapaticci.r@irea.cnr.it](scapaticci.r@irea.cnr.it) Abstract— Early Alzheimer’s disease detection can greatly benefit patients, caregivers, and clinicians. Unfortunately, current diagnostic procedures are invasive, expensive, and not easily portable. To overcome these limitations, microwave sensing is emerging as an alternative non-invasive approach to distinguish between healthy and pathological conditions, based on the variation of permittivity in cerebrospinal fluid in Alzheimer’s patients. In this framework, our paper explores the use of machine learning applied to microwave sensing data, by means of a multilayer perceptron classifier. Different architectures have been considered and appraised by relying on experimental data collected with controlled experiments involving a multi-tissue head phantom that can be filled with tissue-mimicking liquids simulating different stages of the pathology. The initial results confirm the potential of the proposed non-invasive approach

FAQs

Why is non-invasive early detection of Alzheimer’s disease important?

Early detection is essential for slowing disease progression and enabling better decision-making for care and planning. It also improves support for patients and caregivers.

What makes microwave sensing suitable for distinguishing healthy and pathological conditions?

Microwave sensing leverages changes in permittivity in cerebrospinal fluid linked to Alzheimer’s patients, enabling separation between healthy and pathological conditions.

How is machine learning used in the proposed approach?

The method applies machine learning to microwave sensing data using a multilayer perceptron classifier. Different network architectures are tested and compared using experimental data.

Aug 5, 2026

Upload by Lucas Martin