Early detection of mild cognitive impairment through neuropsychological tests in population screenings - a decision support system integrating ontologies and machine learning

Aug 6, 2026

A decision support system is designed to detect Mild Cognitive Impairment (MCI) from neuropsychological assessments in population-based screenings by combining a machine learning model expressed with Semantic Web Rule Language (SWRL) rules in an ontology with domain knowledge from the NIO ontology. The approach was evaluated on 520 Spanish neuropsychological assessments and benchmarked against established ML methods using the F2 coefficient to limit false negatives. Results show comparable performance with added explanation and data standardization. Additional use cases demonstrate robustness with incomplete acquisition records, incorporation of new databases, and ontology-driven cross-domain relations, supporting clinicians and neuropsychologists.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages15

Reading Time38 min

AccessFree to download

Introduction

Alzheimer’s disease, MCI, and the need for early detection

Machine learning for MCI and the role of standardized data

Ontologies and decision support in healthcare

TYPE Original Research PUBLISHED 16 October 2024 DOI 10.3389/fninf.2024.1378281 OPEN ACCESS EDITED BY Emi A. Yuda, Tohoku University, Japan REVIEWED BY José Aparecido Da Silva, University of Brasilia, Brazil Isabel Echeverri, Universidad Autónoma de Manizales, Colombia *CORRESPONDENCE Alba Gómez-Valadés [albagvb@dia.uned.es](albagvb@dia.uned.es) RECEIVED 29 January 2024 ACCEPTED 04 October 2024 PUBLISHED 16 October 2024 CITATION Gómez-Valadés A, Martínez-Tomás R, García-Herranz S, Bjørnerud A and Rincón M (2024) Early detection of mild cognitive impairment through neuropsychological tests in population screenings: a decision support system integrating ontologies and machine learning. Front. Neuroinform. 18:1378281 . doi: 10.3389/fninf.2024.1378281 COPYRIGHT © 2024 Gómez-Valadés, Martínez-Tomás, García-Herranz, Bjørnerud and Rincón. This isan open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Early detection of mild cognitive impairment through neuropsychological tests in population screenings: a decision support system integrating ontologies and machine learning Alba Gómez-Valadés 1*, Rafael Martínez-Tomás 1, Sara García-Herranz 2, Atle Bjørnerud3, 4 and Mariano Rincón 1 1 Department of Artificial Intelligence, Universidad Nacional de Educación a Distancia (UNED), Madrid, Spain, 2Cogni-UNED Research Group, Faculty of Psychology, UNED, Madrid, Spain, 3Computational Radiology and Artificial Intelligence Unit, Department of Physics and Computational Radiology, Clinic for Radiology and Nuclear Medicine, Oslo University Hospital, Oslo, Norway, 4 Department of Physics, University of Oslo, Oslo, Norway Machine learning (ML) methodologies for detecting Mild Cognitive Impairment (MCI) are progressively gaining prevalence to manage the vast volume of processed information. Nevertheless, the black-box nature of ML algorithms and the heterogeneity within the data may result in varied interpretations across distinct studies. To avoid this, in this proposal, we present the design of a decision support system that integrates a machine learning model represented using the Semantic Web Rule Language (SWRL) in an ontology with specialized knowledge in neuropsychological tests, the NIO ontology. The system’s ability to detect MCI subjects was evaluated on a database of 520 neuropsychological assessments conducted in Spanish and compared with other well-established ML methods. Using the F2 coefficient to minimize false negatives, results indicate that the system performs similarly to other well-established ML methods (F2TE2 =0 .830, only below bagging, F2BAG =0 .832) while exhibiting other significant attributes such as explanation capability and data standardization to a common framework thanks to the ontological part. On the other hand, the system’s versatility and ease of use were demonstrated with three additional use cases: evaluation of new cases even if the acquisition stage is incomplete (the case records have missing values), incorporation of a new database into the integrated system, and use of the ontology capabilities to relate different domains. This makes it a useful tool to support physicians and neuropsychologists in population-based screenings for early detection of MCI. KEYWORDS ontology, machine learning, SWRL, decision tree, ensemble, decision support system, MCI 1 Introduction Alzheimer’s disease (AD) is the most common cause of dementia affecting the elderly (Jitsuishi and Yamaguchi, 2022; Sherimon et al., 2021; Zekri et al., 2015), and its incidence is expected to continue to increase as

FAQs

What is the core contribution of this system for MCI detection?

It integrates a machine learning model encoded with SWRL rules into an ontology and combines it with specialized knowledge from the NIO ontology to support MCI detection in population screenings.

How was the system evaluated and what metric was used?

It was tested on 520 Spanish neuropsychological assessments and compared with established ML methods using the F2 coefficient to minimize false negatives.

What additional capabilities does the system demonstrate beyond standard classification?

It supports evaluation with missing values, integration of new databases, and ontology-based relations across different domains, improving interpretability and usability for clinicians.

Aug 6, 2026

Upload by Olivia Brown