The ICN-UN Battery: A Machine Learning-Optimized Tool for Expeditious Alzheimer’s Disease Diagnosis

Barceló, Ernesto; Romero, Duban; Allegri, Ricardo; Meza, Eliana; Mosquera-Heredia, María I.; Vidal, Oscar M.; Silvera-Redondo, Carlos; Arcos-Burgos, Mauricio; Garavito-Galofre, Pilar; Vélez, Jorge I.

doi:10.3390/diagnostics15233045

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

The ICN-UN Battery: A Machine Learning-Optimized Tool for Expeditious Alzheimer’s Disease Diagnosis

by

Ernesto Barceló

^1,2,3,*,

Duban Romero

¹

,

Ricardo Allegri

⁴,

Eliana Meza

¹,

María I. Mosquera-Heredia

⁵

,

Oscar M. Vidal

⁵

,

Carlos Silvera-Redondo

⁵,

Mauricio Arcos-Burgos

⁶,

Pilar Garavito-Galofre

⁵ and

Jorge I. Vélez

^7,*

¹

Instituto Colombiano de Neuropedagogía, Barranquilla 080020, Colombia

²

Department of Health Sciences, Universidad de La Costa, Barranquilla 080002, Colombia

³

Grupo Internacional de Investigación Neuro-Conductual (GIINCO), Universidad de La Costa, Barranquilla 080002, Colombia

⁴

Institute for Neurological Research FLENI, Montañeses 2325, Buenos Aires C1428AQK, Argentina

⁵

Department of Medicine, Universidad del Norte, Barranquilla 081007, Colombia

⁶

Grupo de Investigación en Psiquiatría (GIPSI), Departamento de Psiquiatría, Instituto de Investigaciones Médicas, Facultad de Medicina, Universidad de Antioquia, Medellín 050010, Colombia

⁷

Department of Industrial Engineering, Universidad del Norte, Barranquilla 081007, Colombia

^*

Authors to whom correspondence should be addressed.

Diagnostics 2025, 15(23), 3045; https://doi.org/10.3390/diagnostics15233045 (registering DOI)

Submission received: 15 September 2025 / Revised: 18 November 2025 / Accepted: 22 November 2025 / Published: 28 November 2025

(This article belongs to the Special Issue Artificial Intelligence in Alzheimer’s Disease Diagnosis—2nd Edition)

Download Versions Notes

Abstract

Background/Objectives: Alzheimer’s disease (AD) accounts for ~70% of global dementia cases, with projections estimating 139 million affected individuals by 2050. This increasing burden highlights the urgent need for accessible, cost-effective diagnostic tools, particularly in low- and middle-income countries (LMICs). Traditional neuropsychological assessments, while effective, are resource-intensive and time-consuming. Methods: A total of 760 older adults (394 [51.8%] with AD) were recruited and neuropsychologically evaluated at the Instituto Colombiano de Neuropedagogía (ICN) in collaboration with Universidad del Norte (UN), Barranquilla. Machine learning (ML) algorithms were trained on a screening protocol incorporating demographic data and neuropsychological measures assessing memory, language, executive function, and praxis. Model performance was determined using 10-fold cross-validation. Variable importance analyses identified key predictors to develop optimized, abbreviated ML-based protocols. Metrics of compactness, cohesion, and separation further quantified diagnostic differentiation performance. Results: The eXtreme Gradient Boosting (xgbTree) algorithm achieved the highest diagnostic accuracy (91%) with the full protocol. Five ML-optimized screening protocols were also developed. The most efficient, the ICN-UN battery (including MMSE, Rey–Osterrieth Complex Figure recall, Rey Auditory Verbal Learning, Lawton & Brody Scale, and FAST), maintained strong diagnostic performance while reducing screening time from over four hours to under 25 min. Conclusions: The ML-optimized ICN-UN protocol offers a rapid, accurate, and scalable AD screening solution for LMICs. While promising for clinical adoption and earlier detection, further validation in diverse populations is recommended.

Keywords: Alzheimer’s disease; Machine Learning; neuropsychological assessment; diagnostic protocol; cognitive impairment

Share and Cite

MDPI and ACS Style

Barceló, E.; Romero, D.; Allegri, R.; Meza, E.; Mosquera-Heredia, M.I.; Vidal, O.M.; Silvera-Redondo, C.; Arcos-Burgos, M.; Garavito-Galofre, P.; Vélez, J.I. The ICN-UN Battery: A Machine Learning-Optimized Tool for Expeditious Alzheimer’s Disease Diagnosis. Diagnostics 2025, 15, 3045. https://doi.org/10.3390/diagnostics15233045

AMA Style

Barceló E, Romero D, Allegri R, Meza E, Mosquera-Heredia MI, Vidal OM, Silvera-Redondo C, Arcos-Burgos M, Garavito-Galofre P, Vélez JI. The ICN-UN Battery: A Machine Learning-Optimized Tool for Expeditious Alzheimer’s Disease Diagnosis. Diagnostics. 2025; 15(23):3045. https://doi.org/10.3390/diagnostics15233045

Chicago/Turabian Style

Barceló, Ernesto, Duban Romero, Ricardo Allegri, Eliana Meza, María I. Mosquera-Heredia, Oscar M. Vidal, Carlos Silvera-Redondo, Mauricio Arcos-Burgos, Pilar Garavito-Galofre, and Jorge I. Vélez. 2025. "The ICN-UN Battery: A Machine Learning-Optimized Tool for Expeditious Alzheimer’s Disease Diagnosis" Diagnostics 15, no. 23: 3045. https://doi.org/10.3390/diagnostics15233045

APA Style

Barceló, E., Romero, D., Allegri, R., Meza, E., Mosquera-Heredia, M. I., Vidal, O. M., Silvera-Redondo, C., Arcos-Burgos, M., Garavito-Galofre, P., & Vélez, J. I. (2025). The ICN-UN Battery: A Machine Learning-Optimized Tool for Expeditious Alzheimer’s Disease Diagnosis. Diagnostics, 15(23), 3045. https://doi.org/10.3390/diagnostics15233045

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Article metric data becomes available approximately 24 hours after publication online.

Article Menu

The ICN-UN Battery: A Machine Learning-Optimized Tool for Expeditious Alzheimer’s Disease Diagnosis

Abstract

Share and Cite

Article Metrics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI