Artificial intelligence
technologies focused on the care and development of people with disabilities.
Cuenca Pita Cristhian Paúl1
1 Facultad de Ciencias Informáticas, Universidad Técnica de Manabí
Portoviejo, Ecuador
Ordoñez-Avila Ricardo2
2 Departamento de Ciencias Computacionales, Universidad Técnica de
Manabí,
Portoviejo – Ecuador.
https://orcid.org/0009-0007-1122-9512
https://orcid.org/0000-0003-2583-2076
DOI: https://doi.org/10.56124/encriptar.v9i17.005
ABSTRACT
Artificial intelligence (AI) has
established itself as a technology with the potential to improve the autonomy,
communication, and social inclusion of people with special abilities. However,
some barriers may limit their access to education, health, and employment due
to the lack of existing knowledge about AI applications in the field of
disability. The objective of this study was to conduct a systematic literature
review (SLR) to identify the current state of artificial intelligence
technologies focused on the care and development of individuals with special
abilities, categorizing solutions, algorithms, and domains of application. The
methodology followed the PRISMA checklist model, structured around planning,
searching, selecting, and extracting information. The search was conducted in
five high-impact academic databases (Scopus, IEEE Xplore, ScienceDirect, and
ACM), applying rigorous inclusion and exclusion criteria. Of the total of 314
initial records, 30 primary studies were selected for further analysis. The
most frequent applications include intelligent virtual assistants, augmentative
and alternative communication systems, automatic sign language translators,
brain-computer interfaces, adaptive learning platforms, and innovative mobility
devices. In terms of algorithms, the use of convolutional and recurrent neural
networks, support vector machines, decision trees, unsupervised clustering, and
reinforcement learning techniques stands out, with performance rates exceeding
90% in voice, gesture, or sign language recognition tasks. These technologies
have contributed to educational, therapeutic, and communicative contexts, as
well as emerging applications in assisted mobility and inclusive work
environments. In conclusion, AI is a key tool for supporting inclusion,
promoting accessibility, personalized learning, and rehabilitation. Its
contribution is framed within ethical and user-centered aspects that promote
equity and autonomy for people with disabilities, while laying a solid
foundation for future public policies and inclusive technological developments.
Keywords: Artificial
Intelligence; Disability; Inclusion; Comprehensive Development; Personalized
Care
Tecnologías
de inteligencia artificial enfocadas al cuidado y desarrollo de personas con
discapacidad.
RESUMEN
La inteligencia artificial (IA) se ha consolidado como una
tecnología con el potencial de mejorar la autonomía, la comunicación y la
inclusión social de las personas con capacidades especiales. Sin embargo,
existen algunas barreras que pueden limitar su acceso a la educación, la salud
y el empleo, debido a la falta de conocimiento existente sobre las aplicaciones
de la IA en el ámbito de la discapacidad. El objetivo de este estudio fue
realizar una revisión sistemática de la literatura (RSL) para identificar el
estado actual de las tecnologías de inteligencia artificial orientadas a la
atención y el desarrollo de personas con capacidades especiales, categorizando
las soluciones, los algoritmos y los dominios de aplicación. La metodología
siguió el modelo de la lista de verificación PRISMA, estructurada en torno a la
planificación, búsqueda, selección y extracción de información. La búsqueda se
llevó a cabo en cinco bases de datos académicas de alto impacto (Scopus, IEEE
Xplore, ScienceDirect y ACM), aplicando rigurosos criterios de inclusión y
exclusión. De un total de 314 registros iniciales, se seleccionaron 30 estudios
primarios para un análisis más profundo. Las aplicaciones más frecuentes
incluyen asistentes virtuales inteligentes, sistemas de comunicación
aumentativa y alternativa, traductores automáticos de lengua de señas,
interfaces cerebro-computadora, plataformas de aprendizaje adaptativo y
dispositivos innovadores de movilidad. En cuanto a los algoritmos, destaca el
uso de redes neuronales convolucionales y recurrentes, máquinas de vectores de
soporte, árboles de decisión, técnicas de agrupamiento no supervisado y
aprendizaje por refuerzo, con tasas de desempeño superiores al 90 % en tareas
de reconocimiento de voz, gestos o lengua de señas. Estas tecnologías han
contribuido a contextos educativos, terapéuticos y comunicativos, así como a
aplicaciones emergentes en movilidad asistida y entornos laborales inclusivos.
En conclusión, la IA es una herramienta clave para apoyar la inclusión,
promoviendo la accesibilidad, el aprendizaje personalizado y la rehabilitación.
Su contribución se enmarca en aspectos éticos y centrados en el usuario que
fomentan la equidad y la autonomía de las personas con discapacidad, al tiempo
que sienta una base sólida para futuras políticas públicas y desarrollos
tecnológicos inclusivos.
Palabras
clave: Inteligencia
artificial; Discapacidad; Inclusión; Desarrollo integral; Atención
personalizada.
1. Introduction
The rapid advancement
of artificial intelligence (AI) has revolutionized various fields of human
knowledge, generating tools capable of transforming the lives of historically
excluded groups, such as people with special abilities (Masliković et al.,2025) (Robert et al.,
2024), (Almufareh et al.,
2024). This
sector of the population faces structural barriers in accessing education,
health, employment, and social participation, which requires inclusive
technological solutions adapted to their needs (Hashemi et
al., 2023), (Universidad
Politécnica Salesiana,
2025). Some AI frameworks are being leveraged by people with disabilities, such
as personalized learning, communication tools, smart devices, and interfaces
with specific eMoorthy, 2025, pp.91-114) (Mitre
& Zeneli, 2024), (Tripathi et al., 2024), (Leong, 2025), (L. Smith, 2024), (Smith, 2024, pp. 121-134), (Simone, 2024) (Pagliara et al.,
2024). Ly,
recognizing these technologies in depth from a technical and scope perspective,
can improve the optimization and design of new AI solutions aimed at improving
the care and development of people with disabilities.
In this context, this
research focuses on analyzing the design, scope, and potential of AI-based
technologies for the care and comprehensive development of individuals with
various disabilities, including sensory, cognitive, motor, and other types of
disabilities. The study is part of a systematic literature review that compiles,
organizes, and analyzes the main technological developments in AI aimed at
improving the quality of life and autonomy of these individuals (Pinazo-Hernandis,
2024). Through
the current state of the literature, it was possible to identify the most
widely used applications, the contexts in which they have been implemented, the
results obtained, and the existing limitations, especially in environments with
limited technological resources, as is the case in many developing countries (Mitre & Zeneli,
2024), (Grados-Zubieta
et al., 2025),
(Pin, 2025), (Yepes et al,. 2024), (Salinas et
al, 2024). These
findings enable the systematization of theoretical and empirical knowledge on
inclusive technological solutions, providing strategic recommendations that
promote accessibility, equity, and innovation for people with disabilities (Giansanti et
al, 2025). In
addition, it could highlight the ethical, social, and technical challenges that
accompany the implementation of AI in this area, contributing to the
formulation of public policies by entities and managers, the design of
user-centered technology, and the reduction of digital divides (Salinas,
2024)
The research questions
guiding this review are: Q1) What AI solutions have been proposed or
implemented to support or assist people with disabilities?; Q2) What machine
learning algorithms are used in AI solutions that contribute to the activities
of people with disabilities?; Q3) What has been the performance of models
tested with machine learning algorithms that support the development of people
with disabilities?; Q4) What are the domains or fields of application of AI in
assisting people with disabilities? The document is organized into sections:
Introduction, Method, Results, Discussion, and Conclusions, following the
PRISMA model (Page & McKenzie, 2021)
2. Methods
A systematic review of
the literature was conducted, following the stages outlined in the PRISMA
model: planning, search and selection, and information extraction. The protocol
developed in the systematic review of the literature is summarized below:
2.1. Planning
In the planning stage,
the following steps were organized: defining the search objective, formulating
research questions, and establishing inclusion and exclusion criteria. The main objective of this review was to identify
the Artificial Intelligence technologies that are used in the care and
development of people with special abilities. To address this purpose, four key research questions were formulated.
These questions, along with their descriptions and motivations, are presented
in Table 1.
Table 1.
Systematic literature review research questions.
|
Research Questions |
Motivation and Expected Results |
|
Q1. What AI solutions have been
proposed or implemented to support or assist people with disabilities? |
Identify and classify existing AI
solutions, such as augmentative communication assistants, voice and gesture
recognition systems, smart mobility devices, adaptive learning environments,
and digital accessibility tools. This inventory will allow us to recognize
the state of the art and guide new developments. |
|
Q2. What machine learning
algorithms are used in AI solutions that contribute to the activities of
people with disabilities? |
Systematize the most commonly
used algorithms (deep neural networks, supervised learning, classification
models, natural language processing, computer vision, among others) and
analyze their effectiveness in specific tasks to determine which algorithms are
most appropriate for each type of disability or need. |
|
Q3. What has been the performance
of models tested with machine learning algorithms that support the
development of people with disabilities? |
Document performance metrics,
such as accuracy, sensitivity, specificity, and error rate, in empirical
studies to evaluate the reliability of the models applied. Quantitative
evidence is expected to support the effectiveness of these solutions in
real-world contexts. |
|
Q4. What are the domains or
fields of application of AI in assisting people with disabilities? |
Determine in which sectors AI has
been most successfully implemented (inclusive education, rehabilitation,
health, workplace inclusion, communication, and mobility). To identify
priority areas of impact and scenarios where there are still gaps in research
or a need for technological innovation. |
2.2. Search and selection
The search and selection phase began with the
identification and definition of key terms for analyzing artificial
intelligence technologies applied to individuals with special abilities. For this purpose, an initial group of preliminary
articles was established, which allowed for the standardization of the most
commonly used terms and the construction of effective search strings. The
selected terms included: "artificial
intelligence," "people with disabilities," "assistive
technology," "educational inclusion," "autonomy,"
"virtual assistants," "voice recognition," and "personalized learning." Based
on these concepts, various combinations were formulated, one of the most
effective chains being: "artificial intelligence" AND (disability OR
impaired) AND assistance AND (techniques OR solution OR technologies).
The search was conducted in four scientific databases:
Scopus, IEEE Xplore, ScienceDirect, and ACM Digital Library. These sources were
selected for their relevance in multidisciplinary areas, including engineering,
computer science, education, health, and social sciences.
Table
2. Application of the search string in the information sources.
|
No. |
Database |
Search string used |
|
1 |
Scopus |
TITLE-ABS-KEY (( "artificial
intelligence" AND ( disability OR impaired ) AND assistance AND (
techniques OR solution OR technologies ))) |
|
2 |
IEEE
Xplore |
("artificial intelligence" AND (disability
OR impaired) AND assistance AND (techniques OR solution OR technologies)) |
|
3 |
Science
Direct |
("artificial intelligence" AND (disability
OR impaired) AND assistance AND (techniques OR solution OR technologies)) |
|
4 |
ACM
Digital Library |
[All: "artificial intelligence"] AND
[[All: disability] OR [All: impaired]] AND [All: assistance] AND [[All:
techniques] OR [All: solution] OR [All: technologies]] |
During the evaluation
process, 314 records were initially identified from the databases. Of these,
192 were discarded because they did not meet the established criteria,
resulting in a final sample of 114 studies evaluated in depth, from which 26
primary articles demonstrating high relevance and methodological quality were
selected. Finally, four additional articles were added using manual extraction
methods, bringing the total to 30 primary articles.
The quality assessment
of the selected studies was carried out using a peer review matrix, considering
two groups of criteria: 1) Approach: Thematic relevance regarding the use of AI
with people with disabilities, type of disability addressed, context of
application (educational, therapeutic, social, etc.). 2) Content: Clarity of
objectives, methodological description, data quality, technological
application, and results obtained. Each study was assessed using a weighted
scoring system: 1 point for full compliance with the criterion, 0.5 points for
partial compliance, and 0 points for non-compliance.
Articles with a score
above 70% were classified as optimal quality, those between 50% and 69% as
acceptable, and those below 50% as moderate quality. Only acceptable and
optimal articles were included in the final analysis.
2.3. Information
extraction
The primary purpose of
the information extraction stage in this systematic review was to collect and
organize relevant data from the selected primary studies, thereby evaluating
the implementations, techniques, and results of using artificial intelligence
(AI) in the context of care and development for people with special abilities.
To this end, structured
criteria were defined to enable a rigorous evaluation of the content, including
the purpose of each study, the contexts in which it was applied, the types of
technologies used, the data analyzed, the metrics for assessing effectiveness,
and the methodological approaches employed. This systematization was crucial
for understanding the practical applicability of AI in educational,
therapeutic, communicative, and social inclusion contexts. Below is a detailed
description of the criteria used for the extraction and analysis of
information:
Table 3. Description of the criteria for
extracting information.
|
Criterion |
Description |
|
C1.
Purpose of the study |
Identify the main objective of
the study, the problem addressed, and its alignment with the inclusive
approach to the use of AI for people with disabilities. |
|
C2. Application contexts |
Determine the areas where AI
technologies were implemented (education, health, rehabilitation,
communication, employment, mobility, etc.). |
|
C3. AI technologies used |
Recognize the types of
technologies used (virtual assistants, speech recognition, computer vision,
predictive algorithms, adaptive interfaces, etc.). |
|
C4.
Data and characteristics analyzed |
Describe the types of data used
(e.g., voice, images, platform behavior, responses to stimuli, etc.), as well
as their origin and processing. |
|
C5. Impact indicators |
Identify the metrics used to
evaluate the effect of the technology (improvement in autonomy, cognitive
skills, communication, social integration, etc.). |
|
C6. Recommendations and limitations |
Analyze the recommendations
proposed by the authors, as well as the technical, social, or ethical
limitations mentioned in the studies. |
3. Results
The search and
selection of articles followed the PRISMA model guidelines in three phases: identification,
screening, and inclusion. In the identification phase, 314 studies were
collected through systematic searches in Scopus, IEEE Xplore, ScienceDirect,
and ACM. After removing duplicates and applying filters, 192 studies were
excluded that did not meet the inclusion criteria, such as a direct
relationship with artificial intelligence applied to people with disabilities,
peer review, or full-text availability.
A total of 114 articles
were reviewed in abstracts and full texts, of which 88 were excluded because
they did not present applications of artificial intelligence in contexts of
inclusion, lacked empirical evidence, or dealt with technologies unrelated to
the subject of study, such as financial or industrial automation systems. This
review yielded 26 articles, to which four primary studies were added,
identified through manual searches of secondary literature, institutional
websites, and technical documents. The final sample consisted of 30 studies,
which were used to answer the research questions. This analysis provided
scientific evidence based on the use of artificial intelligence technologies in
the development of people with disabilities. Figure 1 graphically presents the
flow of the systematic review process.
Figure 1. PRISMA diagram of identification, screening, and selection of
primary articles.
Some articles were not
selected because they focused on contexts unrelated to the objective of this
systematic review, such as industrial automation or theoretical analyses without
empirical evidence in populations with disabilities. As part of the analysis of
the quality of the primary studies, 114 articles were evaluated, and 30
scientific articles were ultimately selected that met both methodological and
thematic criteria, allowing their abstracts and full content to be investigated
in accordance with the information needs of this research. Figure 2 presents
the results of the analysis, which assessed the inclusive approach, the
practical application of AI technologies, methodological clarity, and
contextual relevance. Of the 23 articles, 23 obtained a score above 70%, while
seven articles scored between 50% and 69%. All studies addressed direct
applications of AI in educational, therapeutic, or social contexts.
Figure 2. Studies
included in the systematic review, by database
Figure 3 shows the temporal distribution of the
primary studies included in the review, with the highest concentration between
2021 and 2023. In 2023, there were eight studies, in 2022, a total of 7, and in
2021, 6, indicating sustained growth during that period. The years 2020 and
2015 saw fewer publications, reflecting the initial stages of exploration
before the increase in research driven by post-pandemic digitization.
Figure 3. Studies
included by year of publication
Chronological analysis suggests that inclusive
artificial intelligence is emerging as a growing line of research, with studies
testing solutions such as virtual assistants, adaptive platforms, and
augmentative communication systems for people with sensory, motor, or cognitive
disabilities. The increase in publications indicates advances in methodological
design, with the use of mixed approaches, empirical validations, and greater
participation of beneficiaries in the development and evaluation of solutions (Alam et
al.,2025). This evolution provides a framework for future
research aimed at expanding the scope of artificial intelligence to improve the
autonomy and quality of life for people with disabilities (Abidi, et
al., 2024)
3.3. Discussion
In response to question
Q1: What AI solutions have been proposed or implemented to support or assist
people with disabilities? The studies reviewed agree that artificial
intelligence solutions applied to assisting people with disabilities focus on
devices and platforms geared toward augmentative and alternative communication
(AAC), voice recognition, and natural language processing (NLP) systems,
intelligent virtual assistants, computer vision applications, and adaptive
learning platforms (Salinas et al. 2024), (Sierra et al.,
2025). These
technologies have expanded opportunities for interaction, autonomy, and social
participation for people with motor, cognitive, or sensory limitations (Joshi et al., 2020). For example, the
development of brain-computer interfaces enables users with reduced mobility to
control external devices, while automatic sign language translation systems
facilitate communicative inclusion (Troya et al., 2024). In the field of education, AI-based
solutions adapt content to the student's learning style, contributing to
equitable access to inclusive education (Jiménez et al.,
2024)
Advances in artificial
intelligence (AI) have catalyzed the development of highly personalized
assistive technologies designed to enhance the quality of life, autonomy, and
social participation of individuals with disabilities (Cabello, et
al., 2025). These
technologies, based on machine learning algorithms, computer vision, natural
language processing, and intelligent adaptive systems, enable more effective
interaction between individuals and their physical, cognitive, and social
environments (Troya Santillán, 2024).
In addition, systems
based on computer vision and convolutional neural networks enable the
interpretation of the environment through cameras integrated into mobile or
wearable devices (González et al., 2025). Technologies such as Microsoft Seeing AI
or Be My Eyes, supported by object recognition and text reading models (OCR +
NLP), help by providing real-time auditory feedback, facilitating mobility and
document reading (Bariffi, 2024).
Meanwhile, AI models
applied to real-time transcription and machine translation have given rise to
tools that convert spoken language into text or sign language (Navarrete-Cazales
& Manzanilla-Granados, 2023). Representative examples include automatic subtitling systems based on
Automatic Speech Recognition (ASR) and animated avatars generated by generative
adversarial network2s (GANs) to represent linguistic signs (Bariffi, 2025)
Regarding Q2: What are
the machine learning algorithms used in AI solutions that contribute to the
activities of people with disabilities? The literature reviewed shows a
predominance of deep neural network algorithms, particularly convolutional
networks for computer vision and recurrent networks for speech recognition and
sequential data analysis (Lanzagorta-Ortega et
al., 2022). Likewise,
the use of support vector machines and decision trees is reported in
applications for biomedical pattern classification and motor behavior
prediction (Manirajee et
al.,2024) In
adaptive learning environments, reinforced learning techniques are used to
customize study itineraries according to user performance. Complementarily,
unsupervised clustering algorithms have been used to identify profiles of
educational and therapeutic needs (Ryalat, 2025). This methodological diversity reflects
the versatility of AI in addressing diverse issues related to disability (Sánchez,
2025).
Regarding Q3: How have
models tested with machine learning algorithms that support the development of
people with disabilities performed? Empirical results indicate that the models
implemented have achieved varying levels of accuracy and efficiency depending
on the type of application (Almufareh et al.,
2023). In the
case of computer vision systems applied to gesture or sign language
recognition, accuracy rates of over 90% have been reported, validating their
usefulness in inclusive communication. Similarly, virtual assistants trained
with NLP have demonstrated significant improvements in user-machine
interaction, resulting in reduced response times and fewer interpretation
errors. Okolo et al applied a Convolutional Neural Network (CNN) to sign
language recognition in people with hearin, achieving
an accuracy of 95% with an F1-score of 0.93 (Okolo et al., 2024). Other studies
achieved accuracy values close to 90% in medical image classification tasks for
assisted diagnosis (Okolo et al., 2024), (Alvarado-Salazar,
2022). However,
the literature warns that the performance of the models is contingent upon the
quality of the training data, the application context, and the cultural and
linguistic adaptation of the algorithms, which presents a challenge for the
generalizability of the results (Castro, 2025).
According to Q4: What
are the domains or fields of application of AI in assisting people with
disabilities? Systematic studies identify the primary areas of application in
three key areas: education, therapy, and communication (Alvarado-Salazar,
2022). In
education, AI has been applied to adaptive learning platforms that promote the
inclusion of students with sensory or cognitive disabilities (Ghosh et
al., 2025). In the
therapeutic field, tools have been developed to monitor and predict clinical
progress in physical and neurocognitive domains, as well as systems for
predicting clinical outcomes (Peñarreta et, al.,
2025). In the
communicative domain, AI-based AAC systems and automatic sign language
translators stand out, enabling the social participation of nonverbal people (Hashemi, 2023), (Sánchez,
2025). Emerging
applications include assisted mobility (intelligent vehicles, AI-controlled
wheelchairs) and inclusive work environments, where intelligent systems act as
mediators of accessibility (Castro, 2025), (Flor-Unda et al., 2025). This overview highlights the
cross-cutting nature of AI as a tool that facilitates inclusion and equity for
people with disabilities (Shahzad et al., 2024), (Fernández et
al, 2025).
4. Conclusions
The review enabled us to analyze and synthesize
artificial intelligence applications designed to enhance the care, autonomy,
and social inclusion of people with disabilities. Thirty articles that met the
inclusion and exclusion criteria were reviewed, which allowed us to answer the
research questions posed. The results show that the most common solutions
include personalized virtual assistants, voice and gesture recognition systems,
adaptive learning platforms, and brain-computer interfaces, used to support
communication in people with speech impairments, motor rehabilitation
processes, personalization of educational materials, and activities of daily
living.
In terms of the algorithms used, deep neural networks,
supervised and unsupervised learning methods, and reinforcement learning
techniques were identified. These models were trained on biometric, behavioral,
and contextual data, including interaction patterns on digital platforms,
neurological signals, response times, and emotional reactions, which enabled
more personalized outputs tailored to users' needs.
The models evaluated showed improvements in functional
autonomy, communication, and social integration, along with high levels of
accuracy in pattern recognition. Complementary metrics such as user
satisfaction, perceived cognitive load, and caregiver or teacher adaptability
were included, broadening the understanding of the impact of these
technologies. However, the results depend on the quality of the training data
and the context of the application, highlighting the need for greater
standardization and validation across diverse environments.
In the domains of application, artificial intelligence
has focused on the educational, therapeutic, and communicative fields, with
emerging developments in assisted mobility and workplace accessibility. The
research employed methodologies such as feature selection, sensory data
normalization, and cross-validation, aiming to design scalable solutions
applicable in contexts with varying resource conditions.
Advances in Artificial Intelligence in the field of
inclusion underscore the need for coordinated public policies, including
regulatory frameworks for digital accessibility, as well as a shared
responsibility among educational, healthcare, and labor institutions.
Consequently, technological solutions can be consolidated as standardized tools
through widespread adoption, benefiting people with disabilities.
The findings in this study also suggest the need to
promote the co-design of accessible technologies, in accordance with
international standards for universal accessibility and user-centered ethical
principles. In this way, interface designs, device interoperability, and
algorithm transparency can be framed within an inclusive and equitable
approach, supported by social participation.
This
review provides a structured basis for researchers, developers, and
policymakers interested in promoting inclusion through intelligent
technologies. The findings identify advances and research opportunities in
areas such as the integration of affective data, the use of innovative urban
environments, and the design of systems based on universal accessibility with
the active participation of people with disabilities. A collaborative and
ethical approach is key to making artificial intelligence a sustainable and
globally accessible tool.
References
Alvarado
Salazar, R. E. (2022). Inteligencia artificial con enfoque a la
discapacidad visual: un mapeo sistemático [Trabajo de titulación,
Universidad Politécnica Salesiana, Sede Guayaquil]. Repositorio Institucional
UPS. http://dspace.ups.edu.ec/handle/123456789/23327
Bariffi,
F. J. (2024). Tecnologías basadas en inteligencia artificial en el modelo
de cuidados: riesgos y beneficios desde un enfoque de derechos humanos.
DERECHOS Y LIBERTADES: Revista de Filosofía del Derecho y Derechos Humanos,
51, 41–82. https://doi.org/10.20318/dyl.2024.8583
Cabello
Roldán Fco Javier Fernández Orrico Francisca Ferrando García Ma
Carmen López Aniorte Antonio Megías Bas Fco Miguel Ortiz González-Conde Mónica
Galdana Pérez Morales María Monserrate Rodríguez Egío Alejandra Selma Penalva
Elena Signorini, M. Carmen López Aniorte Dirección Fco Miguel Ortiz
González-Conde María Monserrate Rodríguez Egío, y C. Trabajos de
Investigación, «Nuevas tecnologías aplicadas a la docencia universitaria con
especial referencia a la inteligencia artificial».
C.
M. Troya Santillán, A. P. Bernal Párraga, R. Y. Guaman Santillan, M. de los A.
Guzmán Quiña, y M. A. Castillo Alvare, «Formación Docente en el Uso de
Herramientas Tecnológicas para el Apo-yo a las Necesidades Educativas
Especiales en el Aula», Ciencia Latina Revista Científica Multidisciplinar,
vol. 8, n.o 3, pp. 3768-3797, jun. 2024, doi:
10.37811/cl_rcm.v8i3.11588.
D.
Giansanti, A. Lastrucci, A. Iannone, y A. Pirrera, «A Narrative Review of
Systematic Reviews on the Applications of Social and Assistive Support Robots
in the Health Domain», 1 de abril de 2025, Multidisciplinary
Digital Publishing Institute (MDPI). doi:
10.3390/app15073793.
D. Lanzagorta-Ortega, D. L. Carrillo-Pérez, y R.
Carrillo-Esper, «Artificial intelligence in medicine: present and future», Gac
Med Mex, vol. 158, pp. 55-59, dic. 2022, doi: 10.24875/GMM.M22000688.
D. Masliković, B. M. Tomić, y N. Vulikić, «Perspectives of AI in empowering persons with
disabilities in Serbia[Perspektive
veštačke inteligencije u osnaživanju osoba sa invaliditetom u Srbiji]», Stanovnistvo,
vol. 63, n.o 1, pp. 151-166, 2025, doi: 10.59954/stnv.666.
D. Robert et al.,
«Effect of Artificial Intelligence as a Second Reader on the Lung Nodule
Detection and Localization Accuracy of Radiologists and Non-radiology
Physicians in Chest Radiographs: A Multicenter Reader Study», Acad Radiol, vol.
32, n.o 3, pp. 1706-1717, mar. 2025, doi: 10.1016/j.acra.2024.11.003.
Evangeline
y A. D. Moorthy, (2025) «Data-driven approaches in special education: Future
trends and implications», en Driving Quality
Education Through AI and Data Science, IGI Global, 2025, pp. 91-114. doi: 10.4018/979-8-3693-8292-9.ch005.
F. de
Simone, M. Casillo, y S. Collina, «AI and Inclusivity: Co-designing for
Disability Empowerment», Lecture Notes in Networks and Systems, vol.
1067 LNNS, pp. 196-206, 2024, doi: 10.1007/978-3-031-66431-1_12.
G. Hashemi,
A. L. Santos, M. Wickenden, H. Kuper, C. K. Shea, and S. Hameed, «Healthcare
Stakeholders' Perspectives on Challenges in the Provision of Quality Primary
Healthcare for People with Disabilities in Three Regions of Guatemala: A
Qualitative Study», Int J Environ Res Public Health, vol. 20, n.o 19, oct. 2023, doi:
10.3390/ijerph20196896.
G. I.
Okolo, T. Althobaiti, y N. Ramzan, «Assistive
Systems for Visually Impaired Persons: Challenges and Opportunities for
Navigation Assistance», 1 de junio de 2024, Multidisciplinary
Digital Publishing Institute (MDPI). doi:
10.3390/s24113572.
Guillén
Peñarreta, J. P., & Vizhñay Aguilar, C. F. (2016). Gafas especiales
para detección de obstáculos con sistema de ubicación en caso de emergencia y
ayuda de reconocimiento de billetes para personas con discapacidad visual
[Trabajo de titulación, Universidad Politécnica Salesiana, Sede Cuenca].
Repositorio Institucional UPS.
https://dspace.ups.edu.ec/bitstream/123456789/12295/1/UPS-CT006438.pdf
H.
Fernández Calle, S. Condori Crispín, y N. Palma Apaza, «Efectividad del
aprendizaje activo apoyado con la inteligencia artificial en estudiantes
universitarios bolivianos», Mérito - Revista de Educación, vol. 7, n.o
20, pp. 34-49, may 2025, doi: 10.37260/merito.i7n20.4.
J. A.
González Campos, J. C. López Núñez, y C. E. Araya Pérez, «Higher education and
artificial intelligence: challenges for the 21st century», Aloma, vol.
42, n.o 1, pp. 79-90, 2024, doi: 10.51698/ALOMA.2024.42.1.79-90.
J.
E. Grados-Zubieta, E. K. Bravo-Huivin, y S. E. Cieza-Mostacero, «Systematic
Review: Artificial Intelligence System for People with Visual Impairment
between the Years 2012-2022[Revisión Sistemática: Sistemas de Inteligencia
Artificial para Personas con Discapacidad Visual entre los Años 2012-2022]», RISTI
- Revista Iberica de Sistemas e Tecnologias de Informacao, vol. 2022, n.o
E54, pp. 354-366, 2022, Accedido: 14 de septiembre de 2025. [En línea].
Disponible en: https://www.scopus.com/pages/publications/85159192022
L.
Manirajee, S. Q. Hanis Shariff, y S. M. Mohd Rashid, «Assistive Technology for
Visually Impaired Individuals: A Systematic Literature Review (SLR)», International
Journal of Academic Research in Business and Social Sciences, vol. 14, n.o 2, feb. 2024, doi: 10.6007/ijarbss/v14-i2/20827.
L.
M. Décima, «La Inteligencia Artificial como habilitador de la Inclusión
Digital (Modalidad MONOGRAFÍA)», p. 1, 2011, [En línea]. Disponible en: https://www.sas.com/en_us/insights/analytics/what-is-analytics.html
L. Smith y
P. Smith, «The ethical issues raised by the use of Artificial Intelligence
products for the disabled: an analysis by two disabled people», en Ethics in Online Ai-Based Systems: Risks and
Opportunities in Current Technological Trends, Elsevier, 2024, pp.
121-134. doi: 10.1016/B978-0-443-18851-0.00022-6.
M. F. Almufareh, S. Kausar, M. Humayun, and S. Tehsin, «A
Conceptual Model for Inclusive Technology: Advancing Disability Inclusion
through Artificial Intelligence», Journal of Disability Research, vol.
3, no. 1, ene. 2024, doi:
10.57197/JDR-2023-0060.
M. F. Almufareh, S. Tehsin, M. Humayun, y S. Kausar,
«Intellectual Disability and Technology: An Artificial Intelligence
Perspective and Framework», Journal of Disability Research, vol. 2, n.o 4, pp. 58-70, nov.
2023, doi: 10.57197/JDR-2023-0055.
M. F.
Shahzad, S. Xu, W. M. Lim, X. Yang, y Q. R. Khan, «Artificial intelligence and
social media on academic performance and mental well-being: Student
perceptions of positive impact in the age of smart learning», Heliyon, vol. 10, n.o
8, abr. 2024, doi: 10.1016/j.heliyon.2024.e29523.
M. H.
Abidi, A. Noor Siddiquee, H. Alkhalefah, y V. Srivastava, «A comprehensive
review of navigation systems for visually impaired individuals», 15 de junio de 2024, Elsevier Ltd. doi:
10.1016/j.heliyon.2024.e31825.
M. J. Page,
McKenzie, J. E.., «The PRISMA 2020 statement: An updated guideline for
reporting systematic reviews», BMJ, vol. 372, mar. 2021, https://doi.org/10.1136/bmj.n71
M. Ryalat, N. Almtireen, G. Al-refai, H. Elmoaqet, y N.
Rawashdeh, «Research and Education in Robotics: A Comprehensive Review,
Trends, Challenges, and Future Directions», Journal of Sensor and Actuator
Networks, vol. 14, n.o 4, p. 76, jul. 2025, doi:
10.3390/jsan14040076.
N. Alam, S.
Hasan, G. A. Mashud, y S. Bhujel, «Neural Network for Enhancing Robot-Assisted
Rehabilitation: A Systematic Review», 1 de enero de
2025, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/act14010016.
N.
R. Salinas Buestán, E. T. Miranda Briones, Á. I. Torres Quijije, D. F.
Intriago Rodríguez, y D. P. Peña Banegas, «Implementación de un Dispositivo
Inteligente para la Asistencia de Personas con Discapacidad Visual en Entornos
Universitarios», Revista Tecnológica - ESPOL, vol. 36, n.o
E1, pp. 131-145, oct. 2024, doi: 10.37815/rte.v36ne1.1196.
N.
V. Yepes, J. D. Londono, y K. S. J. Pinzo, «Artificial Intelligence in
Communication Support Technologies for people with disabilities», Congreso
Internacional de Innovacion y Tendencias en Ingenieria, CONIITI, n.o
2024, 2024, doi: 10.1109/CONIITI64189.2024.10854792.
O.
Flor-Unda et al., «Challenges in the Development of Exoskeletons
for People with Disabilities», 1 de julio de 2025, Multidisciplinary
Digital Publishing Institute (MDPI). doi:
10.3390/technologies13070291.
P. Li, F.
Cao, S. Yu, X. Wang, X. Zhong, y W. Wu, «Research on the Application of
Artificial Intelligence to Accessibility Services in Science Museums», Proceedings
of 2025 International Conference on Digital Management and Information
Technology, DMIT 2025, pp. 409-419, jul. 2025, doi: 10.1145/3736426.3736491.
Pin
Menéndez, Y. B. (2025). Sistema de inteligencia artificial mediante
tecnología NLP para el control de asistencia de los estudiantes de la carrera
de Tecnologías de la Información [Proyecto de titulación, Universidad
Estatal del Sur de Manabí]. Repositorio Digital UNESUM. https://repositorio.unesum.edu.ec/handle/53000/7320
R.
Alvarado-Salazar y J. Llerena-Izquierdo, «Revisión de la literatura sobre el
uso de Inteligencia Artificial enfocada a la atención de la discapacidad
visual», Revista InGenio, vol. 5, n.o 1, pp. 10-21, ene.
2022, doi: 10.18779/ingenio.v5i1.472.
R. C.
Joshi, S. Yadav, M. K. Dutta, y C. M. Travieso-Gonzalez, «Efficient
multi-object detection and smart navigation using artificial intelligence for
visually impaired people», Entropy, vol. 22, n.o
9, sep. 2020, doi:
10.3390/e22090941.
Sánchez
B. (2025) «trabajo fin de máster: La Inteligencia Artificial como herramienta
inclusiva: Oportunidades y desafíos para estudiantes con necesidades
educativas especiales Artificial Intelligence as an inclusive tool:
Opportunities and challenges for students with special educational needs».
S. Ghosh,
P. Sindhujaa, D. K. Kesavan, B. Gulyás, y D. Máthé, «Brain-Computer Interfaces
and AI Segmentation in Neurosurgery: A Systematic Review of Integrated
Precision Approaches», Surgeries, vol. 6, n.o
3, p. 50, jun. 2025, doi: 10.3390/surgeries6030050.
Sierra,
C., Lemus del Cueto, L., Ausín, T., Hernández Moreno, J., Cerquides Bueno, J.,
& Ribeiro Seijas, Á. (2025). Inteligencia artificial: Transformando la
gestión de políticas y bienes públicos en la era digital (Ciencia para las
Políticas Públicas). CSIC. https://science4policy.csic.es/inteligencia-artificial-transformando-la-gestion-de-politicas-y-bienes-publicos-en-la-era-digital/
S. M.
Pagliara et al., «The Integration of Artificial Intelligence in
Inclusive Education: A Scoping Review», Information (Switzerland), vol.
15, n.o 12, dic.
2024, doi: 10.3390/info15120774.
S.
Pinazo-Hernandis, «Las personas mayores, las tecnologías y los cuidados.
Avances y retos», SCIO: Revista de Filosofía, n.o 26, jul.
2024, doi: 10.46583/scio_2024.26.1152.
X. Mitre y M. Zeneli, «Using AI to Improve Accessibility and
Inclusivity in Higher Education for Students with Disabilities», 2024 21st
International Conference on Information Technology Based Higher Education and
Training, ITHET 2024, 2024, doi:
10.1109/ITHET61869.2024.10837607.
Valle
Escolano, R. V. (2023). Inteligencia artificial y derechos de las personas
con discapacidad: el poder de los algoritmos. Revista Española
de Discapacidad, 11(1), 7–28. https://doi.org/10.5569/2340-5104.11.01.01
V. M., V.
R., P. V., y S. C., «AI Powered Trifocals for Sign Language Detection and
Speech Recognition», Proceedings of 6th International Conference on
Intelligent Communication Technologies and Virtual Mobile Networks, ICICV 2025,
pp. 1218-1224, jul. 2025, doi:
10.1109/ICICV64824.2025.11085984.
V.
Tripathi, Palak, A. Bali, P. Sharma, S. Chadha, y B. Sharma, «“Empowering Education: The Role of Artificial Intelligence
in Supporting Students with Disabilities”», Proceedings of 2024 2nd
International Conference on Recent Trends in Microelectronics, Automation,
Computing, and Communications Systems: Exploration and Blend of Emerging
Technologies for Future Innovation, ICMACC 2024, pp. 134-139, 2024, doi: 10.1109/ICMACC62921.2024.10893983.
W.
J. Jiménez Murillo et al., «Uso de tecnologías y herramientas de
apoyo para favorecer el desempeño académico de estudiantes de bachillerato con
discalculia», LATAM Revista Latinoamericana de Ciencias Sociales y
Humanidades, vol. 5, n.o 6, nov. 2024, doi:
10.56712/latam.v5i6.3006.
W. Y.
Leong, «Personalized AI Solutions for Supporting Communication Needs of
Disabled Students», 2025 14th International Conference on Educational and
Information Technology, ICEIT 2025, pp. 525-529, 2025, doi:
10.1109/ICEIT64364.2025.10976060.
Y.
Castro Blanco, «Inteligencia artificial y transformación social: Una revisión
sistemática», Revista Paraguaya de Pedagogía, vol. 2, n.o 4,
pp. 26-45, may 2025, doi: 10.33996/rpp.v2i4.18.
Z.
Navarrete-Cazales y H. M. Manzanilla-Granados, «Una perspectiva sobre la
inteligencia artificial en la educación», Perfiles Educativos, vol. 45,
n.o Especial, pp. 87-107, 2023, doi:
10.22201/iisue.24486167e.2023.Especial.61693.