Lina Maria Gomez-Garcia

Lina Maria Gomez-Garcia

Auto-generated profile, based on publicly available information

Lina Maria Gomez-Garcia

School of Medicine, Universidad de los Andes, Bogota, Colombia

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 April 2026 in JMIR AI
Verified
Journal Article
Open access
EVEduardo De la Vega-Taboada
Eduardo De la Vega-Taboada
SPSofia A Portillo
Sofia A Portillo
LGLina Maria Gomez-Garcia
Lina Maria Gomez-Garcia
ABAnn Banchoff
Ann Banchoff
VBVictoria Maria Bermudez
Victoria Maria Bermudez
AKAbby C. King
Abby C. King
Background: Generative artificial intelligence (AI) systems are increasingly used in health and community settings, yet empirical evidence on how they function within participatory, youth-led action frameworks remains limited. Large language models can provide structured feedback to support planning and critical reflection, and AI-based image transformation can generate realistic visual prototypes to enhance shared understanding. However, risks include output variability, feasibility gaps when AI-generated recommendations or visualizations imply solutions that are not operationally workable, and the potential to displace adolescent voice and agency if AI outputs are treated as authoritative rather than as inputs for collective deliberation. Objective: This study examines how 2 generative AI tools—structured feedback using a GPT model and AI-based image transformation—functioned as deliberative and visualization supports within a youth-led citizen science intervention addressing environmental health concerns in El Pozón, Cartagena, Colombia. Methods: This exploratory action research study included a preparation phase and an implementation phase. During preparation, researchers iteratively tested SecureGPT (a privacy-enhanced version of ChatGPT 4.0) prompt configurations and compared DALL-E with Adobe Photoshop AI for place-based image modification, selecting a fixed prompt format requesting 3 strengths, 3 weaknesses, and 5 reflective questions (3-3-5). During implementation, 12 adolescent citizen scientists completed the Our Voice process. AI use was facilitator-mediated: prompts were co-developed through youth consensus, a facilitator entered prompts and operated tools while youth observed, and outputs were reviewed with the group in real time before use. Data sources included structured field notes, analytic memos, archived prompts and outputs, and session recordings. Analysis was descriptive and process-oriented, examining how AI shaped deliberation, solution refinement, and stakeholder engagement. Results: Structured GPT prompts supported deeper critical analysis and iterative refinement toward more feasible interventions. Model outputs varied in usefulness; role-based prompting often produced redundant responses, and early outputs were occasionally overly generic, requiring facilitator guidance and prompt refinement. The structured 3-3-5 format improved specificity and reduced wordiness. DALL-E did not generate sufficiently realistic place-based modifications, whereas Adobe Photoshop AI, used with iterative prompting and area-selection tools, produced visually plausible prototypes that supported group discussion and stakeholder communication. Highly realistic visualizations also introduced a feasibility gap when depicted infrastructure exceeded operational constraints, requiring explicit framing of images as aspirational prototypes rather than technical designs. Conclusions: In this facilitated participatory context, generative AI tools served as structured deliberative and visualization supports rather than autonomous decision makers. For participatory action and citizen science researchers, these findings suggest a practical workflow in which structured prompting, real-time group review, and domain-informed oversight can help participants refine feasible solutions, strengthen communication with stakeholders, and document iterative decision-making while managing variability, accuracy, privacy, and feasibility alignment.

9 July 2026 in BMC Public Health
Verified
Journal Article
Open access
PDF file
ZDZakaria Nadeem Doueiri
Zakaria Nadeem Doueiri
ABAnn Banchoff
Ann Banchoff
LGLina María Gómez-García
Lina María Gómez-García
CFCarlene Foldenauer
Carlene Foldenauer
PAPaula Guevara Aladino
Paula Guevara Aladino
AKAbby C. King
Abby C. King
Background: A growing number of studies have highlighted the importance of data visualization when utilizing mixed-methods approaches within community-based participatory research (CBPR). One such CBPR-derived method – Our Voice – employs a citizen-science (CS) framework that leverages mobile technology to improve health outcomes for residents from diverse communities. Virtual reality (VR) and augmented reality (AR) are two cutting-edge technologies that have been cited as potential tools to enhance data visualization and solution-building processes in Our Voice and similar community-facing methods. However, their utilization in such projects remains limited. In the present study, we report the first integration of VR and AR into two Our Voice projects and examine their feasibility and perceived utility within community-engaged settings. Methods: VR/AR technology was integrated into two Our Voice projects: (1) a project with adult unpaid care workers in Ciudad Bolívar, Bogotá, Colombia, and (2) a project with high school students in Half Moon Bay, CA, United States. In both settings, 360-degree simulations were integrated into a newly refined five-step Our Voice method, which included an “Imagine” step. Post-surveys assessed community members’ attitudes toward VR/AR using a six-point Likert scale. Data were descriptively analyzed. Results: Research using the Our Voice method revealed the integration of VR/AR resulted in citizen scientists and local stakeholders reporting VR/AR enhanced their ability to visualize community-level facilitators and barriers to leading healthy lives. Additionally, participants reported an increase in confidence in the potential of VR/AR to facilitate the development of innovative community-facing solutions to various issues around their neighborhoods. Conclusions: The findings from these pilot investigations suggest that VR/AR holds the promise in contributing to relevant advocacy changes across diverse communities, stakeholders, and problem areas. Future studies should explore developing user-friendly software that bridge data visualization and digital solution-building for broader community and organizational engagement.

16 May 2026 in BMC Public Health
Verified
Journal Article
Open access
PDF file
LGLina María Gómez-García
Lina María Gómez-García
EGElena Mª Gras-García
Elena Mª Gras-García
EVEduardo De la Vega-Taboada
Eduardo De la Vega-Taboada
NDNicolás Solórzano Duran
Nicolás Solórzano Duran
AKAbby C. King
Abby C. King
OSOlga Sarmiento
Olga Sarmiento
Background: Latin American cities are transforming in response to climate change, yet residents’ liveability experiences before these transformations begin are rarely documented. In Bogotá, the 2022–2035 Land Use Master Plan’s Green Corridors aim to promote sustainable mobility and integrate green infrastructure in urban design, with the first corridor planned along 7th Street. This study provides a baseline evaluation of liveability conditions along 7th Street before construction, aiming to (i) identify perceptions of social and built environment factors that facilitate or hinder liveability and (ii) document potential solutions to identified barriers. Methods: We employed a multi-method approach. A cross-sectional household survey described residents’ sociodemographic profile and perceptions of the Green Corridor’s expected effects on liveability. The Our Voice citizen science method engaged residents and commuters in identifying perceived facilitators and barriers, proposing potential solutions, and exchanging knowledge with policymakers. Results: Residents’ most expected improvements included increased vegetation, pedestrian and cycling infrastructure, and public space upgrades, while the most anticipated deteriorations included difficulty in car use and worsening public transport operations. Through the Our Voice method, 66 citizen scientists captured 1123 photo-narratives, documenting access to essential services, green areas, and urban trees as the most mentioned facilitators, while poor pedestrian infrastructure and safety concerns as the most mentioned barriers. Proposed solutions included infrastructure improvements, educational campaigns, and evidence-based policymaking. The process increased environmental awareness among citizen scientists and supported knowledge exchange with policymakers. Conclusion: This study underscores the importance of grounding climate mitigation and adaptation efforts in baseline assessments of urban residents’ liveability experiences. Built environment factors were widely valued as facilitators, while social environment factors emerged as persistent barriers, a pattern that the Our Voice method deepened by revealing the conditions that underpin these perceptions. The participatory process generated practical solutions, deepened citizen scientists’ awareness of their surroundings, and enabled meaningful engagement with policymakers. As cities pursue climate goals, these findings offer a foundation for understanding and evaluating the effects of a Green Corridor on residents’ everyday liveability as the intervention unfolds.

21 June 2025 in JMIR Preprints
Verified
Preprint
Open access
EVEduardo De la Vega-Taboada
Eduardo De la Vega-Taboada
SPSofia A Portillo
Sofia A Portillo
LGLina Maria Gomez-Garcia
Lina Maria Gomez-Garcia
ABAnn Banchoff
Ann Banchoff
VBVictoria Maria Bermudez
Victoria Maria Bermudez
AKAbby C. King
Abby C. King
BACKGROUND Generative artificial intelligence (AI) systems are increasingly used in health and community settings, yet empirical evidence on how they function within participatory, youth-led action frameworks remains limited. Large language models can provide structured feedback to support planning and critical reflection, and AI-based image transformation can generate realistic visual prototypes to enhance shared understanding. However, risks include output variability, feasibility gaps when AI-generated recommendations or visualizations imply solutions that are not operationally workable, and the potential to displace adolescent voice and agency if AI outputs are treated as authoritative rather than as inputs for collective deliberation. OBJECTIVE This study examines how 2 generative AI tools—structured feedback using a GPT model and AI-based image transformation—functioned as deliberative and visualization supports within a youth-led citizen science intervention addressing environmental health concerns in El Pozón, Cartagena, Colombia. METHODS This exploratory action research study included a preparation phase and an implementation phase. During preparation, researchers iteratively tested SecureGPT (a privacy-enhanced version of ChatGPT 4.0) prompt configurations and compared DALL-E with Adobe Photoshop AI for place-based image modification, selecting a fixed prompt format requesting 3 strengths, 3 weaknesses, and 5 reflective questions (3-3-5). During implementation, 12 adolescent citizen scientists completed the Our Voice process. AI use was facilitator-mediated: prompts were co-developed through youth consensus, a facilitator entered prompts and operated tools while youth observed, and outputs were reviewed with the group in real time before use. Data sources included structured field notes, analytic memos, archived prompts and outputs, and session recordings. Analysis was descriptive and process-oriented, examining how AI shaped deliberation, solution refinement, and stakeholder engagement. RESULTS Structured GPT prompts supported deeper critical analysis and iterative refinement toward more feasible interventions. Model outputs varied in usefulness; role-based prompting often produced redundant responses, and early outputs were occasionally overly generic, requiring facilitator guidance and prompt refinement. The structured 3-3-5 format improved specificity and reduced wordiness. DALL-E did not generate sufficiently realistic place-based modifications, whereas Adobe Photoshop AI, used with iterative prompting and area-selection tools, produced visually plausible prototypes that supported group discussion and stakeholder communication. Highly realistic visualizations also introduced a feasibility gap when depicted infrastructure exceeded operational constraints, requiring explicit framing of images as aspirational prototypes rather than technical designs. CONCLUSIONS In this facilitated participatory context, generative AI tools served as structured deliberative and visualization supports rather than autonomous decision makers. For participatory action and citizen science researchers, these findings suggest a practical workflow in which structured prompting, real-time group review, and domain-informed oversight can help participants refine feasible solutions, strengthen communication with stakeholders, and document iterative decision-making while managing variability, accuracy, privacy, and feasibility alignment.