Publicação
AI-Enabled Digital Health Promotion and Prevention
| Resumo: | Background: Health promotion aims to strengthen individuals’ and communities’ capacity to maintain health and well-being through behavior change, empowerment, and supportive environments. Achieving this requires interventions that are timely, personalized, and scalable—qualities increasingly supported by artificial intelligence (AI). However, research on AI-enabled health promotion remains fragmented, organized primarily around technological labels rather than the intervention purposes these tools serve, limiting the cumulative understanding of how AI techniques are applied across health promotion contexts. Objective: This study systematically maps peer-reviewed research on AI-enabled digital health promotion interventions to clarify how AI techniques are organized across intervention purposes, target users, and delivery contexts. Methods: We conducted a large-scale computational literature review of 6328 peer-reviewed journal articles using natural language processing and unsupervised machine learning. Topic modeling identified latent thematic structures, and scientometric analyses examined research clusters and application patterns across health promotion contexts. Results: The analysis identified dominant application clusters organized into three broad intervention contexts: (1) AI-enabled digital technologies embedded in health promotion applications, (2) clinical and data-driven AI systems supporting preventive care and health promotion decision-making, and (3) population-level and policy-oriented applications of AI in public health promotion. Conclusions: This study provides a structured synthesis of how AI techniques are applied in digital health promotion interventions, organized by intervention context, target population, and health promotion purpose, facilitating comparison across applications beyond technological form alone. The findings support more purpose-sensitive design, evaluation, and governance of AI-enabled health promotion applications and offer a foundation for cumulative research in this rapidly expanding field. |
|---|---|
| Autores principais: | Girão Carrilho, Mariana |
| Outros Autores: | Pinto, Diego Costa; Wagner, Rafael Luis; Rohden , Simoni F.; Arriaga, Miguel Telo de; Pinto , Leonor Quelhas |
| Assunto: | health promotion digital health artificial intelligence computational literature review topic modeling medical internet research Reviews and References, Medical Radiology Nuclear Medicine and imaging Health Policy Health Informatics SDG 3 - Good Health and Well-being |
| Ano: | 2026 |
| País: | Portugal |
| Tipo de documento: | recensão |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | Universidade Nova de Lisboa |
| Idioma: | inglês |
| Origem: | Repositório Institucional da UNL |
| Resumo: | Background: Health promotion aims to strengthen individuals’ and communities’ capacity to maintain health and well-being through behavior change, empowerment, and supportive environments. Achieving this requires interventions that are timely, personalized, and scalable—qualities increasingly supported by artificial intelligence (AI). However, research on AI-enabled health promotion remains fragmented, organized primarily around technological labels rather than the intervention purposes these tools serve, limiting the cumulative understanding of how AI techniques are applied across health promotion contexts. Objective: This study systematically maps peer-reviewed research on AI-enabled digital health promotion interventions to clarify how AI techniques are organized across intervention purposes, target users, and delivery contexts. Methods: We conducted a large-scale computational literature review of 6328 peer-reviewed journal articles using natural language processing and unsupervised machine learning. Topic modeling identified latent thematic structures, and scientometric analyses examined research clusters and application patterns across health promotion contexts. Results: The analysis identified dominant application clusters organized into three broad intervention contexts: (1) AI-enabled digital technologies embedded in health promotion applications, (2) clinical and data-driven AI systems supporting preventive care and health promotion decision-making, and (3) population-level and policy-oriented applications of AI in public health promotion. Conclusions: This study provides a structured synthesis of how AI techniques are applied in digital health promotion interventions, organized by intervention context, target population, and health promotion purpose, facilitating comparison across applications beyond technological form alone. The findings support more purpose-sensitive design, evaluation, and governance of AI-enabled health promotion applications and offer a foundation for cumulative research in this rapidly expanding field. |
|---|