Table 1
Methodological and contextual characteristics of the studies included in the review (n = 31), Brazil, 2020–2025.
| ID (AUTHOR, YEAR) | TYPE | AI/EDUCATIONAL STRATEGY | AUDIENCE/CHANNEL | MAIN FINDINGS | KEY LIMITATION |
|---|---|---|---|---|---|
| Guo et al. (2024) [8] | Methodological study (ML) | Algorithmic curation of videos (YouTube); proposal of chatbots and integration into apps | Public/professionals; YouTube/apps | Improves the quality and discovery of trustworthy content; feasible integration with official channels | No behavioral evaluation in real‑world settings; platform dependence |
| Xie et al. (2024) [9] | Integrative review | AI chatbots for education/clinical tutoring | Students/educators; digital environment | Potential for personalized tutoring and post‑pandemic support | Heterogeneous evidence; no clinical outcomes |
| Franchini et al. (2021) [10] | Implementation study (mixed methods) | Community chatbot (Dress‑COV) for triage/education | Adults (Telegram) | Reach and interaction with participatory education | Nonequivalent control; limited generalizability |
| Văduva et al. (2023) [11] | Narrative review | eHealth/mHealth/telemedicine (includes AI) | Hospital nurses | Expands access and remote training | Non‑systematic; no effect metrics |
| Parums (2021) [12] | Editorial | Digital transformation (includes AI) | — | Emphasizes the educational role of digital health | No empirical data |
| Abdelouahed et al. (2025) [1] | Exploratory qualitative study | Adaptive AI; simulators; personalized content | Professionals/managers | Continuous training and tailored materials | Documentary/case‑based; no measurement |
| Tekinay (2023) [13] | Exploratory study | ChatGPT as educator | Public questions (COVID‑19) | Accessible and rapid responses | Qualitative assessment; LLM biases |
| Sezgin and Kocaballi (2025) [14] | Exploratory study | Generative AI in messaging (WhatsApp/SMS) | Frequently asked public health questions | Greater clarity and accuracy of responses | No behavioral outcomes |
| McKee et al. (2025) [15] | Applied narrative review | Data/AI for segmented communication | Public health professionals | Popular and digital education with greater impact | Non‑systematic |
| Haupt et al. (2024) [16] | Experimental study (prompts) | Media literacy/AI (role‑playing game versus neutral) | Users/trainees | Better misinformation detection with appropriate prompting | Limited sample/scope |
| Tanui et al. (2024) [17] | Narrative review | Apps with multilingual AI | African populations (general) | Inclusive and scalable education | Descriptive evidence |
| Bharel et al. (2024) [18] | Perspective | Generative AI for communication/efficiency | Health professionals/organizations | Reduces administrative burden; supports messaging | No empirical data |
| Meo et al. (2023) [19] | Performance evaluation | ChatGPT (health questions) | — | Good performance on educational FAQs | No link to behavior |
| Zeeb et al. (2023) [20] | Descriptive narrative | Apps/digital platforms | Population of Bremen | Awareness via apps during COVID‑19 | No causal evaluation |
| Towler et al. (2023) [21] | Methodological study | ML (topic modeling) for rapid analysis of qualitative data | COVID‑19 textual data | Accelerates insights for communication | Does not measure public impact |
| Ma et al. (2023) [22] | Cross‑sectional study | Digital health curriculum with AI | Health students (China) | Need for curricular integration and practice | Self‑reported; non‑experimental |
| Jia et al. (2023) [23] | Narrative review | Training in surveillance with AI | Professionals/public | Training plus real‑time alerts | No educational measurement |
| He et al. (2022) [24] | Observational study | AI in diagnosis/CT (with educational pathway) | Professionals | Training for clinical AI use | Clinical focus; indirect education |
| Grüne et al. (2022) [25] | Retrospective observational study | Symptom app with feedback | App users | Self‑care and awareness | Use bias; no counterfactual |
| Weeks et al. (2022) [26] | Qualitative study | Personalized chatbot for vaccine hesitancy | Urban youth | Empathic messages increase acceptance | Qualitative; no population‑level effect |
| Dzau et al. (2022) [27] | Narrative review | Digital capacity‑building frameworks | Professionals/students | Proposes simulations and remote teaching | No impact data |
| Wang et al. (2023) [2] | Narrative review/conceptual paper | AI‑enhanced curriculum; data‑driven teaching | Public health students/educators; university courses | Framework to integrate AI and big data into public health education | Conceptual paper; no empirical evaluation |
| Wen et al. (2023) [28] | Bibliometric study | Trends in digital/AI research | — | Identifies frontiers (social media) | No educational outcomes |
| Wang and Li (2024) [3] | Narrative review/perspective | Adaptive learning; AI tutoring; simulations | Public health/medical students and professionals; | Digital platforms/simulation‑based training AI can personalize learning and support simulation‑based public health training at scale | Theoretical overview; no primary data or implementation studies |
| Scott and Coiera (2020) [29] | Critical narrative review | Early warning/NLP and modeling | Patients/professionals | Supports policies and messaging | No direct educational assessment |
| Uohara et al. (2020) [30] | Narrative review | Triage chatbots; telemonitoring | Professionals/public | Scales recommendations and recruitment | No trials |
| Montenegro‑López (2020) [31] | Descriptive study | National app plus AI committee | Professionals/patients | Guidance and local management | Qualitative/documentary |
| Simsek and Kantarci (2020) [32] | Case/modeling study | Optimized allocation (AI) | Managers | Informs planning/education | No direct educational channel |
| McKillop et al. (2021) [33] | Mixed‑methods exploratory study | COVID‑19 chatbots based on CDC/WHO | Citizens | Positive use and acceptability | Uncertain behavioral effect |
| Verma et al. (2025) [34] | Feasibility study (mixed methods) | Hospital educational technology | Visitors/patients (OPD) | Improved compliance during the intervention | Single‑center; short term |
| Bynon Neely et al. (2024) [35] | Exploratory study | YouTube plus SEO with ChatGPT support | Communities and health workers | Engagement and reach of videos | No causal evaluation |
Table 2
AI‑based educational strategies: Modality, purpose, platform, and curation (n = 31), Brazil, 2025.
| ID (AUTHOR, YEAR) | AI MODALITY/STRATEGY | EDUCATIONAL PURPOSE (ESSENCE) | CHANNEL/PLATFORM | SUPERVISION | EQUITY/LANGUAGES |
|---|---|---|---|---|---|
| Guo et al. (2024) [8] | ML + NLP for video curation | Filter and recommend trustworthy videos to strengthen health literacy and reduce misinformation | YouTube; apps; messaging | Yes (expert review) | Multilingual potential; integration with official channels |
| Xie et al. (2024) [9] | AI chatbots (integrative review) | Personalized clinical tutoring/learning in the post‑pandemic period | Chatbots/web | Recommended | — |
| Franchini et al. (2021) [10] | Community chatbot (Dress‑COV) | Triage plus participatory education and reinforcement of self‑care | Telegram | Yes (curation) | Accessible; community inclusion |
| Văduva et al. (2023) [11] | eHealth/mHealth/telehealth (with AI) | Remote training and adoption of digital technologies | Apps/telehealth | — | — |
| Parums (2021) [12] | Editorial (AI in digital health) | Emphasizes informing/training for safe use of technologies | — | — | — |
| Abdelouahed et al. (2025) [1] | Adaptive AI; intelligent simulators | Continuous training and profile‑based personalized content | Educational platforms | Desirable | — |
| Tekinay (2023) [13] | ChatGPT | Answer public questions in plain language | Web/messaging | — | — |
| Sezgin and Kocaballi (2025) [14] | Generative AI in messaging | Educational support; assess clarity and relevance of responses | WhatsApp/SMS | Recommended | — |
| McKee et al. (2025) [15] | Data + AI (applied review) | Segmented communication and decision support in public health | Multiple | — | — |
| Haupt et al. (2024) [16] | Prompting (role‑playing game) in LLM | Media literacy and misinformation detection | Training environments | — | — |
| Tanui et al. (2024) [17] | Apps with multilingual AI | Inclusive, scalable education in African public health settings | Apps | — | Local languages |
| Bharel et al. (2024) [18] | Generative AI (perspective) | Support communication, productivity, and insights | Public health agencies | — | Equity/ethics emphasized |
| Meo et al. (2023) [19] | ChatGPT (performance evaluation) | Complementary study/FAQ tool | Web | — | — |
| Zeeb et al. (2023) [20] | Apps/digital platforms | Awareness through apps | Corona Health app | — | — |
| Towler et al. (2023) [21] | ML (topic analysis) | Accelerate insights to guide campaigns | Text data analysis environments | — | — |
| Ma et al. (2023) [22] | Digital health curriculum (with AI) | Curricular integration and simulated practice | Distance/hybrid education | Faculty/tutors | — |
| Jia et al. (2023) [23] | AI in surveillance (review) | Train professionals and issue real‑time alerts | Surveillance platforms | Institutional | — |
| He et al. (2022) [24] | AI in imaging (CT) | Educational track for clinical AI use | Imaging services | Professional | — |
| Grüne et al. (2022) [25] | Symptom diaries + ML | Real‑time educational feedback and self‑care | Symptom apps | — | — |
| Weeks et al. (2022) [26] | Personalized vaccine chatbot | Empathic messages to reduce hesitancy | Messaging/chatbot | Content curation | — |
| Dzau et al. (2022) [27] | Frameworks with AI | Simulations and continuing education | Online platforms | — | — |
| Wang et al. (2023) [2] | Big‑data AI; intelligent tutoring; virtual simulation | Integrate AI into public health curriculum and build AI‑literate, emergency‑ready professionals | University public health courses; computer‑assisted and online learning | Teacher‑led; faculty control of AI tools | No explicit equity or multilingual strategy mentioned |
| Wen et al. (2023) [28] | Bibliometrics (AI/digital) | Map trends to guide education/management | — | — | — |
| Wang and Li, (2024) [3] | Personalized learning algorithms; predictive analytics; AI‑driven simulations | Personalize public health training and support data‑informed decision‑making | Digital learning platforms; simulation/VR; AI‑enhanced online courses | Educator/institutional oversight; emphasis on ethical governance | Discusses fairness and bias; no concrete language/localization plan |
| Scott and Coiera (2020) [29] | NLP/early warning; modeling | Support messaging and rapid response | Media/reports | — | – |
| Uohara et al. (2020) [30] | Triage chatbots; ML for research | Scaled recommendations and recruitment | Web/telehealth/virtual ICU | Human curation | — |
| Montenegro‑López (2020) [31] | National app + AI committee | Guidance and local management with user feedback | CoronApp (Colombia) | Technical committee | — |
| Simsek and Kantarci (2020) [32] | SOFM (optimized mobilization) | Inform logistical planning/education | Models/decision‑support tools | — | — |
| McKillop et al. (2021) [33] | Watson Assistant (chatbots) | COVID‑19 information based on CDC/WHO | Watson Assistant chatbots | Documentary curation | Multilingual support |
| Verma et al. (2025) [34] | YOLO‑V5 + 3D distance | Education/compliance with NPIs in hospital environments | CCTV + IEC campaigns (information, education, communication) | Local management | — |
| Bynon Neely et al. (2024) [35] | ChatGPT for educational SEO | Expand reach/discovery of health videos | YouTube | — | — |
| Guo et al. (2024) [8] | ML + NLP (detailed pipeline) | Preselect relevant and comprehensible videos | YouTube | Yes (experts) | — |
Table 3
Educational functions by phase of the pandemic cycle, AI mechanisms, scalability, and gaps (n = 31), Brazil, 2025.
| ID (AUTHOR, YEAR) | MAIN EDUCATIONAL GOAL | PHASE (PREP/RESPONSE/RECOVERY) | TARGET AUDIENCE | PEDAGOGICAL MECHANISM WITH AI | CHANNEL | SUPERVISION (WHO) | SCALABILITY/OPERATION | LEVEL OF EVIDENCE | KEY GAPS |
|---|---|---|---|---|---|---|---|---|---|
| Guo et al. (2024) [8] | Curation of trustworthy content (literacy) | Response | General public/professionals | ML/NLP for selection; multimedia delivery | YouTube, apps, messaging | Experts (review) | High: integrates with official channels | Methodological (development + evaluation) | Assess behavioral effect; platform dependence |
| Xie et al. (2024) [9] | Tutoring/educational support post‑pandemic | Recovery | Students/educators | Tutor chatbot (personalization) | Web/chatbot | Recommended | High: low marginal cost | Integrative review | Heterogeneity; no clinical outcomes |
| Franchini et al. (2021) [10] | Triage plus participatory community education | Response | Adults (Telegram) | Validated messages plus reinforcement | Telegram | Curation | High: large‑scale app | Implementation study (mixed methods) | Nonequivalent control group |
| Văduva et al. (2023) [11] | Digital capacity building for nurses | Recovery | Nurses | eHealth/mHealth/telehealth with AI support | Apps/telehealth | NR | Variable: depends on infrastructure | Narrative review | Small sample; no effect measurement |
| Abdelouahed et al. (2025) [1] | Continuous training and adaptive content | Preparedness | Professionals/managers | Adaptive AI; simulators | Educational platforms | Desirable (faculty/preceptors) | High: online modules | Exploratory qualitative study | No standardized measures |
| Tekinay (2023) [13] | Public FAQ in plain language | Response | General population | LLM (ChatGPT) Q&A | Web/messaging | NR | High: widely available | Exploratory study | Model bias; update issues |
| Sezgin and Kocaballi (2025) [14] | Clarity and relevance of conversational responses | Response | Public health FAQs | Generative AI in messaging | WhatsApp/SMS | Recommended | High: ubiquitous channels | Exploratory study | No behavioral outcomes |
| McKee et al. (2025) [15] | Data‑driven segmented communication | Preparedness/response | Public health professionals | Modeling and analytics | Multiple channels | NR | High: policy‑informing | Applied review | No field data |
| Haupt et al. (2024) [16] | Media literacy (misinformation detection) | Preparedness/response | Users/trainees | Role‑playing game prompting in LLM | Training environments | NR | High: low cost | Experimental (lab) | Limited sample and scope |
| Tanui et al. (2024) [17] | Inclusive multilingual education | Preparedness/response | African populations | Apps with AI (local languages) | Apps | NR | High: scalable | Narrative review | Descriptive evidence only |
| Bharel et al. (2024) [18] | Institutional communication and productivity | Preparedness | Public health agencies/professionals | Generative AI for summarization/generation | Institutional platforms | NR | Moderate: requires governance | Perspective | No empirical data |
| Meo et al. (2023) [19] | Study/educational FAQ | Preparedness/response | Students/professionals | LLM (Q&A) | Web | NR | High | Performance evaluation | No link to behavior |
| Zeeb et al. (2023) [20] | Awareness through regional apps | Response | Population (Bremen) | Apps plus algorithms | Corona Health app | NR | Moderate: local context | Descriptive narrative | No causal evaluation |
| Towler et al. (2023) [21] | Rapid insights from qualitative data | Response | Public health teams | ML (topic modeling) for rapid synthesis | Analytic environments | NR | High: accelerates decision‑making | Methodological study | Loss of cultural nuances |
| Ma et al. (2023) [22] | Integration of digital health/AI into curricula | Preparedness | Health students | Distance/hybrid learning with AI | Academic environment | Faculty | High: institutional | Cross‑sectional study | Self‑reported data; no impact outcomes |
| Jia et al. (2023) [23] | Surveillance training and alerts | Preparedness/response | Professionals/public | AI for detection and alerts | Surveillance platforms | Institutional | High | Narrative review | No primary data |
| He et al. (2022) [24] | Training for clinical AI use (imaging) | Response | Health professionals | AI diagnostic assistance | Imaging services | Professional | Moderate: requires infrastructure | Observational study | Retrospective data; variability |
| Grüne et al. (2022) [25] | Self‑care via symptom feedback | Response | App users | ML in symptom diaries | Apps | NR | High | Retrospective observational study | Self‑report; external validation |
| Weeks (2022) [26] | Reduction of vaccine hesitancy | Response | Urban youth | Personalized chatbot (empathic messages) | Messaging/chatbot | Curation | High: messaging | Qualitative study | Limited generalizability |
| Dzau et al. (2022) [27] | Digital training and simulations | Preparedness | Professionals/students | Simulations and remote teaching | Online platforms | NR | High | Narrative review | No impact data |
| Wang et al. (2023) [2] | Modernize public health curriculum and train emergency‑ready professionals | Preparedness | Public health students; public health educators | AI‑based intelligent tutoring; data‑driven curriculum design; computer‑assisted learning using big data | University courses; online/computer‑assisted | Teachers/faculty | Potentially high via e‑learning; only proposed | Narrative review | No implementation; no learning outcomes |
| Wen et al. (2023) [28] | Mapping thematic frontiers | Preparedness | — | Bibliometrics of digital/AI | — | NR | High: guides agendas | Bibliometric study | Coverage and language bias |
| Wang and Li (2024) [3] | Personalize and modernize public health training | Response | Public health/medical students; health professionals | Adaptive learning; AI simulations; analytics | Digital platforms; online courses; simulation | Educators/institutions | High theoretical scalability; not tested | Narrative perspective | No primary data; few concrete models for LMICs |
| Scott and Coiera (2020) [29] | Data‑informed messaging and rapid response | Response | Patients/professionals | NLP/early warning; modeling | Media/reports | NR | High | Critical narrative review | No educational evaluation |
| Uohara et al. (2020) [30] | Scaled recommendations and recruitment | Response | Professionals/public | Triage chatbots; ML for research | Web/telehealth/virtual ICU | Human curation | High | Narrative review | Governance and consent |
| Montenegro‑López (2020) [31] | Guidance and local management | Response | Professionals/patients | National app plus AI committee | CoronApp | Technical committee | High: national level | Descriptive study | Validation of decision rules; asymptomatic cases |
| Simsek and Kantarci (2020) [32] | Mobilization planning and logistics | Preparedness | Managers | SOFM for optimal routes | Models/decision‑support tools | NR | High: simulation‑based | Case/modeling study | Dependence on assumptions |
| McKillop et al. (2021) [33] | Automated informational service | Response | Citizens | Chatbots (Watson Assistant) | Web/chatbots | Documentary curation | High | Mixed‑methods exploratory study | No metrics for satisfaction, time, or cost |
| Verma et al. (2025) [34] | Compliance with NPIs in hospitals | Response | Visitors/patients | Video detection (YOLO‑V5 + 3D) | CCTV + IEC campaigns | Local management | Moderate: hardware‑dependent | Feasibility study (mixed methods) | No control group; confounding factors |
| Bynon Neely et al. (2024) [35] | Multimedia educational reach | Response | Communities/public health workers | YouTube + SEO (ChatGPT) | YouTube | NR | High: low cost | Exploratory study | History of misinformation |
[i] Notes: Phases—preparedness (prep), response (response), and recovery (recovery). NR = not reported. “Level of evidence” refers to the type of study/report.
Figure 1
AI framework for public health education and emergency response.