Paweena Khampukka

Generative artificial intelligence (GenAI) may assist evidence-informed health-policy work, but favorable user perceptions and well-written outputs do not establish factual reliability or implementation readiness. A multilevel mixed-methods pilot evaluation examined MUSYA AI, a locally grounded policy-support platform in Thailand. Thirty-five health-sector personnel completed questionnaires, seven participated in Think-Aloud observation, sixteen Policy Briefs were assessed using an expert rubric, and seventy factual claims underwent evidence auditing. The document comparison included eight MUSYA AI and eight ChatGPT (GPT-5.6, OpenAI) outputs under common task instructions and system-specific information access. Mean System Usability Scale, perceived usefulness, and trust scores were 97.29/100, 4.70/5, and 4.57/5, respectively. Ceiling effects and limited internal consistency constrained interpretation of these descriptive indices; user experience, ease of use, and behavioral intention were interpreted at the item level. Observations documented reading and editing, but successful error detection and correction were not evaluated. MUSYA AI documents received higher overall quality ratings than comparator documents (95.38 ± 2.39 versus 72.25 ± 11.90; difference, 23.13 points; bootstrap 95% confidence interval, 15.63–31.38; Hedges’ g = 2.55). However, classification–rationale inconsistencies affected forty-five claims (64.3%), leaving comparative factual-accuracy findings provisional. The small, nonrandomized document sample and absence of verified task pairing prevented causal attribution of quality differences. MUSYA AI elicited favorable pilot-user perceptions and produced higher-rated documents within the evaluated sample. These findings support continued supervised evaluation; institutional readiness requires traceable claim adjudication, demonstrated oversight effectiveness, and broader controlled assessment.

Background: Equitable allocation of public health budgets across multiple intervention domains remains a major challenge in regional health governance. In Thailand’s Health Region 10, annual healthcare budgets must address diverse health burdens across several provinces, while current planning approaches rely on expert deliberation and historical precedent without systematic exploration of alternative allocation strategies. Public health resource allocation decisions are inherently multi-criteria, integrating health impact, cost-effectiveness, equity, disease severity, clinical and ethical priorities, feasibility, and alignment with national health policy agendas—dimensions that cannot be reduced to a single metric. This study introduces H-RL-MUSYA (Hierarchical Reinforcement Learning for Multi-Domain Unified System of Yielding Adaptive allocations), a decision-support framework designed to assist—not replace—public health practitioners by systematically generating and evaluating a menu of Pareto-efficient allocation strategies across four priority domains: nutrition, mental health, behavioral risk, and accident prevention. The framework explicitly acknowledges that DALYs averted and cost-effectiveness ratios are valuable but partial indicators, and that final resource allocation must integrate additional considerations—including underpinning health policies, priority population needs, feasibility, and contextual judgment—that lie beyond the model’s scope. Results: Applied to Thailand’s Health Region 10 (4.6 million inhabitants), H-RL-MUSYA identified 127 Pareto-efficient policies yielding a representative compromise allocation that averted 847,293 DALYs (34.1% improvement over historical allocations), improved cost-effectiveness by 31.3%, and reduced the health equity Gini coefficient from 0.243 to 0.187. A 12-month prospective pilot confirmed +23.1% composite health improvement with 91% stakeholder acceptance. Conclusions: H-RL-MUSYA demonstrates that AI-assisted policy exploration can meaningfully enrich public health decision-making by surfacing non-intuitive allocation strategies and quantifying equity–efficiency trade-offs, while human expertise, policy context, and democratic deliberation remain essential for final allocation decisions.

Designing optimal heritage tourism routes in secondary cities involves complex trade-offs between cultural richness, travel time, carbon emissions, spatial coherence, and group satisfaction. This study addresses the Personalized Group Trip Design Problem (PGTDP) under real-world constraints by proposing DRL–IMVO–GAN—a hybrid multi-objective optimization framework that integrates Deep Reinforcement Learning (DRL) for policy-guided initialization, an Improved Multiverse Optimizer (IMVO) for global search, and a Generative Adversarial Network (GAN) for local refinement and solution diversity. The model operates within a digital twin of Warin Chamrap’s old town, leveraging 92 POIs, congestion heatmaps, and behaviorally clustered tourist profiles. The proposed method was benchmarked against seven state-of-the-art techniques, including PSO + DRL, Genetic Algorithm with Multi-Neighborhood Search (Genetic + MNS), Dual-ACO, ALNS-ASP, and others. Results demonstrate that DRL–IMVO–GAN consistently dominates across key metrics. Under equal-objective weighting, it attained the highest heritage score (74.2), shortest travel time (21.3 min), and top satisfaction score (17.5 out of 18), along with the highest hypervolume (0.85) and Pareto Coverage Ratio (0.95). Beyond performance, the framework exhibits strong generalization in zero- and few-shot scenarios, adapting to unseen POIs, modified constraints, and new user profiles without retraining. These findings underscore the method’s robustness, behavioral coherence, and interpretability—positioning it as a scalable, intelligent decision-support tool for sustainable and user-centered cultural tourism planning in secondary cities.

Designing optimal heritage tourism routes in secondary cities involves complex trade-offs between cultural richness, travel time, carbon emissions, spatial coherence, and group satisfaction. This study addresses the Personalized Group Trip Design Problem (PGTDP) under real-world constraints by proposing DRL–IMVO–GAN—a hybrid multi-objective optimization framework that integrates Deep Reinforcement Learning (DRL) for policy-guided initialization, an Improved Multiverse Optimizer (IMVO) for global search, and a Generative Adversarial Network (GAN) for local refinement and solution diversity. The model operates within a digital twin of Warin Chamrap’s old town, leveraging 92 POIs, congestion heatmaps, and behaviorally clustered tourist profiles. The proposed method was benchmarked against seven state-of-the-art techniques, including PSO + DRL, Genetic Algorithm with Multi-Neighborhood Search (Genetic + MNS), Dual-ACO, ALNS-ASP, and others. Results demonstrate that DRL–IMVO–GAN consistently dominates across key metrics. Under equal-objective weighting, it attained the highest heritage score (74.2), shortest travel time (21.3 minutes), and top satisfaction score (17.5 out of 18), along with the highest hypervolume (0.85) and Pareto Coverage Ratio (0.95). Beyond performance, the framework exhibits strong generalization in zero- and few-shot scenarios, adapting to unseen POIs, modified constraints, and new user profiles without retraining. These findings underscore the method’s robustness, behavioral coherence, and interpretability—positioning it as a scalable, intelligent decision-support tool for sustainable and user-centered cultural tourism planning in secondary cities.