Structural predictors and latent maturity regimes of robotic readiness in global health systems: evidence from...

The systematic integration of robotics into health service delivery systems requires periodic assessment of robotic readiness in terms of digital-health maturity regimes across countries. The current study aims to cluster 169 countries into maturity regimes and classify and predict cluster membership accuracy based on digital-health maturity dimensions determining the system's perception and interoperability, coordination, and workforce-regulatory reliability readiness. These country-level proxy concepts are applied due to a dearth of cross-country robotic readiness measures at the global level. The study also proposed an adaptive readiness framework for robotic deployment decision-making.

This study applies a multilayered robotic systems readiness proxy framework based on diffusion of innovations and multi-agent systems theories, which hypothesise health-system readiness as adaptive and learning-driven instead of static. Using 31 global digital-health maturity indicators from the Global Digital Health Monitor 2023, three latent proxy dimensions are constructed to measure perception/interoperability readiness, governance/coordination readiness, and workforce-regulatory reliability readiness. The data represent 169 countries at different stages of digital-health maturity, starting from phase 1 to phase 5, where 67 countries reflect evidence-based digital-health maturity status and 102 countries had no data reported and are below phase 1. The sample included these 102 countries in the study, imputing the lowest values for each indicator to prioritise them and eliminate participation bias in global health policy decisions. To address concerns regarding missing data and its handling, the analysis was repeated across different robust scenarios. The latent proxy dimensions are created using principal component analysis, reducing 31 dimensions to 3 dimensions. Their associations were explored using ordinary least squares regression. Unsupervised clustering techniques (K-means, agglomerative hierarchical clustering, and Gaussian mixture modelling) were applied to identify latent readiness regimes, and comparative model assessment brought a four-cluster solution. External validation was conducted against the World Bank classification of countries. The separability of the latent regimes was assessed through repeated cross-validations and post-clustering recoverability analysis using conservative supervised learning models, where five latent clusters were considered in line with the World Health Organization's five-phase maturity categories.

The three proxy indices have shown internally coherent loading structures with 85%-95% scale reliability. Significant positive structural associations are evident where the perception/interoperability (β = 0.343, p < 0.01; observed-only scenario) and governance/coordination readiness (β = 0.838, p < 0.01; baseline scenario) layers reflect stronger partial associations with workforce-regulatory reliability readiness (R2 = 0.892, p < 0.001; baseline scenario) for intelligent robot implementation in healthcare. K-means, Gaussian mixture modelling (GMM), and agglomerative (hierarchical) unsupervised learning models reveal good cluster distinctiveness (silhouette = 0.633 [k = 4]; 0.617 [k = 5]) varying between the scenarios, ranging from 0.357 to 0.514 under four robust cluster regimes, indicating distinct maturity regimes in the "RPI-MRCI-ACRI readiness" space. Robustness analyses indicated that the readiness structure remained considerably identifiable across three alternative missing data scenarios, although some boundary cases were overlapping. External validation using the World Bank and WHO's country classification indicated profound alignment with the final cluster regimes. Post-clustering recoverability analysis depicted that the latent clusters were significantly separable within the readiness space. Cluster membership in moderate to very good system readiness requires ∼30% contribution of each of the readiness indices to classify the country at the advanced to transformed phase of intelligent robotics implementation readiness in most of the scenarios under K-means and GMM. Machine learning (ML) models are run on a five-cluster specification given the main data categorisation requirement of phase "1" to phase "5." Among four supervised machine learning models, random forest and XGBoost achieved the highest (accuracy up to 0.980; area under the receiver operating characteristic curve (AUROC) ≈ 1.00) and most reliable performance (cross-validated accuracy ≈ 0.91), supporting robust separability and recoverability of the latent readiness regimes. SHAP analysis identified macro-level governance and coordination readiness index (0.111) as the most influential predictor of cluster classification under K-means and perception readiness (0.106) as the most influential under GMM.

Findings uncover heterogeneous readiness clusters of countries and exhibit that digital health governance coherence, standards and interoperability, and institutional digital literacy are stronger predictors of robotics integration potential in healthcare than technological dimensions alone. The study does not provide a direct estimate of robotics deployment but offers a thoughtful, system-level framework for comparing structural enablers relevant to robotics ingestion for health-system strengthening. An adaptive monitoring framework is proposed as a conceptual future-work direction rather than an empirically validated component of the present study.