Key points are not available for this paper at this time.
Artificial Intelligence (AI) and Machine Learning (ML) are already being used in public health surveillance for the analysis of trends, predictions of outcomes and interventions. However, their use in addressing global health inequity is still relatively constrained, especially in LMICs, where other structural factors such as economic and social determinants and governance issues continue to be a challenge. This work uses AI/ML to analyze global public health data, with an emphasis on health inequality, as captured by the Health Access and Quality (HAQ) Index, Mortality-to-Incidence Ratios (MIR), and Risk-Standardized Death Rates (RSD). The data from the Global Burden of Disease Study 2019 was used to predict healthcare trends using Random Forest regression and to categorise countries into meaningful groups for action using K-Means clustering. Clustering was evaluated by silhouette scores, and the predictive accuracy was evaluated by cross-validation. and Mean Absolute Error (MAE). Results reveal significant disparities: Germany and other Western European countries scored HAQ Index values of 85 and above, while countries in Sub-Saharan Africa, including Chad and Nigeria, scored between 25 and 35. Some countries in the South Asian region such as India have moved up from 45th to 65th place which shows that there is much room for strategic change. Random Forest was more accurate than the baseline models ( =0.94 in Germany and = 0.80 in Afghanistan) and suggested Chad and Afghanistan as the regions where the intervention should be conducted.
Dr Ashwini L H (Tue,) studied this question.