RESUMEN
One key task in the early fight against the COVID-19 pandemic was to plan non-pharmaceutical interventions to reduce the spread of the infection while limiting the burden on the society and economy. With more data on the pandemic being generated, it became possible to model both the infection trends and intervention costs, transforming the creation of an intervention plan into a computational optimization problem. This paper proposes a framework developed to help policy-makers plan the best combination of non-pharmaceutical interventions and to change them over time. We developed a hybrid machine-learning epidemiological model to forecast the infection trends, aggregated the socio-economic costs from the literature and expert knowledge, and used a multi-objective optimization algorithm to find and evaluate various intervention plans. The framework is modular and easily adjustable to a real-world situation, it is trained and tested on data collected from almost all countries in the world, and its proposed intervention plans generally outperform those used in real life in terms of both the number of infections and intervention costs.
Asunto(s)
Inteligencia Artificial , COVID-19 , Humanos , COVID-19/epidemiología , COVID-19/prevención & control , Pandemias , Algoritmos , Aprendizaje AutomáticoRESUMEN
AIM: To determine biological (sex and age), socioeconomic (marital status, education, and mother tongue) and geographical (region) factors connected with causes of death and lifespan (age at death, years-of-potential-life-lost, and mortality rate) in Slovenia in the 1990s. METHODS: In this population-based cross-sectional study, we analyzed all deaths in the 25-64 age group (N=14 816) in Slovenia in 1992, 1995, and 1998. Causes of death, classified into groups according to the 10th revision of International Classification of Diseases, were linked to the data on the deceased from the 1991 Census. Stratified contingency-table analyses were performed. Years-of-potential-life-lost (YPLL) were calculated on the basis of population life-tables stratified by region and linearly modeled by the characteristics of the deceased. Poisson regression was applied to test the differences in mortality rate. RESULTS: Across all socioeconomic strata, men died at younger age than women (index of excess mortality in men exceeded 200 for all studied years) and from different prevailing causes (injuries in men aged <45 years; neoplasms in women aged >35 years). For men, higher education was associated with fewer deaths from digestive and respiratory system diseases. The least educated women died relatively often from circulatory diseases, but rarely from neoplasms. Single people died from neoplasms less often. Marriage in comparison with divorce reduced the mortality rate by 1.9-fold in both men and women (P<0.001). Mortality rate in both men and women decreased with increasing education level (P<0.001). Mortality rate of ethnic Slovenians was half the mortality rate of ethnic minority members and immigrants (P<0.001). Analysis of YPLL revealed limited and nonlinear impact of education level on premature mortality. The share of neoplasms was the highest in the cluster of socioeconomically prosperous regions, whereas the share of circulatory diseases was increased in poorer regions. Significant differences were found between individual regions in age at death and mortality rate, and the differences decreased over the studied period. CONCLUSION: These data may aid in understanding the nature, prevalence and consequences of mortality as related to socioeconomic inequalities, and thus serve as a basis for setting health and social policy goals and planning health measures.