Multilevel Analysis of the Patterns of Physical-Mental Multimorbidity in General Population of Sao Paulo Metropolitan Area, Brazil

Chronic diseases are often comorbid and present a weighty burden for communities in the 21st century. The present investigation depicted patterns of multimorbidity in the general population and examined its association with the individual-and area-level factors in an urban sample of non-elderly adults of Brazil. Data were from the cross-sectional Sao Paulo Megacity Mental Health Survey, a stratified multistage area probability sampling investigation. Trained interviewers assessed mental morbidities and asked about physical conditions for 1,571 community-dwelling women and 1,142 men, aged between 18 and 64 years. Principal component analysis depicted patterns of physicalmental multimorbidity, by sex. Following, the patterns of multimorbidity were subjected to multilevel regression analysis, taking into account individual-and area-level variables. Three patterns of clustering were found for women: 'irritable mood and headache', 'chronic diseases and pain', and 'substance use disorders'. Among men, the patterns were: 'chronic pain and respiratory disease', 'psychiatric disorders', and 'chronic diseases'. Multilevel analyses showed associations between multimorbidity patterns and both individual- and area-level determinants. Our findings call for a reformulation of health-care systems worldwide, especially in low-resource countries. Replacing the single-disease framework by multi-disease patterns in health-care settings can improve the ability of general practitioners in the health-care of person-centred needs.