BACKGROUND Optimal care for older patients with complex chronic conditions (CCC) is challenging. Not only do older patients with CCC present with multiple conditions and functional impairments, these often interact with each other, as well as with their treatments. Patients with CCC are concentrated in home care and nursing home settings. Professionals working in these settings often lack appropriate decision support that mirrors the medical and functional complexity of these persons. AIM To improve prognoses and estimation of treatment impact for older care recipients with CCC in home care and nursing homes settings, and develop, validate, and test next generation individualised decision support. IMPACT Better informed decision making for clinical management of older care recipients with CCC in home care and nursing homes, through (1) high quality internationally validated predictive algorithms on disease trajectories and treatment outcomes; (2) a multi-nationally tested e-platform for health professionals to receive predictive scenarios on course and treatment outcomes of newly assessed care recipients at point of care; and (3) dissemination among health professionals working in nursing homes and home care. APPROACH We collated longitudinal data from 52 million older recipients of home care and nursing home care from eight countries including (1) highly reliable, valid and harmonised comprehensive assessments of functional capacities, diseases, and treatments, linked with (2) administrative repositories on mortality and care use. We develop and validate decision support algorithms using a variety of techniques including machine learning to better predict (i) outcomes (eg death, acute admissions, quality of life) and the modifying impact of (ii) pharmacological and (iii) non-pharmacological treatments. We co-create decision support output with health professionals and patients and pilot it's applicability at point of care with an e-platform.