摘要：Improving health workers' performance is vital for achieving the Millennium Development Goals. In the literature on human resource management (HRM) interventions to improve health workers' performance in Low and Middle Income Countries (LMIC), hardly any attention has been paid to the question how HRM interventions might bring about outcomes and in which contexts. Such information is, however, critical to assess the transferability of results. Our aim was to explore if realist review of published primary research provides better insight into the functioning of HRM interventions in LMIC. A realist review not only asks whether an intervention has shown to be effective, but also through which mechanisms an intervention produces outcomes and which contextual factors appear to be of critical influence. Forty-eight published studies were reviewed. The results show that HRM interventions can improve health workers' performance, but that different contexts produce different outcomes. Critical implementation aspects were involvement of local authorities, communities and management; adaptation to the local situation; and active involvement of local staff to identify and implement solutions to problems. Mechanisms that triggered change were increased knowledge and skills, feeling obliged to change and health workers' motivation. Mechanisms to contribute to motivation were health workers' awareness of local problems and staff empowerment, gaining acceptance of new information and creating a sense of belonging and respect. In addition, staff was motivated by visible improvements in quality of care and salary supplements. Only a limited variety of HRM interventions have been evaluated in the health sector in LMIC. Assumptions underlying HRM interventions are usually not made explicit, hampering our understanding of how HRM interventions work. Application of a realist perspective allows identifying which HRM interventions might improve performance, under which circumstances, and for which groups of health workers. To be better able to contribute to an understanding of how HRM interventions could improve health workers' performance, a combination of qualitative and quantitative research methods would be needed and the use of common indicators for evaluation and a common reporting format would be required.
