OBJECTIVES: An automated dose dispensing (ADD) service is implemented in primary health care in some countries, particularly in the Nordic countries. In this service, regularly used medicines are machine-packed into unit-dose bags for each point of administration. The aim of this study is to review the evidence of the ADD’s influence on the appropriateness of medication use, medication safety and costs in the primary health care. METHODS: A literature search was performed on the most relevant databases, including the Medline, Embase, and Cochrane Library. An article was included in the review if the study was conducted in primary health care or nursing home settings and medicines were dispensed in unit-dose bags. All study designs were approved and control groups were not required. Studies applying outcome measures that were related to the appropriateness of medication use, medication safety or costs were included. RESULTS: Out of 278 abstracts, six studies were found to be acceptable. The prevalencies of potential inappropriate drug use (IDU) were higher among ADD users than non-ADD users. After controlling for confounding factors, ADD reduced the probability of long-acting benzodiazepine use among women and drug-drug interactions among women and men. The ADD users aged ≥65-79 years had more problems with potential IDU than older ones (≥80 years). The risk of administration errors was lower if medicines were supplied by the ADD service. The ADD service also reduced discrepancies in the documentation of patient medication records. Any costs were not investigated in the studies. CONCLUSIONS: The evidence of the influence of ADD on appropriateness of medication use and medication safety is limited, and missing on costs. The findings of this review suggest that the ADD service may improve medication safety in primary health care, but does not effectively reduce potential IDU.