Physical activity occurs during work, transport, domestic, and leisure-time activities. Too little physical activity increases the risks of ischaemic heart disease, stroke, colon cancer, breast cancer, and type 2 diabetes [1], as well as obesity [2] and falls in later life [3]. The World Health Organization recommends at least 30 minutes of regular, moderate-intensity physical activity on most days to reduce the risk of disease and injury [4].

Lack of physical activity is a problem in many developed countries, and a growing concern for developing countries adopting a progressively “Westernised” lifestyle [5]. Australia is no exception, with only 44% of men and 36% of women achieving sufficient physical activity for health [6]. This inactivity contributes 7% of Australia's disease burden and 10% of all deaths, mostly due to cardiovascular disease and diabetes [7]. It also places a substantial burden on the Australian economy through the costs of treatment for physical activity–related disease and injury, lost productivity, and diminished quality of life [8].

Interventions to promote physical activity (referred to herein as “physical activity interventions”) typically involve teaching individuals the skills to change physical activity behaviour, providing the population with knowledge about physical activity goals or opportunities to be active, or creating a more physically active environment [9]. Currently, in Australia, general practitioners (GPs) are relied upon to deliver physical activity interventions (when time permits). In addition, governments provide some encouragement to change physical activity behaviour through local mass media and transport campaigns, but investment is minimal. It is likely that a combination of intervention approaches will be needed to achieve a meaningful change in population participation in physical activity [10]–[12].

Efficient allocation of health resources to different intervention programs hinges on identifying those interventions (or combinations of interventions) that achieve maximum population health benefits relative to cost. However, there is a need for more cost-effectiveness analyses using standardised methods to enable comparison of different types of physical activity interventions [13]. Although there have been a number of cost-effectiveness analyses of individual interventions [14]–[20], including two studies reporting cost-effectiveness of GP prescription in the Australian context [17],[19], there has been only one cost-effectiveness analysis, by the National Institute of Clinical Excellence (NICE) in the United Kingdom [21], that used a standardised approach to compare multiple interventions. All ten interventions, which involved brief advice by a health professional or referral to an exercise physiologist, were found to be dominant (i.e., cost-saving) when compared with usual care. However, the NICE study focused only on intervention alternatives rather than evaluating a range of complementary interventions (including broader public health approaches incorporating media, active transport, etc.) and the potential benefits of combining interventions as a package.

In Australia, a standardised approach to assessing cost-effectiveness (ACE) has been developed for evaluating interventions in the Australian health care context [22]. These methods are being used to evaluate 150 interventions, focusing on prevention of noncommunicable disease, including six interventions to promote physical activity. In this paper, we present the ACE results for the physical activity interventions, which range from individualised counselling interventions to broad population health approaches. The cost-effectiveness of each intervention is compared with current practice for physical activity intervention in the Australian population, and from this we derive an optimal intervention pathway for improving population health.

Intervention to encourage an increase in physical activity participation is highly recommended in Australia. Potential reductions in costs of treating ischaemic heart disease, stroke, diabetes, breast cancer, and colon cancer mean that there is a high probability of cost-savings from a health sector perspective. Taken as a package of interventions, all six physical activity interventions could lead to a substantial improvement in population health at under AUS$50,000 per DALY.

Cost-effectiveness of the package is not highly sensitive to the sustainability of behavioural changes (total package is under AUS$50,000 per DALY at maximum rates of decay). However, it is likely that some interventions will lead to a more sustained effect than others, and this could affect the order of implementation in the pathway. It is also possible that there will be synergistic effects with implementation of multiple interventions, which could improve the sustainability of intervention effects on physical activity over time, thus increasing cost-effectiveness of the intervention package. However, this may well be countered by a decrease in effectiveness of each additional intervention, due to the increasing proportion of the population less willing or able to change their physical activity behaviour.

When modelled from the selected studies of intervention effectiveness, intervention programs that encourage use of pedometers and mass media-based community campaigns are the most cost-effective strategies to implement and are very likely to be cost-saving. We found that these interventions have the potential to deliver large health benefits to the population, despite the seemingly small or nonsignificant effects on physical activity behaviour when measured at a population level [34],[35].

Overall, our intervention cost-effectiveness ratios, which ranged from dominant up to AUS$75,000 per DALY, were not as favourable as the entirely dominant results reported by NICE for ten GP prescription and referral interventions in the United Kingdom [21]. This may be because the NICE analysis did not include patient costs of time and travel, and assumed a slower decay in physical activity behaviour change (50% of participants assumed to maintain change in behaviour long enough to experience health benefits e.g. 20 y for a 25-y-old), but there were also other differences in modelling methods and assumptions (e.g., discount rates) that may have influenced the more favourable NICE results.

Conversely, our cost-effectiveness ratios were mostly more favourable than the cost-effectiveness ratios recently reported for seven physical activity intervention programs in the US [25]. Costs per QALY ranged from US$14,000 (2003AUS$19,000) to US$69,000 (2003AUS$91,000) for the physical activity promotion interventions, which included two community-wide campaigns, two social support walking programs, two individually adapted behaviour change programs, and one program to enhance access to a more active environment (e.g., new bicycle paths, fitness centre, etc.). Some additional costs were included in the US analysis (e.g., patient out-of-pocket expenses for physical activity clothing and equipment) contributing to relatively high intervention costs per person, which may have led to the less favourable US results, but there were also many other differences in analysis methods and assumptions, such as a shorter time horizon (40 y), additional medical inflation on disease costs (8% per annum), and more sustained effects on behaviour (33% to 50% decay in the second year, with maintenance of effect thereafter), which complicate interpretation of the contrasting results.

However, the NICE results, the US study, and our own analyses together provide good evidence that physical activity intervention can be cost-effective in the UK, US, and Australia. Over 20 different intervention programs have now been evaluated in these countries, with only four programs exceeding a cost-effectiveness threshold of AUS$50,000.

To our knowledge, no other studies have evaluated cost-effectiveness of this package of interventions. However, two studies have previously evaluated GP prescription intervention based on the randomised controlled trial of New Zealand's Green Prescription program [36], reporting costs per QALY of NZ$2,100 (2003AUS$2,000) [19] and dominant [21]. Although not directly comparable to each other or to our cost per DALY of AUS$11,000 due to different analysis methods and assumptions (e.g., discount rates), the growing number of analyses reporting cost-effectiveness under varying methods and assumptions strengthens the argument for this particular physical activity intervention as a cost-effective measure for improving public health. However, the results for the Green Prescription program do not necessarily reflect the cost-effectiveness of all physical activity prescription programs (many of which have not shown a significant effect on physical activity behaviour [37]–[40]).

A number of limitations must be taken into account when evaluating the results of this research. For example, because of inconsistent physical activity outcome measures and a limited number of randomised controlled trials, for some interventions we selected single intervention studies for cost-effectiveness analysis rather than combining multiple trials in a meta-analysis. Therefore, while the results reflect the cost-effectiveness of the interventions that were evaluated, and based on the best available evidence, they should not be generalised to all interventions of a similar type.

In addition, although interventions were evaluated as if implemented for one year, in some cases it was necessary to include studies of less than one-year duration. While it would be preferable to include only those studies with follow-up data at one year, this would exclude a number of interventions from cost-effectiveness analysis (e.g., active transport interventions, community mass media and pedometer programs, etc.), and potentially bias cost-effectiveness analyses toward the more targeted interventions (e.g., general practice interventions) for which longer-term studies are more readily available. We have included shorter-duration studies in the interests of modelling a wide range of interventions, but acknowledge that these interventions may not prove to be as cost-effective if subsequent intervention studies find a significant drop in effectiveness at one year.

Furthermore, the level of evidence underlying the measures of intervention effect is relatively weak. For example, evaluation of the mass media campaign effect on population health was based only on the results of a single quasi-experimental study, and evaluation of the pedometer program effect on population health was based on a meta-analysis that included only 277 participants in total. In addition, it is likely that those who volunteered to participate in the pedometer trials were more active or more motivated to change their activity behaviour than the general population, leading to a more favourable estimate of cost-effectiveness than might actually occur with rollout of a pedometer program across Australia. Further randomised controlled trials, using consistent measures of physical activity behaviour, would improve our confidence in both the relative position of interventions in the pathway and the overall magnitude of the health gain that could be achieved.

There are a number of other unknowns in modelling physical activity that may have influenced our cost-effectiveness results. Due to the reliance on (mainly) observational studies in the meta-analyses of relative risks of disease by Bull et al. [1], it is possible that the risk would not be fully reversible for those increasing their physical activity in response to an intervention. It is also plausible that there is a time lag between change in physical activity behaviour and change in risk, which may be relatively short for cardiovascular diseases [41], but longer for cancers [42]. These factors could lead to an overestimate of cost-effectiveness ratios. We do, however, incorporate an attenuation of cancer risk by age (see Table I in Text S2), which Bull et al. [1] based on ischaemic heart disease data, that might be an overestimate of attenuation and may, therefore, offset risk reversibility and lag effects.

Nevertheless, the research illustrates how combining physical activity interventions in a cost-effectiveness expansion pathway can provide guidance to policymakers in identifying the most cost-effective approaches to decreasing the burden of disease due to physical inactivity, based on the best available evidence. For Australia, based on current evidence, it is likely that the package of interventions would not only be cost-effective but very likely cost-saving to the health sector, leading to substantial improvements in health for the Australian population.