The search strategy generated a number of potentially eligible papers. After screening through titles and abstracts, 26 papers were initially identified as potentially relevant and their full texts were accessed to determine whether they met the inclusion criteria. Of those 26 papers, 20 were excluded as their participants did not include homeless adults, or did not include any interventions for the management of diabetes as shown in Fig. 1. After carrying out a second search, no further studies met our criteria for inclusion. Therefore, a total of six papers were included in the analysis of this review (characteristics of included studies are presented in Table 2).

Fig. 1

Flowchart of selection process

All of the studies found were conducted in developed countries, three of the studies included within this review were conducted in Canada (studies 1, 2 and 3) and the other three studies were conducted within the United States (studies 4, 5 and 6). All of the studies included participants who attended organisations that are dedicated in serving the vulnerable populations. One study included patients from a nurse-run clinic (study 6). Another study recruited participants from three supportive inner-city housing facilities (study 3). One study recruited participants who volunteered at a homeless oriented primary care clinic (study 5) and another study included participants from a rehab centre (study 2). One of the study recruited participants from a community health care (study 1) and lastly one study recruited participants from a local outreach organisation (study 4).

The studies included in this review had an average number of 167 participants (range 8–524). Across all six studies the mean age of the participants was ranged from 37 to 76 years old. All of the studies recruited a majority of male participants which ranged from 35 to 100% of the participants. The definitions of homeless also varied across all the studies. However, two studies included the definition of homelessness as a criteria of their study enrolment (studies 5 and 6). While one study recorded the duration of homelessness (study 3), no details were provided about the participants housing transitions. Two of the studies included previous diabetes diagnosis as a criteria for study enrolment (studies 1 and 6). Information on the participants’ ethnic background was included in half of the studies (studies 1, 4 and 5). Most of the participants in the studies were individuals from minority populations, for example African-American. However, no studies investigated whether there was a difference in outcomes by ethnic race. Out of the six studies, only one study provided details on their participants’ education level, employment status and income (study 4).

Interventions that exist for managing diabetes in homeless adults

As can be seen in Table 2, the majority of the studies measured the effects of an intervention for diabetes care, which included a participant questionnaire alongside various assessments for diabetes. Two of the studies (33%) involved a medical assessment as one of the outcome measure of their intervention (studies 2 and 5). One study retrieved information about participants’ diabetes management through self-reported survey data only (study 6). Half of the studies assessed the effectiveness of their intervention through gaining feedback from the participants (studies 1, 3 and 4). None of the studies assessed participants’ diabetes management over a long period of time.

The methodological quality reported in most of the studies were generally moderate with a median score of 18 (range 14–26). The main study objectives were clear in all 6 of the studies, and the main outcomes were adequately described. Two of studies lacked participants’ characteristics such as age, gender, other sociodemographic data and how participants were recruited (studies 3 and 4). Details on participants who lost a follow-up were not reported in any of the six studies. Majority of the studies scores were low on internal and external validity (studies 1, 3 and 4). Whilst one study was determined to be insufficiently powered in order to detect clinically meaningful differences (study 6).

Principles and barriers to the successful management of diabetes in homeless adults

All studies included within this review highlighted not only the need of diabetes management programmes for the homeless but also the barriers and obstacles that this population group faces in accessing care for their diabetes. There is a need for effective and innovative models of care to help overcome these disparities. A few studies have suggested that diabetes is a “holistic and social” disease amongst people who are homeless. It is described as an additional challenge to a person’s daily life struggles (studies 2, 3 and 5). Effective strategies for addressing the challenges and obstacles that the homeless population face demands for not only well-coordinated models of care, but also for them to be flexible, diverse and most importantly multi-sectored. All individuals with diabetes needs to be understood and consulted as a “whole person”. This acknowledgement will build rapport between patients and healthcare professionals, and ultimately improve their care (studies 1, 2 and 3). Two of these studies suggested that healthcare professionals should be knowledgeable about the process of behaviour change, understand how social disadvantages might influence the change process and furthermore should be able to provide appropriate referrals, facilitate discussion and mobilise professional support to address the challenges that this particular population face (studies 1 and 3). It is necessary that healthcare professionals receive sufficient and appropriate training to understand how to incorporate the principles of patient-centred care when working with the homeless population. A collaborative relationship between the healthcare professionals and the patients will likely lead to both greater concordance and goal achievement within the management of the patient’s diabetes. Diabetes management interventions reported in the studies identified by this review were categorised as:

Diabetes education

Majority of the studies included in this review provided participants with educational sessions on what diabetes is, educational materials and access to disease management classes as part of the described intervention provided (studies 3, 4, 5 and 6). However, in studies 3, 4 and 6 there were no outcomes related data to enable the comparison of the effects of participants with or without diabetes following a class (such as improvements in HbA1c levels for participants with diabetes). It is unclear in study 5 whether the recorded decrease in HbA1c was a direct result of participants attending the diabetes education component of the intervention.

Medication support and supplies for blood monitoring

The most common challenges that are experienced by the homeless population includes the lack of access they have to medication such as insulin due to not having health insurance and the lack of support in gaining prescriptions. A few studies included services whereby participants received blood glucose monitoring supplies (studies 2 and 6), medication, advice on medication management and assistance with their prescriptions (studies 2, 3 and 6). However there was a lack of information across all 3 studies on the effect the supplies had on the management of diabetes.

Improvements in self-care behaviours

Participants also received dietary supplements, had access to food sources and assistance with meal preparations in the majority of the studies (studies 2, 3, 5 and 6). However, only one study noted that there was an improvement in the access to healthier foods by participants (study 2). Although baseline and follow-up assessments were done for all the participants who had diabetes in this study, only 15 participants (34%) were included in the final assessments. It was noted that there was an improvement in access to healthier foods, for example: fruits, vegetables and whole grains. A dietitian was also available to support the participants in making the best choices from the healthy food options available. However the study found that only 27% of the participants were consuming 3 meals a day, this is because the majority of the participants left the shelter after having breakfast. In one study participants were also provided with sessions on preventing complications whilst living on the streets which included an introduction to physical activity, stress management and relaxation strategies (study 6).

Improvements in diabetes control

Amongst the six studies included in this review only two studies recorded improvements in the participants’ blood pressure, LDL and HbA1c levels (studies 2 and 5). One study found that amongst their entire sample size only 28 of the participants with diabetes had their baseline results available. Amongst these participants, 16 (75%) had elevated fasting blood glucose (mean 9.5 mmol/L; min 5.0 mmol/L, max 23.4 mmol/L). However both the baseline and follow-up results were only recorded for 10 (36%) of these participants. The 3 and 12 month follow-up results showed that there was significant improvements in their fasting blood glucose and HbA1c levels with a reduction of − 4.0 mmol/L and − 1.1% respectively (study 2). Whilst another study found that there was a decrease in HbA1c levels (− 2.3%) within the intervention group and contrastingly an increase within the control group (HbA1c: + 0.2%). In study 5, 65.4% of the participants within the intervention group achieved their target goal in comparison to 45.5% in the control group. The study also noted that there was a decrease in the LDL levels in both the intervention and control groups (− 6.4 mg/dL and − 1.1 mg/dL respectively).

Patient empowerment and engagement

As the homeless population has a daily struggle in securing the basic necessities such as food and shelter, diabetes in this population often goes unnoticed or not appropriately recognised because their symptoms are screened and diagnosed as other diseases or conditions. One study however, was successful in raising awareness on diabetes and empowering their participants to manage the disease (study 2). Whereas another study found that participants perceived group peer support as enhancing their capacities for diabetes management through group problem solving, modelling, the provision of information, emotional support, and social comparison (study 1). Supportive intragroup relationships have long been recognised as a therapeutic mechanism in group therapy, and are increasingly seen as a motivational tool in group-based diabetes self-management programming.

Community engagement and partnerships

Two studies out of the six included in this review concluded that having a multi-sectored approach results in greater community support and actions with aiding the homeless. There is a need for further partnerships with other organisations such as food agencies and pharmaceutical companies which would prompt the provision of medications, food supplements and blood glucose monitoring supplies (studies 2 and 5). These two studies (study 2 and 5) also included on-site integration of homeless-specific services within their interventions (i.e. housing and benefits assistance staff available on-site). One of these studies interpreted the improvement in blood pressures, HbA1c readings, and LDL values as a direct result of the participants having an increased contact with primary care and management services (study 5). Whereas two other studies (studies 1 and 6) concluded that healthcare providers play an important role in fostering supportive and helpful relationships among group members by orienting participants to their roles in the group, monitoring and encouraging supportive interactions among group members, and modelling positive regard.