A group-based lifestyle intervention for diabetes prevention in low- and middle-income country: implementation evaluation of the Kerala Diabetes Prevention Program

Background: While several efficacy trials have demonstrated diabetes risk reduction through targeting key lifestyle behaviours, there is a significant evidence gap in relation to the successful implementation of such interventions in low- and middle-income countries (LMICs). This paper evaluates the implementation of a cluster randomised controlled trial of a group-based lifestyle intervention among individuals at high-risk of developing type 2 diabetes mellitus (T2DM) in the state of Kerala, India. Our aim is to uncover provider-, participant-and community-level factors salient to successful implementation and transferable to other LMICs. Methods: The 12-month intervention program consisted of (1) a group-based peer-support program consisting of 15 sessions over a period of 12 months for high-risk individuals, (2) peer leader (PL) training and ongoing support for intervention delivery, (3) diabetes education resource materials and (4) strategies to stimulate broader community engagement. The evaluation was informed by the RE-AIM and PIPE frameworks. Results: Provider-level factors: Twenty-nine (29/30, 97%) intervention groups organised all 15 sessions. A 2-day PL training was attended by 51(85%) of 60 PLs. The PL handbook was found to be 'very useful' by 78% of PLs. Participant-level factors: Of 1327 eligible individuals, 1007(76%) participants were enrolled. On average, participants attended eight sessions. Sixty-eight percent rated their interest in group sessions as ` very interested', and 55% found the group sessions 'very useful' in making lifestyle changes. Inconvenient time (43%) and location (21%) were found to be important barriers for participants who did not attend any sessions. Community-level factors: Community-based activities reached to 41% of the participants for walking groups, 40% for kitchen garden training, and 31% for yoga training. PLs were readily available for support outside the sessions, as 75% of participants reported extracurricular contacts with their PLs. The commitment from the local partner institute and political leaders facilitated the high uptake of the program. Conclusion: A comprehensive evaluation of program implementation from the provider-, participant- and communitylevel perspectives demonstrates that the K-DPP program was feasible and acceptable in changing lifestyle behaviours in high-risk individuals. The findings from this evaluation will guide the future delivery of structured lifestyle modification diabetes programs in LMICs.